local p = {}
local getArgs = require("Module:Arguments").getArgs
function p.strip(text)
local accents = {["À"]="A",["Á"]="A",["Â"]="A",["Ã"]="A", -- accent list
["Ä"]="A",["Å"]="A",["Ç"]="C",["È"]="E",["É"]="E",
["Ê"]="E",["Ë"]="E",["Ì"]="I",["Í"]="I",["Î"]="I",
["Ï"]="I",["Ñ"]="N",["Ò"]="O",["Ó"]="O",["Ô"]="O",
["Õ"]="O",["Ö"]="O",["Ø"]="O",["Ù"]="U",["Ú"]="U",
["Û"]="U",["Ü"]="U",["Ý"]="Y"
}
local remove = {"NATION OF","COUNTRY OF","TERRITORY OF", -- text to be removed list
"FLAG OF","FLAG","KINGDOM OF","STATE OF"," STATE ",
"PROVINCE OF","PROVINCE","TERRITORY"
}
local patterns = {[".+:"]="",["|.+"]="",["%(.-%)"]="", -- patterns to follow (order may matter)
["%..*"]="",["^THE "]="",["%_"]=" ",["%-"]=" ",
["%d%d?%d?PX"]="",
}
text = mw.ustring.upper(text) -- Case insensitivity
text = mw.ustring.gsub(text,"[À-Ý]",accents) -- Deaccent
for pattern,value in pairs(patterns) do -- Follow patterns
text = mw.ustring.gsub(text,pattern,value)
end
for _,words in pairs(remove) do -- Remove unneeded words
text = mw.ustring.gsub(text,words,"")
end
text = mw.ustring.gsub(text,"%W","") -- Remove non alpha-numeric
return text
end
function p.callstrip(frame)
local args = getArgs(frame)
return p.strip(args[1]) or ""
end
return p
