The tags are generated partially by data-mining the Signpost series templates, and partially by text-matching the subpage name and the long title (converted to lower case) against the following Python dictionary:
#!/usr/bin/python
# -*- coding: utf-8 -*-
keywordTags = {
r"\babuse filter": [u"abusefilter"],
r"\baccessibility": [u"accessibility"],
r"\badmin": [u"administrators"],
r"\badmins": [u"administrators"],
r"\badministrator": [u"administrators"],
r"\badminship": [u"requestsforadminship"],
r"\badrianne wadewitz": [u"adriannewadewitz"],
r"\bafc": [u"articlesforcreation"],
r"\bafd": [u"articlesfordeletion", u"deletion"],
r"\baffiliates": [u"wikimediamovementaffiliates"],
r"\bannual plan": [u"annualplan"],
r"\bapril fool'?s": [u"aprilfools"],
r"\barbcom election": [u"arbitrationcommitteeelections"],
r"\barbcom": [u"arbitrationcommittee"],
r"\barbitration report": [u"arbitrationreport"], # standard section name
r"\barticle alerts": [u"articlealerts"],
r"\barticle assessment": [u"articleassessment"],
r"\baudit": [u"finance", u"audits"],
r"\bautoconfirmed": [u"autoconfirmation"],
r"\baward": [u"awards"],
r"\bbacklog": [u"backlogs"],
r"\blocked": [u"blocking"],
r"\bbanned": [u"banning"],
r"\bbias": [u"systematicbias", u"bias"],
r"\bbiograph": [u"biographies"],
r"\bblp": [u"biographiesoflivingpeople"],
r"\bboard election": [u"boardelections"],
r"\bboard": [u"wikimediafoundationboard"],
r"\bbook review": [u"bookreview"], # Irregular section.
r"\bbureaucrats?\b": [u"bureaucrats"],
r"\bcategor": [u"categorization"],
r"\bchapter": [u"chapters"],
r"\bcheckuser": [u"checkuser"],
r"\bcitation": [u"citations"],
r"\bcitizendium": [u"citizendium"],
r"\bcoi\b": [u"coi"],
r"\bcommons": [u"commons"],
r"\bcompromised": [u"compromisedaccounts"],
r"\bconference": [u"conferences"],
r"\bconflict of interest": [u"coi"],
r"\bcontest": [u"contests", u"contest"],
r"\bcopyright": [u"copyright"],
r"\bdeath": [u"deaths"],
r"\bdelet": [u"deletion"],
r"\bdesysop": [u"desysopping"],
r"\bdiscussion report": [u"discussionreport"],
r"\bdonat": [u"donations"],
r"\be-?mail": [u"email"],
r"\bedit( |-)counter": [u"editcounter", u"editcountitis"],
r"\bedit( |-)war": [u"editwars"],
r"\beducation": [u"educationprogram", u"education"],
r"\belection": [u"elections"],
r"\bemployee": [u"staff", u"employees"],
r"\besperanza": [u"esperanza"],
r"\bessay": [u"essays"],
r"\bessjay": [u"essjay"],
r"\bevent": [u"events"],
r"\bfair use": [u"fairuse"],
r"\bfdc": [u"fundsdisseminationcommittee"],
r"\bfinanc": [u"finance"],
r"\bflagged revisions": [u"flaggedrevisions"],
r"\bflow\b": [u"flow"],
r"\bforum": [u"forum"],
r"\bfoundation": [u"wikimediafoundation"],
r"\bfreedom of panaroma": [u"freedomofpanaroma"],
r"\bfromtheeditor": [u"fromtheeditors"],
r"\bfromtheeditors": [u"fromtheeditors"],
r"\bfrom the editor": [u"fromtheeditors"],
r"\bfrom the editors": [u"fromtheeditors"],
r"\bfrom-the-editor": [u"fromtheeditors"],
r"\bfrom-the-editors": [u"fromtheeditors"],
r"\bfundrais": [u"fundraising"],
r"\bgamergate": [u"gamergate"],
r"\bgardner": [u"suegardner"],
r"\bgender gap": [u"gendergap"],
r"\bgeneral council": [u"generalcouncil"],
r"\bgeodata": [u"geodata"],
r"\bgerman wikipedia": [u"germanwikipedia"],
r"\bglam\b": [u"glam"],
r"\bglobal south": [u"globalsouth"],
r"\bgoogle": [u"google"],
r"\bgrantmaking": [u"grantmaking"],
r"\bgrowth": [u"growth"],
r"\bguild of copy editors": [u"guildofcopyeditors"],
r"\bhhvm": [u"hhvm"],
r"\bhoax": [u"hoaxes"],
r"\bhuggle": [u"huggle"],
r"\bhumor": [u"humour"],
r"\bhumour": [u"humour"],
r"\bieg\b": [u"individualengagementgrants"],
r"\bimage filter": [u"imagefilter"],
r"\bimage": [u"images"],
r"\bincubator": [u"incubator"],
r"\binfobox": [u"infoboxes"],
r"\binfocus": [u"infocus"],
r"\bin focus": [u"infocus"],
r"\binterview": [u"interviews"],
r"\bipv6": [u"ipv6"],
r"\bwales": [u"jimmywales"],
r"\bjournal": [u"journals"],
r"\blawsuit": [u"legal"],
r"\blgbt": [u"lgbt"],
r"\bpride": [u"lgbt"],
r"\blibel": [u"legal"],
r"\blicens": [u"licensing"],
r"\blink rot": [u"linkrot"],
r"\bliquid threads": [u"liquidthreads"],
r"\blog( |-)?in": [u"login"],
r"\blua\b": [u"lua"],
r"\bmailing list": [u"mailinglists"],
r"\bmain page redesign": [u"mainpageredesign"],
r"\bmain page": [u"mainpage"],
r"\bmanning": [u"manning"],
r"\bmanual of style": [u"manualofstyle"],
r"\bmedia viewer": [u"mediaviewer"],
r"\bmediation": [u"mediation", u"disputeresolution"],
r"\bmediawiki": [u"mediawiki"],
r"\bmedic": [u"medical"],
r"\bmeta\b": [u"metawiki"],
r"\bmusic": [u"music"],
r"\bnew page patrol": [u"newpagepatrol"],
r"\bnews and notes": [u"newsandnotes"],
r"\bnofollow": [u"nofollow"],
r"\bnoticeboard": [u"noticeboards"],
r"\boauth": [u"oauth"],
r"\bobama": [u"obama"],
r"\boffice action": [u"officeaction"],
r"\boped": [u"opinion", u"oped"],
r"\bop ed": [u"opinion", u"oped"],
r"\bop-ed": [u"opinion", u"oped"],
r"\bopinion essay": [u"opinion", u"oped"],
r"\borphan": [u"orphans"],
r"\boutage": [u"servers", u"tech"],
r"\boversighter": [u"oversight"],
r"\bpage creation": [u"pagecreation"],
r"\bpaid advocacy": [u"paidadvocacy", u"paidediting", u"coi"],
r"\bpaid editing": [u"paidediting", u"coi"],
r"\bparsoid": [u"parsoid", u"parser"],
r"\bparser function": [u"parserfunctions"],
r"\bpediapress": [u"pediapress"],
r"\bpending changes": [u"pendingchanges"],
r"\bpicture of the year": [u"pictureoftheyear"],
r"\bplagiari": [u"plagiarism"],
r"\bpodcast": [u"podcasts"],
r"\bpolicy": [u"policy"],
r"\bpolish wikipedia": [u"polishwikipedia"],
r"\bpolitician": [u"politicians"],
r"\bpoll": [u"polls"],
r"\bporn": [u"porn"],
r"\bportal": [u"portals"],
r"\bportals": [u"portals"],
r"\bprivacy": [u"privacy"],
r"\bprotection": [u"protection"],
r"\bpublic policy": [u"publicpolicypilot"],
r"\bqrpedia": [u"qrpedia"],
r"\brecent research": [u"recentresearch", u"research"],
r"\breference desk": [u"referencedesk"],
r"\bresearch": [u"research"],
r"\bresidence": [u"wikimediansinresidence"],
r"\bresign": [u"resignations"],
r"\bresysop": [u"admins"],
r"\bsanger": [u"larrysanger"],
r"\bschool": [u"schools"],
r"\bscientology": [u"scientology"],
r"\bsearch": [u"search"],
r"\bsecurity": [u"security"],
r"\bseigenthaler": [u"seigenthaler"],
r"\bserver": [u"servers"],
r"\bsignpost": [u"signpost"],
r"\bsimilpedia": [u"similpedia"],
r"\benglish wikipedia": [u"englishwikipedia"],
r"\bsimple english wikipedia": [u"simpleenglishwikipedia"],
r"\bsister projects": [u"sisterprojects"],
r"\bsnowden": [u"edwardsnowden"],
r"\bsockpuppet": [u"sockpuppetry"],
r"\bsopa\b": [u"sopa"],
r"\bspam\b": [u"spam"],
r"\bspecial report": [u"specialreport"],
r"\bspecial story": [u"specialstory"],
r"\bspoiler": [u"spoilers"],
r"\bspoken": [u"spokenwikipedia"],
r"\bstaff": [u"staff"],
r"\bstatistics": [u"statistics"],
r"\bstats\b": [u"statistics"],
r"\bsteve jobs": [u"stevejobs"],
r"\bsteward": [u"stewards"],
r"\bstrategic plan": [u"strategicplan"],
r"\bstub": [u"stubs"],
r"\bsummer of research": [u"summerofresearch"],
r"\bsystemic bias": [u"systematicbias"],
r"\bteahouse": [u"teahouse"],
r"\btechnology report": [u"techreport", u"tech"],
r"\btemplate": [u"templates"],
r"\bterms of use": [u"termsofuse", u"tou"],
r"\bthree-revert rule": [u"threerevertrule", u"3rr"],
r"\btools": [u"toolserver"],
r"\btrademark": [u"trademarks"],
r"\btraffic report": [u"trafficreport", u"traffic", u"statistics"],
r"\btraffic statistics": [u"traffic", u"statistics"],
r"\btraffic": [u"traffic"],
r"\btransparency report": [u"transparency", u"transparencyreport"],
r"\btron": [u"tron"],
r"\btropenmuseum": [u"tropenmuseum"],
r"\btrustee": [u"board"],
r"\btutorial": [u"tutorial"],
r"\btypography": [u"typography"],
r"\bupload wizard": [u"uploadwizard"],
r"\busability": [u"usability"],
r"\buserbox": [u"userboxes"],
r"\bvandal": [u"vandalism"],
r"\bvfd": [u"votesfordeletion"],
r"\bvideo": [u"video"],
r"\bvisual ?editor": [u"visualeditor"],
r"\bweasel words": [u"weaselwords"],
r"\bwebcite": [u"webcite"],
r"\bwomen": [u"women"],
r"\bwiki loves monuments": [u"wikilovesmonuments"],
r"\bwiki-pr": [u"wikipr"],
r"\bwikia\b": [u"wikia"],
r"\bwikicup": [u"wikicup", u"contests"],
r"\bwikidashboard": [u"wikidashboard"],
r"\bwikidata": [u"wikidata"],
r"\bwikijunior": [u"wikijunior"],
r"\bwikileaks": [u"wikileaks"],
r"\bwikilove": [u"wikilove"],
r"\bwikimania": [u"wikimania", u"events"],
r"\bwikimedia conference": [u"wikimediaconference"],
r"\bwikimedia germany": [u"wikimediagermany"],
r"\bwikimedia israel": [u"wikimediaisrael"],
r"\bwikimedia labs": [u"wikimedialabs"],
r"\bwikimedia russia": [u"wikimediarussia"],
r"\bwikimedia uk": [u"wikimediauk"],
r"\bwikinews": [u"wikinews"],
r"\bwikipedia library": [u"wikipedialibrary"],
r"\bwikipedia loves art": [u"wikipedialovesart"],
r"\bwikipedia offline": [u"wikipediaoffline"],
r"\bwikipedia zero": [u"wikipediazero"],
r"\bwikipedian in residence": [u"wikimediansinresidence"],
r"\bwikiproject report": [u"wikiprojectreport", u"wikiprojects"],
r"\bwikiproject": [u"wikiprojects"],
r"\bwikiscanner": [u"wikiscanner"],
r"\bwikisource": [u"wikisource"],
r"\bwikispecies": [u"wikispecies"],
r"\bwikibooks": [u"wikibooks"],
r"\bwikisym": [u"wikisym"],
r"\bwikiversity": [u"wikiversity"],
r"\bwikivoyage": [u"wikivoyage"],
r"\bwiktionary": [u"wikitionary"],
r"\bwikiquote": [u"wikiquote"],
r"\bwikiworld": [u"wikiworld"],
r"\byahoo": [u"yahoo"],
r"\bswedish wikipedia": [u"swedishwikipedia"],
r"\bdutch wikipedia": [u"dutchwikipedia"],
r"\bfrench wikipedia": [u"frenchwikipedia"],
r"\bwaray-waray wikipedia": [u"waraywaraywikipedia"],
r"\brussian wikipedia": [u"russianwikipedia"],
r"\bcebuano wikipedia": [u"cebuanowikipedia"],
r"\bitalian wikipedia": [u"italianwikipedia"],
r"\bspanish wikipedia": [u"spanishwikipedia"],
r"\bvietnamese wikipedia": [u"vietnamesewikipedia"],
r"\bjapanese wikipedia": [u"japanesewikipedia"],
r"\bportugese wikipedia": [u"portugesewikipedia"],
r"\bchinese wikipedia": [u"chinesewikipedia"],
r"\bukrainian wikipedia": [u"ukrainianwikipedia"],
r"\bcatalan wikipedia": [u"catalanwikipedia"],
r"\bpersian wikipedia": [u"persianwikipedia"],
r"\bnorwegian wikipedia": [u"norwegianwikipedia"],
r"\bserbo-croatian wikipedia": [u"serbocroatianwikipedia"],
r"\bfinnish wikipedia": [u"finnishwikipedia"],
r"\bindonesian wikipedia": [u"indonesianwikipedia"],
r"\barabic wikipedia": [u"arabicwikipedia"],
r"\bczech wikipedia": [u"czechwikipedia"],
r"\bserbian wikipedia": [u"serbianwikipedia"],
r"\bkorean wikipedia": [u"koreanwikipedia"],
r"\bmobile": [u"mobile"],
r"\btwinkle": [u"twinkle"],
r"\bsul\b": [u"singleuserlogin"],
r"\bmagic word": [u"magicwords"],
r"\bscribunto": [u"scribunto"],
r"\bfoundation wiki": [u"foundationwiki"],
r"\bnupedia": [u"nupedia"],
}
-- This module processes data from [[Module:Signpost/index]], to be loaded from
-- [[Module:Signpost]] with mw.loadData.
local PAGE_FORMAT = 'Wikipedia:Wikipedia Signpost/%s/%s'
local INDEX_START_YEAR = 2005
local INDEX_BASE = 'Module:Signpost/index/'
local ALIASES_MODULE = 'Module:Signpost/aliases'
local insert = table.insert
local format = string.format
local function makePageName(date, subpage)
return format(PAGE_FORMAT, date, subpage)
end
local function addSubtable(tIn, tOut, key)
tOut[key] = tOut[key] or {}
insert(tOut[key], tIn)
end
local function maybeRequire(page)
local success, module = pcall(require, page)
if success then
return module
end
end
local function getYearIndexes()
local ret = {}
for i = INDEX_START_YEAR, os.date('*t').year + 1 do
local module = maybeRequire(INDEX_BASE .. tostring(i))
insert(ret, module)
end
return ret
end
local function makeAliases()
local aliasData = require(ALIASES_MODULE)
local ret = {}
for key, aliases in pairs(aliasData) do
for i, alias in ipairs(aliases) do
ret[alias] = key
end
end
return ret
end
local function main()
local list, dates, tags, pages = {}, {}, {}, {}
local i = 0
for j, index in ipairs(getYearIndexes()) do
for k, t in ipairs(index) do
i = i + 1
t.sortKey = i
local date = t.date
local page = makePageName(date, t.subpage)
t.page = page
list[i] = t
addSubtable(t, dates, date)
for l, tag in ipairs(t.tags) do
addSubtable(t, tags, tag)
end
pages[page] = t
end
end
return {
list = list,
dates = dates,
tags = tags,
pages = pages,
aliases = makeAliases()
}
end
return main()