Module:string

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

localstr={}-- Cannot include null byte.localUTF8_char="[\1-\127\194-\244][\128-\191]*"--[[ulenCounts UTF-8 characters. Faster than mw.ustring.len.Assumes that the encoding is correct. Unlike mw.ustring.len, does not return nilif encoding is invalid.Does not count the bytes 192, 193, and 245-255. They are not used in UTF-8 andwill not occur if the string is valid. They are replaced with the replacementcharacter (U+FFFD) on MediaWiki pages.--]]functionstr.ulen(text)local_,length=string.gsub(text,UTF8_char,"")returnlengthend--[[lenThis function returns the length of the target string.Usage:{{#invoke:string|len|target_string|}}OR{{#invoke:string|len|s=target_string}}Parameters s: The string whose length to reportIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the target string.]]functionstr.len(frame)localnew_args=str._getParameters(frame.args,{'s'});locals=new_args['s']or'';returnmw.ustring.len(s)end--[[subThis function returns a substring of the target string at specified indices.Usage:{{#invoke:string|sub|target_string|start_index|end_index}}OR{{#invoke:string|sub|s=target_string|i=start_index|j=end_index}}Parameters s: The string to return a subset of i: The fist index of the substring to return, defaults to 1. j: The last index of the string to return, defaults to the last character.The first character of the string is assigned an index of 1. If either i or jis a negative value, it is interpreted the same as selecting a character bycounting from the end of the string. Hence, a value of -1 is the same asselecting the last character of the string.If the requested indices are out of range for the given string, an error isreported.]]functionstr.sub(frame)localnew_args=str._getParameters(frame.args,{'s','i','j'});locals=new_args['s']or'';locali=tonumber(new_args['i'])or1;localj=tonumber(new_args['j'])or-1;locallen=mw.ustring.len(s);-- Convert negatives for range checkingifi<0theni=len+i+1;endifj<0thenj=len+j+1;endifi>lenorj>lenori<1orj<1thenreturnstr._error('String subset index out of range');endifj<ithenreturnstr._error('String subset indices out of order');endreturnmw.ustring.sub(s,i,j)end--[[This function implements that features of {{str sub old}} and is kept in orderto maintain these older templates.]]functionstr.sublength(frame)locali=tonumber(frame.args.i)or0locallen=tonumber(frame.args.len)returnmw.ustring.sub(frame.args.s,i+1,lenand(i+len))end--[[matchThis function returns a substring from the source string that matches aspecified pattern.Usage:{{#invoke:string|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}OR{{#invoke:string|pos|s=source_string|pattern=pattern_string|start=start_index |match=match_number|plain=plain_flag|nomatch=nomatch_output}}Parameters s: The string to search pattern: The pattern or string to find within the string start: The index within the source string to start the search. The first character of the string has index 1. Defaults to 1. match: In some cases it may be possible to make multiple matches on a single string. This specifies which match to return, where the first match is match= 1. If a negative number is specified then a match is returned counting from the last match. Hence match = -1 is the same as requesting the last match. Defaults to 1. plain: A flag indicating that the pattern should be understood as plain text. Defaults to false. nomatch: If no match is found, output the "nomatch" value rather than an error.If invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from each string. In some circumstances this is desirable, inother cases one may want to preserve the whitespace.If the match_number or start_index are out of range for the string being queried, thenthis function generates an error. An error is also generated if no match is found.If one adds the parameter ignore_errors=true, then the error will be suppressed andan empty string will be returned on any failure.For information on constructing Lua patterns, a form of [regular expression], see:* http://www.lua.org/manual/5.1/manual.html#5.4.1* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns]]functionstr.match(frame)localnew_args=str._getParameters(frame.args,{'s','pattern','start','match','plain','nomatch'});locals=new_args['s']or'';localstart=tonumber(new_args['start'])or1;localplain_flag=str._getBoolean(new_args['plain']orfalse);localpattern=new_args['pattern']or'';localmatch_index=math.floor(tonumber(new_args['match'])or1);localnomatch=new_args['nomatch'];ifs==''thenreturnstr._error('Target string is empty');endifpattern==''thenreturnstr._error('Pattern string is empty');endifmath.abs(start)<1ormath.abs(start)>mw.ustring.len(s)thenreturnstr._error('Requested start is out of range');endifmatch_index==0thenreturnstr._error('Match index is out of range');endifplain_flagthenpattern=str.pattern_escape(pattern);endlocalresultifmatch_index==1then-- Find first match is simple caseresult=mw.ustring.match(s,pattern,start)elseifstart>1thens=mw.ustring.sub(s,start);endlocaliterator=mw.ustring.gmatch(s,pattern);ifmatch_index>0then-- Forward searchforwiniteratordomatch_index=match_index-1;ifmatch_index==0thenresult=w;break;endendelse-- Reverse searchlocalresult_table={};localcount=1;forwiniteratordoresult_table[count]=w;count=count+1;endresult=result_table[count+match_index];endendifresult==nilthenifnomatch==nilthenreturnstr._error('Match not found');elsereturnnomatch;endelsereturnresult;endend--[[posThis function returns a single character from the target string at position pos.Usage:{{#invoke:string|pos|target_string|index_value}}OR{{#invoke:string|pos|target=target_string|pos=index_value}}Parameters target: The string to search pos: The index for the character to returnIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the target string. In some circumstances this is desirable, inother cases one may want to preserve the whitespace.The first character has an index value of 1.If one requests a negative value, this function will select a character by counting backwardsfrom the end of the string. In other words pos = -1 is the same as asking for the last character.A requested value of zero, or a value greater than the length of the string returns an error.]]functionstr.pos(frame)localnew_args=str._getParameters(frame.args,{'target','pos'});localtarget_str=new_args['target']or'';localpos=tonumber(new_args['pos'])or0;ifpos==0ormath.abs(pos)>mw.ustring.len(target_str)thenreturnstr._error('String index out of range');endreturnmw.ustring.sub(target_str,pos,pos);end--[[str_findThis function duplicates the behavior of {{str_find}}, including all of its quirks.This is provided in order to support existing templates, but is NOT RECOMMENDED fornew code and templates. New code is recommended to use the "find" function instead.Returns the first index in "source" that is a match to "target". Indexing is 1-based,and the function returns -1 if the "target" string is not present in "source".Important Note: If the "target" string is empty / missing, this function returns avalue of "1", which is generally unexpected behavior, and must be accounted forseparatetly.]]functionstr.str_find(frame)localnew_args=str._getParameters(frame.args,{'source','target'});localsource_str=new_args['source']or'';localtarget_str=new_args['target']or'';iftarget_str==''thenreturn1;endlocalstart=mw.ustring.find(source_str,target_str,1,true)ifstart==nilthenstart=-1endreturnstartend--[[findThis function allows one to search for a target string or pattern within anotherstring.Usage:{{#invoke:string|find|source_str|target_string|start_index|plain_flag}}OR{{#invoke:string|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}Parameters source: The string to search target: The string or pattern to find within source start: The index within the source string to start the search, defaults to 1 plain: Boolean flag indicating that target should be understood as plain text and not as a Lua style regular expression, defaults to trueIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the parameter. In some circumstances this is desirable, inother cases one may want to preserve the whitespace.This function returns the first index >= "start" where "target" can be foundwithin "source". Indices are 1-based. If "target" is not found, then thisfunction returns an empty string. If either "source" or "target" are missing / empty, thisfunction also returns an empty string.This function should be safe for UTF-8 strings.]]functionstr.find(frame)localparams={[1]={required=true,allow_empty=true},[2]={required=true,allow_empty=true},[3]={type="number"},[4]={type="boolean"},}localargs=require("Module:parameters").process(frame.args,params)returnmw.ustring.find(args[1],args[2],args[3],args[4])end--[[replaceThis function allows one to replace a target string or pattern within anotherstring.Usage:{{#invoke:string|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}OR{{#invoke:string|replace|source=source_string|pattern=pattern_string|replace=replace_string| count=replacement_count|plain=plain_flag}}Parameters source: The string to search pattern: The string or pattern to find within source replace: The replacement text count: The number of occurences to replace, defaults to all. plain: Boolean flag indicating that pattern should be understood as plain text and not as a Lua style regular expression, defaults to true]]functionstr.replace(frame)localnew_args=str._getParameters(frame.args,{'source','pattern','replace','count','plain'});localsource_str=new_args['source']or'';localpattern=new_args['pattern']or'';localreplace=new_args['replace']or'';localcount=tonumber(new_args['count']);localplain=new_args['plain']ortrue;ifsource_str==''orpattern==''thenreturnsource_str;endplain=str._getBoolean(plain);ifplainthenpattern=str.pattern_escape(pattern);replace=mw.ustring.gsub(replace,"%%","%%%%");--Only need to escape replacement sequences.endlocalresult;result=mw.ustring.gsub(source_str,pattern,replace,count);returnresult;endfunctionstr.gsub(frame)localparams={[1]={required=true,allow_empty=true,allow_whitespace=true},[2]={required=true,allow_empty=true,allow_whitespace=true},[3]={required=true,allow_empty=true,allow_whitespace=true},[4]={type="number"},}localargs=require("Module:parameters").process(frame.args,params)return(mw.ustring.gsub(args[1],args[2],args[3],args[4]))end--[[ simple function to pipe string.rep to templates.]]functionstr.rep(frame)localrepetitions=tonumber(frame.args[2])ifnotrepetitionsthenreturnstr._error('function rep expects a number as second parameter, received "'..(frame.args[2]or'')..'"')endreturnstring.rep(frame.args[1]or'',repetitions)endfunctionstr.lower(frame)localtext=frame.args[1]or''returnmw.ustring.lower(text)endstr.lc=str.lower--[[formatThis function allows one to format strings according to a template. This is a direct interface ontostr.format() in Lua, and works like the C printf() function.For example:{{#invoke:string|format|page_%04d.html|65}}will produce the resultpage_0065.htmlParameters 1: The format template. See https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#string.format 2, 3, ...: Arguments to be inserted into the template.Note that leading and trailing whitespace is not removed from the arguments.]]functionstr.format(frame)localfmt=frame.args[1]-- You can't call unpack() directly on frame.args because it isn't really a-- table, and doesn't support the # operator.localargs={}locali=2whiletruedolocalval=frame.args[i]ifnotvalthenbreakendtable.insert(args,val)i=i+1endreturnfmt:format(unpack(args))end--[[Helper function that populates the argument list given that user may need to use a mix ofnamed and unnamed parameters. This is relevant because named parameters are notidentical to unnamed parameters due to string trimming, and when dealing with stringswe sometimes want to either preserve or remove that whitespace depending on the application.]]functionstr._getParameters(frame_args,arg_list)localnew_args={};localindex=1;localvalue;for_,arginipairs(arg_list)dovalue=frame_args[arg]ifvalue==nilthenvalue=frame_args[index];index=index+1;endnew_args[arg]=value;endreturnnew_args;end--[[Helper function to handle error messages.]]functionstr._error(error_str)localframe=mw.getCurrentFrame();localerror_category=frame.args.error_categoryor'Errors reported by Module String';localignore_errors=frame.args.ignore_errorsorfalse;localno_category=frame.args.no_categoryorfalse;ifstr._getBoolean(ignore_errors)thenreturn'';endlocalerror_str='<strong class="error">String Module Error: '..error_str..'</strong>';iferror_category~=''andnotstr._getBoolean(no_category)thenerror_str='[[Category:'..error_category..']]'..error_str;endreturnerror_str;end--[[Helper Function to interpret boolean strings]]functionstr._getBoolean(boolean_str)localboolean_value;iftype(boolean_str)=='string'thenboolean_str=boolean_str:lower();ifboolean_str=='false'orboolean_str=='no'orboolean_str=='0'orboolean_str==''thenboolean_value=false;elseboolean_value=true;endelseiftype(boolean_str)=='boolean'thenboolean_value=boolean_str;elseerror('No boolean value found');endreturnboolean_valueend--[[Helper function that escapes all pattern characters – ().%+-*?[^$] – so that they will be treatedas plain text.]]functionstr.pattern_escape(pattern_str)localinvoked=falselocalescape=require("Module:string/pattern_escape")iftype(pattern_str)=="table"thenifpattern_str.argsthenlocalframe=pattern_strinvoked=trueifframe.args[1]thenpattern_str=frame.args[1]elsepattern_str=frame:getParent().args[1]endelseerror("First argument to pattern_escape should be a string, a number, or a frame object.")endelseifnot(type(pattern_str)=="string"ortype(pattern_str)=="number")thenerror("First argument to pattern_escape should be a string or a number.")endifinvokedthenreturn(escape(pattern_str))-- only the first valueelsereturnescape(pattern_str)endendfunctionstr.count(text,pattern,plain)ifnot(type(text)=="string"ortype(text)=="number")thenerror('The first argument to the function "count" must be a string or a number, not a '..type(text)..'.')endifnot(type(pattern)=="string"ortype(pattern)=="number")thenerror('The first argument to the function "count" must be a string or a number, not a '..type(text)..'.')endifplainthenpattern=str.pattern_escape(pattern)endlocal_,count=mw.ustring.gsub(text,pattern,"")returncountendfunctionstr.plain_gsub(text,pattern,replacement)localinvoked=falseiftype(text)=="table"theninvoked=trueiftext.argsthenlocalframe=textlocalparams={[1]={},[2]={},[3]={allow_empty=true},}localargs=require("Module:parameters").process(frame.args,params)text=args[1]pattern=args[2]replacement=args[3]elseerror("If the first argument to plain_gsub is a table, it should be a frame object.")endelseifnot(type(pattern)=="string"ortype(pattern)=="number")thenerror("The second argument to plain_gsub should be a string or a number.")endifnot(type(replacement)=="string"ortype(replacement)=="number")thenerror("The third argument to plain_gsub should be a string or a number.")endendpattern=str.pattern_escape(pattern)ifinvokedthentext=mw.ustring.gsub(text,pattern,replacement)returntextelsereturnmw.ustring.gsub(text,pattern,replacement)endendfunctionstr.matchToArray(text,pattern)localinvoked=falseiftype(text)=="table"theninvoked=trueiftext.argsthenlocalframe=textlocalparams={[1]={required=true},[2]={required=true},}localargs=require("Module:parameters").process(frame.args,params)text=args[1]pattern=args[2]elseerror("If the first argument to matchToArray is a table, it should be a frame object.")endelseifnot(type(pattern)=="string"ortype(pattern)=="number")thenerror("The second argument to matchToArray should be a string or a number.")endendlocalmatches={}locali=0formatchinmw.ustring.gmatch(text,pattern)doi=i+1matches[i]=matchendifi>0thenifinvokedthenreturntable.concat(matches,", ")elsereturnmatchesendelseifinvokedthenreturn""elsereturnnilendendend--[=[ Similar to gmatch, but it returns the count of the match in addition to the list of captures, something like ipairs(). If the pattern doesn't contain any captures, the whole match is returned. Invoke thus: for i, whole_match in require("Module:string").imatch(text, pattern) do [ do something with i and whole_match ] end or for i, capture1[, capture2[, capture3[, ...]]] in require("Module:string").imatch(text, pattern) do [ do something with i and capture1 ] end For example, this code for i, whole_match in require("Module:string").imatch("a b c", "[a-z]") do mw.log(i, whole_match) end will log 1 a 2 b 3 c]=]functionstr.imatch(text,pattern,pos,plain,use_basic_Lua_function)locali=0pos=posor0ifnotstring.find(pattern,"%b()")thenpattern="("..pattern..")"endlocalfind=use_basic_Lua_functionandstring.findormw.ustring.findreturnfunction()i=i+1localreturn_values={find(text,pattern,pos,plain)}localj=return_values[2]ifreturn_values[3]thenpos=j+1-- Skip the first two returned values, which are the indices of the-- whole match.returni,unpack(return_values,3)endendendfunctionstr.escapebytes(s)return(string.gsub(s,'.',function(char)return('\\%03d'):format(string.byte(char))end))endfunctionstr.URIdecode(frame)returnmw.uri.decode(frame.args[1],frame.args[2]or"PATH")end--Reverses a UTF8 string; equivalent to string.reversefunctionstr.reverse(s)s=s:gsub(UTF8_char,function(c)return#c>1andc:reverse()end)returns:reverse()endreturnstr