Modul:Text

localyesNo=require("Modul:Yesno")
localText={serial="2024-09-21",
suite="Text"}
--[=[
Text utilities
]=]
localfunctionfiatQuote(apply,alien,advance)
-- Quote text
-- Parameter:
--     apply    -- string, with text
--     alien    -- string, with language code
--     advance  -- number, with level 1 or 2
localr=applyandtostring(apply)or""
alien=alienor"en"
advance=tonumber(advance)or0
localsuite
localdata=mw.loadData('Modul:Text/data')
localQuoteLang=data.QuoteLang
localQuoteType=data.QuoteType
localslang=alien:match("^(%l+)-")
suite=QuoteLang[alien]orslangandQuoteLang[slang]orQuoteLang["en"]
ifsuitethen
localquotes=QuoteType[suite]
ifquotesthen
localspace
ifquotes[3]then
space=" "
else
space=""
end
quotes=quotes[advance]
ifquotesthen
r=mw.ustring.format("%s%s%s%s%s",
mw.ustring.char(quotes[1]),
space,
apply,
space,
mw.ustring.char(quotes[2]))
end
else
mw.log("fiatQuote() "..suite)
end
end
returnr
end-- fiatQuote()
Text.char=function(apply,again,accept)
-- Create string from codepoints
-- Parameter:
--     apply   -- table (sequence) with numerical codepoints, or nil
--     again   -- number of repetitions, or nil
--     accept  -- true, if no error messages to be appended
-- Returns: string
localr=""
apply=type(apply)=="table"andapplyor{}
again=math.floor(tonumber(again)or1)
ifagain<1then
return""
end
localbad={}
localcodes={}
for_,vinipairs(apply)do
localn=tonumber(v)
ifnotnor(n<32andn~=9andn~=10)then
table.insert(bad,tostring(v))
else
table.insert(codes,math.floor(n))
end
end
if#bad>0then
ifnotacceptthen
r=tostring(mw.html.create("span")
:addClass("error")
:wikitext("titik kode tidak valid: "..table.concat(bad," ")))
end
returnr
end
if#codes>0then
r=mw.ustring.char(unpack(codes))
ifagain>1then
r=r:rep(again)
end
end
returnr
end-- Text.char()
localfunctiontrimAndFormat(args,fmt)
localresult={}
iftype(args)~='table'then
args={args}
end
for_,vinipairs(args)do
v=mw.text.trim(tostring(v))
ifv~=""then
table.insert(result,fmtandmw.ustring.format(fmt,v)orv)
end
end
returnresult
end
Text.concatParams=function(args,apply,adapt)
-- Concat list items into one string
-- Parameter:
--     args   -- table (sequence) with numKey=string
--     apply  -- string (optional); separator (default: "|")
--     adapt  -- string (optional); format including "%s"
-- Returns: string
localcollect={}
returntable.concat(trimAndFormat(args,adapt),applyor"|")
end-- Text.concatParams()
Text.containsCJK=function(s)
-- Is any CJK code within?
-- Parameter:
--     s  -- string
-- Returns: true, if CJK detected
s=sandtostring(s)or""
localpatternCJK=mw.loadData('Modul:Text/data').PatternCJK
returnmw.ustring.find(s,patternCJK)~=nil
end-- Text.containsCJK()
Text.removeDelimited=function(s,prefix,suffix)
-- Remove all text in s delimited by prefix and suffix (inclusive)
-- Arguments:
--    s = string to process
--    prefix = initial delimiter
--    suffix = ending delimiter
-- Returns: stripped string
s=sandtostring(s)or""
prefix=prefixandtostring(prefix)or""
suffix=suffixandtostring(suffix)or""
localprefixLen=mw.ustring.len(prefix)
localsuffixLen=mw.ustring.len(suffix)
ifprefixLen==0orsuffixLen==0then
returns
end
locali=s:find(prefix,1,true)
localr=s
localj
whileido
j=r:find(suffix,i+prefixLen)
ifjthen
r=r:sub(1,i-1)..r:sub(j+suffixLen)
else
r=r:sub(1,i-1)
end
i=r:find(prefix,1,true)
end
returnr
end
Text.getPlain=function(adjust)
-- Remove wikisyntax from string, except templates
-- Parameter:
--     adjust  -- string
-- Returns: string
localr=Text.removeDelimited(adjust,"<!--","-->")
r=r:gsub("(</?%l[^>]*>)","")
:gsub("'''","")
:gsub("''","")
:gsub("&nbsp;"," ")
returnr
end-- Text.getPlain()
Text.isLatinRange=function(s)
-- Are characters expected to be latin or symbols within latin texts?
-- Arguments:
--  s = string to analyze
-- Returns: true, if valid for latin only
s=sandtostring(s)or""--- ensure input is always string
localPatternLatin=mw.loadData('Modul:Text/data').PatternLatin
returnmw.ustring.match(s,PatternLatin)~=nil
end-- Text.isLatinRange()
Text.isQuote=function(s)
-- Is this character any quotation mark?
-- Parameter:
--     s = single character to analyze
-- Returns: true, if s is quotation mark
s=sandtostring(s)or""
ifs==""then
returnfalse
end
localSeekQuote=mw.loadData('Modul:Text/data').SeekQuote
returnmw.ustring.find(SeekQuote,s,1,true)~=nil
end-- Text.isQuote()
Text.listToText=function(args,adapt)
-- Format list items similar to mw.text.listToText()
-- Parameter:
--     args   -- table (sequence) with numKey=string
--     adapt  -- string (optional); format including "%s"
-- Returns: string
returnmw.text.listToText(trimAndFormat(args,adapt))
end-- Text.listToText()
Text.quote=function(apply,alien,advance)
-- Quote text
-- Parameter:
--     apply    -- string, with text
--     alien    -- string, with language code, or nil
--     advance  -- number, with level 1 or 2, or nil
-- Returns: quoted string
apply=applyandtostring(apply)or""
localmode,slang
iftype(alien)=="string"then
slang=mw.text.trim(alien):lower()
else
slang=mw.title.getCurrentTitle().pageLanguage
ifnotslangthen
-- TODO FIXME: Introduction expected 2017-04
slang=mw.language.getContentLanguage():getCode()
end
end
ifadvance==2then
mode=2
else
mode=1
end
returnfiatQuote(mw.text.trim(apply),slang,mode)
end-- Text.quote()
Text.quoteUnquoted=function(apply,alien,advance)
-- Quote text, if not yet quoted and not empty
-- Parameter:
--     apply    -- string, with text
--     alien    -- string, with language code, or nil
--     advance  -- number, with level 1 or 2, or nil
-- Returns: string; possibly quoted
localr=mw.text.trim(applyandtostring(apply)or"")
locals=mw.ustring.sub(r,1,1)
ifs~=""andnotText.isQuote(s,advance)then
s=mw.ustring.sub(r,-1,1)
ifnotText.isQuote(s)then
r=Text.quote(r,alien,advance)
end
end
returnr
end-- Text.quoteUnquoted()
Text.removeDiacritics=function(adjust)
-- Remove all diacritics
-- Parameter:
--     adjust  -- string
-- Returns: string; all latin letters should be ASCII
--                  or basic greek or cyrillic or symbols etc.
localcleanup,decomposed
localPatternCombined=mw.loadData('Modul:Text/data').PatternCombined
decomposed=mw.ustring.toNFD(adjustandtostring(adjust)or"")
cleanup=mw.ustring.gsub(decomposed,PatternCombined,"")
returnmw.ustring.toNFC(cleanup)
end-- Text.removeDiacritics()
Text.sentenceTerminated=function(analyse)
-- Is string terminated by dot, question or exclamation mark?
--     Quotation, link termination and so on granted
-- Parameter:
--     analyse  -- string
-- Returns: true, if sentence terminated
localr
localPatternTerminated=mw.loadData('Modul:Text/data').PatternTerminated
ifmw.ustring.find(analyse,PatternTerminated)then
r=true
else
r=false
end
returnr
end-- Text.sentenceTerminated()
Text.ucfirstAll=function(adjust)
-- Capitalize all words
-- Arguments:
--     adjust = string to adjust
-- Returns: string with all first letters in upper case
adjust=adjustandtostring(adjust)or""
localr=mw.text.decode(adjust,true)
locali=1
localc,j,m
m=(r~=adjust)
r=" "..r
whileido
i=mw.ustring.find(r,"%W%l",i)
ifithen
j=i+1
c=mw.ustring.upper(mw.ustring.sub(r,j,j))
r=string.format("%s%s%s",
mw.ustring.sub(r,1,i),
c,
mw.ustring.sub(r,i+2))
i=j
end
end-- while i
r=r:sub(2)
ifmthen
r=mw.text.encode(r)
end
returnr
end-- Text.ucfirstAll()
Text.uprightNonlatin=function(adjust)
-- Ensure non-italics for non-latin text parts
--     One single greek letter might be granted
-- Precondition:
--     adjust  -- string
-- Returns: string with non-latin parts enclosed in <span>
localr
localdata=mw.loadData('Modul:Text/data')
localPatternLatin=data.PatternLatin
localRangesLatin=data.RangesLatin
localNumLatinRanges=data.NumLatinRanges
ifmw.ustring.match(adjust,PatternLatin)then
-- latin only, horizontal dashes, quotes
r=adjust
else
localc
localj=false
localk=1
localm=false
localn=mw.ustring.len(adjust)
localspan="%s%s<span dir='auto' style='font-style:normal'>%s</span>"
localflat=function(a)
-- isLatin
localrange
-- NumLatinRanges has to be precomputed because # does not work from loadData
fori=1,NumLatinRangesdo
range=RangesLatin[i]
ifa>=range[1]anda<=range[2]then
returntrue
end
end-- for i
end-- flat()
localfocus=function(a)
-- char is not ambivalent
localr=(a>64)
ifrthen
r=(a<8192ora>8212)
else
r=(a==38ora==60)-- '&' '<'
end
returnr
end-- focus()
localform=function(a)
returnstring.format(span,
r,
mw.ustring.sub(adjust,k,j-1),
mw.ustring.sub(adjust,j,a))
end-- form()
r=""
fori=1,ndo
c=mw.ustring.codepoint(adjust,i,i)
iffocus(c)then
ifflat(c)then
ifjthen
ifmthen
ifi==mthen
-- single greek letter.
j=false
end
m=false
end
ifjthen
localnx=i-1
locals=""
forix=nx,1,-1do
c=mw.ustring.sub(adjust,ix,ix)
ifc==" "orc=="("then
nx=nx-1
s=c..s
else
break-- for ix
end
end-- for ix
r=form(nx)..s
j=false
k=i
end
end
elseifnotjthen
j=i
ifc>=880andc<=1023then
-- single greek letter?
m=i+1
else
m=false
end
end
elseifmthen
m=m+1
end
end-- for i
ifjand(notmorm<n)then
r=form(n)
else
r=r..mw.ustring.sub(adjust,k)
end
end
returnr
end-- Text.uprightNonlatin()
Text.test=function(about)
localr
ifabout=="quote"then
data=mw.loadData('Modul:Text/data')
r={}
r.QuoteLang=data.QuoteLang
r.QuoteType=data.QuoteType
end
returnr
end-- Text.test()
-- Non Unicode-aware version of mw.text.split and mw.text.gsplit
-- based on [[phab:diffusion/ELUA/browse/master/includes/Engines/LuaCommon/lualib/mw.text.lua]]
-- These run up to 60 times faster than the Unicode-aware versions
Text.split=function(text,pattern,plain)
localret={}
forminText.gsplit(text,pattern,plain)do
ret[#ret+1]=m
end
returnret
end
Text.gsplit=function(text,pattern,plain)
locals,l=1,string.len(text)
returnfunction()
ifsthen
locale,n=string.find(text,pattern,s,plain)
localret
ifnotethen
ret=string.sub(text,s)
s=nil
elseifn<ethen
-- Empty separator!
ret=string.sub(text,s,e)
ife<lthen
s=e+1
else
s=nil
end
else
ret=e>sandstring.sub(text,s,e-1)or''
s=n+1
end
returnret
end
end,nil,nil
end
-- Export
localp={}
for_,funcinipairs({'containsCJK','isLatinRange','isQuote','sentenceTerminated'})do
p[func]=function(frame)
returnText[func](frame.args[1]or"")and"1"or""
end
end
for_,funcinipairs({'getPlain','removeDiacritics','ucfirstAll','uprightNonlatin'})do
p[func]=function(frame)
returnText[func](frame.args[1]or"")
end
end
functionp.char(frame)
localparams=frame:getParent().args
localstory=params[1]
localcodes,lenient,multiple
ifnotstorythen
params=frame.args
story=params[1]
end
ifstorythen
localitems=mw.text.split(mw.text.trim(story),"%s+")
if#items>0then
localj
lenient=(yesNo(params.errors)==false)
codes={}
multiple=tonumber(params["*"])
for_,vinipairs(items)do
j=tonumber((v:sub(1,1)=="x"and"0"or"")..v)
table.insert(codes,jorv)
end
end
end
returnText.char(codes,multiple,lenient)
end
functionp.concatParams(frame)
localargs
localtemplate=frame.args.template
iftype(template)=="string"then
template=mw.text.trim(template)
template=(template=="1")
end
iftemplatethen
args=frame:getParent().args
else
args=frame.args
end
returnText.concatParams(args,
frame.args.separator,
frame.args.format)
end
functionp.listToFormat(frame)
locallists={}
localpformat=frame.args["format"]
localsep=frame.args["sep"]or";"
-- Parameter parsen: Listen
fork,vinpairs(frame.args)do
localknum=tonumber(k)
ifknumthenlists[knum]=vend
end
-- Listen splitten
localmaxListLen=0
fori=1,#listsdo
lists[i]=mw.text.split(lists[i],sep)
if#lists[i]>maxListLenthenmaxListLen=#lists[i]end
end
-- Ergebnisstring generieren
localresult=""
localresult_line=""
fori=1,maxListLendo
result_line=pformat
forj=1,#listsdo
result_line=mw.ustring.gsub(result_line,"%%s",lists[j][i],1)
end
result=result..result_line
end
returnresult
end
functionp.listToText(frame)
localargs
localtemplate=frame.args.template
iftype(template)=="string"then
template=mw.text.trim(template)
template=(template=="1")
end
iftemplatethen
args=frame:getParent().args
else
args=frame.args
end
returnText.listToText(args,frame.args.format)
end
functionp.quote(frame)
localslang=frame.args[2]
iftype(slang)=="string"then
slang=mw.text.trim(slang)
ifslang==""then
slang=false
end
end
returnText.quote(frame.args[1]or"",
slang,
tonumber(frame.args[3]))
end
functionp.quoteUnquoted(frame)
localslang=frame.args[2]
iftype(slang)=="string"then
slang=mw.text.trim(slang)
ifslang==""then
slang=false
end
end
returnText.quoteUnquoted(frame.args[1]or"",
slang,
tonumber(frame.args[3]))
end
functionp.zip(frame)
locallists={}
localseps={}
localdefaultsep=frame.args["sep"]or""
localinnersep=frame.args["isep"]or""
localoutersep=frame.args["osep"]or""
-- Parameter parsen
fork,vinpairs(frame.args)do
localknum=tonumber(k)
ifknumthenlists[knum]=velse
ifstring.sub(k,1,3)=="sep"then
localsepnum=tonumber(string.sub(k,4))
ifsepnumthenseps[sepnum]=vend
end
end
end
-- sofern keine expliziten Separatoren angegeben sind, den Standardseparator verwenden
fori=1,math.max(#seps,#lists)do
ifnotseps[i]thenseps[i]=defaultsepend
end
-- Listen splitten
localmaxListLen=0
fori=1,#listsdo
lists[i]=mw.text.split(lists[i],seps[i])
if#lists[i]>maxListLenthenmaxListLen=#lists[i]end
end
localresult=""
fori=1,maxListLendo
ifi~=1thenresult=result..outersepend
forj=1,#listsdo
ifj~=1thenresult=result..innersepend
result=result..(lists[j][i]or"")
end
end
returnresult
end
functionp.split(frame)
localtext=frame.args.textorframe.args[1]or''
localpattern=frame.args.patternorframe.args[2]or''
localplain=yesNo(frame.args.plainorframe.args[3])
localindex=tonumber(frame.args.index)ortonumber(frame.args[4])or1
locala=Text.split(text,pattern,plain)
ifindex<0thenindex=#a+index+1end
returna[index]
end
functionp.failsafe()
returnText.serial
end
p.Text=function()
returnText
end-- p.Text
returnp