Changes

add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink, strip_apostrophe_markup;

table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table

single-letter/digit second-level domains in the .org , .cash, and .cash today TLDs

if not domain:match ('^[%a%dw]') then -- first character must be letter or digit

-- Do most common case first if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld return true; elseif domain:match ('%f[^%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix return true; elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname return true; elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/digit .org hostname return true; elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) return true; elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) return true; elseif domainhack to detect things that look like s:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) return true; elseif domainPage:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld return true; elseif domainTitle where Page:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address return true; elseis namespace at wikisource

URL=table.concat ({domain.., path}); -- and reassemble

  base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url 

label base_url = safe_for_url substitute (label); -- replace square brackets and newlines  base_url = tablecfg.concat ( -- assemble external link with access signal { '<span class="plainlinks">presentation[', ext-link- opening css and url markup URL, access-- the url ' signal'], -- the required space label, '<span style="padding-left:0{cfg.presentation[access].15em">'class, -- signal spacing css cfg.presentation[access].title, -- the appropriate icon '</span>', -- close signal spacing span ']</span>' -- close url markup and plain links span }); else base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" }); -- no signal markupadd the appropriate icon

return table.concat({ base_url, error_str });

table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message

Supports |script-title= and , |script-chapter=, |script-<periodical>=

local function format_script_value (script_value, script_param)

name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize

add_prop_cat table.insert(z.message_tail, { set_error( 'script_parameter', {script_param, 'scriptunknown language code'}, true )} ); -- unknown script-language; add error message

local function script_concatenate (title, script, script_param)

script = format_script_value (script, script_param); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error

return substitute( msg, str ); -- including template text

--[[--------------------------< F W I K I S O U R M A T _ C H A P T E _ U R L _ T I T L M A K E >---------------------------------------- makes a wikisource url from wikisource interwiki link. returns the url and appropriate label; nil else.

Format str is the four chapter parameters: value assigned to |script-chapter=, (or aliases) or |chaptertitle=, or |transtitle-chapterlink=, and |chapter-url= into a single Chapter meta-parameter (chapter_url_source used for error messages).

local function format_chapter_title wikisource_url_make (scriptchapterstr) local wl_type, chapterD, transchapterL; local ws_url, chapterurlws_label;  wl_type, chapter_url_sourceD, no_quotesL = is_wikilink (str); -- wl_type is 0 (not a wikilink), access1 (simple wikilink), 2 (complex wikilink)  local chapter_error if 0 == wl_type then -- not a wikilink; might be from |title-link= str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace if not is_set (chapterstr) then chapter ws_url = table.concat ({ -- build a wikisource url 'https://en.wikisource.org/wiki/', -- prefix str, -- article title }); ws_label = str; -- to be safe label for concatenationthe url end else if false elseif 1 == no_quotes wl_type then -- simple wikilink: [[Wikisource:ws article]] chapter str = kern_quotes D:match ('^[Ww]ikisource:(chapter.+)') or D:match ('^[Ss]:(.+)'); -- if necessary, separate chapter article title's leading and trailing quote marks from Module provided quote marksinterwiki link with long-form or short-form namespace if is_set (str) then chapter ws_url = wrap_style table.concat ({ -- build a wikisource url 'https://en.wikisource.org/wiki/'quoted, -- prefix str, -- article title', chapter }); ws_label = str; -- label for the url

end  chapter elseif 2 == script_concatenate (chapter, scriptchapter) wl_type then -- non-so- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped  if is_set simple wikilink: [[Wikisource:ws article|displayed text]] (transchapter[[L|D]]) then transchapter str = wrap_style L:match ('^[Ww]ikisource:(.+)') or L:match ('trans^[Ss]:(.+)'); -quoted-article title', transchapter);from interwiki link with long-form or short-form namespace if is_set (chapterstr) then chapter ws_label = chapter .. ' ' .. transchapterD; else -- here when transchapter without chapter or script-chapterget ws article name from display portion of interwiki link chapter ws_url = transchapter; table.concat ({ -- build a wikisource url chapter_error = ' ' https://en.wikisource. set_error ('trans_missing_titleorg/wiki/', {'chapter' -- prefix str, -- article title without namespace from link portion of wikilink });

if is_set ws_url then ws_url = mw.uri.encode (chapterurlws_url, 'WIKI') then; -- make a usable url chapter ws_url = external_link ws_url:gsub (chapterurl'%%23', chapter, chapter_url_source, access'#'); -- adds bare_url_missing_title error if appropriateundo percent encoding of anchor

return chapter .. chapter_errorws_url, ws_label, L or D; -- return proper url or nil and a label or nil

--[[--------------------------< H F O R M A S T _ P E R I N V O D I S I B L E _ C H A R S L >-------------------------------------------- Format the four periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta-parameter.

This local function will detect the visible replacement character when it is part of the wikisource.format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) local periodical_error = '';

Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers if not is_set (gallery, math, pre, refperiodical)thenand identifies them with a slightly different error message. See also coins_cleanup periodical = ''; -- to be safe for concatenation else periodical = wrap_style ('italic-title', periodical).; -- style end

Output of this function is an error message that identifies the character or the Unicode group if is_set (trans_periodical) then trans_periodical = wrap_style ('trans-italic-title', or the stripmarkertrans_periodical);that was detected along with its position if is_set (periodical) then periodical = periodical .. ' ' .. trans_periodical; else -- here when transchapter without chapter or, for multiscript-byte characterschapter periodical = trans_periodical; periodical_error = ' ' .. set_error ('trans_missing_title', the position of its first byte{'periodical'}) in the;parameter value. end end

 --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >-------------------------------------- Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-parameter (chapter_url_source used for error messages). ]] local function has_invisible_chars format_chapter_title (paramscriptchapter, vscript_chapter_source, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access) local position chapter_error = ''; -- position of invisible char or starting position of stripmarker  local dummyws_url, ws_label, L = wikisource_url_make (chapter); -- end of matching string; not used but required to hold end position when make a wikisource url and label from a capture is returnedwikisource interwiki link local capture; -- used by stripmarker detection to hold name of the stripmarkerif ws_url then local i=1; local stripmarker, apostrophe; capture ws_label = string.match ws_label:gsub (v'_', '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true if capture == v then -- if same there are no unicode replace underscore separaters with space characters returnchapter = ws_label;

while cfg.invisible_chars[i] doif not is_set (chapter) then local charchapter =cfg.invisible_chars[i][1] ''; -- the character or group name local pattern=cfg.invisible_chars[i][2] -- the pattern used to find itbe safe for concatenation position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern else if position and (char false == 'zero width joiner') no_quotes then -- if we found a zero width joiner character if mw.ustring.find chapter = kern_quotes (v, cfg.indic_scriptchapter) then ; -- its ok if one of the indic scriptsnecessary, separate chapter title's leading and trailing quote marks from Module provided quote marks position chapter = nilwrap_style ('quoted-title', chapter); -- unset position end

end if position then if 'nowiki' chapter == capture or 'math' == capture then script_concatenate (chapter, scriptchapter, script_chapter_source); -- nowiki<bdi> tags, math stripmarker lang atribute, categorization, etc; must be done after title is wrapped  if is_set (not an error conditionchapterurl)then stripmarker chapter = trueexternal_link (chapterurl, chapter, chapter_url_source, access); -- set a flagadds bare_url_missing_title error if appropriate elseif true ws_url then chapter == stripmarker and external_link (ws_url, chapter .. 'delete&nbsp;' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nilws link in chapter'); -- unset else local err_msgadds bare_url_missing_title error if appropriate; if capture then err_msg = capture .. ' ' .. space charto move icon away from chap text;TODO: better way to do this? else err_msg chapter = char .substitute (cfg. presentation[' interwiki-icon' ], {cfg.. presentation['characterclass-wikisource'], L, chapter}); end

table.insert if is_set ( z.message_tail, { set_errortranschapter) then transchapter = wrap_style ( 'invisible_chartrans-quoted-title', {err_msg, wrap_style transchapter); if is_set (chapter) then chapter = chapter .. 'parameter', param), position}, true ) } ).. transchapter; else -- add error messagehere when transchapter without chapter or script-chapter return chapter = transchapter; -- and done with this parameter endchapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});

--[[--------------------------< H A R G U M S _ I N V I S I B L E N T _ W R C H A P P E R S >---------------------------------------------- This function searches a parameter's value for nonprintable or invisible characters. The search stops at thefirst match.

Argument wrapper. This function provides support for argument mapping defined in will detect the configuration file so thatmultiple names can be transparently aliased to single internal variablevisible replacement character when it is part of the wikisource.

Output of this function is an error message that identifies the character or the Unicode group, or the stripmarkerthat was detected along with its position (or, for multi-byte characters, the position of its first byte) in theparameter value. ]] local function argument_wrapperhas_invisible_chars ( args param, v) local origin position = ''; -- position of invisible char or starting position of stripmarker local dummy; -- end of matching string; not used but required to hold end position when a capture is returned local capture; -- used by stripmarker detection to hold name of the stripmarker local i= {}1; local stripmarker, apostrophe; return setmetatable({ ORIGIN capture = functionstring.match ( selfv, k '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true if capture == v then -- if same there are no unicode characters return; end  while cfg.invisible_chars[i] do local char=cfg.invisible_chars[i][1] -- the character or group name local dummy pattern= selfcfg.invisible_chars[i][k2]; --force the variable pattern used to be loadedfind it position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern if position and (char == 'zero width joiner') then -- if we found a zero width joiner character return origin[k]if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts position = nil; -- unset position end

if position then if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) ('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters stripmarker = true; -- set a flag elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset else local err_msg; if capture then err_msg = capture .. ' ' .. char; else err_msg = char .. ' ' .. 'character'; end  table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message return; -- and done with this parameter end end i=i+1; -- bump our index endend  --[[--------------------------< A R G U M E N T _ W R A P P E R >---------------------------------------------- Argument wrapper. This function provides support for argument mapping defined in the configuration file so thatmultiple names can be transparently aliased to single internal variable. ]] local function argument_wrapper( args ) local origin = {}; return setmetatable({ ORIGIN = function( self, k ) local dummy = self[k]; --force the variable to be loaded. return origin[k]; end }, { __index = function ( tbl, k ) if origin[k] ~= nil then

error( cfg.messages['unknown_argument_map'] .. ': ' .. k);

--[[--------------------------< V N O W R A L I P _ D A T E >-------------------------------------------------------- When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM---DD</span>. When date is DD MMMM YYYY or isMMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY

Looks for a parameter's name in one DOES NOT yet support MMMM YYYY or any of several whiteliststhe date ranges.

local function validatenowrap_date ( name, cite_class date) local name cap=''; local cap2= tostring'';  if date:match( name "^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date); local state elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$"); date = substitute (cfg.presentation['nowrap2'], {cap, cap2}); end

if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- limited parameter sets allowed for these templates state = whitelist.limited_basic_arguments[ name ]return date; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end

if 'arxiv' == cite_class then -- basic parameters unique to these templates state = whitelist.arxiv_basic_arguments[name]; end if 'biorxiv' == cite_class then state = whitelist.biorxiv_basic_arguments[name]; end if 'citeseerx' == cite_class then state = whitelist.citeseerx_basic_arguments[name]; end--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------

if true This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.Also handles the special case where it is desirable to omit the title type from the rendered citation (|type= state none). ]] local function set_titletype (cite_class, title_type) if is_set(title_type) then return true; end -- valid actively supported parameter if false "none" == state title_type then deprecated_parameter (name)title_type = ""; -- if |type=none then type parameter is deprecated but still supported return true;not displayed

-- limited enumerated parameters list name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) state = whitelist.limited_numbered_arguments[ name ]; if true == state then return truetitle_type; end -- valid actively supported parameter if false |type== state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end  return false; -- not supported because not found or name is has been set to nil end -- end limited parameter-set templates state = whitelist.basic_arguments[ name ]; -- all any other templates; all normal parameters allowed if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true;value use that value

if true == state then return truecfg.title_types [cite_class] or ''; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end return falseset template's default title type; -- not supported because not found or name is set to nilelse empty string for concatenation

--[[--------------------------< H Y P H E N _ T O W R A P _ D A T E S H >-------------------------------------------------- Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items arereturned unmodified. These forms are modified: letter - letter (A - B) digit - digit (4-5) digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5) digitletter -digitletter (5a -5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d)

When date is YYYY-MM-DD format wrap in nowrap span: <span any other forms are returned unmodified...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or isMMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY

DOES NOT yet support MMMM YYYY str may be a comma- or any of the date ranges.semicolon-separated list

local function nowrap_date hyphen_to_dash(datestr ) local cap=''; local cap2='';  if date:matchnot is_set ("^%d%d%d%d%-%d%d%-%d%d$"str) then date = substitute (cfg.presentation['nowrap1'], date)return str; end

elseif datestr, count = str:matchgsub ("'^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then cap, cap2 = string.match (date, "^(.*+)%s+(%d%d%d)%d)$"', '%1'); -- remove accept-this-as-written markup when it wraps all of str if 0 ~= count then -- non-zero when markup removed; zero else date = substitute (cfg.presentation['nowrap2return str; -- nothing to do, we'], {cap, cap2});re done

return datestr = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.splitend local out = {}; local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any

  for _, item in ipairs (list) do --for each item in the list if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then --if a hyphenated range or has endash or emdash separators if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or --letterdigit hyphen letterdigit (optional separator between letter and digit) item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or --digitletter hyphen digitletter (optional separator between digit and letter) item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or --digit separator digit hyphen digit separator digit item:match ('%d+%s*%-%s*%d+') or --digit hyphen digit item:match ('%a+%s*%-%s*%a+') then --letter hyphen letter item = item:gsub ('(%w*[%.%-< S E T _ T I T L E T Y P E >------------------------------------------------]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); --replace hyphen, remove extraneous space characters elseThis function sets default title types (equivalent to the citation including |type item =<default value>) for those templates that have defaultsmw.ustring.Also handles the special case where it is desirable to omit the title type from the rendered citation gsub (|type=none). item, '%s*[–—]] local function set_titletype (cite_class%s*', title_type'–') if is_set(title_type) then if "none" == title_type then; title_type = ""; -- if |type=none then type parameter not displayedfor endash or emdash separated ranges, replace em with en, remove extraneous white space end

return title_typeitem = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup table.insert (out, item); -- if |type= has been set add the (possibly modified) item to any other value use that valuethe output table

return cfgtable.title_types [cite_class] or concat (out, ', '); -- set template's default title type; else empty concatenate the output table into a comma separated string for concatenation

--[[--------------------------< H Y P H S A F E N _ T J O _ D A S H I N >------------------------------------------------------------

Converts Joins a hyphen to a dashsequence of strings together while checking for duplicate separation characters.

local function hyphen_to_dashsafe_join( str tbl, duplicate_char ) if not is_set(str) or str:match( "[%[%]local f = {}<>]" ) ~; -- create a function table appropriate to type of 'dupicate character' if 1 == nil #duplicate_char then -- for single byte ascii characters use the string library functions f.gsub=string.gsub f.match=string.match f.sub=string.sub return str;else -- for multi-byte characters use the ustring library functions f.gsub=mw.ustring.gsub end f.match=mw.ustring.match return str:gsub( '-', '–' ); f.sub=mw.ustring.sub end 

if comp:f.sub(comp, 1,1) == duplicate_char then -- is first charactier character same as duplicate_char? why test first character? -- Because individual string segments often (always?) begin with terminal punct for ththe

end_chr = str:f.sub(str, -1,-1); -- get the last character of the output string

str = str:f.sub(str, 1,-2); -- remove it

if str:f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' str = str:f.sub(str, 1, -4) .. "''"; -- remove them and add back '' elseif str: f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''

elseif str:f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''

if str:f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink

elseif str:f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link

elseif str: f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link

elseif str:f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.

if str:f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> str = str:f.sub(str, 1,-3); -- remove them both

if dup2:f.match( dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it

value = value:f.gsub( value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup

value = value:f.sub( value, 2, -1 ); -- remove duplicate_char when it is first character

end

local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it

sep = cfg.presentation[',sep_nl_vanc']; -- name-list separator between authors is a comma namesep = cfg.presentation[' sep_name_vanc']; -- last/first separator is a space

sep = cfg.presentation['sep_nl'];' -- name-list separator between authors is a semicolon namesep = cfg.presentation[', sep_name' ]; -- last/first separator is <comma><space>

Evaluates the content of name parameters (author and , editor name parameters , etc) for variations on the theme of et al. If found,

previous passes through this function or by the parameters associated |display-authors=etal or |display-editors<names>=etalparameter

local function name_has_etal (name, etal, nocat, param)

local etal_pattern patterns = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%cfg.\"']*$" -- variations on the 'et al' theme local others_pattern = "[et_al_patterns;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.get patterns from configuration

if name:match for _, pattern in ipairs (etal_patternpatterns) then -- variants on et al. name = name:gsub (etal_pattern, ''); -- if found, remove etal = true; -do - set flag (may have been set previously here or by |display-authors=etal)loop through all of the patterns if not nocat then -- no categorization for |vauthors= add_maint_cat ('etal'); -- and add a category if not already added end elseif name:match (others_patternpattern) then -- if not this 'et al.', then 'and others'?pattern is found in name name = name:gsub (others_patternpattern, ''); -- if found, removethe offending text etal = true; -- set flag (may have been set previously here or by |display-authors<names>=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat table.insert( z.message_tail, {set_error ('etal', {param})}); -- and add a category set an error if not already added end

local patterns = { -- these patterns match annotations at end of name '%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%cfg.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')' '[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'editor_markup_patterns; case sensitive (ED could be initials Ed could be name) '%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')' '[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive -- these get patterns match annotations at beginning of name '^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.' '^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.' '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's' '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets }from configuration

local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'last_alias, first_alias; -- modify AuthorList or EditorList for use selected parameter aliases used in error messages if necessarymessaging

last , last_alias = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 first , first_alias = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );

last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al. first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.

table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_namefirst_alias, ifirst_alias:gsub('first', 'last')}, true ) } ); -- add this error message

table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_namelist_name:match ("(%w+)List"):lower(), i-1}, true ) } ); -- add this error message

are used as sub-domain names: cbk-zam.wikipedia.org. These A list of language names and codes supported by fetchLanguageNames()can be found (for the time being) athttpsTemplate:Citation Style documentation/language/phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEn.phpdoc

Names but that are included in the list will be found if that name is provided in the |language= parameter. For example,

and the associated code is not two or three characters, this function returns only the Wikimedia WikiMedia language name. Some language names have multiple entries under different codes: Aromanian has code rup and code roa-rupWhen this occurs, this function returns the language name and the 2- or 3-character code

local remap = { if cfg.lang_name_remap['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla lang:lower(the endonym) but we want Bengali (the exonym); here we remap ['bengali'] = {'Bengali', 'bn'}, then -- if there is a remapped name (because MediaWiki doesnuses something that we don't use exonym so here we provide think is correct language name and 639-1 code ['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replace 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found ['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org } if remap[lang:lower()] then return remapcfg.lang_name_remap[lang:lower()][1], remapcfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code

if 2 ~== code:len() and or 3 ~== code:len() then -- two- or three-character codes only; extensions not supported return name, code; -- so return the name but not and the code

return name, ietf_code = code; -- remember that we found it, return an ietf-like code and save its name to ensure proper capitalization and the the ietf_name = name; -- but keep looking for a 2- or 3-char code

-- didn't find name with 2- or 3-char code; if ietf-like code found return return ietf_code and ietf_name or lang; -- not valid languageassociated name; return original language in original case and nil for the codetext else

if name then -- there was a remapped code so lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietf tags from code else if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? end if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code name = mw.language.fetchLanguageName (lang:lower(), this_wiki_code); -- get language name if |language= is a proper code end

name = remapcfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names

add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it

add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template

name = table.concat (language_list, cfg.messages[' and parameter-pair-separator']) -- insert '<space>and<space>' between two language names

name = table.concat (language_list[code] = , 'and , ' .. language_list[code]); -- prepend last name and concatenate with 'and<comma><space>'separators name = table.concat name:gsub (', (language_list[^, ]+)$', cfg.messages['parameter-final-separator'] .. '%1') ; -- and concatenate replace last '<comma><space>' separator with '<comma><space>and<space>' separatorsseparator

ps = cfg.presentation['.ps_cs1']; -- terminate the rendered citation with a period

return cfg.presentation['.sep_cs1'], ps; -- element separator is a full stop

ps = cfg.presentation['ps_cs2']; -- make sure it isn't nilterminate the rendered citation

return cfg.presentation[',sep_cs2'], ps, ref; -- element separator is a comma

return url:match ('%.pdf$') or url:match ('%.PDF$') or url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or url:match ('%.PDF&#035') or url:match ('%.pdf&#035');

--[[--------------------------< G E T _ D I S P L A Y _ N A U T H O R S _ M E D I T O R S >--------------------------------------------

local function get_display_authors_editors get_display_names (max, count, list_name, etal)

add_maint_cat ('disp_auth_eddisp_name', cfg.special_case_translation [list_name]);

v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas

elseif in_array(value:lower(), possible) then

local vol = ''; -- here for all cites except magazine

if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters vol = substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold add_prop_cat ('long_vol'); else -- four or less characters vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)});-- bold

local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);

elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number

--[[--------------------------< I N S O U R C E _ L O C _ G E T >---------------------------------------------- returns one of the in-source locators: page, pages, or at.  If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain textfor use in COinS. This COinS thing is done because here we convert an interwiki link to and external link andadd an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?  TODO: add support for sheet and sheets?; streamline; TODO: make it so that this function returns only one of the three as the single in-source (the return value assignedto a new name)? ]] local function insource_loc_get (page, pages, at) local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)  if is_set (page) then if is_set (pages) or is_set(at) then pages = ''; -- unset the others at = ''; end extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.  ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label if ws_url then page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page}); coins_pages = ws_label; end elseif is_set (pages) then if is_set (at) then at = ''; -- unset end extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.  ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label if ws_url then pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages}); coins_pages = ws_label; end elseif is_set (at) then ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label if ws_url then at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? at = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at}); coins_pages = ws_label; end end return page, pages, at, coins_pages;end   --[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------

path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation

--[[--------------------------< M C I S S T A T I O N G _ P I P E _ C H E C K 0 >------------------------------------------------------------

Look at This is the contents of a parameter. If the content has a string of characters and digits followed by an equalsign, compare the alphanumeric string to main function doing the list majority of cs1|2 parameters. If found, then the string is possibly aparameter that is missing its pipe: {{cite ... |title=Title access-date=2016-03-17}} cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/htmltags are removed before the search. If a missing pipe is detected, this function adds the missing pipe maintenance categorycitation formatting.

local function missing_pipe_check (value) local capture; value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc   capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes if capture and validate (capture) then -- if the capture is a valid parameter name add_maint_cat ('missing_pipe'); endend  --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ This is the main function doing the majority of the citation formatting. ]] local function citation0( config, args) --[[

local interviewer_etal; local interviewers_list = {}; local Interviewers = A['Interviewers'] if is_set (Interviewers) then ; -- add a maint cat if the |interviewers= is used add_maint_cat ('interviewers'); -- because use of this parameter is discouragedlater else interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters end

if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'

local DeadURL UrlStatus = A['DeadURLUrlStatus']; if 'url-status' == A:ORIGIN ('UrlStatus') then -- interim: TODO: this line goes away if not is_valid_parameter_value (DeadURLUrlStatus, 'deadurl-urlstatus', cfg.keywords ['deadurlurl-status']) then -- set in config.defaults to 'yesdead' UrlStatus = ''; -- anything else, set to empty string end -- interim: TODO: this line goes away elseif is_set (A:ORIGIN ('UrlStatus')) then -- interim: while both |dead-url= and |url-status= allowed use separate keyword lists; TODO: remove this section if not is_valid_parameter_value (UrlStatus, A:ORIGIN ('UrlStatus'), cfg.keywords ['deadurl']) then -- interim: assume |dead-url=; use those keywords; TODO: this line goes away DeadURL UrlStatus = ''; -- anything else, set to empty string; interim: TODO: this line goes away end -- interim: TODO: this line goes away end -- interim: TODO: this line goes away if in_array (UrlStatus, {'yes', 'true', 'y'}) then -- TODO: remove this whole thing when |dead-url=[yes|no] parameters removed from articles UrlStatus = 'dead'; elseif 'no' == UrlStatus then UrlStatus = 'live'; end

local Periodical_origin = ''; if is_set (Periodical) then Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter local i; Periodical, i = strip_apostrophe_markup (Periodical); -- strip appostrophe markup so that metadata isn't contaminated if i then -- non-zero when markup was stripped so emit an error message table.insert( z.message_tail, {set_error ('apostrophe_markup', {Periodical_origin}, true)}); end end  local ScriptPeriodical = A['ScriptPeriodical']; local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); -- web and news not tested for now because of -- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors? if not (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message if p[config.CitationClass] then table.insert( z.message_tail, {set_error ('missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)}); end end  local TransPeriodical = A['TransPeriodical'];

if 'citation' == config.CitationClass then if is_set (Periodical) then if not in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals' Volume = A['Volume']; -- but does for all other 'periodicals' end elseif is_set (ScriptPeriodical) then if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website= Volume = A['Volume']; -- but does for all other 'periodicals' end else Volume = A['Volume']; -- and does for non-'periodical' cites end elseif in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings

Pages = hyphen_to_dash( A['Pages'] );

if not is_valid_parameter_value (ChapterUrlAccess, A:ORIGIN('chapter-url-accessChapterUrlAccess'), cfg.keywords ['url-access']) then -- same as url-access

table.insert( z.message_tail, { set_error( 'param_access_requires_param', {A:ORIGIN('chapterChapterUrlAccess'):gsub ('%-access', '')}, true ) } ); end  local MapUrlAccess = A['MapUrlAccess']; if not is_valid_parameter_value (MapUrlAccess, 'map-url-access', cfg.keywords ['url-access']) then MapUrlAccess = nil; end if not is_set(A['MapURL']) and is_set(MapUrlAccess) then MapUrlAccess = nil; table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'map-url'}, true ) } );

local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma

use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text

select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category  local coins_pages; Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);

if not is_set(PagePublicationPlace) then if and is_set(Pages) or is_set(At) then Pages = ''; -- unset the others At = ''; end extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp. elseif is_set(Pages) then if is_set(AtPlace) then At = ''; -- unset end extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. end   -- both |publication-place= and |place= (|location=) allowed if different if not is_set(PublicationPlace) and is_set(Place) then PublicationPlace = Place; -- promote |place= (|location=) to |publication-place

if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same

if is_set(Periodical) then -- Periodical is set when |encyclopedia is set

else elseif is_set (Chapter) then -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title

elseif 'mailinglist' == A:ORIGIN('Periodical') Periodical_origin then

ChapterUrlAccess = UrlAccessMapUrlAccess;

if is_set(SeriesNumber) then table.insert(s, wrap_msg ('seriesseriesnum', SeriesNumber, use_lowercase)); end

-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.

if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then

table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message end if 'arxiv' == config.CitationClass then Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string end  if 'biorxiv' == config.CitationClass then Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string

if Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = bioRxiv, ['citeseerx' ] ='CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass then Periodical = 'CiteSeerX']; -- set to CiteSeerX for COinS; after that, must be set to empty string end

local date_parameters_list = { ['access-date']= {val=AccessDate, name=A:ORIGIN ('AccessDate')}, ['archive-date']={val=ArchiveDate, name=A:ORIGIN ('ArchiveDate')}, ['date']= {val=Date, name=Date_origin}, ['doi-broken-date']= {val=DoiBroken, name=A:ORIGIN ('DoiBroken')}, ['embargo']={val=Embargo, name=A:ORIGIN ('Embargo')}, ['lay-date']= {val=LayDate, name=A:ORIGIN ('LayDate')}, ['publication-date']={val=PublicationDate, name=A:ORIGIN ('PublicationDate')}, ['year']= {val=Year, name=A:ORIGIN ('Year')}, }; anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);

-- set date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)-- if date_name_xlate (date_parameters_list, false) then

AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list['archive-date'].val; Date = date_parameters_list['date'].val; DoiBroken = date_parameters_list['doi-broken-date'].val; LayDate = date_parameters_list['lay-date'].val; PublicationDate = date_parameters_list['publication-date'].val;

if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and (is_set (Periodical) or is_set (ScriptPeriodical)) and ('journal' == A:ORIGIN(Periodical_origin or 'Periodicalscript-journal'== ScriptPeriodical_origin) then -- special case for journal cites Title = ''; -- set title to empty string add_maint_cat ('untitled');

check_for_url ({ -- add error message when any of these parameters contains hold a URL

[A:ORIGIN('Periodical')Periodical_origin]=Periodical, [A:ORIGIN('PublisherName')PublisherName_origin] = PublisherName

['Periodical'] = strip_apostrophe_markup (Periodical), -- no markup in the metadata ['Encyclopedia'] = strip_apostrophe_markup (Encyclopedia),

['Pages'] = coins_pages or get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links

['PublisherName'] = PublisherName, -- any apostrophe markup already removed

-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite citeseerxssrn}} AFTER generation of COinS data. if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or CiteSeerX ssrn now unset so it isn't displayed

PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName')PublisherName_origin, nil ));

control.maximum , editor_etal = get_display_authors_editors get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal);

control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal); -- number of interviewerss Interviewers = list_people(control, interviewers_list, falseinterviewer_etal); -- et al not currently supported

control.maximum , translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal); -- number of translators Translators = list_people(control, t, falsetranslator_etal); -- et al not currently supported

control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal); -- number of contributors Contributors = list_people(control, c, falsecontributor_etal); -- et al not currently supported

control.maximum , author_etal = get_display_authors_editors get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal);

Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.

if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or ('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia))) then

if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then or -- |url= required for cite web, cite podcast, and cite mailinglist ('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website= table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );

-- DeadURL = DeadURL:lower(); -- used later when assembling archived text UrlStatus = UrlStatus:lower(); -- used later when assembling archived text

if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it

OriginalFormat = ChapterFormat; -- and original |chapter-format= -- if 'no' ~= DeadURL then if 'live' ~= UrlStatus then

-- if 'no' ~= DeadURL then -- if URL set then archive-url applies to it if 'live' ~= UrlStatus then -- if URL set then archive-url applies to it

if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) then

chap_param = A:ORIGIN ('ScriptChapter')ScriptChapterOrigin;

Chapter = format_chapter_title (ScriptChapter, ScriptChapterOrigin, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter

if '...' == Title:sub is_set (-3ArchiveURL) then -- if elipsis is the last three characters of |title= Title = and mw.ustring.gsub (Title, 'match (%.%.%.)%.+$', '%1'); -- limit the number of dots to three elseif not mw.ustring.find lower(Title), cfg.special_case_translation['%.%s*%a%.archived_copy']) then -- end of if title is not a 'dot-Archived copy' (optional space-place holder added by bots that can't find proper title)letter-dot' initialism Title = mw.ustring.gsubadd_maint_cat (Title, '%'..sepc..'$', 'archived_copy'); -- remove any trailing separator character end if is_set(TitleLink) and is_set(Title) then add maintenance category before we modify the content of Title = make_wikilink (TitleLink, Title);

if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup: Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup else if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title= Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ... not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.) Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters end end if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or ('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) or ('map' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical))) then -- special case for cite map when the map is in a periodical treat as an article

Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped

Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped

Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped

if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format;

local ws_url, ws_label; ws_url, ws_label, L = wikisource_url_make (Title); -- make ws url from |title= interwiki link; link portion L becomes tool tip label if ws_url then Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); Title = Title .. TransTitle .. TransError; else Title = Title .. TransTitle .. TransError; end

Others = safe_join ({sepc .. ' ' .. , wrap_msg ('translated', Translators, use_lowercase) .. , Others}, sepc);

Others = safe_join ({sepc .. ' ' .. , wrap_msg ('interview', Interviewers, use_lowercase) .. , Others}, sepc);

Series = is_set(Series) and wrap_msg ('series', {sepc .. " " .. , Series}) or ""; -- not the same as SeriesNum OrigYear = is_set(OrigYear) and wrap_msg (" [" .. 'origyear', OrigYear .. "]") or ""''; -- TODO: presentation  Agency = is_set(Agency) and wrap_msg ('agency', {sepc .. " " .. , Agency}) or ""; 

if Via = is_set(Via) then Via = " " .. and wrap_msg ('via', Via)or ''; end

if "nolive" == DeadURL UrlStatus then

Archived = sepc .. " " .. substitute( cfg.messages['archived-not-deadlive'],

elseif is_set(OriginalURL) then -- DeadURL UrlStatus is empty, 'yesdead', 'trueunfit', 'yusurped', 'unfit', 'usurpedbot: unknown'

if in_array (DeadURLUrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then

if 'bot: unknown' == DeadURL UrlStatus then

else -- DeadURL UrlStatus is empty, 'yes', 'true', or 'ydead'

if (is_set(Periodical) or is_set (ScriptPeriodical) or is_set (TransPeriodical)) then

Periodical = sepc .. " " .. wrap_style format_periodical ('italic-title'ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical) ;

Periodical = wrap_style format_periodical ('italic-title'ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical);

if "speech" == config.CitationClass then -- cite speech only TitleNote = " (Speech)"; -- annotate the citation if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter if is_set (Conference) then -- and if |event= is set Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering

if is_set(Others) then Others = safe_join ({Others .. , sepc .. " " }, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?

tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );

local idcommon; if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); else idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); end

end end if EditorCount <= 1 then post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case

if EditorCount <= 1 then post_text = ", (" .. cfg.messages['editoreditors']; else post_text = .. ", )" .. cfg.messages['editors']; end end

text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.

table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation

if 0 ~= #z.message_tail ~= 0 then

if 0 ~= #z.maintenance_cats ~= 0 then table.insert (render, '<span classlocal maint_msgs ="citation{}; -comment" style="display:none; color:#33aa33; margin-left:0.3em">');here we collect all of the maint messages

local maint = {}; -- here we assemble a maintenence message table.insert (rendermaint, v); -- maint msg is the category name table.insert (rendermaint, ' ('); -- open the link text table.insert (rendermaint, make_wikilink (':Category:' .. v, 'link'));-- add the link table.insert (rendermaint, ') '); -- and close it table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table

table.insert (render, substitute (cfg.presentation['</span>hidden-maint'], table.concat (maint_msgs, ' ')));-- wrap the group of maint message with proper presentation and save

--[[--------------------------< C S 1 . C V A L I T D A T I O N E >--------------------------------------------------------------

This is used by templates such as {{cite book}} to create the actual citation textLooks for a parameter's name in one of several whitelists.

local function cs1.citationvalidate (framename, cite_class) Frame = frame; -- save a copy incase we need to display an error message in preview mode local pframe name = frame:getParenttostring (name); local validation, utilities, identifiers, metadatastate;

if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- limited parameter sets allowed for these templates state = whitelist.limited_basic_arguments[name]; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end  state = whitelist[cite_class .. '_basic_arguments'][name]; -- look in the parameter-list for the template identified by cite_class  if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end -- limited enumerated parameters list name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) state = whitelist.limited_numbered_arguments[name]; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end  return false; -- not supported because not found or name is set to nil end -- end limited parameter-set templates state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end -- all enumerated parameters allowed name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) state = whitelist.numbered_arguments[name];  if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end return false; -- not supported because not found or name is set to nilend  --[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ Look at the contents of a parameter. If the content has a string of characters and digits followed by an equalsign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly aparameter that is missing its pipe: {{cite ... |title=Title access-date=2016-03-17}} cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/htmltags are removed before the search. If a missing pipe is detected, this function adds the missing pipe maintenance category. ]] local function missing_pipe_check (parameter, value) local capture; value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc   capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes if capture and validate (capture) then -- if the capture is a valid parameter name table.insert( z.message_tail, {set_error ('missing_pipe',parameter)}); endend  --[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >-------------------------------------- look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked ]] local function has_extraneous_punc (param, value) if cfg.punct_skip[param] then return; -- parameter name found in the skip table so done end if value:match ('[,;:]$') then add_maint_cat ('extra_punct'); -- has extraneous punctuation; add maint cat endend  --[[--------------------------< C I T A T I O N >-------------------------------------------------------------- This is used by templates such as {{cite book}} to create the actual citation text. ]] local function citation(frame) Frame = frame; -- save a copy incase we need to display an error message in preview mode local pframe = frame:getParent() local validation, utilities, identifiers, metadata, styles; if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); utilities = require ('Module:Citation/CS1/Utilities/sandbox'); validation = require ('Module:Citation/CS1/Date_validation/sandbox'); identifiers = require ('Module:Citation/CS1/Identifiers/sandbox'); metadata = require ('Module:Citation/CS1/COinS/sandbox'); styles = 'Module:Citation/CS1/sandbox/styles.css'; else -- otherwise cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); utilities = require ('Module:Citation/CS1/Utilities'); validation = require ('Module:Citation/CS1/Date_validation'); identifiers = require ('Module:Citation/CS1/Identifiers'); metadata = require ('Module:Citation/CS1/COinS'); styles = 'Module:Citation/CS1/styles.css';  end  utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module  dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation year_date_check = validation.year_date_check; reformat_dates = validation.reformat_dates; date_hyphen_to_dash = validation.date_hyphen_to_dash; date_name_xlate = validation.date_name_xlate;  is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities in_array = utilities.in_array; substitute = utilities.substitute; error_comment = utilities.error_comment; set_error = utilities.set_error; select_one = utilities.select_one; add_maint_cat = utilities.add_maint_cat; wrap_style = utilities.wrap_style; safe_for_italics = utilities.safe_for_italics; is_wikilink = utilities.is_wikilink; make_wikilink = utilities.make_wikilink; strip_apostrophe_markup = utilities.strip_apostrophe_markup;  z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities

error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );-- suggest the lowercase version of the parameter

param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator) if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists) error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the suggestion error message else error_text, error_state = set_error( 'parameter_ignored', {param}, true ); -- suggested param not supported by this template end

missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe? args[k] = v; elseif args[k] ~= nil or (k == 'postscript') then -- TODO: is this the best place for this translation?

return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})});

--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------]] return cs1{citation = citation};