--[[For functions related to Internet ArchiveNotes:1. Internet Archive runs Elasticsearch search engine as of 4 Nov 20152. Program flowchart: Break name down into number of words Build a base URL based on number of words (1,2,3,4,5+), use of sopt=t switch, and availability of birth-death dates If any words contain extended-ascii characters append extra code for wildcards based on sopt=t or w return finished URL3. URL length should not exceed 2000 characters or it will break certain popular browsers4. Wildcard (*) replacements should be avoided in the first letter of the first word, and with any single-letter words5. Changing search formulations will have impacts on existing uses of the template and off-line tools which are optimized for these search recipes.]]localp={}--[[For Template:Internet Archive author]]functionp.author(frame)localpframe=frame:getParent()localargs=pframe.argslocaltname="Internet Archive author"-- name of calling template. Change if template rename.localname=nil-- article name (default: current page name)dname=nil-- display name (default: current page name)localsname=nil-- search name (default: current page name)localsopt=nil-- search options (default: nil)byabout="Works by or about"tagline="at the [[Internet Archive]]"urlhead="https://archive.org/search.php?query="mydate=""-- birth-death date--- Determine namename=trimArg(args.name)-- When using template outside main article space, the 'name' parameter is required (not optional)ifnotnamethenname=mw.title.getCurrentTitle().textenddname=mw.ustring.gsub(name,'%s+%([^%(]-%)$','')-- Remove the final disambig parenthesessname=dnameiftrimArg(args.sname)thensname=trimArg(args.sname)endiftrimArg(args.dname)thendname=trimArg(args.dname)end--- Determine search optionsopt=trimArg(args.sopt)ifsoptthensopt=mw.ustring.lower(sopt)ifsopt=="tight"thensopt="t"endifsopt=="tightx"thensopt="tx"endifsopt=="wild"thensopt="w"endifsopt~="t"andsopt~="tx"andsopt~="w"thensopt="unknown"endend--- Determine taglineiftrimArg(args.coda)thentagline=tagline.." "..trimArg(args.coda)end--- Custom search. Do early to avoid unnecessary processing.iftrimArg(args.search)thenlocalsearch=p.ia_url_encode(trimArg(args.search))return"["..urlhead..search.." "..byabout.." "..dname.."] "..taglineend-- Determine media stringmedia=p.mediaTypes(args.media)ifmedia==""thenmediaopen="%28"-- added a default mediatype Dec 2015 see p.mediaTypes()elsemediaopen="%28"end-- Determine date of birth and deathlocaltemp=mw.text.split(p.bdDate(args.birth,args.death,name)," ")localbirth=temp[1]localdeath=temp[2]ifbirth=="Error"ordeath=="Error"thenreturn"Error in [[:Template:"..tname.."]]: [["..name.."]] doesn't exist."end--- Split sname into words and count wordslocalN=mw.text.split(sname," ")locall,count=mw.ustring.gsub(sname,"%S+","")ifcount==0thenreturn"Error in [[:Template:"..tname.."]]: Zero-word name."end--- Date stringifbirth~="none"anddeath~="none"thenifp.ia_extendedascii(N[count])==1thenmydate="%20OR%20%28%22"..birth.."-"..death.."%22%20AND%20%28%22"..p.urlX(N[count]).."%22%20OR%20"..p.urlX(p.ia_deaccent(N[count])).."%29%29"elsemydate="%20OR%20%28%22"..birth.."-"..death.."%22%20AND%20"..p.urlX(N[count]).."%29"endend--- wild stringwild="%29"ifsopt=="w"andp.ia_extendedascii(sname)==1thenifp.wildcheck(N,count)==1thenmyurl=p.wildfix(N,count)returnp.IArender()endifcount<3orcount>3then-- (first last)wild="%20OR%20%28"..p.ia_url_encode(p.ia_extendedascii2wildcard(sname)).."%29%29"endifcount==3then-- (first last)wild="%20OR%20%28"..p.ia_url_encode(p.ia_extendedascii2wildcard(N[1])).."%20"..p.ia_url_encode(p.ia_extendedascii2wildcard(N[3])).."%29%29"endend--[[ Format URL ]]ifcount==1thenmyurl=p.oneWord(sname)ifsopt=="t"andp.ia_extendedascii(sname)==1thenlocalplainname=p.ia_deaccent(sname)localA1="%20OR%20%22"..p.urlX(plainname)myurl=myurl..A1.."%22"returnp.IArender()endreturnp.IArender()endifcount==2thenmyurl=p.twoWords(N,sopt)ifsopt=="t"andp.ia_extendedascii(sname)==1thenlocalplainname=p.ia_deaccent(sname)localPN=mw.text.split(plainname," ")-- Last, FirstlocalA1="%20OR%20%22"..p.urlX(PN[2]).."%2C%20"..p.urlX(PN[1])-- First LastlocalA2="%22%20OR%20%22"..p.urlX(PN[1]).."%20"..p.urlX(PN[2])myurl=myurl..A1..A2.."%22"returnp.IArender()endreturnp.IArender()endifcount==3thenmyurl=p.threeWords(N,sopt)ifsopt=="t"andp.ia_extendedascii(sname)==1thenlocalplainname=p.ia_deaccent(sname)localPN=mw.text.split(plainname," ")localFIRST=p.urlX(PN[1])localMIDDLE=p.urlX(PN[2])localLAST=p.urlX(PN[3])localfirstinitialp=p.urlX(p.firstLetter(PN[1]))localmiddleinitialp=p.urlX(p.firstLetter(PN[2]))-- First Middle LastlocalA1="%20OR%20%22"..FIRST.."%20"..MIDDLE.."%20"..LAST-- Last, First MiddlelocalA2="%22%20OR%20%22"..LAST.."%2C%20"..FIRST.."%20"..MIDDLE-- Last, First M.localA3="%22%20OR%20%22"..LAST.."%2C%20"..FIRST.."%20"..middleinitialp.."%2E"-- Last, F. M.localA4="%22%20OR%20%22"..LAST.."%2C%20"..firstinitialp..".%20"..middleinitialp.."%2E"localALL=A1..A2..A3..A4.."%22"myurl=myurl..ALLreturnp.IArender()endreturnp.IArender()endifcount==4thenmyurl=p.fourWords(N,sopt)ifsopt=="t"andp.ia_extendedascii(sname)==1thenlocalplainname=p.ia_deaccent(sname)localPN=mw.text.split(plainname," ")localFIRST=p.urlX(PN[1])localSECOND=p.urlX(PN[2])localTHIRD=p.urlX(PN[3])localLAST=p.urlX(PN[4])localfirstinitialp=p.urlX(p.firstLetter(PN[1]))localsecondinitialp=p.urlX(p.firstLetter(PN[2]))localthirdinitialp=p.urlX(p.firstLetter(PN[3]))-- Last, First Second ThirdlocalA1="%20OR%20%22"..LAST.."%2C%20"..FIRST.."%20"..SECOND.."%20"..THIRD-- First Second Third LastlocalA2="%22%20OR%20%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- Last, F. S. T.localA3="%22%20OR%20%22"..LAST.."%2C%20"..firstinitialp.."%2E%20"..secondinitialp.."%2E%20"..thirdinitialp.."%2E"localALL=A1..A2..A3.."%22"myurl=myurl..ALLreturnp.IArender()endreturnp.IArender()endifcount>4thenmyurl=""ifsopt=="w"andp.ia_extendedascii(sname)==1thenmyurl="%28"endmyurl=myurl.."%28"..p.ia_url_encode(sname)ifsopt=="w"andp.ia_extendedascii(sname)==1thenmyurl=myurl.."%29"endifsopt=="t"andp.ia_extendedascii(sname)==1thenlocalplainname=p.ia_deaccent(sname)localA1="%29%20OR%20%28"..p.ia_url_encode(plainname)myurl=myurl..A1returnp.IArender()endreturnp.IArender()endreturn"Unknown error (1). Please check documentation for [[Template:"..tname.."]]"end-- Build final output and renderfunctionp.IArender()return"["..urlhead..mediaopen..myurl..wild..mydate..media.." "..byabout.." "..dname.."] "..taglineendfunctionp.oneWord(sname)localnameurl=p.ia_url_encode(sname)localA1="%28subject%3A%22"..nameurllocalA2="%22%20OR%20creator%3A%22"..nameurllocalA3="%22%20OR%20description%3A%22"..nameurllocalA4="%22%20OR%20title%3A%22"..nameurlreturnA1..A2..A3..A4.."%22"endfunctionp.twoWords(N,sopt)localFIRST=p.urlX(N[1])localLAST=p.urlX(N[2])localfirstinitial=p.urlX(p.firstLetter(N[1]))-- Last, FirstlocalS1="%28subject%3A%22"..LAST.."%2C%20"..FIRST-- First LastlocalS2="%22%20OR%20subject%3A%22"..FIRST.."%20"..LASTlocalSALL=S1..S2-- Last, FirstlocalC1="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRST-- First LastlocalC2="%22%20OR%20creator%3A%22"..FIRST.."%20"..LASTlocalCALL=C1..C2-- First LastlocalT1="%22%20OR%20title%3A%22"..FIRST.."%20"..LASTlocalTALL=T1-- Last, FirstlocalD1="%22%20OR%20description%3A%22"..LAST.."%2C%20"..FIRST-- First LastlocalD2="%22%20OR%20description%3A%22"..FIRST.."%20"..LASTlocalDALL=D1..D2ifsopt=="t"orsopt=="tx"thenreturnSALL..CALL..TALL..DALL.."%22"else-- Last, F.localC3="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..firstinitial.."%2E"localCALL=CALL..C3returnSALL..CALL..TALL..DALL.."%22"endendfunctionp.threeWords(N,sopt)-- CAUTION: The following is near the max 2000 character URL limit for most browsers when using long names-- such as "René-Nicolas Dufriche Desgenettes".localFIRST=p.urlX(N[1])localMIDDLE=p.urlX(N[2])localLAST=p.urlX(N[3])localfirstinitial=p.urlX(p.firstLetter(N[1]))localmiddleinitial=p.urlX(p.firstLetter(N[2]))-- Last, First MiddlelocalS1="%28subject%3A%22"..LAST.."%2C%20"..FIRST.."%20"..MIDDLE-- Last, First M.localS2="%22%20OR%20subject%3A%22"..LAST.."%2C%20"..FIRST.."%20"..middleinitial.."%2E"-- Last, F. M.localS3="%22%20OR%20subject%3A%22"..LAST.."%2C%20"..firstinitial.."%2E%20"..middleinitial.."%2E"-- First Middle LastlocalS4="%22%20OR%20subject%3A%22"..FIRST.."%20"..MIDDLE.."%20"..LAST-- First M. LastlocalS5="%22%20OR%20subject%3A%22"..FIRST.."%20"..middleinitial.."%2E%20"..LAST-- F. M. LastlocalS6="%22%20OR%20subject%3A%22"..firstinitial.."%2E%20"..middleinitial.."%2E%20"..LASTlocalSALL=S1..S2..S3..S4..S5..S6-- First Middle LastlocalC1="%22%20OR%20creator%3A%22"..FIRST.."%20"..MIDDLE.."%20"..LAST-- First M. LastlocalC2="%22%20OR%20creator%3A%22"..FIRST.."%20"..middleinitial.."%2E%20"..LAST-- F. M. LastlocalC3="%22%20OR%20creator%3A%22"..firstinitial.."%2E%20"..middleinitial.."%2E%20"..LAST-- F. Middle LastlocalC4="%22%20OR%20creator%3A%22"..firstinitial.."%2E%20"..MIDDLE.."%20"..LAST-- Last, First MiddlelocalC5="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRST.."%20"..MIDDLE-- Last, First M.localC6="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRST.."%20"..middleinitial.."%2E"-- Last, F. M.localC7="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..firstinitial.."%2E%20"..middleinitial.."%2E"-- Last, F. M.localC8="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..firstinitial.."%2E%20"..MIDDLElocalCALL=C1..C2..C3..C4..C5..C6..C7..C8-- First Middle LastlocalT1="%22%20OR%20title%3A%22"..FIRST.."%20"..MIDDLE.."%20"..LAST-- First M. LastlocalT2="%22%20OR%20title%3A%22"..FIRST.."%20"..middleinitial.."%2E%20"..LAST-- F. M. LastlocalT3="%22%20OR%20title%3A%22"..firstinitial.."%2E%20"..middleinitial.."%2E%20"..LASTlocalTALL=T1..T2..T3-- First Middle LastlocalD1="%22%20OR%20description%3A%22"..FIRST.."%20"..MIDDLE.."%20"..LAST-- First M. LastlocalD2="%22%20OR%20description%3A%22"..FIRST.."%20"..middleinitial.."%2E%20"..LAST-- F. M. LastlocalD3="%22%20OR%20description%3A%22"..firstinitial.."%2E%20"..middleinitial.."%2E%20"..LAST-- Last, First MiddlelocalD4="%22%20OR%20description%3A%22"..LAST.."%2C%20"..FIRST.."%20"..MIDDLE-- Last, First M.localD5="%22%20OR%20description%3A%22"..LAST.."%2C%20"..FIRST.."%20"..middleinitial.."%2E"localDALL=D1..D2..D3..D4..D5ifsopt=="t"orsopt=="tx"thenreturnSALL..CALL..TALL..DALL.."%22"else-- Last, FirstlocalS7="%22%20OR%20subject%3A%22"..LAST.."%2C%20"..FIRST-- First LastlocalS8="%22%20OR%20subject%3A%22"..FIRST.."%20"..LASTlocalSALL=SALL..S7..S8-- First LastlocalC9="%22%20OR%20creator%3A%22"..FIRST.."%20"..LAST-- Last, FirstlocalC10="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRSTlocalCALL=CALL..C9..C10-- First LastlocalT4="%22%20OR%20title%3A%22"..FIRST.."%20"..LASTlocalTALL=TALL..T4-- First LastlocalD6="%22%20OR%20description%3A%22"..FIRST.."%20"..LAST-- Last, FirstlocalD7="%22%20OR%20description%3A%22"..LAST.."%2C%20"..FIRSTlocalDALL=DALL..D6..D7returnSALL..CALL..TALL..DALL.."%22"endendfunctionp.fourWords(N,sopt)localFIRST=p.urlX(N[1])localSECOND=p.urlX(N[2])localTHIRD=p.urlX(N[3])localLAST=p.urlX(N[4])localfirstinitial=p.firstLetter(N[1])localsecondinitial=p.firstLetter(N[2])localthirdinitial=p.firstLetter(N[3])ifsopt=="t"orsopt=="tx"then-- Last, First Second ThirdlocalS1="%28subject%3A%22"..LAST.."%2C%20"..FIRST.."%20"..SECOND.."%20"..THIRD-- First Second Third LastlocalS2="%22%20OR%20subject%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- Last, First Second ThirdlocalC1="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRST.."%20"..SECOND.."%20"..THIRD-- First Second Third LastlocalC2="%22%20OR%20creator%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- First Second Third LastlocalT1="%22%20OR%20title%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- First Second Third LastlocalD1="%22%20OR%20description%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LASTreturnS1..S2..C1..C2..T1..D1.."%22"end-- Last, First Second ThirdlocalS1="%28subject%3A%22"..LAST.."%2C%20"..FIRST.."%20"..SECOND.."%20"..THIRD-- First Second Third LastlocalS2="%22%20OR%20subject%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- Last, First Second ThirdlocalC1="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..FIRST.."%20"..SECOND.."%20"..THIRD-- First Second Third LastlocalC2="%22%20OR%20creator%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- Last, F. S. T.localC3="%22%20OR%20creator%3A%22"..LAST.."%2C%20"..firstinitial.."%2E%20"..secondinitial.."%2E%20"..thirdinitial.."%2E"-- First Second Third LastlocalT1="%22%20OR%20title%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LAST-- First Second Third LastlocalD1="%22%20OR%20description%3A%22"..FIRST.."%20"..SECOND.."%20"..THIRD.."%20"..LASTreturnS1..S2..C1..C2..C3..T1..D1.."%22"end-- ElasticSearch speed/resource problems if first letter of first word is "*" wildcard ie. accented letter-- Build special search in these cases.-- https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#_wildcardsfunctionp.wildfix(N,count)--- Split along "-" and use only first word ie. John-Taylor-Smith becomes JohnlocalNF=mw.text.split(N[1],"-")localNL=mw.text.split(N[count],"-")-- ..but use full name for 1-word namesifcount==1thenNF[1]=N[1]NL[1]=N[1]end-- ((Fïrst OR First) AND (Lást OR Last))return"%28%28%22"..NF[1].."%22%20OR%20"..p.ia_deaccent(NF[1]).."%29%20AND%20%28%22"..NL[1].."%22%20OR%20"..p.ia_deaccent(NL[1]).."%29"end-- Return 1 if the first letter of first word, or any single-letter word, is extended asciifunctionp.wildcheck(N,count)locali=0-- first letter of first word is extended asciiifN[1]:byte(1)<32orN[1]:byte(1)>126thenreturn1end-- any single-letter word that is composed of only extended asciiwhilei<countdoi=i+1ifN[i]:len()==1thenifN[i]:byte(1)<32orN[i]:byte(1)>126thenreturn1endendendreturn0endfunctiontrimArg(arg)ifarg==""orarg==nilthenreturnnilelsereturnmw.text.trim(arg)endendfunctionp.mediaTypes(argsmedia)-- Added a default mediatype Dec 2015 due to too many false positives in the software mediatype, caused by birth-death dates catching numbers in source codeslocalmedia="-mediatype:software"ifargsmedia~=""andargsmedia~=nilthenlocalmedialist=mw.text.split(mw.text.trim(argsmedia)," ")localal,acount=mw.ustring.gsub(mw.text.trim(argsmedia),"%S+","")locali=0repeat-- the following could be condensed but repetitive for clarityi=i+1if(mw.ustring.lower(medialist[i])=="text"ormw.ustring.lower(medialist[i])=="texts")thenmedia=media..p.ia_url_encode(" OR mediatype:texts")endif(mw.ustring.lower(medialist[i])=="audio")thenmedia=media..p.ia_url_encode(" OR mediatype:audio")endif(mw.ustring.lower(medialist[i])=="video")thenmedia=media..p.ia_url_encode(" OR mediatype:video")enduntili==acountendmedia="%29%20AND%20%28"..media.."%29"returnmediaend-- Alt way to get b/d dates via getContent()functionp.bdDateAlt(argsbirth,argsdeath,name)localpagetext=nillocalbirth="none"localdeath="none"-- Load the pagelocalt=mw.title.new(name)if(t.exists)thenpagetext=t:getContent()endifpagetext==nilthenreturn"Error"end-- Remove false positivespagetext=mw.ustring.gsub(mw.ustring.gsub(pagetext,"<!--.--->",""),"<nowiki>.-</nowiki>","")-- "Category:1900 births"ifargsbirth==""orargsbirth==nilthenlocalbirthcheck=mw.ustring.match(pagetext,"%[%[%s-[Cc]ategory:%s-%d+%.?%d*%s-births%s-%]%]")ifbirthcheck~=nilthenbirth=mw.ustring.match(birthcheck,"%d+%.?%d*")elsebirth="none"endelsebirth=mw.text.trim(argsbirth)end-- "Category:2000 deaths"ifargsdeath==""orargsdeath==nilthenlocaldeathcheck=mw.ustring.match(pagetext,"%[%[%s-[Cc]ategory:%s-%d+%.?%d*%s-deaths%s-%]%]")ifdeathcheck~=nilthendeath=mw.ustring.match(deathcheck,"%d+%.?%d*")elsedeath="none"endelsedeath=mw.text.trim(argsdeath)endreturnbirth.." "..deathend-- Get b/d dates via Wikidata.-- functionp.bdDate(argsbirth,argsdeath,name)localpagetext=nillocalbirth="none"localdeath="none"entity=mw.wikibase.getEntityObject()ifnotentityornotentity.claimsthen-- Alternative if template not on a page in mainspace. This is needed since Wikidata can only be retrieved-- for the article where the template is located.returnp.bdDateAlt(argsbirth,argsdeath,name)end-- Note: The below uses formatPropertyValues() to get and format the date from Wikidata.-- For an alternative method, see sandbox revision dated 5:58 am, 15 October 2014ifargsbirth==""orargsbirth==nilthenlocalbirthtable=entity:formatPropertyValues('P569')localbirthsplit=mw.text.split(birthtable["value"]," ")locall,count=mw.ustring.gsub(birthtable["value"],"%S+","")ifcount>0thenifstring.find(birthsplit[count],"^%d")thenbirth=birthsplit[count]elseifstring.find(birthsplit[count],"BCE")thenbirth=birthsplit[count-1]elseifstring.find(birthsplit[count],"BC")thenbirth=birthsplit[count-1]elseifstring.find(birthsplit[count],"AD")thenbirth=birthsplit[count-1]endendelsebirth=mw.text.trim(argsbirth)endifargsdeath==""orargsdeath==nilthenlocaldeathtable=entity:formatPropertyValues('P570')localdeathsplit=mw.text.split(deathtable["value"]," ")locall,count=mw.ustring.gsub(deathtable["value"],"%S+","")ifcount>0thenifstring.find(deathsplit[count],"^%d")thendeath=deathsplit[count]elseifstring.find(deathsplit[count],"BCE")thendeath=deathsplit[count-1]elseifstring.find(deathsplit[count],"BC")thendeath=deathsplit[count-1]elseifstring.find(deathsplit[count],"AD")thendeath=deathsplit[count-1]endendelsedeath=mw.text.trim(argsdeath)endifbirth=="none"anddeath=="none"then-- Alternative if Wikidata is missing data-- return p.bdDateAlt(name)returnbirth.." "..deathelsereturnbirth.." "..deathendend--- URL-encode special characters--- Note: this function was added later to deal with "&" characters instead of using p.ia_url_encode since--- that may break existing instances of the template.functionp.urlX(str)if(str)thenstr=mw.ustring.gsub(str,"&","%%26")endreturnstrend--- URL-encode a string--- http://lua-users.org/wiki/StringRecipes---functionp.ia_url_encode(str)if(str)thenstr=mw.ustring.gsub(str,"\n","\r\n")str=mw.ustring.gsub(str,"([^%w %-%_%.%~])",function(c)returnmw.ustring.format("%%%02X",string.byte(c))end)str=mw.ustring.gsub(str," ","+")endreturnstrend-- Does str contain extended ascii? 1 = yesfunctionp.ia_extendedascii(str)fori=1,str:len()doif(str:byte(i)>=32andstr:byte(i)<=126)andstr:byte(i)~=39then-- 39 = "'"--do nothingelsereturn1endendreturn0end-- UTF-8 aware replacement for string.sub() which doesn't support UTF-8.-- Note: Using instead of mw.ustring.sub() which I suspect(?) might be cause of intermittent error, and faster here for first-letter job.-- Source: prapin @ Stack Overflow http://stackoverflow.com/questions/13235091/extract-the-first-letter-of-a-utf-8-string-with-luafunctionp.firstLetter(str)returnstr:match("[%z\1-\127\194-\244][\128-\191]*")end-- Replace all extended ascii characters with wildcard '*'-- Replace "-" with <space> eg. Pierre-Jean -> Pierre Jeanfunctionp.ia_extendedascii2wildcard(str)locals=""localj=0localk=0fori=1,str:len()dok=str:byte(i)ifk>=32andk<=126then-- For list of Lucene special characters needing to be escaped:-- http://lucene.apache.org/core/4_10_0/queryparser/org/apache/lucene/queryparser/classic/package-summary.html#Escaping_Special_Characters-- We only worry about - (45) and " (34) since the others are unlikely to appear in a proper name.-- Also ' (39) since it is sometimes the extended character ’ifk==34ork==39thens=s.."*"elseifk==45thens=s.." "elses=s..str:sub(i,i)endelseifj==1thens=s.."*"j=2endifj==0thenj=1endifj==2thenj=0endendendreturnsend-- Replace accented letters with non-accented equivalent letters-- Note: this is not a complete list of all possible accented letters. It is-- all of the accented letters found in the first 10,000 names using-- the Internet Archive author template.functionp.ia_deaccent(str)locals=strs=mw.ustring.gsub(s,"á","a")s=mw.ustring.gsub(s,"a︡","a")s=mw.ustring.gsub(s,"Á","A")s=mw.ustring.gsub(s,"ă","a")s=mw.ustring.gsub(s,"â","a")s=mw.ustring.gsub(s,"æ","ae")s=mw.ustring.gsub(s,"Æ","AE")s=mw.ustring.gsub(s,"à","a")s=mw.ustring.gsub(s,"ā","a")s=mw.ustring.gsub(s,"Ā","A")s=mw.ustring.gsub(s,"ą","a")s=mw.ustring.gsub(s,"å","a")s=mw.ustring.gsub(s,"Å","A")s=mw.ustring.gsub(s,"ã","a")s=mw.ustring.gsub(s,"ä","a")s=mw.ustring.gsub(s,"Ä","A")s=mw.ustring.gsub(s,"β","B")s=mw.ustring.gsub(s,"ć","c")s=mw.ustring.gsub(s,"č","c")s=mw.ustring.gsub(s,"Č","C")s=mw.ustring.gsub(s,"ç","c")s=mw.ustring.gsub(s,"Ç","C")s=mw.ustring.gsub(s,"ĉ","c")s=mw.ustring.gsub(s,"ď","d")s=mw.ustring.gsub(s,"đ","d")s=mw.ustring.gsub(s,"é","e")s=mw.ustring.gsub(s,"É","E")s=mw.ustring.gsub(s,"ě","e")s=mw.ustring.gsub(s,"ê","e")s=mw.ustring.gsub(s,"è","e")s=mw.ustring.gsub(s,"È","E")s=mw.ustring.gsub(s,"ε","e")s=mw.ustring.gsub(s,"ē","e")s=mw.ustring.gsub(s,"Ē","E")s=mw.ustring.gsub(s,"ę","e")s=mw.ustring.gsub(s,"ð","e")s=mw.ustring.gsub(s,"ë","e")s=mw.ustring.gsub(s,"Ë","E")s=mw.ustring.gsub(s,"γ","Y")s=mw.ustring.gsub(s,"ħ","h")s=mw.ustring.gsub(s,"i︠a︡","ia")s=mw.ustring.gsub(s,"í","i")s=mw.ustring.gsub(s,"i︠","i")s=mw.ustring.gsub(s,"ĭ","i")s=mw.ustring.gsub(s,"Í","I")s=mw.ustring.gsub(s,"î","i")s=mw.ustring.gsub(s,"Î","I")s=mw.ustring.gsub(s,"ì","i")s=mw.ustring.gsub(s,"ī","i")s=mw.ustring.gsub(s,"ł","i")s=mw.ustring.gsub(s,"ï","i")s=mw.ustring.gsub(s,"Ï","I")s=mw.ustring.gsub(s,"ĺ","I")s=mw.ustring.gsub(s,"Ĺ","L")s=mw.ustring.gsub(s,"μ","u")s=mw.ustring.gsub(s,"µ","u")s=mw.ustring.gsub(s,"ń","n")s=mw.ustring.gsub(s,"ň","n")s=mw.ustring.gsub(s,"ņ","n")s=mw.ustring.gsub(s,"ñ","n")s=mw.ustring.gsub(s,"Ñ","N")s=mw.ustring.gsub(s,"ó","o")s=mw.ustring.gsub(s,"Ó","O")s=mw.ustring.gsub(s,"ô","o")s=mw.ustring.gsub(s,"œ","oe")s=mw.ustring.gsub(s,"ò","o")s=mw.ustring.gsub(s,"ō","o")s=mw.ustring.gsub(s,"ø","o")s=mw.ustring.gsub(s,"Ø","o")s=mw.ustring.gsub(s,"õ","o")s=mw.ustring.gsub(s,"ö","o")s=mw.ustring.gsub(s,"ő","o")s=mw.ustring.gsub(s,"Ö","O")s=mw.ustring.gsub(s,"φ","o")s=mw.ustring.gsub(s,"ŕ","r")s=mw.ustring.gsub(s,"ř","r")s=mw.ustring.gsub(s,"Ř","R")s=mw.ustring.gsub(s,"ß","ss")s=mw.ustring.gsub(s,"ś","s")s=mw.ustring.gsub(s,"Ś","S")s=mw.ustring.gsub(s,"š","s")s=mw.ustring.gsub(s,"ṣ","s")s=mw.ustring.gsub(s,"Š","S")s=mw.ustring.gsub(s,"ş","s")s=mw.ustring.gsub(s,"Ş","S")s=mw.ustring.gsub(s,"ŝ","s")s=mw.ustring.gsub(s,"σ","s")s=mw.ustring.gsub(s,"ť","t")s=mw.ustring.gsub(s,"ţ","t")s=mw.ustring.gsub(s,"τ","t")s=mw.ustring.gsub(s,"þ","p")s=mw.ustring.gsub(s,"Þ","p")s=mw.ustring.gsub(s,"ú","u")s=mw.ustring.gsub(s,"Ú","U")s=mw.ustring.gsub(s,"û","u")s=mw.ustring.gsub(s,"ù","u")s=mw.ustring.gsub(s,"ū","u")s=mw.ustring.gsub(s,"ů","u")s=mw.ustring.gsub(s,"ü","u")s=mw.ustring.gsub(s,"Ü","U")s=mw.ustring.gsub(s,"ŵ","w")s=mw.ustring.gsub(s,"ý","y")s=mw.ustring.gsub(s,"ŷ","y")s=mw.ustring.gsub(s,"¥","y")s=mw.ustring.gsub(s,"ÿ","y")s=mw.ustring.gsub(s,"Ÿ","Y")s=mw.ustring.gsub(s,"ź","z")s=mw.ustring.gsub(s,"Ž","Z")s=mw.ustring.gsub(s,"ž","z")s=mw.ustring.gsub(s,"ż","z")s=mw.ustring.gsub(s,"Ż","Z")returnsendreturnp
