Module:String2

Documentation for this module may be created at Module:String2/doc

-- Version 2021-01-30localp={}p.trim=function(frame)locals=mw.text.trim(frame.args[1]or"")returnsendp.upper=function(frame)locals=mw.text.trim(frame.args[1]or"")returnstring.upper(s)endp.lower=function(frame)locals=mw.text.trim(frame.args[1]or"")returnstring.lower(s)endp.sentence=function(frame)frame.args[1]=string.lower(frame.args[1])returnp.ucfirst(frame)endp.ucfirst=function(frame)locals=mw.text.trim(frame.args[1]or"")locals1=""-- if it's a list chop off and (store as s1) everything up to the first <li>locallipos=mw.ustring.find(s,"<li>")ifliposthens1=mw.ustring.sub(s,1,lipos+3)s=mw.ustring.sub(s,lipos+4)end-- s1 is either "" or the first part of the list markup, so we can continue-- and prepend s1 to the returned stringlocalletterposifmw.ustring.find(s,"^%[%[[^|]+|[^%]]+%]%]")then-- this is a piped wikilink, so we capitalise the text, not the pipelocal__,letterpos=mw.ustring.find(s,"|%A*%a")-- find the first letter after the pipeelseletterpos=mw.ustring.find(s,'%a')endifletterposthenlocalfirst=mw.ustring.sub(s,1,letterpos-1)localletter=mw.ustring.sub(s,letterpos,letterpos)localrest=mw.ustring.sub(s,letterpos+1)returns1..first..mw.ustring.upper(letter)..restelsereturns1..sendendp.title=function(frame)-- http://grammar.yourdictionary.com/capitalization/rules-for-capitalization-in-titles.html-- recommended by The U.S. Government Printing Office Style Manual:-- "Capitalize all words in titles of publications and documents,-- except a, an, the, at, by, for, in, of, on, to, up, and, as, but, or, and nor."localalwayslower={['a']=1,['an']=1,['the']=1,['and']=1,['but']=1,['or']=1,['for']=1,['nor']=1,['on']=1,['in']=1,['at']=1,['to']=1,['from']=1,['by']=1,['of']=1,['up']=1}localres=''locals=mw.text.trim(frame.args[1]or"")localwords=mw.text.split(s," ")fori,sinipairs(words)dos=string.lower(s)if(i>1andalwayslower[s]==1)then-- leave in lowercaseelses=mw.getContentLanguage():ucfirst(s)endwords[i]=sendreturntable.concat(words," ")end-- findlast finds the last item in a list-- the first unnamed parameter is the list-- the second, optional unnamed parameter is the list separator (default = comma space)-- returns the whole list if separator not foundp.findlast=function(frame)locals=mw.text.trim(frame.args[1]or"")localsep=frame.args[2]or""ifsep==""thensep=", "endlocalpattern=".*"..sep.."(.*)"locala,b,last=s:find(pattern)ifathenreturnlastelsereturnsendend-- stripZeros finds the first number and strips leading zeros (apart from units)-- e.g "0940" -> "940"; "Year: 0023" -> "Year: 23"; "00.12" -> "0.12"p.stripZeros=function(frame)locals=mw.text.trim(frame.args[1]or"")localn=tonumber(string.match(s,"%d+"))or""s=string.gsub(s,"%d+",n,1)returnsend-- nowiki ensures that a string of text is treated by the MediaWiki software as just a string-- it takes an unnamed parameter and trims whitespace, then removes any wikicodep.nowiki=function(frame)localstr=mw.text.trim(frame.args[1]or"")returnmw.text.nowiki(str)end-- posnq (position, no quotes) returns the numerical start position of the first occurrence-- of one piece of text ("match") inside another ("str").-- It returns nil if no match is found, or if either parameter is blank.-- It takes the text to be searched in as the first unnamed parameter, which is trimmed.-- It takes the text to match as the second unnamed parameter, which is trimmed and-- any double quotes " are stripped out.p.posnq=function(frame)localargs=frame.argslocalpargs=frame:getParent().argsfork,vinpairs(pargs)doargs[k]=vendlocalstr=mw.text.trim(args[1]orargs.sourceor"")localmatch=mw.text.trim(args[2]orargs.targetor""):gsub('"','')ifstr==""ormatch==""thenreturnnilendlocalplain=mw.text.trim(args[3]orargs.plainor"")ifplain=="false"thenplain=falseelseplain=trueendlocalnomatch=mw.text.trim(args[4]orargs.nomatchor"")-- just take the start positionlocalpos=mw.ustring.find(str,match,1,plain)ornomatchreturnposend-- split splits text at boundaries specified by separator-- and returns the chunk for the index idx (starting at 1)-- #invoke:String2 |split |text |separator |index |true/false-- #invoke:String2 |split |txt=text |sep=separator |idx=index |plain=true/false-- if plain is false/no/0 then separator is treated as a Lua pattern - defaults to plain=truep.split=function(frame)localargs=frame.argsifnot(args[1]orargs.txt)thenargs=frame:getParent().argsendlocaltxt=args[1]orargs.txtor""iftxt==""thenreturnnilendlocalsep=(args[2]orargs.sepor""):gsub('"','')localidx=tonumber(args[3]orargs.idx)or1localplain=(args[4]orargs.plainor"true"):sub(1,1)plain=(plain~="f"andplain~="n"andplain~="0")localsplittbl=mw.text.split(txt,sep,plain)ifidx<0thenidx=#splittbl+idx+1endreturnsplittbl[idx]end-- val2percent scans through a string, passed as either the first unnamed parameter or |txt=-- it converts each number it finds into a percentage and returns the resultant string.p.val2percent=function(frame)localargs=frame.argsifnot(args[1]orargs.txt)thenargs=frame:getParent().argsendlocaltxt=mw.text.trim(args[1]orargs.txtor"")iftxt==""thenreturnnilendlocalfunctionv2p(x)x=(tonumber(x)or0)*100ifx==math.floor(x)thenx=math.floor(x)endreturnx.."%"endtxt=txt:gsub("%d[%d%.]*",v2p)-- store just the stringreturntxtend-- one2a scans through a string, passed as either the first unnamed parameter or |txt=-- it converts each occurrence of 'one ' into either 'a ' or 'an ' and returns the resultant string.p.one2a=function(frame)localargs=frame.argsifnot(args[1]orargs.txt)thenargs=frame:getParent().argsendlocaltxt=mw.text.trim(args[1]orargs.txtor"")iftxt==""thenreturnnilendtxt=txt:gsub(" one "," a "):gsub("^one","a"):gsub("One ","A "):gsub("a ([aeiou])","an %1"):gsub("A ([aeiou])","An %1")returntxtend-- findpagetext returns the position of a piece of text in a page-- First positional parameter or |text is the search text-- Optional parameter |title is the page title, defaults to current page-- Optional parameter |plain is either true for plain search (default) or false for Lua pattern search-- Optional parameter |nomatch is the return value when no match is found; default is nilp._findpagetext=function(args)-- process parameterslocalnomatch=args.nomatchor""ifnomatch==""thennomatch=nilend--localtext=mw.text.trim(args[1]orargs.textor"")iftext==""thenreturnnilend--localtitle=args.titleor""localtitleobjiftitle==""thentitleobj=mw.title.getCurrentTitle()elsetitleobj=mw.title.new(title)end--localplain=args.plainor""ifplain:sub(1,1)=="f"thenplain=falseelseplain=trueend-- get the page content and look for 'text' - return position or nomatchlocalcontent=titleobj:getContent()returnmw.ustring.find(content,text,1,plain)ornomatch-- returns multiple valuesendp.findpagetext=function(frame)localargs=frame.argslocalpargs=frame:getParent().argsfork,vinpairs(pargs)doargs[k]=vendifnot(args[1]orargs.text)thenreturnnilend-- just the first valuereturn(p._findpagetext(args))end-- what follows was merged from Module:StringFunc-- helper functionsp._GetParameters=require('Module:GetParameters')-- Argument list helper function, as per Module:Stringp._getParameters=p._GetParameters.getParameters-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:Stringfunctionp._escapePattern(pattern_str)returnmw.ustring.gsub(pattern_str,"([%(%)%.%%%+%-%*%?%[%^%$%]])","%%%1");end-- Helper Function to interpret boolean strings, as per Module:Stringp._getBoolean=p._GetParameters.getBoolean--[[StripThis function Strips characters from stringUsage:{{#invoke:String2|strip|source_string|characters_to_strip|plain_flag}}Parameters source: The string to strip chars: The pattern or list of characters to strip from string, replaced with '' plain: A flag indicating that the chars should be understood as plain text. defaults to true.Leading and trailing whitespace is also automatically stripped from the string.]]functionp.strip(frame)localnew_args=p._getParameters(frame.args,{'source','chars','plain'})localsource_str=new_args['source']or'';localchars=new_args['chars']or''or'characters';source_str=mw.text.trim(source_str);ifsource_str==''orchars==''thenreturnsource_str;endlocall_plain=p._getBoolean(new_args['plain']ortrue);ifl_plainthenchars=p._escapePattern(chars);endlocalresult;result=mw.ustring.gsub(source_str,"["..chars.."]",'')returnresult;endreturnp