--[=[Lua support for the {{lang}}, {{lang-xx}}, and {{transliteration}} templates and replacement of various supporting templates.]=]require('strict');localgetArgs=require('Module:Arguments').getArgs;localunicode=require("Module:Unicode data");-- for is_latin() and is_rtl()localyesno=require('Module:Yesno');locallang_data=mw.loadData('Module:Lang/data');-- language name override and transliteration tool-tip tableslocallang_name_table=lang_data.lang_name_table;-- language codes, names, regions, scripts, suppressed scriptslocallang_table=lang_data.lang_name_table.lang;locallang_dep_table=lang_data.lang_name_table.lang_dep;localscript_table=lang_data.lang_name_table.script;localregion_table=lang_data.lang_name_table.region;localvariant_table=lang_data.lang_name_table.variant;localsuppressed_table=lang_data.lang_name_table.suppressed;localoverride_table=lang_data.override;localsynonym_table=mw.loadData('Module:Lang/ISO 639 synonyms');-- ISO 639-2/639-2T code translation to 639-1 codelocalnamespace=mw.title.getCurrentTitle().namespace;-- used for categorizationlocalcontent_lang=mw.language.getContentLanguage();localthis_wiki_lang_tag=content_lang.code;-- get this wiki's language taglocalthis_wiki_lang_dir=content_lang:getDir();-- get this wiki's language directionlocalinitial_style_state;-- set by lang_xx_normal() and lang_xx_italic()localmaint_cats={};-- maintenance categories go herelocalmaint_msgs={};-- and their messages go here--[[--------------------------< I S _ S E T >------------------------------------------------------------------Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.]]localfunctionis_set(var)returnnot(var==nilorvar=='');end--[[--------------------------< I N V E R T _ I T A L I C S >-------------------------------------------------This function attempts to invert the italic markup a args.text by adding/removing leading/trailing italic markupin args.text. Like |italic=unset, |italic=invert disables automatic italic markup. Individual leading/trailingapostrophes are converted to their html numeric entity equivalent so that the new italic markup doesn't becomebold markup inadvertently.Leading and trailing wiki markup is extracted from args.text into separate table elements. Addition, removal,replacement of wiki markup is handled by a string.gsub() replacement table operating only on these separate elements.In the string.gsub() matching pattern, '.*' matches empty string as well as the three expected wiki markup patterns.This function expects that markup in args.text is complete and correct; if it is not, oddness may result.]]localfunctioninvert_italics(source)localinvert_pattern_table={-- leading/trailing markup add/remove/replace patterns[""]="\'\'",-- empty string becomes italic markup["\'\'"]="",-- italic markup becomes empty string["\'\'\'"]="\'\'\'\'\'",-- bold becomes bold italic["\'\'\'\'\'"]="\'\'\'",-- bold italic become bold};localseg={};source=source:gsub("%f[\']\'%f[^\']",''');-- protect single quote marks from being interpreted as bold markupseg[1]=source:match('^(\'\'+%f[^\']).+')or'';-- get leading markup, if any; ignore single quoteseg[3]=source:match('.+(%f[\']\'\'+)$')or'';-- get trailing markup, if any; ignore single quoteif''~=seg[1]and''~=seg[3]then-- extract the 'text'seg[2]=source:match('^\'\'+%f[^\'](.+)%f[\']\'\'+$')-- from between leading and trailing markupelseif''~=seg[1]thenseg[2]=source:match('^\'\'+%f[^\'](.+)')-- following leading markupelseif''~=seg[3]thenseg[2]=source:match('(.+)%f[\']\'\'+$')-- preceding trailing markupelseseg[2]=source-- when there is no markupendseg[1]=invert_pattern_table[seg[1]]orseg[1];-- replace leading markup according to pattern tableseg[3]=invert_pattern_table[seg[3]]orseg[3];-- replace leading markup according to pattern tablereturntable.concat(seg);-- put it all back together and doneend--[[--------------------------< V A L I D A T E _ I T A L I C >------------------------------------------------validates |italic= or |italics= assigned values.When |italic= is set and has an acceptible assigned value, return the matching css font-style property value or,for the special case 'default', return nil.When |italic= is not set, or has an unacceptible assigned value, return nil and a nil error message.When both |italic= and |italics= are set, returns nil and a 'conflicting' error message.The return value nil causes the calling lang, lang_xx, or transl function to set args.italic according to the template'sdefined default ('inherit' for {{lang}}, 'inherit' or 'italic' for {{lang-xx}} depending onthe individual template's requirements, 'italic' for {{transliteration}}) or to the value appropriate to |script=, if set ({{lang}}and {{lang-xx}} only).Accepted values and the values that this function returns are are:nil-when |italic= absent or not set; returns nildefault-for completeness, should rarely if ever be used; returns nilyes-force args.text to be rendered in italic font; returns 'italic'no-force args.text to be rendered in normal font; returns 'normal'unset-disables font control so that font-style applied to text is dictated by markup inside or outside the template; returns 'inherit'invert-disables font control so that font-style applied to text is dictated by markup outside or inverted inside the template; returns 'invert']]localfunctionvalidate_italic(args)localproperties={['yes']='italic',['no']='normal',['unset']='inherit',['invert']='invert',['default']=nil};localcount=0for_,arginpairs{'italic','italics','i'}doifargs[arg]thencount=count+1endendifcount>1then-- return nil and an error message if more than one is setreturnnil,'only one of |italic=, |italics=, or |i= can be specified';endreturnproperties[args.italicorargs.italicsorargs.i],nil;-- return an appropriate value and a nil error messageend--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------Default behavior of the {{lang}} and {{lang-xx}} templates is to add categorization when the templates are used in mainspace.This default functionality may be suppressed by setting |nocat=yes or |cat=no. This function selects one of these two parametersto control categorization.Because having two parameters with 'opposite' names and 'opposite' values is confusing, this function accepts only affirmativevalues for |nocat= and only negative values for |cat=; in both cases the 'other' sense (and non-sense) is not accepted and theparameter is treated as if it were not set in the template.Sets args.nocat to true if categorization is to be turned off; to nil if the default behavior should apply.Accepted values for |nocat= are the text strings:'yes', 'y', 'true', 't', on, '1'-- [[Module:Yesno]] returns logical true for all of these; false or nil elsefor |cat='no', 'n', 'false', 'f', 'off', '0'-- [[Module:Yesno]] returns logical false for all of these; true or nil else]=]localfunctionvalidate_cat_args(args)ifnot(args.nocatorargs.cat)then-- both are nil, so categorizereturn;endiffalse==yesno(args.cat)ortrue==yesno(args.nocat)thenargs.nocat=true;-- set to true when args.nocat is affirmative; nil else (as if the parameter were not set in the template)else-- args.nocat is the parameter actually used.args.nocat=nil;endend--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------Whether needle is in haystack]]localfunctionin_array(needle,haystack)ifneedle==nilthenreturnfalse;endforn,vinipairs(haystack)doifv==needlethenreturnn;endendreturnfalse;end--[[--------------------------< F O R M A T _ I E T F _ T A G >------------------------------------------------prettify ietf tags to use recommended subtag formats:code: lower casescript: sentence caseregion: upper casevariant: lower caseprivate: lower case prefixed with -x-]]localfunctionformat_ietf_tag(code,script,region,variant,private)localout={};ifis_set(private)thenreturntable.concat({code:lower(),'x',private:lower()},'-');-- if private, all other tags ignoredendtable.insert(out,code:lower());ifis_set(script)thenscript=script:lower():gsub('^%a',string.upper);table.insert(out,script);endifis_set(region)thentable.insert(out,region:upper());endifis_set(variant)thentable.insert(out,variant:lower());endreturntable.concat(out,'-');end--[[--------------------------< G E T _ I E T F _ P A R T S >--------------------------------------------------extracts and returns IETF language tag parts:primary language subtag (required) - 2 or 3 character IANA language codescript subtag - four character IANA script coderegion subtag - two-letter or three digit IANA region codevariant subtag - four digit or 5-8 alnum variant code; only one variant subtag supportedprivate subtag - x- followed by 1-8 alnum private code; only supported with the primary language tagin any one of these formslanglang-variantlang-scriptlang-script-variantlang-regionlang-region-variantlang-script-regionlang-script-region-variantlang-x-privateeach of lang, script, region, variant, and private, when used, must be validLanguages with both two- and three-character code synonyms are promoted to the two-character synonym becausethe IANA registry file omits the synonymous three-character code; we cannot depend on browsers understandingthe synonymous three-character codes in the lang= attribute.For {{lang-xx}} templates, the parameters |script=, |region=, and |variant= are supported (not supported in {{lang}}because those parameters are superfluous to the IETF subtags in |code=)returns six values; all lower case. Valid parts are returned as themselves; omitted parts are returned as empty strings, invalidparts are returned as nil; the sixth returned item is an error message (if an error detected) or nil.see http://www.rfc-editor.org/rfc/bcp/bcp47.txt section 2.1]]localfunctionget_ietf_parts(source,args_script,args_region,args_variant)localcode,script,region,variant,private;-- ietf tag partsifnotis_set(source)thenreturnnil,nil,nil,nil,nil,'missing language tag';endlocalpattern={-- table of tables holding acceptibe ietf tag patterns and short names of the ietf part captured by the pattern{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$','s','r','v'},-- 1 - ll-Ssss-RR-variant (where variant is 4 digits){'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$','s','r','v'},-- 2 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits){'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$','s','r','v'},-- 3 - ll-Ssss-RR-variant (where variant is 5-8 alnum characters){'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$','s','r','v'},-- 4 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters){'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$','s','v'},-- 5 - ll-Ssss-variant (where variant is 4 digits){'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$','s','v'},-- 6 - ll-Ssss-variant (where variant is 5-8 alnum characters){'^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$','r','v'},-- 7 - ll-RR-variant (where variant is 4 digits){'^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$','r','v'},-- 8 - ll-DDD-variant (where region is 3 digits; variant is 4 digits){'^(%a%a%a?)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$','r','v'},-- 9 - ll-RR-variant (where variant is 5-8 alnum characters){'^(%a%a%a?)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$','r','v'},-- 10 - ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters){'^(%a%a%a?)%-(%d%d%d%d)$','v'},-- 11 - ll-variant (where variant is 4 digits){'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$','v'},-- 12 - ll-variant (where variant is 5-8 alnum characters){'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$','s','r'},-- 13 - ll-Ssss-RR{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$','s','r'},-- 14 - ll-Ssss-DDD (region is 3 digits){'^(%a%a%a?)%-(%a%a%a%a)$','s'},-- 15 - ll-Ssss{'^(%a%a%a?)%-(%a%a)$','r'},-- 16 - ll-RR{'^(%a%a%a?)%-(%d%d%d)$','r'},-- 17 - ll-DDD (region is 3 digits){'^(%a%a%a?)$'},-- 18 - ll{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$','p'},-- 19 - ll-x-pppppppp (private is 1-8 alnum characters)}localt={};-- table of captures; serves as a translator between captured ietf tag parts and named variablesfori,vinipairs(pattern)do-- spin through the pattern table looking for a matchlocalc1,c2,c3,c4;-- captures in the 'pattern' from the pattern table go herec1,c2,c3,c4=source:match(pattern[i][1]);-- one or more captures set if source matches pattern[i])ifc1then-- c1 always set on matchcode=c1;-- first capture is always codet={[pattern[i][2]or'x']=c2,-- fill the table of captures with the rest of the captures[pattern[i][3]or'x']=c3,-- take index names from pattern table and assign sequential captures[pattern[i][4]or'x']=c4,-- index name may be nil in pattern[i] table so "or 'x'" spoofs a name for this index in this table};script=t.sor'';-- translate table contents to named variables;region=t.ror'';-- absent table entries are nil so set named ietf parts to empty string for concatenationvariant=t.vor'';private=t.por'';break;-- and doneendendifnotcodethenreturnnil,nil,nil,nil,nil,table.concat({'unrecognized language tag: ',source});-- don't know what we got but it is malformedendcode=code:lower();-- ensure that we use and return lower case version of thisifnot(override_table[code]orlang_table[code]orsynonym_table[code]orlang_dep_table[code])thenreturnnil,nil,nil,nil,nil,table.concat({'unrecognized language code: ',code});-- invalid language code, don't know about the others (don't care?)endifsynonym_table[code]then-- if 639-2/639-2T code has a 639-1 synonymtable.insert(maint_cats,table.concat({'Lang and lang-xx code promoted to ISO 639-1|',code}));table.insert(maint_msgs,table.concat({'code: ',code,' promoted to code: ',synonym_table[code]}));code=synonym_table[code];-- use the synonymendifis_set(script)thenifis_set(args_script)thenreturncode,nil,nil,nil,nil,'redundant script tag';-- both code with script and |script= not allowedendelsescript=args_scriptor'';-- use args.script if providedendifis_set(script)thenscript=script:lower();-- ensure that we use and return lower case version of thisifnotscript_table[script]thenreturncode,nil,nil,nil,nil,table.concat({'unrecognized script: ',script,' for code: ',code});-- language code ok, invalid script, don't know about the others (don't care?)endendifsuppressed_table[script]then-- ensure that code-script does not use a suppressed scriptifin_array(code,suppressed_table[script])thenreturncode,nil,nil,nil,nil,table.concat({'script: ',script,' not supported for code: ',code});-- language code ok, script is suppressed for this codeendendifis_set(region)thenifis_set(args_region)thenreturncode,nil,nil,nil,nil,'redundant region tag';-- both code with region and |region= not allowedendelseregion=args_regionor'';-- use args.region if providedendifis_set(region)thenregion=region:lower();-- ensure that we use and return lower case version of thisifnotregion_table[region]thenreturncode,script,nil,nil,nil,table.concat({'unrecognized region: ',region,' for code: ',code});endendifis_set(variant)thenifis_set(args_variant)thenreturncode,nil,nil,nil,nil,'redundant variant tag';-- both code with variant and |variant= not allowedendelsevariant=args_variantor'';-- use args.variant if providedendifis_set(variant)thenvariant=variant:lower();-- ensure that we use and return lower case version of thisifnotvariant_table[variant]then-- make sure variant is validreturncode,script,region,nil,nil,table.concat({'unrecognized variant: ',variant});end-- does this duplicate/replace tests in lang() and lang_xx()?ifis_set(script)then-- if script set it must be part of the 'prefix'ifnotin_array(table.concat({code,'-',script}),variant_table[variant]['prefixes'])thenreturncode,script,region,nil,nil,table.concat({'unrecognized variant: ',variant,' for code-script pair: ',code,'-',script});endelseifis_set(region)then-- if region set, there are some prefixes that require lang code and region (en-CA-newfound)ifnotin_array(code,variant_table[variant]['prefixes'])then-- first see if lang code is all that's required (en-oxendict though en-GB-oxendict is preferred)ifnotin_array(table.concat({code,'-',region}),variant_table[variant]['prefixes'])then-- now try for lang code and region (en-CA-newfound)returncode,script,region,nil,nil,table.concat({'unrecognized variant: ',variant,' for code-region pair: ',code,'-',region});endendelse-- cheap way to determine if there are prefixes; fonipa and others don't have prefixes; # operator always returns 0ifvariant_table[variant]['prefixes'][1]andnotin_array(code,variant_table[variant]['prefixes'])thenreturncode,script,region,nil,nil,table.concat({'unrecognized variant: ',variant,' for code: ',code});endendendifis_set(private)thenprivate=private:lower();-- ensure that we use and return lower case version of thisifnotoverride_table[table.concat({code,'-x-',private})]then-- make sure private tag is valid; note that indexreturncode,script,region,nil,nil,table.concat({'unrecognized private tag: ',private});endendreturncode,script,region,variant,private,nil;-- return the good bits; make sure that msg is nilend--[[--------------------------< M A K E _ E R R O R _ M S G >--------------------------------------------------assembles an error message from template name, message text, help link, and error category.]]localfunctionmake_error_msg(msg,args,template)localout={};localcategory;if'Transliteration'==templatethencategory='Transliteration';elsecategory='Lang and lang-xx'endtable.insert(out,table.concat({'[',args.textor'undefined','] '}));-- for error messages output args.text if availabletable.insert(out,table.concat({'<span style=\"color:#d33\">Error: {{',template,'}}: '}));table.insert(out,msg);table.insert(out,table.concat({' ([[:Category:',category,' template errors|help]])'}));table.insert(out,'</span>');if(0==namespaceor10==namespace)andnotargs.nocatthen-- categorize in article space (and template space to take care of broken usages)table.insert(out,table.concat({'[[Category:',category,' template errors]]'}));endreturntable.concat(out);end--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------Makes a wikilink; when both link and display text is provided, returns a wikilink in the form [[L|D]]; if onlylink is provided, returns a wikilink in the form [[L]]; if neither are provided or link is omitted, returns anempty string.]=]localfunctionmake_wikilink(link,display)ifis_set(link)thenifis_set(display)thenreturntable.concat({'[[',link,'|',display,']]'});elsereturntable.concat({'[[',link,']]'});endelsereturn'';endend--[[--------------------------< D I V _ M A R K U P _ A D D >--------------------------------------------------adds <i> and </i> tags to list-item text or to implied <p>..</p> text. mixed not supported]]localfunctiondiv_markup_add(text,style)localimplied_p={};iftext:find('^\n[%*:;#]')then-- look for list markup; list markup must begin at start of textif'italic'==stylethenreturntext:gsub('(\n[%*:;#]+)([^\n]+)','%1<i>%2</i>');-- insert italic markup at each list itemelsereturntext;endendiftext:find('\n+')then-- look for any number of \n characters in texttext=text:gsub('([^\n])\n([^\n])','%1 %2');-- replace single newline characters with a space character which mimics mediawikiif'italic'==stylethentext=text:gsub('[^\n]+','<p><i>%1</i></p>');-- insert p and italic markup tags at each impled p (two or more consecutive '\n\n' sequences)elsetext=text:gsub('[^\n]+','<p>%1</p>');-- insert p markup at each impled ptext=text:gsub('\n','');-- strip newline charactersendendreturntext;end--[[--------------------------< T I T L E _ W R A P P E R _ M A K E >------------------------------------------makes a <span title="<title text>"><content_text></span> or <div title="<title text>"><content_text></div> where<title text> is in the tool-tip in the wiki's local language and <content_text> is non-local-language text inhtml markup. This because the lang= attibute applies to the content of its enclosing tag.<tag> holds a string 'div' or 'span' used to choose the correct wrapping tag]]localfunctiontitle_wrapper_make(title_text,content_text,tag)localwrapper_t={};table.insert(wrapper_t,table.concat({'<',tag}));-- open opening wrapper tagtable.insert(wrapper_t,' title=\"');-- begin title attributetable.insert(wrapper_t,title_text);-- add <title_text>table.insert(wrapper_t,'\">');-- end title attribute and close opening wrapper tagtable.insert(wrapper_t,content_text);-- add <content_text>table.insert(wrapper_t,table.concat({'</',tag,'>'}));-- add closing wrapper tagreturntable.concat(wrapper_t);-- make a big string and doneend--[[--------------------------< M A K E _ T E X T _ H T M L >--------------------------------------------------Add the html markup to text according to the type of content that it is: <span> or <i> tags for inline content or<div> tags for block contentThe lang= attribute also applies to the content of the tag where it is placed so this is wrong because 'Spanishlanguage text' is English:<i lang="es" title="Spanish language text">casa</i>should be:<span title="Spanish language text"><i lang="es">casa</i></span>or for <div>...</div>:<div title="Spanish language text"><div lang="es"><spanish-language-text></div></div>]]localfunctionmake_text_html(code,text,tag,rtl,style,size,language)localhtml_t={};localstyle_added='';localwrapper_tag=tag;-- <tag> gets modified so save a copy for use when/if we create a wrapper span or diviftext:match('^%*')thentable.insert(html_t,'*');-- move proto language text prefix outside of italic markup if any; use numeric entity because plain splat confuses MediaWikitext=text:gsub('^%*','');-- remove the splat from the textendif'span'==tagthen-- default html tag for inline contentif'italic'==stylethen-- but if italictag='i';-- change to <i> tagsendelse-- must be div so gotext=div_markup_add(text,style);-- handle implied <p>, implied <p> with <i>, and list markup (*;:#) with <i>endtable.insert(html_t,table.concat({'<',tag}));-- open the <i>, <span>, or <div> html tagcode=code:gsub('%-x%-.*','');-- strip private use subtag from code tag because meaningless outside of wikipediatable.insert(html_t,table.concat({' lang="',code,'\"'}));-- add language attributeif(rtlorunicode.is_rtl(text))and('ltr'==this_wiki_lang_dir)then-- text is right-to-left on a left-to-right wikitable.insert(html_t,' dir="rtl"');-- add direction attribute for right-to-left languageselseifnot(rtlorunicode.is_rtl(text))and('rtl'==this_wiki_lang_dir)then-- text is left-to-right on a right-to-left wikitable.insert(html_t,' dir="ltr"');-- add direction attribute for left-to-right languagesendif'normal'==stylethen-- when |italic=notable.insert(html_t,' style=\"font-style: normal;');-- override external markup, if anystyle_added='\"';-- remember that style attribute added and is not yet closedendifis_set(size)then-- when |size=<something>ifis_set(style_added)thentable.insert(html_t,table.concat({' font-size: ',size,';'}));-- add when style attribute already insertedelsetable.insert(html_t,table.concat({' style=\"font-size: ',size,';'}));-- create style attributestyle_added='\"';-- remember that style attribute added and is not yet closedendendtable.insert(html_t,table.concat({style_added,'>'}));-- close the opening html tagtable.insert(html_t,text);-- insert the texttable.insert(html_t,table.concat({'</',tag,'>'}));-- close the 'text' <i>, <span>, or <div> html tagifis_set(language)then-- create a <title_text> string for the title= attribute in a wrapper span or divlocaltitle_text;if'zxx'==codethen-- special case for this tag 'no linguistic content'title_text=table.concat({language,' text'});-- not a language so don't use 'language' in title textelseifmw.ustring.find(language,'languages',1,true)thentitle_text=table.concat({language,' collective text'});-- for collective languageselsetitle_text=table.concat({language,'-language text'});-- for individual languagesendreturntitle_wrapper_make(title_text,table.concat(html_t),wrapper_tag);elsereturntable.concat(html_t);endend--[=[-------------------------< M A K E _ C A T E G O R Y >----------------------------------------------------For individual language, <language>, returns:[[Category:Articles containing <language>-language text]]for English:[[Category:Articles containing explicitly cited English-language text]]for ISO 639-2 collective languages (and for 639-1 bh):[[Category:Articles with text in <language> languages]]]=]localfunctionmake_category(code,language_name,nocat,name_get)localcat={};localretval;if((0~=namespace)ornocat)andnotname_getthen-- only categorize in article spacereturn'';-- return empty string for concatenationendifmw.ustring.find(language_name,'languages',1,true)thenreturntable.concat({'[[Category:Articles with text in ',language_name,']]'});endtable.insert(cat,'[[Category:Articles containing ');ifthis_wiki_lang_tag==codethentable.insert(cat,'explicitly cited '..language_name);-- unique category name for the local languageelsetable.insert(cat,language_name);endtable.insert(cat,'-language text]]');returntable.concat(cat);end--[[--------------------------< M A K E _ T R A N S L I T >----------------------------------------------------return translit <i lang=xx-Latn>...</i> where xx is the language code; else return empty stringThe value |script= is not used in {{transliteration}} for this purpose; instead it uses |code. Because language scriptsare listed in the {{transliteration}} switches they are included in the data tables. The script parameter is introducedat {{Language with name and transliteration}}. If |script= is set, this function uses it in preference to code.To avoid confusion, in this module and the templates that use it, the transliteration script parameter is renamedto be |translit-script= (in this function, tscript)This function is used by both lang_xx() and transl()lang_xx() always provides code, language_name, and translit; may provide tscript; never provides styletransl() always provides language_name, translit, and one of code or tscript, never both; always provides styleFor {{transliteration}}, style only applies when a language code is provided]]localfunctionmake_translit(code,language_name,translit,std,tscript,style)localtitle;localout_t={};localtitle_t=lang_data.translit_title_table;-- table of transliteration standards and the language codes and scripts that apply to those standardslocaltitle_text='';-- tool tip text for title= attributestd=stdandstd:lower();-- lower case for table indexingifnotis_set(std)andnotis_set(tscript)then-- when neither standard nor script specifiedtitle_text=language_name;-- write a generic tool tipifnotmw.ustring.find(language_name,'languages',1,true)then-- collective language names (plural 'languages' is part of the name)title_text=title_text..'-language';-- skip this text (individual and macro languages only)endtitle_text=title_text..' romanization';-- finish the tool tip; use romanization when neither script nor standard suppliedelseifis_set(std)andis_set(tscript)then-- when both are specifiediftitle_t[std]then-- and if standard is legitimateiftitle_t[std][tscript]then-- and if script for that standard is legitimateifscript_table[tscript]thentitle_text=title_text..table.concat({title_t[std][tscript:lower()],' (',script_table[tscript],' script) transliteration'});-- add the appropriate text to the tool tipelsetitle_text=title_text..title_t[std]['default'];-- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?endelsetitle_text=title_text..title_t[std]['default'];-- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?endelsereturn'';-- invalid standard, setup for error messageendelseifis_set(std)then-- translit-script not set, use language codeifnottitle_t[std]thenreturn'';end-- invalid standard, setup for error messageiftitle_t[std][code]then-- if language code is in the table (transl may not provide a language code)title_text=title_text..table.concat({title_t[std][code:lower()],' (',language_name,' language) transliteration'});-- add the appropriate text to the tool tipelse-- code doesn't matchtitle_text=title_text..title_t[std]['default'];-- so use the standard's defaultendelse-- here if translit-script set but translit-std not setiftitle_t['no_std'][tscript]thentitle_text=title_text..title_t['no_std'][tscript];-- use translit-script if setelseiftitle_t['no_std'][code]thentitle_text=title_text..title_t['no_std'][code];-- use language codeelseifis_set(tscript)thentitle_text=title_text..table.concat({language_name,'-script transliteration'});-- write a script tool tipelseifis_set(code)thenifnotmw.ustring.find(language_name,'languages',1,true)then-- collective language names (plural 'languages' is part of the name)title_text=title_text..'-language';-- skip this text (individual and macro languages only)endtitle_text=title_text..' transliteration';-- finish the tool tipelsetitle_text=title_text..' transliteration';-- generic tool tip (can we ever get here?)endendendlocalclose_tag;ifis_set(code)then-- when a language code is provided (always with {{lang-xx}} templates, not always with {{transliteration}})code=code:match('^(%a%a%a?)');-- strip all subtags leaving only the language subtagifnotstylethen-- nil for the default italic styletable.insert(out_t,"<i lang=\"");-- so use <i> tagclose_tag='</i>';-- tag to be used when closingelsetable.insert(out_t,table.concat({'<span style=\"font-style: ',style,'\" lang=\"'}));-- non-standard style, construct a span tag for itclose_tag='</span>';-- tag to be used when closingendtable.insert(out_t,code);table.insert(out_t,"-Latn\">");-- transliterations are always Latin scriptelsetable.insert(out_t,"<span>");-- when no language code: no lang= attribute, not italic ({{transliteration}} only)close_tag='</span>';endtable.insert(out_t,translit);-- add the translit texttable.insert(out_t,close_tag);-- and add the appropriate </i> or </span>if''==title_textthen-- when there is no need for a tool-tipreturntable.concat(out_t);-- make a string and doneelsereturntitle_wrapper_make(title_text,table.concat(out_t),'span');-- wrap with a tool-tip span and donendend--[[--------------------------< V A L I D A T E _ T E X T >----------------------------------------------------This function checks the content of args.text and returns empty string if nothing is amiss else it returns anerror message. The tests are for empty or missing text and for improper or disallowed use of apostrophe markup.Italic rendering is controlled by the |italic= template parameter so italic markup should never appear in args.texteither as ''itself'' or as '''''bold italic''''' unless |italic=unset or |italic=invert.]]localfunctionvalidate_text(template,args)ifnotis_set(args.text)thenreturnmake_error_msg('no text',args,template);endifargs.text:find("%f[\']\'\'\'\'%f[^\']")orargs.text:find("\'\'\'\'\'[\']+")then-- because we're looking, look for 4 appostrophes or 6+ appostrophesreturnmake_error_msg('text has malformed markup',args,template);endlocalstyle=args.italic;if('unset'~=style)and('invert'~=style)thenifargs.text:find("%f[\']\'\'%f[^\']")orargs.text:find("%f[\']\'\'\'\'\'%f[^\']")then-- italic but not bold, or bold italicreturnmake_error_msg('text has italic markup',args,template);endendend--[[--------------------------< R E N D E R _ M A I N T >------------------------------------------------------render mainenance messages and categories]]localfunctionrender_maint(nocat)localmaint={};if0<#maint_msgsthen-- when there are maintenance messagestable.insert(maint,table.concat({'<span class="lang-comment" style="font-style: normal; display: none; color: #33aa33; margin-left: 0.3em;">'}));-- opening <span> tagfor_,msginipairs(maint_msgs)dotable.insert(maint,table.concat({msg,' '}));-- add message stringsendtable.insert(maint,'</span>');-- close the spanendif(0<#maint_cats)and(0==namespace)andnotnocatthen-- when there are maintenance categories; article namespace onlyfor_,catinipairs(maint_cats)dotable.insert(maint,table.concat({'[[Category:',cat,']]'}));-- format and add the categoriesendendreturntable.concat(maint);end--[[--------------------------< P R O T O _ P R E F I X >------------------------------------------------------for proto languages, text is prefixed with a splat. We do that here as a flag for make_text_html() so that a splatwill be rendered outside of italic markup (if used). If the first character in text here is already a splat, wedo nothingproto_param is boolean or nil; true adds splat prefix regardless of language name; false removes and / or inhibitsregardless of language name; nil does nothing; presumes that the value in text is correct but removes extra splac]]localfunctionproto_prefix(text,language_name,proto_param)iffalse==proto_paramthen-- when forced by |proto=noreturntext:gsub('^%**','');-- return text without splat prefix regardless of language name or existing splat prefix in textelseif(language_name:find('^Proto%-')or(true==proto_param))then-- language is a proto or forced by |proto=yesreturntext:gsub('^%**','*');-- prefix proto-language text with a splat; also removes duplicate prefixing splatsendreturntext:gsub('^%*+','*');-- return text unmolested except multiple splats reduced to one splatend--[[--------------------------< H A S _ P O E M _ T A G >------------------------------------------------------looks for a poem strip marker in text; returns true when found; false elseauto-italic detection disabled when text has poem stripmarker because it is not possible for this code to knowthe content that will replace the stripmarker.]]localfunctionhas_poem_tag(text)returntext:find('\127[^\127]*UNIQ%-%-poem%-[%a%d]+%-QINU[^\127]*\127')andtrueorfalse;end--[[--------------------------< H T M L _ T A G _ S E L E C T >------------------------------------------------Inspects content of and selectively trims text. Returns text and the name of an appropriate html tag for text.If text contains:\n\ntext has implied <p>..</p> tags - trim leading and trailing whitespace and returnIf text begins with list markup:\n*unordered\n;definition\n:definition\n#orderedtrim all leading whitespace except \n and trim all trailing whitespaceIf text contains <poem>...</poem> stripmarker, return text unmodified and choose <div>..</div> tags becausethe stripmarker is replaced with text wrapped in <div>..</div> tags.If the text contains any actual <div>...</div> tags, then it's again returned unmodified and <div>...</div>tags are used to wrap it, to prevent div/span inversion.]]localfunctionhtml_tag_select(text)localtag;ifhas_poem_tag(text)then-- contains poem stripmarker (we can't know the content of that)tag='div';-- poem replacement is in div tags so lang must use div tagselseiftext:find('<div')then-- reductive; if the text contains a div tag, we must use div tagstag='div';elseifmw.text.trim(text):find('\n\n+')then-- contains implied p tagstext=mw.text.trim(text);-- trim leading and trailing whitespace characterstag='div';-- must be div because span may not contain p tags (added later by MediaWiki); poem replacement is in div tagselseiftext:find('\n[%*:;%#]')then-- if text has list markuptext=text:gsub('^[\t\r\f ]*',''):gsub('%s*$','');-- trim all whitespace except leading newline character '\n'tag='div';-- must be div because span may not contain ul, dd, dl, ol tags (added later by MediaWiki)elsetext=mw.text.trim(text);-- plain texttag='span';-- so span is fineendreturntext,tag;end--[[--------------------------< V A L I D A T E _ P R O T O >--------------------------------------------------validates value assigned to |proto=; permitted values are yes and no; yes returns as true, no returns as false,empty string (or parameter omitted) returns as nil; any other value returns as nil with a second return value oftrue indicating that some other value has been assigned to |proto=]]localfunctionvalidate_proto(proto_param)if'yes'==proto_paramthenreturntrue;elseif'no'==proto_paramthenreturnfalse;elseifis_set(proto_param)thenreturnnil,true;-- |proto= something other than 'yes' or 'no'elsereturnnil;-- missing or emptyendend--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------common function to return language name from the data set according to IETF tagreturns language name if found in data tables; nil else]]localfunctionlanguage_name_get(ietf,code,cat)ietf=ietf:lower();-- ietf:lower() because format_ietf_tag() returns mixed caselocalname;-- remains nil if not foundifoverride_table[ietf]then-- look for whole IETF tag in override tablename=override_table[ietf];elseifoverride_table[code]then-- not there so try basic language tagname=override_table[code];elseiflang_table[code]then-- shift to iana active tag/name tablename=lang_table[code];elseiflang_dep_table[code]then-- try the iana deprecated tag/name tablename=lang_dep_table[code];endiflang_dep_table[code]andcatthen-- because deprecated code may have been overridden to en.wiki preferred nametable.insert(maint_cats,table.concat({'Lang and lang-xx using deprecated ISO 639 codes|',code}));table.insert(maint_msgs,table.concat({'code: ',code,' is deprecated'}));endreturnname;-- name from data tables or nilend--[[--------------------------< _ L A N G >--------------------------------------------------------------------entry point for {{lang}}there should be no reason to set parameters in the {{lang}} {{#invoke:}}<includeonly>{{#invoke:lang|lang}}</includeonly>parameters are received from the template's frame (parent frame)]]localfunction_lang(args)localout={};locallanguage_name;-- used to make category nameslocalcategory_name;-- same as language_name except that it retains any parenthetical disambiguators (if any) from the data setlocalsubtags={};-- IETF subtags script, region, variant, and privatelocalcode;-- the language codelocalmsg;-- for error messageslocaltag='span';-- initial value for make_text_html()localtemplate=args.templateor'Lang';maint_cats={};-- initialize because when this module required into another module, these only declared once so only initialzed oncemaint_msgs={};validate_cat_args(args);-- determine if categorization should be suppressedifargs[1]andargs.codethenreturnmake_error_msg('conflicting: {{{1}}} and |code=',args,template);elseargs.code=args[1]orargs.code;-- prefer args.codeendifargs[2]andargs.textthenreturnmake_error_msg('conflicting: {{{2}}} and |text=',args,template);elseargs.text=args[2]orargs.text;-- prefer args.textendmsg=validate_text(template,args);-- ensure that |text= is setifis_set(msg)then-- msg is an already-formatted error messagereturnmsg;endargs.text,tag=html_tag_select(args.text);-- inspects text; returns appropriate html tag with text trimmed accordinglyargs.rtl=args.rtl=='yes';-- convert to boolean: 'yes' -> true, other values -> falseargs.proto,msg=validate_proto(args.proto);-- return boolean, or nil, or nil and error message flagifmsgthenreturnmake_error_msg(table.concat({'invalid |proto=: ',args.proto}),args,template);endcode,subtags.script,subtags.region,subtags.variant,subtags.private,msg=get_ietf_parts(args.code);-- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})ifmsgthenreturnmake_error_msg(msg,args,template);endargs.italic,msg=validate_italic(args);ifmsgthenreturnmake_error_msg(msg,args,template);endifnil==args.italicthen-- nil when |italic= absent or not set or |italic=default; args.italic controlsif('latn'==subtags.script)or-- script is latn(this_wiki_lang_tag~=codeandnotis_set(subtags.script)andnothas_poem_tag(args.text)andunicode.is_Latin(args.text))then-- text not this wiki's language, no script specified and not in poem markup but is wholly latn script (auto-italics)args.italic='italic';-- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italicelseargs.italic='inherit';-- italic not set; script not latn; inherit current styleendendifis_set(subtags.script)then-- if script set, override rtl settingifin_array(subtags.script,lang_data.rtl_scripts)thenargs.rtl=true;-- script is an rtl scriptelseargs.rtl=false;-- script is not an rtl scriptendendargs.code=format_ietf_tag(code,subtags.script,subtags.region,subtags.variant,subtags.private);-- format to recommended subtag styleslanguage_name=language_name_get(args.code,code,true);-- get language name; try ietf tag first, then code w/o variant then code w/ variantif'invert'==args.italicand'span'==tagthen-- invert only supported for in-line contentargs.text=invert_italics(args.text)endargs.text=proto_prefix(args.text,language_name,args.proto);-- prefix proto-language text with a splattable.insert(out,make_text_html(args.code,args.text,tag,args.rtl,args.italic,args.size,language_name));table.insert(out,make_category(code,language_name,args.nocat));table.insert(out,render_maint(args.nocat));-- maintenance messages and categoriesreturntable.concat(out);-- put it all together and doneend--[[--------------------------< L A N G >----------------------------------------------------------------------entry point for {{lang}}there should be no reason to set parameters in the {{lang}} {{#invoke:}}<includeonly>{{#invoke:lang|lang}}</includeonly>parameters are received from the template's frame (parent frame)]]localfunctionlang(frame)localargs=getArgs(frame,{-- this code so that we can detect and handle wiki list markup in textvalueFunc=function(key,value)if2==keyor'text'==keythen-- the 'text' parameter; do not trim wite spacereturnvalue;-- return untrimmed 'text'elseifvaluethen-- all other values: if the value is not nilvalue=mw.text.trim(value);-- trim whitespaceif''~=valuethen-- empty string when value was only whitespacereturnvalue;endendreturnnil;-- value was empty or contained only whitespaceend-- end of valueFunc});return_lang(args);end--[[--------------------------< T R A N S L A T I O N _ M A K E >----------------------------------------------stand-alone function to create literal translation of main textAlso used by {{lang-x2}}]]localfunctiontranslation_make(args_t)localtranslation_t={', '};-- initialize outputif'none'~=args_t.labelthen-- if we want a labeltable.insert(translation_t,'<small>');-- open the <small> html tagif'no'==args_t.linkthentable.insert(translation_t,'<abbr title="literal translation">lit.</abbr>');-- unlinked formelsetable.insert(translation_t,make_wikilink('Literal translation','lit.'));-- linked formendtable.insert(translation_t," </small>");-- close the <small> html tagendtable.insert(translation_t,table.concat({''',args_t.translation,'''}));-- use html entities to avoid wiki markup confusionreturntable.concat(translation_t);-- make a big string and doneend--[[--------------------------< L A N G _ X X >----------------------------------------------------------------For the {{lang-xx}} templates, the only parameter required to be set in the template is the language code. Allother parameters can, usually should, be written in the template call. For {{lang-xx}} templates for languagesthat can have multiple writing systems, it may be appropriate to set |script= as well.For each {{lang-xx}} template choose the appropriate entry-point function so that this function knows the defaultstyling that should be applied to text.For normal, upright style:<includeonly>{{#invoke:lang|lang_xx_inherit|code=xx}}</includeonly>For italic style:<includeonly>{{#invoke:lang|lang_xx_italic|code=xx}}</includeonly>All other parameters should be received from the template's frame (parent frame)Supported parameters are:|code = (required) the IANA language code|script = IANA script code; especially for use with languages that use multiple writing systems|region = IANA region code|variant = IANA variant code|text = (required) the displayed text in language specified by code|link = boolean false ('no') does not link code-spcified language name to associated language article|rtl = boolean true ('yes') identifies the language specified by code as a right-to-left language|nocat = boolean true ('yes') inhibits normal categorization; error categories are not affected|cat = boolian false ('no') opposite form of |nocat=|italic = boolean true ('yes') renders displayed text in italic font; boolean false ('no') renders displayed text in normal font; not set renders according to initial_style_state|lit = text that is a literal translation of text|label = 'none' to suppress all labeling (language name, 'translit.', 'lit.')any other text replaces language-name label - automatic wikilinking disabledfor those {{lang-xx}} templates that support transliteration (those templates where |text= is not entirely latn script):|translit = text that is a transliteration of text|translit-std = the standard that applies to the transliteration|translit-script = ISO 15924 script name; falls back to codeFor {{lang-xx}}, the positional parameters are:{{{1}}}text{{{2}}}transliterated text{{{3}}}literal translation textno other positional parameters are allowed]]localfunction_lang_xx(args)localout={};locallanguage_name;-- used to make display text, article linkslocalcategory_name;-- same as language_name except that it retains any parenthetical disambiguators (if any) from the data setlocalsubtags={};-- IETF subtags script, region, and variantlocalcode;-- the language codelocaltranslit_script_name;-- name associated with IANA (ISO 15924) script codelocaltranslit;localtranslit_title;localmsg;-- for error messageslocaltag='span';-- initial value for make_text_html()localtemplate=args.templateor'Lang-xx';maint_cats={};-- initialize because when this module required into another module, these only declared once so only initialzed oncemaint_msgs={};ifargs[1]andargs.textthenreturnmake_error_msg('conflicting: {{{1}}} and |text=',args,template);elseargs.text=args[1]orargs.text;-- prefer args.textendmsg=validate_text(template,args);-- ensure that |text= is set, does not contain italic markup and is protected from improper boldingifis_set(msg)thenreturnmsg;endargs.text,tag=html_tag_select(args.text);-- inspects text; returns appropriate html tag with text trimmed accordinglyifargs[2]andargs.translitthenreturnmake_error_msg('conflicting: {{{2}}} and |translit=',args,template);elseargs.translit=args[2]orargs.translit-- prefer args.translitendifargs[3]and(args.translationorargs.lit)thenreturnmake_error_msg('conflicting: {{{3}}} and |lit= or |translation=',args,template);elseifargs.translationandargs.litthenreturnmake_error_msg('conflicting: |lit= and |translation=',args,template);elseargs.translation=args[3]orargs.translationorargs.lit;-- prefer args.translationendifargs.linksandargs.linkthenreturnmake_error_msg('conflicting: |links= and |link=',args,template);elseargs.link=args.linkorargs.links;-- prefer args.linkendvalidate_cat_args(args);-- determine if categorization should be suppressedargs.rtl=args.rtl=='yes';-- convert to boolean: 'yes' -> true, other values -> falsecode,subtags.script,subtags.region,subtags.variant,subtags.private,msg=get_ietf_parts(args.code,args.script,args.region,args.variant);-- private omitted because privateifmsgthen-- if an error detected then there is an error messagereturnmake_error_msg(msg,args,template);endargs.italic,msg=validate_italic(args);ifmsgthenreturnmake_error_msg(msg,args,template);endifnil==args.italicthen-- args.italic controlsifis_set(subtags.script)thenif'latn'==subtags.scriptthenargs.italic='italic';-- |script=Latn; set for font-style:italicelseargs.italic=initial_style_state;-- italic not set; script is not latn; set for font-style:<initial_style_state>endelseargs.italic=initial_style_state;-- here when |italic= and |script= not set; set for font-style:<initial_style_state>endendifis_set(subtags.script)then-- if script set override rtl settingifin_array(subtags.script,lang_data.rtl_scripts)thenargs.rtl=true;-- script is an rtl scriptelseargs.rtl=false;-- script is not an rtl scriptendendargs.proto,msg=validate_proto(args.proto);-- return boolean, or nil, or nil and error message flagifmsgthenreturnmake_error_msg(table.concat({'invalid |proto=: ',args.proto}),args,template);endargs.code=format_ietf_tag(code,subtags.script,subtags.region,subtags.variant,subtags.private);-- format to recommended subtag styleslanguage_name=language_name_get(args.code,code,true);-- get language name; try ietf tag first, then code w/o variant then code w/ variantcategory_name=language_name;-- category names retain IANA parenthetical diambiguators (if any)language_name=language_name:gsub('%s+%b()','');-- remove IANA parenthetical disambiguators or qualifiers from names that have themifargs.labelthenif'none'~=args.labelthentable.insert(out,table.concat({args.label,': '}));-- custom labelendelseif'no'==args.linkthentable.insert(out,language_name);-- language name without wikilinkelseifmw.ustring.find(language_name,'languages',1,true)thentable.insert(out,make_wikilink(language_name));-- collective language name uses simple wikilinkelseiflang_data.article_name[args.code:lower()]then-- is ietf tag in article name over ride?table.insert(out,make_wikilink(lang_data.article_name[args.code:lower()],language_name));-- language name with wikilink from override dataelseiflang_data.article_name[code]then-- is language tag in article overridetable.insert(out,make_wikilink(lang_data.article_name[code],language_name));-- language name with wikilink from override dataelsetable.insert(out,make_wikilink(language_name..' language',language_name));-- language name with wikilinkendendtable.insert(out,': ');-- separatorendif'invert'==args.italicthenargs.text=invert_italics(args.text)endargs.text=proto_prefix(args.text,language_name,args.proto);-- prefix proto-language text with a splattable.insert(out,make_text_html(args.code,args.text,tag,args.rtl,args.italic,args.size,('none'==args.label)andlanguage_nameornil))ifis_set(args.translit)andnotunicode.is_Latin(args.text)then-- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)table.insert(out,', ');-- comma to separate text from translitif'none'~=args.labelthentable.insert(out,'<small>');ifscript_table[args['translit-script']]then-- when |translit-script= is set, try to use the script's nametranslit_script_name=script_table[args['translit-script']];elsetranslit_script_name=language_name;-- fall back on language nameendtranslit_title=mw.title.makeTitle(0,table.concat({'Romanization of ',translit_script_name}));-- make a title objectiftranslit_title.existsand('no'~=args.link)thentable.insert(out,make_wikilink('Romanization of '..translit_script_nameorlanguage_name,'romanized')..':');-- make a wikilink if there is an article to link toelsetable.insert(out,'romanized:');-- else plain textendtable.insert(out,' </small>');-- close the small tagendtranslit=make_translit(args.code,language_name,args.translit,args['translit-std'],args['translit-script'])ifis_set(translit)thentable.insert(out,translit);elsereturnmake_error_msg(table.concat({'invalid translit-std:\'',args['translit-std']or'[missing]'}),args,template);endendifis_set(args.translation)then-- translation (not supported in {{lang}})table.insert(out,translation_make(args));endtable.insert(out,make_category(code,category_name,args.nocat));table.insert(out,render_maint(args.nocat));-- maintenance messages and categoriesreturntable.concat(out);-- put it all together and doneend--[[--------------------------< L A N G _ X X _ A R G S _ G E T >----------------------------------------------common function to get args table from {{lang-??}} templatesreturns table of args]]localfunctionlang_xx_args_get(frame)localargs=getArgs(frame,{parentFirst=true,-- parameters in the template override parameters set in the {{#invoke:}}valueFunc=function(key,value)if1==keythen-- the 'text' parameter; do not trim wite spacereturnvalue;-- return untrimmed 'text'elseifvaluethen-- all other values: if the value is not nilvalue=mw.text.trim(value);-- trim whitespaceif''~=valuethen-- empty string when value was only whitespacereturnvalue;endendreturnnil;-- value was empty or contained only whitespaceend-- end of valueFunc});returnargs;end--[[--------------------------< L A N G _ X X _ I T A L I C >--------------------------------------------------Entry point for those {{lang-xx}} templates that call lang_xx_italic(). Sets the initial style state to italic.]]localfunctionlang_xx_italic(frame)localargs=lang_xx_args_get(frame);initial_style_state='italic';return_lang_xx(args);end--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------Entry point ffrom another module. Sets the initial style state to italic.]]localfunction_lang_xx_italic(args)initial_style_state='italic';return_lang_xx(args);end--[[--------------------------< L A N G _ X X _ I N H E R I T >------------------------------------------------Entry point for those {{lang-xx}} templates that call lang_xx_inherit(). Sets the initial style state to inherit.]]localfunctionlang_xx_inherit(frame)localargs=lang_xx_args_get(frame);initial_style_state='inherit';return_lang_xx(args);end--[[--------------------------< _ L A N G _ X X _ I N H E R I T >----------------------------------------------Entry point from another module. Sets the initial style state to inherit.]]localfunction_lang_xx_inherit(args)initial_style_state='inherit';return_lang_xx(args);end--[[--------------------------< _ I S _ I E T F _ T A G >------------------------------------------------------Returns true when a language name associated with IETF language tag exists; nil else. IETF language tag must be valid.All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.Module entry point from another module]]localfunction_is_ietf_tag(tag)-- entry point when this module is require()d into anotherlocalc,s,r,v,p,err;-- code, script, region, variant, private, error messagec,s,r,v,p,err=get_ietf_parts(tag);-- disassemble tag into constituent part and validatereturn((candnoterr)andtrue)ornil;-- return true when code portion has a value without error message; nil elseend--[[--------------------------< I S _ I E T F _ T A G >--------------------------------------------------------Module entry point from an {{#invoke:}}]]localfunctionis_ietf_tag(frame)return_is_ietf_tag(getArgs(frame)[1]);-- args[1] is the ietf language tag to be tested; also get parent frameend--[[--------------------------< I S _ I E T F _ T A G _ F R A M E >--------------------------------------------Module entry point from an {{#invoke:}}; same as is_ietf_tag() except does not get parameters from the parent(template) frame. This function not useful when called by {{lang|fn=is_ietf_tag_frame|<tag>}} because <tag>is in the parent frame.]]localfunctionis_ietf_tag_frame(frame)return_is_ietf_tag(getArgs(frame,{frameOnly=true,})[1]);-- args[1] is the ietf language tag to be tested; do not get parent frameend--[[--------------------------< _ N A M E _ F R O M _ T A G >--------------------------------------------------Returns language name associated with IETF language tag if valid; error message else.All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.Set invoke's |link= parameter to yes to get wikilinked version of the language name.Module entry point from another module]]localfunction_name_from_tag(args)localsubtags={};-- IETF subtags script, region, variant, and privatelocalraw_code=args[1];-- save a copy of the input IETF subtaglocallink='yes'==args['link'];-- make a booleanlocallabel=args.label;localcode;-- the language codelocalmsg;-- gets an error message if IETF language tag is malformed or invalidlocallanguage_name='';code,subtags.script,subtags.region,subtags.variant,subtags.private,msg=get_ietf_parts(raw_code);ifmsgthenlocaltemplate=(args['template']andtable.concat({'{{',args['template'],'}}: '}))or'';-- make template name (if provided by the template)returntable.concat({'<span style=\"color:#d33\">Error: ',template,msg,'</span>'});endraw_code=format_ietf_tag(code,subtags.script,subtags.region,subtags.variant,subtags.private);-- format to recommended subtag styles; private omitted because privatelanguage_name=language_name_get(raw_code,code);-- get language name; try ietf tag first, then code w/o variant then code w/ variantlanguage_name=language_name:gsub('%s+%b()','');-- remove IANA parenthetical disambiguators or qualifiers from names that have themiflinkthen-- when |link=yes, wikilink the language nameifmw.ustring.find(language_name,'languages',1,true)thenlanguage_name=make_wikilink(language_name,label);-- collective language name uses simple wikilinkelseiflang_data.article_name[raw_code:lower()]then-- is ietf tag in article name override?language_name=make_wikilink(lang_data.article_name[raw_code:lower()],labelorlanguage_name);-- language name with wikilink from override dataelseiflang_data.article_name[code]then-- is language tag in article name override?language_name=make_wikilink(lang_data.article_name[code],labelorlanguage_name);-- language name with wikilink from override dataelselanguage_name=make_wikilink(language_name..' language',labelorlanguage_name);-- language name with wikilinkendendreturnlanguage_name;end--[[--------------------------< N A M E _ F R O M _ T A G >----------------------------------------------------Module entry point from an {{#invoke:}}]]localfunctionname_from_tag(frame)-- entry point from an {{#invoke:Lang|name_from_tag|<ietf tag>|link=<yes>|template=<template name>}}return_name_from_tag(getArgs(frame))-- pass-on the args table, nothing else; getArgs() so we also get parent frameend--[[--------------------------< _ T A G _ F R O M _ N A M E >--------------------------------------------------Returns the ietf language tag associated with the language name. Spelling of language name must be correctaccording to the spelling in the source tables. When a standard language name has a parenthetical disambiguator,that disambiguator must be omitted (they are not present in the data name-to-tag tables).Module entry point from another module]]localfunction_tag_from_name(args)-- entry point from another modulelocalmsg;ifargs[1]and''~=args[1]thenlocaldata=mw.loadData('Module:Lang/tag from name');-- get the reversed data tables TODO: change when going livelocallang=args[1]:lower();-- allow any-case for the language name (speeling must till be correct)localtag=data.rev_override_table[lang]ordata.rev_lang_table[lang]ordata.rev_lang_dep_table[lang];-- get the code; look first in the override then in the standardiftagthenreturntag,true;-- language name found so return tag and done; second return used by is_lang_name()elsemsg='language: '..args[1]..' not found'-- language name not found, error messageendelsemsg='missing language name'-- language name not provided, error messageendlocaltemplate='';ifargs.templateand''~=args.templatethentemplate=table.concat({'{{',args['template'],'}}: '});-- make template name (if provided by the template)endreturntable.concat({'<span style=\"color:#d33\">Error: ',template,msg,'</span>'});end--[[--------------------------< T A G _ F R O M _ N A M E >----------------------------------------------------Module entry point from an {{#invoke:}}]]localfunctiontag_from_name(frame)-- entry point from an {{#invoke:Lang|tag_from_name|<language name>|link=<yes>|template=<template name>}}localresult,_=_tag_from_name(getArgs(frame))-- pass-on the args table, nothing else; getArgs() so we also get parent frame; supress second return used by is_lang_name()returnresult;end--[[--------------------------< I S _ L A N G _ N A M E >------------------------------------------------------Module entry point from an {{#invoke:}}]]localfunctionis_lang_name(frame)local_,result=_tag_from_name(getArgs(frame))-- pass-on the args table, nothing else; getArgs() so we also get parent frame; supress second return used by tag_from_name()returnresultandtrueornil;end--[[--------------------------< _ T R A N S L >----------------------------------------------------------------Module entry point from another module]]localfunction_transl(args)localtitle_table=lang_data.translit_title_table;-- table of transliteration standards and the language codes and scripts that apply to those standardslocallanguage_name;-- language name that matches language code; used for tool tiplocaltranslit;-- transliterated text to displaylocalscript;-- IANA scriptlocalmsg;-- for when called functions return an error messagemaint_cats={};-- initialize because when this module required into another module, these only declared once so only initialzed oncemaint_msgs={};ifis_set(args[3])then-- [3] set when {{transliteration|code|standard|text}}args.text=args[3];-- get the transliterated textargs.translit_std=args[2]andargs[2]:lower();-- get the standard; lower case for table indexingifnottitle_table[args.translit_std]thenreturnmake_error_msg(table.concat({'unrecognized transliteration standard: ',args.translit_std}),args,'Transliteration');endelseifis_set(args[2])then-- [2] set when {{transliteration|code|text}}args.text=args[2];-- get the transliterated textelseifargs[1]and(args[1]:match('^%a%a%a?%a?$')or-- args[2] missing; is args[1] a language or script tag or is it the transliterated text?args[1]:match('^%a%a%a?%-x%-'))then-- or is args[1] a private-use tagreturnmake_error_msg('no text',args,'Transliteration');-- args[1] is a code so we're missing textelseargs.text=args[1];-- args[1] is not a code so we're missing that; assign args.text for error messagereturnmake_error_msg('missing language / script code',args,'Transliteration');endendendifis_set(args[1])then-- IANA language code used for html lang= attribute; or ISO 15924 script codeifargs[1]:match('^%a%a%a?%a?$')orargs[1]:match('^%a%a%a?%-x%-')then-- args[1] has correct form?args.code=args[1]:lower();-- use the language/script code; only (2, 3, or 4 alpha characters) or private-use; lower case because table indexes are lower caseelsereturnmake_error_msg(table.concat({'unrecognized language / script code: ',args[1]}),args,'Transliteration');-- invalid language / script codeendelsereturnmake_error_msg('missing language / script code',args,'Transliteration');-- missing language / script code so quitendargs.italic,msg=validate_italic(args);ifmsgthenreturnmake_error_msg(msg,args,'Transliteration');endif'italic'==args.italicthen-- 'italic' when |italic=yes; because that is same as absent or not set and |italic=defaultargs.italic=nil;-- set to nil;endifoverride_table[args.code]then-- is code a language code defined in the override table?language_name=override_table[args.code];args.code=args.code:match('^%a%a%a?');-- if private use, strip all but language subtagelseiflang_table[args.code]then-- is code a language code defined in the standard language code tables?language_name=lang_table[args.code];elseiflang_dep_table[args.code]then-- is code a language code defined in the deprecated language code tables?language_name=lang_dep_table[args.code];elseifscript_table[args.code]then-- if here, code is not a language code; is it a script code?language_name=script_table[args.code];script=args.code;-- code was an ISO 15924 script so use that insteadargs.code='';-- unset because not a language codeelsereturnmake_error_msg(table.concat({'unrecognized language / script code: ',args.code}),args,'Transliteration');-- invalid language / script codeend-- here only when all parameters passed to make_translit() are validreturnmake_translit(args.code,language_name,args.text,args.translit_std,script,args.italic);end--[[--------------------------< T R A N S L >------------------------------------------------------------------Module entry point from an {{#invoke:}}]]localfunctiontransl(frame)return_transl(getArgs(frame));end--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------Returns category name associated with IETF language tag if valid; error message elseAll code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.Module entry point from another module]]localfunction_category_from_tag(args_t)localsubtags={};-- IETF subtags script, region, variant, and privatelocalraw_code=args_t[1];-- save a copy of the input IETF subtaglocallink='yes'==args_t.link;-- make a booleanlocallabel=args_t.label;localcode;-- the language codelocalmsg;-- gets an error message if IETF language tag is malformed or invalidlocalcategory_name='';code,subtags.script,subtags.region,subtags.variant,subtags.private,msg=get_ietf_parts(raw_code);ifmsgthenlocaltemplate=(args_t.templateandtable.concat({'{{',args_t.template,'}}: '}))or'';-- make template name (if provided by the template)returntable.concat({'<span style=\"color:#d33\">Error: ',template,msg,'</span>'});endraw_code=format_ietf_tag(code,subtags.script,subtags.region,subtags.variant,subtags.private);-- format to recommended subtag styles; private omitted because privatecategory_name=language_name_get(raw_code,code);-- get language name; try ietf tag first, then code w/o variant then code w/ variantcategory_name=make_category(code,category_name,nil,true):gsub('[%[%]]','');iflinkthenreturntable.concat({'[[:',category_name,']]'});elsereturncategory_name;endend--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------Module entry point from an {{#invoke:}}]]localfunctioncategory_from_tag(frame)-- entry point from an {{#invoke:Lang|category_from_tag|<ietf tag>|template=<template name>}}return_category_from_tag(getArgs(frame));-- pass-on the args table, nothing else; getArgs() so we also get parent frameend--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------]]return{category_from_tag=category_from_tag,lang=lang,-- entry point for {{lang}}lang_xx_inherit=lang_xx_inherit,-- entry points for {{lang-??}}lang_xx_italic=lang_xx_italic,is_ietf_tag=is_ietf_tag,is_ietf_tag_frame=is_ietf_tag_frame,is_lang_name=is_lang_name,tag_from_name=tag_from_name,-- returns ietf tag associated with language namename_from_tag=name_from_tag,-- used for template documentation; possible use in ISO 639 name from code templatestransl=transl,-- entry point for {{transliteration}}_category_from_tag=_category_from_tag,-- entry points when this module is require()d into other modules_lang=_lang,_lang_xx_inherit=_lang_xx_inherit,_lang_xx_italic=_lang_xx_italic,_is_ietf_tag=_is_ietf_tag,get_ietf_parts=get_ietf_parts,_tag_from_name=_tag_from_name,_name_from_tag=_name_from_tag,_transl=_transl,_translation_make=translation_make,};
