local cs1 z = { error_categories = {}; -- for categorizing citations that contain errors error_ids ={}; message_tail = {}; maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance}
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation
local dates, year_date_check, reformat_dates, date_hyphen_to_dash, cfg = {}; -- functions table of configuration tables that are defined in Module:Citation/CS1/Date_validationConfiguration date_name_xlatelocal whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink;[[--------------------------< I S _ S E T >------------------------------------------------------------------
local z ={}Returns true if argument is set; -- tables in Module:Citation/CS1/Utilities local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configurationlocal whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelistfalse otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. --[[--------------------------< P A G E S C O P E V A R I A B L E S >-------------------------------------- delare variables here that have page-wide scope that are not brought in This function is global because it is called from other modules; thatare created hereboth this module and used herefrom Date validation
]]
function is_set( var )local added_deprecated_cat; -- boolean flag so that the category is added only oncelocal added_prop_cats return not (var == nil or var == {}''); -- list of property categories that have been added to z.properties_catslocal added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category local Frame; -- holds the module's frame tableend
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
end
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------Whether needle is in haystack ]]
Adds a category to z.properties_cats using names from the configuration file with additional text local function in_array( needle, haystack ) if any.needle == nil then return false; end for n,v in ipairs( haystack ) do if v == needle then return n; end end return false;end
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languagesmay be categorized but multiples of the same language are not categorized.--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
added_prop_cats is Populates numbered arguments in a message string using an argument table declared in page scope variables above.
]]
local function add_prop_cat substitute(keymsg, argumentsargs ) if not added_prop_cats [key] then added_prop_cats [key] = true; -- note that we've added this category key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname tablereturn args and mw.insert( zmessage.properties_cats, substitute newRawMessage(cfg.prop_cats [key]msg, argumentsargs ):plain()or msg; -- make name then add to table end
end
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------
--[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- Adds a single Vancouver system Wraps error message messages with css markup according to the template's output regardless state of how many error actually exist.To prevent duplication, added_vanc_errs is nil until an error message is emittedhidden. added_vanc_errs is a boolean declared in page scope variables above
]]
local function add_vanc_error error_comment(sourcecontent, hidden ) if not added_vanc_errs then added_vanc_errs = true; -return substitute( hidden and cfg.presentation['hidden- note that weerror've added this category table.insert( z] or cfg.message_tail, { set_error( presentation['vancouvervisible-error'], {source}, true ) } content ); end
end
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------Sets an error condition and returns the appropriate error message. The actual placement of the error message in the output isthe responsibility of the calling function.
does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see ]]local function set_error( error_id, arguments, raw, prefix, suffix ) local error_state = cfg.error_conditions[ error_id ]; prefix = prefix or ""; suffix = suffix or ""; if iterror_state == nil thenis in agreement with http://tools error( cfg.ietfmessages['undefined_error'] ); elseif is_set( error_state.org/html/std66#section-3category ) then table.insert( z.error_categories, error_state.1 which says:category ); end Scheme names consist of a sequence of characters beginning with a letter and followed by any combination of letters local message = substitute( error_state.message, digits, plusarguments ); message = message .. " ([[" .. cfg.messages['help page link'] .. "#" .. error_state.anchor .. "+|".. cfg.messages['help page label'] .. "]]), period ("; z."error_ids[ error_id ] = true; if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } ) and z.error_ids['citation_missing_title'] then return '', or hyphen false; end message = table.concat("-"{ prefix, message, suffix }); if raw == true then return message, error_state.hidden; end return error_comment( message, error_state.hidden );end --[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
returns true Adds a category to z.maintenance_cats using names from the configuration file with additional text if it doesany.To prevent duplication, else falsethe added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.
]]
local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_catslocal function is_scheme add_maint_cat (schemekey, arguments) return scheme and scheme:match if not added_maint_cats [key] then added_maint_cats [key] = true; -- note that we've added this category table.insert( z.maintenance_cats, substitute ('^%acfg.maint_cats [%a%d%+%.%-key]*:', arguments)); -- true if scheme is set and matches the patternmake name then add to table end
end
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------Adds a category to z.properties_cats using names from the configuration file with additional text if any.
Does this thing that purports to be a domain name seem to be a valid domain name?]]
Syntax defined here: http://tools.ietf.org/html/rfc1034#sectionlocal added_prop_cats = {} --3list of property categories that have been added to z.5properties_catsBNF defined here: https://tools.ietf.org/html/rfc4234local function add_prop_cat (key, arguments) if not added_prop_cats [key] thenSingle character names are generally reserved added_prop_cats [key] = true; see https://tools -- note that we've added this category table.insert( z.ietfproperties_cats, substitute (cfg.org/html/draftprop_cats [key], arguments)); -ietf-dnsind-iana-dns-01#page-15;make name then add to table see also [[Single-letter second-level domain]]endlist of tlds: https://www.iana.org/domains/root/dbend
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Betweenthe first and last characters the name may use letters, digits, and the hyphen.--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Also allowed are IPv4 addressesAdds a single Vancouver system error message to the template's output regardless of how many error actually exist.To prevent duplication, added_vanc_errs is nil until an error message is emitted. IPv6 not supported
domain is expected to be stripped of any path so that the last character in the last character of the tld. tldis two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be strippedhere. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.]]
There are several tests: the first character of the whole domain name including subdomains must be a letter or a digit internationalized domain name (ascii characters with .xnlocal added_vanc_errs; -- ASCII Compatible Encoding flag so we only emit one Vancouver error / categorylocal function add_vanc_error (ACE) prefix xn-- in the tld) see https://tools.ietf.org/html/rfc3490 singleif not added_vanc_errs then added_vanc_errs = true; -letter/digit second-level domains in the note that we've added this category table.org and insert( z.cash TLDs qmessage_tail, { set_error( 'vancouver', x{}, and z SL domains in the .com TLD i and q SL domains in the .net TLD single-letter SL domains in the ccTLDs (where the ccTLD is two letterstrue ) two-character SL domains in gTLDs (where the gTLD is two or more letters} ); three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)end IPv4 dot-decimal address format; TLD not allowedend
returns true if domain appears to be a proper name and tld or IPv4 address, else false
]=]--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
local function is_domain_name (domain) if not domain then return false; -- if not set, abandon end domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have does this thing that purports to do it once if not domain:match ('^[%be a%d]') then -- first character must uri scheme seem to be letter or digit return false; end -- Do most common case first a valid scheme? The scheme is checked to see if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tldit return true; elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name is in agreement with ACE prefix return true; elseif domainhttp:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit /tools.cash hostname return true; elseif domain:match ('%f[%a%d][%a%d]%ietf.org$') then /html/std66#section-- one character/digit 3.org hostname return true;1 which says: elseif domain:match ('%f[%Scheme names consist of a sequence of characters beginning with a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) return true; letter and followed by any combination of letters, digits, plus elseif domain:match ('%f[%a][iq]%.net$'"+") then -- assigned one character .net hostname , period (q".net registered but not active 2015-12-10") return true; elseif domain:match , or hyphen ('%f[%a%d][%a%d]%.%a%a$') then "-- one character hostname and cctld (2 chars") return true; elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld return true; elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address return returns true; if it does, else return false; endend
]]
--[local function is_scheme (scheme) return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -------------------------< I S _ U R L >------------------------------------------------------------------true if scheme is set and matches the patternend
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
This function is the last step in the validation process. This function is separate because there are cases thatare not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted externalwikilinks.--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
]]Does this thing that purports to be a domain name seem to be a valid domain name?
local function is_url (scheme, domain)Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5BNF defined here: https://tools.ietf.org/html/rfc4234 if is_set (scheme) then Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page- if scheme is set check it and domain return is_scheme (scheme) and is_domain_name (domain)15; else return is_domain_name (domain); see also [[Single-letter second- scheme not set when url is protocol relative endlevel domain]]endlist of tlds: https://www.iana.org/domains/root/db
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between
the first and last characters the name may use letters, digits, and the hyphen.
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------Also allowed are IPv4 addresses. IPv6 not supported
Split domain is expected to be stripped of any path so that the last character in the last character of the tld. tldis two or more alpha characters. Any preceding '//' (from splitting a url into with a scheme, authority indicator, and domain) will be strippedhere. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
First remove Fully Qualified Domain Name terminator (There are several tests: the first character of the whole domain name including subdomains must be a letter or a dot following tld) digit single-letter/digit second-level domains in the .org TLD q, x, and z SL domains in the .com TLD i and q SL domains in the .net TLD single-letter SL domains in the ccTLDs (if anywhere the ccTLD is two letters) and any path two-character SL domains in gTLDs (/where the gTLD is two or more letters), query three-plus-character SL domains in gTLDs (?) where the gTLD is two or fragment(#more letters). IPv4 dot-decimal address format; TLD not allowed
If protocol relative urlreturns true if domain appears to be a proper name and tld or IPv4 address, return nil scheme and domain else return nil for both scheme and domain.false
When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (oneor more '/' characters immediately following the scheme's colon), make sure that there are only 2.]=]
Strip off any port and path; ]] local function split_url is_domain_name (url_strdomain) local schemeif not domain then return false; -- if not set, authorityabandon end domain = domain:gsub ('^//', ''); -- strip '//' from domainname if present;done here so we only have to do it once
url_str = url_strif not domain:gsub match ('(^[%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url domain = url_str:match ('^//(%S*)') elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to first character must be a scheme, optional authority indicator, and domain name scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portionsletter or digit authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return schemefalse; -- return scheme only making domain nil which will cause an error message end domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname return scheme, domaintrue;end -- elseif domain:match ('%f[%a][qxz]%.com$') then --assigned one character .com hostname (x.com times out 2015-12-----------------------< L I N K _ P A R A M _ O K >---------------------------------------------------10) return true;checks the content of |title elseif domain:match ('%f[%a][iq]%.net$') then -link=, |series-link=, |authorassigned one character .net hostname (q.net registered but not active 2015-12-link= etc for properly formatted content: no wikilinks, no urls10) return true;Link parameters are to hold the title of a wikipedia article so none of the WP elseif domain:TITLESPECIALCHARACTERS are allowed: # < > match ('%f[ %a%d] | { } _except the underscore which is used as [%a space in wiki urls and # which is used for section links returns false when the value contains any of these characters%d]%. When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be %a%a valid url (the|<param>$') then --link= parameter is ok); else false when value appears to be a valid url one character hostname and cctld (the |<param>-link= parameter is NOT ok2 chars). return true; elseif domain:match ('%f[%a%d][%a%d] local function link_param_ok (value[%a%d]%.%a%a+$')then -- two character hostname and tld local scheme, domain return true; if valueelseif domain:find match ('%f[<>%a%d][%a%d]|{}[%a%d%-]+[%a%d]%.%a%a+$') then -- if any prohibited charactersthree or more character hostname.hostname or hostname.tld return true; elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address return true; else
return false;
end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
--[[--------------------------< L I N K S _ T I T U R L E _ O K >------------------------------------------------------------------
Use link_param_ok() returns true if the scheme and domain parts of a url appear to validate |<param>-link= value and its matching |<title>= valuebe a valid url; else false.
|<title>= may be wikilinked but not when |<param>-link= has a valueThis function is the last step in the validation process. This function emits an error message whenis separate because there are cases thatare not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted externalthat condition existswikilinks.
]]
local function link_title_ok is_url (linkscheme, lorig, title, torigdomain)local orig; if is_set (linkscheme) then -- don't bother if <param>-link doesn't have a valuescheme is set check it and domain if not link_param_ok return is_scheme (linkscheme) then -- check |<param>-link= markup orig = lorig; -- identify the failing link parameter elseif title:find and is_domain_name ('%[%['domain) then -- check |title= for wikilink markup orig = torig; -- identify the failing |title= parameter end end if is_set (orig) thenelse table.insert( z.message_tail, { set_errorreturn is_domain_name ( 'bad_paramlink', orig)}domain); -- scheme not set when url or wikilink in |title= with |title-link=;is protocol relative
end
end
--[[--------------------------< C H E C K S P L I T _ U R L >------------------------------------------------------------
Determines whether Split a URL string appears to be validurl into a scheme, authority indicator, and domain.If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
First we test for space characters. If any are foundWhen not protocol relative, return false. Then split the url into get scheme and domainportions, or for protocol relative (//example.com) urlsauthority indicator, just the and domain. Use is_urlIf there is an authority indicator () to validate the twooneportions of or more '/' characters following the url. If both are validscheme's colon), or for protocol relative if domain is valid, return true, else false. Because it is different from a standard url, and because this module used external_link() to make external linkssure that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup nameis at https://tools.ietf.org/html/rfc5536#section-3.1there are only 2.4
]]
local function check_urlsplit_url ( url_str ) if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url return false; end local scheme, domain; schemeauthority, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
if 'news:' =url_str = scheme then -- special case for newsgroups return domainurl_str:matchgsub ('^([%a%d%+%-_]+)%.?[/%a%d%+%-_%?#].]*[%a%d%+$', '%-_]$1'); end return is_url -- strip FQDN terminator and path(/), query(scheme?), domainfragment (#) (the capture prevents false replacement of '//'); -- return true if value appears to be a valid urlend
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
domain = url_str:match ('^//(%S*)')
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
return scheme; -- return scheme only making domain nil which will cause an error message
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
end
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
non-space characters following the opening bracket appear to be a url. The test will also find external wikilinks
that use protocol relative urls. Also finds bare urls.
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests thatfind bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=--[[//Hus]]is possible as might be [[en://Hus]].--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
]checks the content of |title-link=], |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
local function is_parameter_ext_wikilink (value)Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:local scheme, domain; # < > [ ] | { } _except the underscore which is used as a space in wiki urls and # which is used for section links
if returns false when the value:match ('%f[%[]%[%a%S*:%S+contains any of these characters.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz] scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]')); elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text scheme, domain = split_url (value:match ('(%a%S*:%S+)')); elseif value:match ('//%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain else return false; -- didn't find anything that is obviously a url end
return is_url (schemeWhen there are no illegal characters, domain); -- return true this function returns TRUE if value appears DOES NOT appear to be a valid url(theend --[[-------------------------|< C H E C K _ F O R _ U R L param>----------------------------------------------------- loop through link= parameter is ok); else false when value appears to be a list of parameters and their values. Look at valid url (the value and if it has an external |<param>-link, emit an error message= parameter is NOT ok).
]]
local function check_for_url link_param_ok (parameter_listvalue) local error_message = ''scheme, domain; for k, v in pairs (parameter_list) do -- for each parameter in the list if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message if is_set:find (error_message) then -- once we've added the first portion of the error message ... error_message=error_message .. ", "; -- ... add a comma space separator end error_message=error_message .. "|" .. k .. "="; -- add the failed parameter end end if is_set (error_message[<>%[%]|{}]') then -- done looping, if there is an error message, display itany prohibited characters table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } )return false;
end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
--[[--------------------------< S A F C H E _ F O R C K _ U R L >------------------------------------------------------------ Determines whether a URL string appears to be valid.
Escape sequences First we test for content that will be used space characters. If any are found, return false. Then split the url into scheme and domainportions, or for URL descriptionsprotocol relative (//example.com) urls, just the domain. Use is_url() to validate the twoportions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false.
]]
local function safe_for_urlcheck_url( str url_str ) if strnil == url_str:match( "^%[%[.-%]%]S+$" ) ~then -- if there are any spaces in |url= nil then value it can't be a proper url table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } )return false;
end
local scheme, domain; return str:gsub( '[%[%]\n]'scheme, { ['['] domain = '[split_url (url_str); -- get scheme or nil and domain or nil from url;', [']'] = ']' return is_url (scheme, ['\n'] = ' ' } domain); -- return true if value appears to be a valid url
end
--[=[--------------------------< I S _ P A R A M E X T E R N A L _ E X T _ W I K I L I N K >---------------------------- Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the firstnon------------------------space characters following the opening bracket appear to be a url. The test will also find external wikilinksthat use protocol relative urls. Also finds bare urls. The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests thatfind bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]is possible as might be [[en://Hus]]. ]=]
Format an external link with error checkinglocal function is_parameter_ext_wikilink (value)local scheme, domain;
value = value:gsub ('([^%s/])/[%a%d].*', '%1'); -- strip path information (the capture prevents false replacement of '//')
local function external_link( URL, label, source, access) local error_str = ""; local domain; local path; local base_url; if not is_setvalue:match ( label '%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz] label scheme, domain = URL;value:match ('%f[%[]%[(%a%S*:)(%S+).*%]') if is_set elseif value:match ( source '%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] error_str domain = set_errorvalue:match ( 'bare_url_missing_title%f[%[]%[//(%S*%.%S+).*%]', { wrap_style ); elseif value:match ('parameter%a%S*:%S+', source) }, false, " " )then -- if bare url with scheme;may have leading or trailing plain text else errorscheme, domain = value:match ('(%a%S*:)( cfg.messages["bare_url_no_origin"] %S+)'); end end if not check_urlelseif value:match ( URL '//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text error_str domain = set_errorvalue:match ( 'bad_url', {wrap_style //(%S*%.%S+)'parameter', source)}, ; -- what is left should be the domain else return false, " " ) .. error_str; -- didn't find anything that is obviously a url
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
URL=domain..path; -- and reassemble
end
if is_set (access) then -- access level (subscription, registration, limited)
label = safe_for_url (label); -- replace square brackets and newlines
base_url = table.concat ( -- assemble external link with access signal { '<span class="plainlinks">[', -- opening css and url markup URL, -- the url ' ', -- the required space label, '<span style="padding-left:0.15em">', -- signal spacing css cfg.presentation[access], -- the appropriate icon '</span>', -- close signal spacing span ']</span>' -- close url markup and plain links span }); else base_url = table.concatreturn is_url ({ "[", URLscheme, " ", safe_for_url( label ), "]" }domain); -- no signal markup end return table.concat({ base_url, error_str });true if value appears to be a valid url
end
--[[--------------------------< D E P R C H E C A T E D K _ P A F O R A M E T E _ U R L >-----------------------------------------------------
Categorize loop through a list of parameters and emit an error message when the citation contains one or more deprecated parameterstheir values. The function includes Look at theoffending parameter name to the error message. Only one value and if it has an external link, emit an error message is emitted regardless of the number of deprecatedparameters in the citation. added_deprecated_cat is a boolean declared in page scope variables above
]]
local function deprecated_parametercheck_for_url (nameparameter_list)local error_message = ''; for k, v in pairs (parameter_list) do -- for each parameter in the list if not added_deprecated_cat is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message added_deprecated_cat = true; if is_set(error_message) then -- note that once we've added this categorythe first portion of the error message ... error_message=error_message .. ", "; -- ... add a comma space separator end error_message=error_message .. "|" .. k .. "="; -- add the failed parameter end end if is_set (error_message) then -- done looping, if there is an error message, display it table.insert( z.message_tail, { set_error( 'deprecated_paramsparam_has_ext_link', {nameerror_message}, true ) } ); -- add error message endend
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quotemark contained in a |title= or |chapter= parameter's value.--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
This function Protects a string that will positive kern either single or double quotes: "be wrapped in wiki italic markup 'Unkerned title with leading and trailing single quote marks'" " ... 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)Double single quotes (italic or bold wikimarkup) are not kerned.
Replaces unicode quotemarks in plain text or Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the label portion of a [[L|D]] style wikilink with typewritertitle is thatquote marks regardless of they will be inverted (i.e. unitalicized) in the need for kerningresulting references. Unicode quote marks are not replaced in simple [[D]] wikilinksIn addition, <i> and '' tend to interactpoorly under Mediawiki's HTML tidy.
Call this function for chapter titles, for website titles, etc; not for book titles.]]
]local function safe_for_italics( str ) if not is_set(str) then return str; else if str:sub(1,1) =]= "'" then str = "<span></span>" .. str; end if str:sub(-1,-1) == "'" then str = str .. "<span></span>"; end -- Remove newlines as they break italics. return str:gsub( '\n', ' ' ); endend
local function kern_quotes (str) local cap=''; local cap2=''; local wl_type, label, link;--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks str = substitute (cfg.presentation['kern-wl-both'], str); elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks str = substitute (cfg.presentation['kern-wl-left'], str); elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks str = substitute (cfg.presentation['kern-wl-right'], str); endEscape sequences for content that will be used for URL descriptions
else -- plain text or [[L|D]]; text in label variable label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
cap, cap2 = mw.ustring.local function safe_for_url( str ) if str:match (label, "^(%[%[\"\'.-%])([^\'%].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)~= nil then if is_set table.insert(cap) then label = substitute z.message_tail, { set_error(cfg.presentation['kern-leftwikilink_in_url'], {cap}, cap2true ) }); end
cap, cap2 = mw.ustring.match return str:gsub(label, "^(.+'[%[^%]\'n])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup), { if is_set (cap) then label = substitute (cfg.presentation['kern-right[']= '[', {cap, cap2}); end if 2 [']'] == wl_type then str = make_wikilink (link']', label); -- reassemble the wikilink else str ['\n'] = label; end end return str' ' } );
end
--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------
Applies styling to various parameters. Supplied string is wrapped using a message_list configuration taking oneargument; protects italic styled parameters. Additional text taken from citation_config.presentation --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------the reasonthis function is similar to but separate from wrap_msg().
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts shouldnot be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrappedin italic markup.]]
Regardless of languagelocal function wrap_style (key, all values provided by |scriptstr) if not is_set( str ) then return ""; elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then str = are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.safe_for_italics( str ); end
|script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon: |script-title=ja:*** *** return substitute(where * represents a Japanese charactercfg.presentation[key], {str} );Spaces between the two-character code and the colon and the colon and the first script character are allowed: |script-title=ja : *** *** |script-title=ja: *** *** |script-title=ja :*** ***Spaces preceding the prefix are allowed: |script-title = ja:*** ***end
The prefix is checked for validity. If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the -[[--------------------------<bdiE X T E R N A L _ L I N K > tag so that browsers canknow the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attributeis not added. At this time there is no error message for this condition.----------------------------------------------------
Supports |script-title= and |script-chapter=Format an external link with error checking
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
local function format_script_value external_link(script_valueURL, label, source ) local langerror_str =''; -- initialize to empty string local name""; if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script if not is_set (langlabel ) then return ''; -- script_value was just the prefix so return empty string end -- if we get this far we have prefix and script name label = mw.language.fetchLanguageName( lang, "en" )URL; -- get language name so that we can use it to categorize if is_set (namesource ) then -- is prefix a proper ISO 639-1 language code? script_value error_str = script_value:gsub set_error('^%l%l%s*:%s*bare_url_missing_title', { wrap_style ('parameter'); -- strip prefix from script -- is prefix one of these language codes? if in_array (lang, cfg.script_lang_codessource) then add_prop_cat ('script_with_name'}, {namefalse, lang}) else add_prop_cat ('script') end lang = ' lang="' .. lang .. '" '); -- convert prefix into a lang attribute
else
lang error( cfg.messages["bare_url_no_origin"] ); end end if not check_url( URL ) then error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str; -- invalid so set lang to empty string end
end
script_value = substitute return table.concat(cfg.presentation{ "['bdi'", URL, " ", safe_for_url( label ), "]", {lang, script_valueerror_str }); -- isolate in case script is rtl return script_value;
end
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------Formats a wiki style external link
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
wrapped in <bdi> tags.
]]
local function script_concatenate external_link_id(title, scriptoptions) local url_string = options.id; if is_set (script) options.encode == true or options.encode == nil then script url_string = format_script_value mw.uri.encode(scripturl_string ); -- end return mw.ustring.format( '[%s%s%s \<span title\=\"%s\"\>%s%s%s\<bdi\/span\> tags]', options.prefix, lang atributeurl_string, categorizationoptions.suffix or "", etc; returns empty string on error if is_set (script) then title = title options.link, options. ' ' label, options.. scriptseparator or " -- concatenate title and script title", endmw.text.nowiki(options.id) end return title);
end
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
--[[--------------------------< W R A P _ M S G >-------------------------------------------------------------- Applies additional Categorize and emit an error message text to various parameter values. Supplied string is wrapped using a message_listconfiguration taking when the citation contains one argumentor more deprecated parameters. Supports lower case text for {{citation}} templatesThe function includes theoffending parameter name to the error message. Additional text takenOnly one error message is emitted regardless of the number of deprecatedfrom citation_config.messages - parameters in the reason this function is similar to but separate from wrap_style()citation.
]]
local page_in_deprecated_cat; -- sticky flag so that the category is added only oncelocal function wrap_msg deprecated_parameter(key, str, lowername) if not is_set( str ) page_in_deprecated_cat then return ""page_in_deprecated_cat = true; -- note that we've added this category table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
if true == lower then
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return substitute( msg, str ); -- including template text
else
return substitute( cfg.messages[key], str );
end
end
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.This function will positive kern either single or double quotes: "'Unkerned title with leading and trailing single quote marks'" " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)Double single quotes (italic or bold wikimarkup) are not kerned.
Format the four chapter parameters: |script-Call this function for chapter=titles, |chapter=for website titles, |trans-chapter=, and |chapter-url= into a single Chapter meta-parameter (chapter_url_source used etc; not for error messages)book titles.
]]
local function format_chapter_title kern_quotes (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, accessstr) local chapter_error cap=''; local cap2= '';
if not is_set cap, cap2 = str:match ("^(chapter[\"\']) then chapter = '([^\'].+)"); -- to be safe for concatenationmatch leading double or single quote but not double single quotes else if false == no_quotes then chapter = kern_quotes is_set (chaptercap); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marksthen chapter str = wrap_style substitute (cfg.presentation['quotedkern-titleleft'], chapter{cap, cap2}); end
end
chapter cap, cap2 = script_concatenate str:match (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped if is_set "^(transchapter.+[^\']) then transchapter = wrap_style ([\"\'trans-quoted-title', transchapter])$"); if is_set (chaptercap) then chapter str = chapter .substitute (cfg. ' presentation[' .. transchapter; else -- here when transchapter without chapter or script-chapter chapter = transchapter; -kern- chapter_error = ' ' .. set_error ('trans_missing_titleright'], {'chapter'cap, cap2}); end
end
if is_set (chapterurl) then chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate end return chapter .. chapter_errorstr;
end
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts shouldnot be italicized and may be written right-[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >--------------------------------------to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrappedin italic markup.
This function searches a parameter's value for nonprintable or invisible charactersRegardless of language, all values provided by |script-title= are wrapped in <bdi>. The search stops at ..</bdi> tags to isolate rtl languages from thefirst matchEnglish left to right.
This function will detect |script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon: |script-title=ja:*** *** (where * represents a Japanese character)Spaces between the two-character code and the colon and the colon and the visible replacement first script character when it is part of are allowed: |script-title=ja : *** *** |script-title=ja: *** *** |script-title=ja :*** ***Spaces preceding the wikisource.prefix are allowed: |script-title = ja:*** ***
Detects but ignores nowiki and math stripmarkersThe prefix is checked for validity. Also detects other named stripmarkers If it is a valid ISO639-1 language code, the lang attribute (gallery, math, prelang="ja") is added to the <bdi> tag so that browsers canknow the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, ref)the lang attributeand identifies them with a slightly different is not added. At this time there is no error message. See also coins_cleanup()for this condition.
Detects but ignores the character pattern that results from the transclusion of {{'}} templates. 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 multiSupports |script-byte characters, the position of its first byte) in theparameter value.title= and |script-chapter=
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
local function has_invisible_chars format_script_value (param, vscript_value) local position lang= ''; -- position of invisible char or starting position of stripmarker local dummy; -- end of matching initialize to empty 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; capture = string.if script_value:match (v, '[^%l%wl%p ]s*:'); then -- Test for values that if first 3 non-space characters are simple ASCII text and bypass other tests if truescript language prefix if capture lang == v then script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if same there are is no unicode charactersscript if not is_set (lang) then return''; end while cfg.invisible_chars[i] do local char=cfg.invisible_chars[i][1] -- script_value was just the character or group nameprefix so return empty string local pattern=cfg.invisible_chars[i][2] end -- the pattern used to find itif we get this far we have prefix and script position, dummy, capture name = mw.ustringlanguage.find fetchLanguageName(vlang, patternmw.getContentLanguage():getCode() ) ; -- see if the parameter value contains characters get language name so that match the pattern we can use it to categorize if position and is_set (char == 'zero width joiner'name) then -- if we found is prefix a zero width joiner characterproper ISO 639-1 language code? if mw.ustring.find script_value = script_value:gsub (v'^%l%l%s*:%s*', cfg.indic_script'') then ; -- its ok if one of the indic scriptsstrip prefix from script position = nil; -- unset position end end if position thenis prefix one of these language codes? if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'nowikiug' == capture or , 'mathyi' == capture then -- nowiki, math stripmarker (not an error condition'zh'})then stripmarker = true; -- set a flag elseif true == stripmarker and add_prop_cat ('deletescript_with_name' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset{name, lang})
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 add_prop_cat ('parameterscript', param), position}, true ) } ); -- add error message return; -- and done with this parameter
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
i=i+1; -- bump our index
end
if is_set(script_value) then script_value = '-{R|' .. script_value .. '}-'; end script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
return script_value;
end
--[[--------------------------< S C R I P T _ C O N C A R G U M T E N A 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.
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
wrapped in <bdi> tags.
]]
local function argument_wrapperscript_concatenate ( args title, script) local origin if is_set(title) then title = '-{zh;zh-hans;zh-hant|' .. title .. '}-'; end return setmetatableif is_set ({script) then ORIGIN script = functionformat_script_value ( selfscript); -- <bdi> tags, k lang atribute, categorization, etc; returns empty string on error if is_set (script)then local dummy title = self[k]title .. ' ' .. script; --force the variable to be loaded. return origin[k];concatenate title and script title
end
end return title;end --[[--------------------------< W R A P _ M S G >-------------------------------------------------------------- Applies additional message text to various parameter values. Supplied string is wrapped using a message_listconfiguration taking one argument. Supports lower case text for {{citation}}templates. Additional text takenfrom citation_config.messages - the reason this function is similar to but separate from wrap_style(). ]] local function wrap_msg (key, str,lower) {if not is_set( str ) then return ""; end if true == lower then local msg; __index msg = cfg.messages[key]:lower(); -- set the message to lower case before return substitute( msg, str ); -- including template text else return substitute( cfg.messages[key], str ); end end --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- This function is used by select_one( tbl) to determine if one of a list of alias parameters is in the argument listprovided by the template. Input: args – pointer to the arguments table from calling template alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration index – for enumerated parameters, k identifies which one enumerated – true/false flag used choose how enumerated aliases are examined value – value associated with an alias that has previously been selected; nil if not yet selected selected – the alias that has previously been selected; nil if not yet selected error_list – list of aliases that are duplicates of the alias already selected Returns: value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected ]] local function is_alias_used (args, alias, index, enumerated, value, selected, error_list) if enumerated then -- is this a test for an enumerated parameters? alias = alias:gsub ('#', index); -- replace '#' with the value in index else alias = alias:gsub ('#', ''); -- remove '#' if it exists end if originis_set(args[kalias] ) then -- alias is in the template's argument list if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases local skip; for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias if v == alias then skip = true; break; -- has been added so stop looking return nilend end if not skip then -- has not been added so table.insert( error_list, alias ); -- add error alias to the error list
end
else local args, list, v value = args, cfg.aliases[kalias]; if type( list ) == 'table' then v, origin[k] = select_one( args, list, 'redundant_parameters' ); if origin[k] == nil then origin[k] = ''; -- Empty string, not nil end elseif list ~= nil then v, origin[k] = args[list]yet selected an alias, list;so select this one else -- maybe let through instead of raising an error? -- v, origin[k] selected = args[k], kalias; error( cfg.messages['unknown_argument_map'] ); end -- Empty strings, not nil; if v == nil then v = cfg.defaults[k] or ''; origin[k] = ''; end tbl = rawset( tbl, k return value, v )selected; -- return v; endnewly selected alias, });or previously selected alias
end
--[[--------------------------< V A S E L I D A E C T _ O N E >---------------------------------------------------------- Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is justnames. For parameters that may be enumerated, the position of the numerator in the parameter name is identifiedby the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'. Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
Looks for a parameter's name in Generates an error if more than one of several whitelistsmatch is present.
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
local function validateselect_one( nameargs, aliases_list, error_condition, cite_class index ) local name value = tostring( name )nil; -- the value assigned to the selected parameter local state; if in_array (cite_class, {selected = 'arxiv', 'biorxiv', 'citeseerx'}) then ; -- limited the name of the parameter sets allowed for these templateswe have chosen state local error_list = whitelist.limited_basic_arguments[ name ]{}; if true index ~== state nil then return true; end -- valid actively supported parameter if false index == state then deprecated_parameter tostring(nameindex); -- parameter is deprecated but still supported return true; end
for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list if alias:match ('arxiv#' == cite_class ) then -- basic parameters unique to these templatesif this alias can be enumerated state = whitelist.arxiv_basic_arguments[name]; end if 'biorxiv1' == cite_class index then -- when index is 1 test for enumerated and non-enumerated aliases state value, selected = whitelist.biorxiv_basic_arguments[name]is_alias_used (args, alias, index, false, value, selected, error_list);-- first test for non-enumerated alias end value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias if 'citeseerx' == cite_class thenelse state value, selected = whitelist.citeseerx_basic_arguments[name]is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias
end
end
if true =#error_list > 0 and 'none' ~= state error_condition then return true; end -- valid actively supported parameterfor cases where this code is used outside of extract_names() local error_str = ""; for _, k in ipairs( error_list ) do if false error_str ~="" then error_str = state thenerror_str .. cfg.messages['parameter-separator'] end deprecated_parameter error_str = error_str .. wrap_style (name'parameter', k); -- parameter is deprecated but still supported return true;
end
-- limited enumerated parameters list name = name:gsub( "%d+", "if #" ); -- replace digit(s) with # (last25 becomes last#)error_list > 1 then state error_str = whitelisterror_str .. cfg.limited_numbered_argumentsmessages[ name 'parameter-final-separator']; if true else error_str == state then return true; end -- valid actively supported error_str .. cfg.messages['parameter if false == state then deprecated_parameter (name); -pair- parameter is deprecated but still supported return trueseparator'];
end
return false; -- not supported because not found or name is set to nil end -- end limited parameter-set templates state error_str = whitelisterror_str ..basic_arguments[ name ]; -- all other templates; all normal parameters allowed if true == state then return true; end -- valid actively supported wrap_style ('parameter if false == state then deprecated_parameter (name', selected); -- parameter is deprecated but still supported return true; end -- all enumerated parameters allowed name = name:gsubtable.insert( "%d+"z.message_tail, "#" ); -- replace digit{ set_error(serror_condition, {error_str}, true ) with # (last25 becomes last# 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 falsevalue, selected; -- not supported because not found or name is set to nil
end
--[[--------------------------< N F O W R M A T _ C H A P T E R _ D A T I T L E >--------------------------------------------------------
When date is YYYYFormat the four chapter parameters: |script-MMchapter=, |chapter=, |trans-DD format wrap in nowrap span: <span ...>YYYYchapter=, and |chapter-MMurl= into a single Chapter meta-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 or any of the date rangesparameter (chapter_url_source used for error messages).
]]
local function nowrap_date format_chapter_title (datescriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) local cap=''; local cap2chapter_error =''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date);
elseif date:matchif not is_set ("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$"chapter) then cap, cap2 chapter = ''; -- to be safe for concatenation else if false == no_quotes then chapter = string.match kern_quotes (datechapter); -- if necessary, "^(.*)%separate chapter title's+(%d%d%d%d)$");leading and trailing quote marks from Module provided quote marks date chapter = substitute wrap_style (cfg.presentation['nowrap2quoted-title'], {cap, cap2}chapter); end
end
return date;
end
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
if is_set (transchapter) then transchapter = wrap_style ('trans-quoted-[[--------------------------< S E T _ T I T L E T Y P E >-----------------------------------------------title', transchapter); if is_set (chapter) then chapter = chapter .. ' ' .. transchapter; else --here when transchapter without chapter or script-chapter chapter = transchapter; -- chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); end end
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=none). ]] local function set_titletype (cite_class, title_type) if is_set(title_typechapterurl) then if "none" chapter == title_type then title_type = ""external_link (chapterurl, chapter, chapter_url_source); -- if |type=none then type parameter not displayed end return title_type; -- adds bare_url_missing_title error if |type= has been set to any other value use that valueappropriate
end
return cfgchapter .title_types [cite_class] or ''; -- set template's default title type. chapter_error; else empty string for concatenation
end
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------This function searches a parameter's value for nonprintable or invisible characters. The search stops at thefirst match.
Converts a hyphen to a dashThis function will detect the visible replacement character when it is part of the wikisource.
]]Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)and identifies them with a slightly different error message. See also coins_cleanup().
local function hyphen_to_dash( str ) if not is_set(str) or str:match( "[%[%]Detects but ignores the character pattern that results from the transclusion of {{'}}<>]" ) ~= nil then return str; end return str:gsub( '-', '–' );endtemplates.
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
parameter value.
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------]]
Joins local function has_invisible_chars (param, v) local 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 sequence capture is returned local capture; -- used by stripmarker detection to hold name of strings together while checking for duplicate separation characters.the stripmarker local i=1; local stripmarker, apostrophe;
while cfg.invisible_chars[i]]do local function safe_join( tbl, duplicate_char ) --char=cfg.invisible_chars[i][ Note: we use string functions here, rather than ustring functions. This has considerably faster performance and should work correctly as long as the duplicate_char is strict ASCII. The strings in tbl may be ASCII or UTF8. 1]] local str = ''; -- the output stringcharacter or group name local comp pattern= ''; cfg.invisible_chars[i][2] -- what does 'comp' mean?the pattern used to find it local end_chr position, dummy, capture = ''; local trim; for _mw.ustring.find (v, value in ipairs( tbl pattern) do -- see if the parameter value == nil then value = ''; endcontains characters that match the pattern
if str position then-- if 'nowiki' == capture or 'math' == capture or ('ref' == capture and 'quote' == param) then -- if output string is emptynowiki, math, or quote param and ref stripmarker (not an error condition) str if 'nowiki' == capture or 'math' == value; capture then -- assign value to it nowiki, math stripmarker (first time through the loopnot an error condition) stripmarker = true; -- set a flag elseif value ~true = = stripmarker and 'delete' == char then if value:sub(1-- because stripmakers begin and end with the delete char,1) =assume that we've found one end of a stripmarker position = nil; -- unset elseif '<apostrophe' == char then -- Special case of values enclosed in spans apostrophe template uses ‍, hair space and other markup.zero-width space comp apostrophe = true; elseif true = value:gsub= apostrophe and in_array ( "%b<>"char, {'zero width joiner', 'zero width space', "" 'hair space'})then position = nil; - - remove html markup (<span>string</span> -> string)unset
else
comp local err_msg; if capture then err_msg = valuecapture .. ' ' .. cfg.invisible_chars[i][3] or char; else err_msg = cfg.invisible_chars[i][3] or (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
-- typically duplicate_char is sepc end if comp:sub( i=i+1,1) == duplicate_char then ; -- is first charactier same as duplicate_char? why test first character?bump our index endend -- Because individual string segments often (always?) begin with terminal punct for th -- preceding segment: 'First element' .. 'sepc next element' .. etc? trim = false; end_chr = str:sub([[-1,-1); -- get the last character of the output string -- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? if end_chr == duplicate_char then -- if same as separator str = str:sub(1,-2); -- remove it elseif end_chr == "'" then -- if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' str = str:sub(1, -4) .. "''"; -- remove them and add back '' elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' trim = true; < A R G U M E N T _ W R A P P E R >-- why? why do this and next differently from previous? elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' trim = true; -- same question end elseif end_chr == "]" then -- if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink trim = true; elseif str:sub(-3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link trim = true; elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link trim = true; elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. trim = true; end elseif end_chr == " " then -- if last char of output string is a space if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> str = str:sub(1,-3); -- remove them both end end if trim then if value ~= comp then -- value does not equal comp when value contains html markup local dup2 = duplicate_char; if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup else value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character end end end str = str .. value; --add it to the output string end end return str;end
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------ returns true is suffix is properly formed Jr, Sr, or ordinal Argument wrapper. This function provides support for argument mapping defined in the range 2–9. Puncutation not allowedconfiguration file so thatmultiple names can be transparently aliased to single internal variable.
]]
local function is_suffix argument_wrapper(suffixargs ) if in_array (suffix, local origin = {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then return true; end return false;setmetatable({end ORIGIN = function( self, k ) -- local dummy = self[[--------------------------< I S _ G O O D _ V A N C _ N A M E >---------------------k]; ----------------------- For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a nameuses characters that contain diacritical marks, those characters are to converted to force the corresponding Latin character.When a name is written using a non-Latin alphabet or logogram, that name is variable to be transliterated into Latin charactersloaded.These things are not currently possible in this module so are left to the editor to do. return origin[k]; This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets end [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A}, 0061–007A [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6{ __index = function ( tbl, 00D8–00F6, 00F8–00FFk ) if origin[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-Ak] 0100–017F~= nil then [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F return nil; end |lastn local args, list, v = also allowed to contain hyphensargs, spaces, and apostrophescfg. aliases[k]; if type(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/list )== 'table' then|firstn v, origin[k] = also allowed to contain hyphensselect_one( args, spaceslist, apostrophes, and periods'redundant_parameters' ); This original test: if nil origin[k] == mw.ustring.find (last, "^nil then origin[Ak] = ''; -Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or Empty string, not nil end elseif list ~== mw.ustring.find (firstnil then v, "^origin[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.k]+= args[2-6%alist]*$") then, list;was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position. elseThe test has been rewritten to use decimal character escape sequence for the individual bytes -- maybe let through instead of the unicode characters so that it is not necessaryto use raising an external editor to maintain this code.error? \195\128 -\195\150 – À- Ö (U+00C0–U+00D6 – C0 controls) \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls) \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controlsv, Latin extended A & B) \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B) origin[k]= args[k] local function is_good_vanc_name (last, first)k; local first, suffix = first:match (' error(cfg.-),?%s*(messages[%dJS][%drndth'unknown_argument_map']+)%.?$') or first; -- if first has something that looks like a generational suffix, get it if is_set (suffix) then if not is_suffix (suffix) then end add_vanc_error ('suffix'); return false; -- Empty strings, not a name with an appropriate suffixnil; end end if v == nil then v == mwcfg.ustring.find (last, "^defaults[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'k]*$") or''; nil origin[k] == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then'; end add_vanc_error tbl = rawset('non-Latin character'tbl, k, v ); return false; -- not a string of latin charactersv; Vancouver requires Romanization end;, return true});
end
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.
Parameters in the whitelist can have three values: true -active, supported parameters false -[[--------------------------< R E D U C E _ T O _ I N I T I A L S >-----------------------------------------deprecated, supported parameters nil -unsupported parameters ]]
Attempts to convert names to initials local function validate( name ) local name = tostring( name ); local state = whitelist.basic_arguments[ name ]; -- Normal arguments 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 -- Arguments with numbers in support of |them name= name:gsub( "%d+", "#" ); -list-formatreplace digit(s) with # (last25 becomes last# state =vancwhitelist. numbered_arguments[ name ]; if true == state then return true; end -- valid actively supported parameterNames in |firstn if false == may be separated by spaces state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end return false; -- Not supported because not found or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.name is set to nilend
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
This -- Formats a wiki style internal linklocal function uses internal_link_id(options) return mw.ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name .format( '[[%s%s%s|\<span title\=\"%s\"\>%s\<\/span\>%s%s]]', options.prefix, options.id, options.suffix or "", options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) ).;end
]]
local function reduce_to_initials(first) local name, suffix = mw.ustring.match(first, "^(%u+) (--[%dJS][%drndth]+)$");--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
if not name then When date is YYYY-MM- if not initials and a suffix name = mwDD format wrap in nowrap span: <span ..ustring.match(first, "^(%u+)$"); >YYYY-MM- DD</span>. When date is DD MMMM YYYY or is it just intials? endMMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
if name then -- if first is initials with DOES NOT yet support MMMM YYYY or without suffix if 3 > mwany of the date ranges.ustring.len (name) then -- if one or two initials if suffix then -- if there is a suffix if is_suffix (suffix) then -- is it legitimate? return first; -- one or two initials and a valid suffix so nothing to do else add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message return first; -- and return first unmolested end else return first; -- one or two initials without suffix; nothing to do end end end -- if here then name has 3 or more uppercase letters so treat them as a word
]]
local function nowrap_date (date) local initials, names cap= {}, {}''; -- tables to hold name parts and initials local i cap2= 1''; -- counter for number of initials
names if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = mwsubstitute (cfg.text.split (first, presentation['nowrap1'[%s],]+'date); -- split into a table of names and possible suffix while names[i] do -- loop through the table if 1 < i and names[i]elseif date:match ('["^%a+%s*%d%dJS][d?,%drndth]s+%.d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$'") then -- if not the first name cap, cap2 = string.match (date, and looks like a suffix "^(.*)%s+(may have trailing dot%d%d%d%d)$"); names[i] date = namessubstitute (cfg.presentation[i]:gsub ('%.nowrap2'], ''{cap, cap2}); end return date;end -- remove terminal dot if present if is_suffix (names[i]) then [--------------------------< IS _ V A L I D _ I S X N >----------------------------------------------------- if a legitimate suffix tableISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit.insert ISBN-13 is checked in check_isbn(initials).If the number is valid the result will be 0. Before calling this function, ' ' issbn/issn must be checked for length and stripped of dashes,spaces and other non-isxn characters.. names[i ]] local function is_valid_isxn (isxn_str, len) local temp = 0; isxn_str = { isxn_str:byte(1, len) }; -- add make a separator spacetable of byte values '0' → 0x30 .. '9' → 0x39, insert at end of initials table'X' → 0x58 break len = len+1; -- and done because suffix must fall at the end of adjust to be a nameloop counter end for i, v in ipairs( isxn_str ) do -- no error message if not a suffix; possibly because loop through all of Romanization endthe bytes and calculate the checksum if 3 > i v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58) table.insert temp = temp + 10*(initials, mw.ustring.sub(names[len - i],1,1)); -- insert the intial at end of initials tableit represents 10 decimal endelse i temp = temp + tonumber( string.char(v) )*(len-i+1); -- bump the counter end end return table.concat(initials) temp % 11 == 0; -- Vancouver format does not include spaces.returns true if calculation result is zero
end
--[[--------------------------< IS _ V A L I D _ I S T X N _ P E O P L E 1 3 >-------------------------------------------------------
Formats a list of people (eISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.gIf the number is valid, the result will be 0. authors Before calling this function, isbn-13/ editors) ismn must be checked for lengthand stripped of dashes, spaces and other non-isxn-13 characters.
]]
local function list_peopleis_valid_isxn_13 (control, people, etalisxn_str) local septemp=0; local namesep; local format isxn_str = control{ isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .format. '9' → 0x39 local maximum for i, v in ipairs( isxn_str ) do temp = controltemp + (3 - 2*(i % 2)) * tonumber( string.maximumchar(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit local lastauthoramp end return temp % 10 == control.lastauthoramp0; -- sum modulo 10 is zero when isbn-13/ismn is correctend --[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------ local text = {}Determines whether an ISBN string is valid
]] local function check_isbn( isbn_str ) if 'vanc' nil ~=isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X isbn_str = format then isbn_str:gsub( "-", "" ):gsub( " ", "" ); - Vancouver-like author/editor name stylingremove hyphens and spaces local len = isbn_str:len(); if len ~= 10 and len ~= 13 then return false; end if len == 10 then if isbn_str:match( "^%d*X?$" ) == nil then return false; end sep return is_valid_isxn(isbn_str, 10); else local temp = ','0; if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979 return is_valid_isxn_13 (isbn_str); endend --[[--------------------------< C H E C K _ I S M N >----------------------------------------------------------- name-list separator between authors Determines whether an ISMN string is a commavalid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the namesep same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdfsection 2, pages 9–12. ]] local function ismn (id) local handler = cfg.id_handlers[' ISMN']; local text; local valid_ismn = true; id=id:gsub( "[%s-–]", "" ); - last/first separator is a space- strip spaces, hyphens, and endashes from the ismn elseif 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790 sep valid_ismn = 'false;' -- name-list separator between authors is a semicolon else namesep valid_ismn= ', ' is_valid_isxn_13 (id); -- last/first separator is <comma><space>validate ismn
end
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet
if false == valid_ismn then
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
end
if sep:sub(return text;end --[[--------------------------< I S S N >----------------------------------------------------------------------1 Validate and format an issn. This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of fourdigits with a space. When that condition occurred,-1) ~the resulting link looked like this: |issn= " " then sep = sep 0819 4327 gives: [http://www.worldcat. " " endorg/issn/0819 4327 0819 4327] -- can't have spaces in an external link if is_set This code now prevents that by inserting a hyphen at the issn midpoint. It also validates the issn for length and makes sure that the checkdigit agreeswith the calculated value. Incorrect length (maximum8 digits) , characters other than 0-9 and maximum < 1 then return ""X, or checkdigit / calculated value mismatch will all cause a check issnerror message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits. ]] local function issn(id, 0e) local issn_copy = id; end -- returned 0 is save a copy of unadulterated issn; use this version for EditorCountdisplay if issn does not validate local handler; local text; local valid_issn = true; not used for authors
for i,person in ipairs(people) do if is_set(person.last) e then local mask = person.mask local one local sep_one = sep; if is_set (maximum) and i > maximum then etal = true; break; elseif (mask ~= nil) then local n = tonumber(mask) if (n ~= nil) then one = string.rep("—",n) else one = mask; sep_one = " "; end else one = person.last local first = person.first if is_set(first) then if ( "vanc" handler == format ) then -- if vancouver format one = one:gsub ('%cfg.id_handlers[', 'EISSN')]; -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not testedelse first = reduce_to_initials(first) -- attempt to convert first name(s) to initials end end one = one .. namesep .. first; end if is_set(person.link) and person.link ~ handler = controlcfg.page_name then one = make_wikilink (person.link, one); -- link author/editor if this page is not the authorid_handlers['s/editorISSN's page end end table.insert( text, one ) table.insert( text, sep_one ) end];
end
local count id= #text / 2id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn if 8 ~= id:len() or nil == id:match(number of names + number of separators"^%d*X?$" ) divided by 2then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position valid_issn=false; -- wrong length or improper character if count > 0 then else if count > 1 and is_setvalid_issn=is_valid_isxn(lastauthorampid, 8) and not etal ; -- validate issn end if true == valid_issn then text[#text-2] id = string.sub( id, 1, 4 ) .. " & -".. string.sub( id, 5 ); -- replace last separator with ampersand textif valid, display correctly formatted version end else text[#text] id = nilissn_copy; -- erase if not valid, use the last separatorshow the invalid issn with error message
end
local result text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id= tableid,separator=handler.concat(textseparator, encode=handler.encode}) -- construct list if etal and is_set (result) false == valid_issn then -- etal may be set by |display-authors=etal but we might not have a last-first list result text = result .. sep text .. ' ' .. cfg.messages[set_error( 'et albad_issn']; ) -- we've go a last-first list and etal so add et al.an error message if the issn is invalid end
return result, counttext
end
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alphacharacters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digitisbn. If 10-[[--------------------------< A N C H O R _ I D >------------------------------------------------------------digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.]]
namelist is one of the contributor-local function amazon(id, author-, or editor-name lists chosen in that order. year is Year or anchor_year.domain) local err_cat = ""
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") thenlocal function anchor_id err_cat = ' ' .. set_error (namelist, year'bad_asin') local names={}; -- asin is not a table for the one to four names mix of 10 uppercase alpha and yearnumeric characters for i,v in ipairs else if id:match(namelist"^%d%d%d%d%d%d%d%d%d[%dX]$") do then -- if 10-digit numeric (or 9 digits with terminal X) if check_isbn( id ) then -- loop through the list and take up to the first four last namessee if asin value is isbn10 add_maint_cat ('ASIN'); elseif not is_set (err_cat) then err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10 end nameselseif not id:match("^%u[i%d%u] +$") then err_cat = v ' ' .last . set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha if i == 4 then break end -- if four then done
end
table.insert if not is_set(names, yeardomain); -- add the year at the endthen local id domain = table.concat(names)"com"; -- concatenate names and year for CITEREF id if is_set elseif in_array (iddomain, {'jp', 'uk'}) then -- if concatenation is not an empty stringJapan, United Kingdom return domain = "CITEREFco." .. iddomain; -- add the CITEREF portion else return elseif in_array (domain, {'au', 'br', 'mx'; }) then -- return an empty stringAustralia, Brazil, Mexico domain = "com." .. domain; no reason to include CITEREF id in this citation
end
local handler = cfg.id_handlers['ASIN'];
return external_link_id({link=handler.link,
label=handler.label, prefix=handler.prefix .. domain .. "/dp/",
id=id, encode=handler.encode, separator = handler.separator}) .. err_cat;
end
--[[--------------------------< A R X I V >--------------------------------------------------------------------
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------See: http://arxiv.org/help/arxiv_identifier
Evaluates the content of author format and editor name parameters for variations on the theme of et alerror check arXiv identifier. If foundThere are three valid forms of the identifier:the first form,valid only between date codes 9108 and 0703 is:the et al arXiv:<archive>. <class>/<date code><number><version>where: <archive> is a string of alpha characters - may be hyphenated; no other punctuation <class> is removed, a flag string of alpha characters - may be hyphenated; no other punctuation <date code> is four digits in the form YYMM where YY is set to true and the function returns last two digits of the modified name four-digit year and MM is the flagmonth number January = 01 first digit of YY for this form can only 9 and 0 <number> is a three-digit number <version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented) the second form, valid from April 2007 through December 2014 is: arXiv:<date code>.<number><version>where:This function never sets <date code> is four digits in the form YYMM where YY is the flag to false but returns it's previous state because it may have been set byprevious passes through this function or by last two digits of the parameters |displayfour-authorsdigit year and MM is the month number January =etal 01 <number> is a four-digit number <version> is a 1 or |display-editors=etalmore digit number preceded with a lowercase v; no spaces
the third form, valid from January 2015 is:
arXiv:<date code>.<number><version>
where:
<date code> and <version> are as defined for 0704-1412
<number> is a five-digit number
]]
local function name_has_etal arxiv (nameid, etal, nocatclass) local handler = cfg.id_handlers['ARXIV']; if is_set (name) then -- name can be nil in which case just returnlocal year, month, version; local etal_pattern err_cat = "[''; local text;,]? *[\ if id:match("']*^%fa[%a%.%-]+/[Ee90]%d[Tt01] *%d%d%d%d$") or id:match("^%a[Aa%a%.%-]+/[Ll90]%d[01]%d%.\"']*d%d%dv%d+$" ) then -- variations on test for the 'et al' theme9108-0703 format w/ & w/o version local others_pattern year, month = id:match("^%a[;,%a%.%-]+/([90]? *%fd)([01]%d)%d%d%a]and d[Oov%d]thers*$"); year = tonumber(year); -- and alternate to et al. month = tonumber(month); if name:match (etal_pattern(not (90 < year or 8 > year)) or (1 > month or 12 < month)) then or -- variants on et al.if invalid year or invalid month name ((91 = name:gsub = year and 7 > month) or (etal_pattern, ''7 == year and 3 < month)); then -- if foundyears ok, removeare starting and ending months ok? etal err_cat = true' ' .. set_error( 'bad_arxiv' ); -- set flag error message end elseif id:match(may have been set previously here "^%d%d[01]%d%.%d%d%d%d$") or by |displayid:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-authors1412 w/ & w/o version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); year =etaltonumber(year); month = tonumber(month); if not nocat then ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- no categorization is year invalid or is month invalid? (doesn't test for |vauthorsfuture years) ((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)? add_maint_cat err_cat = ' ' .. set_error('etalbad_arxiv'); -- and add a category if not already addedset error message end elseif nameid:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match (others_pattern"^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- if not 'et al.'test for the 1501- format w/ & w/o version year, then 'and others'? name month = nameid:gsub match("^(others_pattern, ''%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); -- if found, remove etal year = truetonumber(year); -- set flag month = tonumber(may have been set previously here or by |display-authors=etalmonth); if not nocat ((15 > year) or (1 > month or 12 < month)) then -- no categorization is year invalid or is month invalid? (doesn't test for |vauthorsfuture years) err_cat = add_maint_cat ' ' .. set_error('etalbad_arxiv'); -- and add a category if not already added endset error message
end
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
return name, etal; --
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
-- if is_set (class) then class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; --external link within square brackets, not wikilink else class = ''; ------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------empty string for concatenation end return text .. class;end
Evaluates --[[lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)1. Remove all blanks.2. If there is a forward slash (/) in the content string, remove it, and remove all characters to the right of author and editor parameters for extranious editor annotationsthe forward slash.3. If there is a hyphen in the string: ed, ed a. Remove it. b., eds, Inspect the substring following (to the right of) the (Edremoved) hyphen.Then (and assuming that steps 1 and 2 have been carried out): 1. All these characters should be digits, etcand there should be six or less.These annotation do (not belong done in author parameters and are redundant in editor parametersthis function) 2. If foundthe length of the substring is less than 6, left-fill the functionadds substring with zeroes until the editor markup maintenance categorylength is six.
Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function.
]]
local function name_has_ed_markup normalize_lccn (name, list_namelccn) local _, pattern; local patterns lccn = { -- these patterns match annotations at end of name '%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds)lccn: leading 'gsub (', case insensitive 'ed', optional 's', '.' and/or ')' '[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name) '%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (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 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', '1.' '^[%(%[]?%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 }strip whitespace
if is_set nil ~= string.find (namelccn,'/') then for _, pattern in ipairs (patterns) do -- spin through patterns table and if namelccn = lccn:match (pattern) then add_maint_cat "('extra_text_names', cfg.special_case_translation [list_name]-)/"); -- add a maint cat for this template break; end end2. remove forward slash and all character to the right of it
end
return name; -- and done
end
local prefix
local suffix
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
if nil ~= suffix then --[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >-----------------------------------if there was a hyphen suffix=string.rep("0", 6-string.len (suffix)) .. suffix; --3.b.2 left fill the suffix with 0s if suffix length less than 6 lccn=prefix..suffix; --reassemble the lccn endEvaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name return lccn;(author or editor) maintenance category. end
]]--[[Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; therightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
local function name_has_mult_names (name, list_name)local count, _; if is_set (name) length = 8 thenall digits _, count length = name:gsub ('9 then lccn[;,1]', ''); -- count the number of separator-like charactersis lower case alpha if length = 10 then lccn[1 < count then -- param could be |author= ] and lccn[2] are both lower case alpha or |editorboth digitslength = so one separator character 11 then lccn[1] is acceptable add_maint_cat ('mult_names'lower case alpha, cfg.special_case_translation lccn[list_name2]); -- more than one separator indicates multiple names so add a maint cat for this templateand lccn[3] are both lower case alpha or both digits end end return name; -- length = 12 then lccn[1] and doneendlccn[2] are both lower case alpha
]]
--[local function lccn(lccn) local handler = cfg.id_handlers['LCCN']; local err_cat = ''; --presume that LCCN is valid local id = lccn; ------------------------< N A M E _ C H E C K S >--------------------------------------------------------This function calls various name checking functions used to validate the content local copy of the various name-holdingparameters.lccn
]] id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) local len = id:len(); -- get the length of the lccn
local function name_checks if 8 == len then if id:match(last, first, list_name"[^%d]") then -- if LCCN has anything but digits (nil if only digits) if is_set err_cat = ' ' .. set_error(last'bad_lccn' ) ; -- set an error message end elseif 9 == len then -- LCCN should be adddddddd if lastnil == id:match ('^"%l%d%d%d%d%(d%(.*d%)d%d")$then -- does it match our pattern? err_cat = ' ' .. set_error( 'bad_lccn'); -- set an error message end elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd if id:match("[^%d]") then -- if wrapped in doubled parentheses, accept as written LCCN has anything but digits (nil if only digits) ... last if nil = last= id:match ('"^%(l%l%d%d%d%d%d%((.*)d%)d%d")$then -- ... see if it matches our pattern err_cat = ' ' .. set_error( 'bad_lccn'); -- strip parensno match, set an error message end elseend last elseif 11 == name_has_mult_names len then -- LCCN should be aaadddddddd or adddddddddd if not (last, list_nameid:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")); then -- check for multiple names in the parameter (last only)see if it matches one of our patterns last err_cat = name_has_ed_markup ' ' .. set_error(last, list_name'bad_lccn' ); -- check for extraneous 'editor' annotationno match, set an error message
end
end if is_set (first) elseif 12 == len then -- LCCN should be aadddddddddd if firstnot id:match ('"^%(l%l%d%d%d%d%d%d%d%(.*d%)d%)$'d") then -- see if wrapped in doubled parentheses, accept as written it matches our pattern first err_cat = first:match ' ' .. set_error('^%(%((.*)%)%)$bad_lccn'); -- strip parens else first = name_has_ed_markup (firstno match, list_name); -- check for extraneous 'editor' annotationset an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
end
return last, firstif not is_set (err_cat) and nil ~= lccn:find ('%s') then err_cat = ' ' .. set_error( 'bad_lccn' ); -- donelccn contains a space, set an error message
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------Gets name list from Format PMID and do simple error checking. PMIDs are sequential numbers beginning at 1 and counting up. This code checks the input argumentsPMID to see that itcontains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.]]
Searches through args in sequential order to find |lastnlocal function pmid(id) local test_limit = 30000000; -- update this value as PMIDs approach local handler = and |firstncfg.id_handlers['PMID']; local err_cat = parameters ''; -- presume that PMID is valid if id:match(or their aliases"[^%d]"), and their matching link and mask parametersthen -- if PMID has anything but digits err_cat = ' ' ..set_error( 'bad_pmid' ); -- set an error message else -- PMID is only digits local id_num = tonumber(id); -- convert id to a number for range testingStops searching when both |lastn if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries err_cat = and |firstn' ' .. set_error( 'bad_pmid' ); -- set an error message end end return external_link_id({link = are not found in args after two sequential attempts: found |last1handler.link, label =handler.label, |last2 prefix=handler.prefix, and |last3id= but doesn'tfind |last4id,separator= and |last5handler.separator, encode= then the search is donehandler.encode}) ..err_cat;end
This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
When an author or editor parameter contains some form of Determines if a PMC identifier'et als online version is embargoed.', Compares the date in |embargo= against today'et als date.' If embargo date is stripped from in the parameter and a flag (etal) returnedthat will cause list_people() to add future, returns the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out content of |embargo=; otherwise, returns and empty string because the embargo has expired or becausetemplate's metadata. When |embargo= was not set in this occurs, the page is added to a maintenance categorycite.
]]
local function extract_namesis_embargoed (args, list_nameembargo) if is_set (embargo) then local names lang = {}mw.getContentLanguage(); -- table of names local lastgood1, embargo_date, good2, todays_date; -- individual name components local first good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo ); local link good2, todays_date = pcall( lang.formatDate, lang, 'U' ); local mask; local i if good1 and good2 then -- if embargo date and today's date are good dates if tonumber( embargo_date ) >= 1tonumber( todays_date ) then -- is embargo date is in the future? return embargo; -- loop counter/indexerstill embargoed else add_maint_cat ('embargo') local n = 1 return ''; -- output table indexerunset because embargo has expired end end local count = 0end return ''; -- used to count the number of times we haven't found a |lastembargo= (or alias for authors, |editornot set return empty stringend --[[--------------------------< P M C >----------------------------------------------------------------------last or alias for editors) local etal=false; -- return value set to true when we find some form of et al Format a PMC, do simple error checking, and check for embargoed articles. in an author parameter
local err_msg_list_name = list_name:match ("(%w+)List") The embargo parameter takes a date for a value.If the embargo date is in the future the PMC identifier will notbe linked to the article. 's list'; -- modify AuthorList If the embargo date is today or EditorList for use in error messages the past, or if necessary while true doit is empty or omitted, then the last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search PMC identifier is linked to the article through args for name components beginning the link at 1 first = select_one( args, cfg.aliasesid_handlers[list_name .. '-FirstPMC'], 'redundant_parameters', i ); link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); mask = select_one( args, cfg.aliases[list_name .prefix. '-Mask'], 'redundant_parameters', i );
last, etal = name_has_etal PMC embargo date testing is done in function is_embargoed (last, etal, false); -- find and remove variations on et al.which is called earlier because when the citation first, etal has |pmc= name_has_etal (first, etal, false); -- find and remove variations on et al. last, first<value> but does not have a |url= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks if first and not last then -- if there |title= is a firstn without a matching lastn table.insert( zlinked with the PMC link.message_tail, { set_error Function is_embargoed ( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message elseif not first and not last then -- returns the embargo date if both firstn and lastn aren't found, are we done? count = count + 1; -- number of times we haven't found last and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there the PMC article is a two-name hole in the list; can't tell which end else -- we have last with or without a first link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. istill embargoed, last, list_name:match ("(%w+)List"):lower() .. '-last' otherwise it returns an empty string.. i); -- check for improper wikimarkup
names[nPMCs are sequential numbers beginning at 1 and counting up. This code checks the PMC to see that it contains only digits and is lessthan test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued. ]] = {last = last local function pmc(id, first = first, link = link, mask = mask, corporateembargo) local test_limit =false}6000000; -- add update this name to our names list (corporate for |vauthorsvalue as PMCs approach local handler = only)cfg.id_handlers['PMC']; n local err_cat = n + 1 ''; -- point to next location in the names tablepresume that PMC is valid local text; if 1 == count id:match("[^%d]") then -- if the previous name was missingPMC has anything but digits table err_cat = ' ' .insert( z.message_tail, { set_error( 'missing_namebad_pmc', {err_msg_list_name, i-1}, true ) } ); -- add this set an error message end else -- PMC is only digits local id_num = tonumber(id); -- convert id to a number for range testing if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries count err_cat = 0' ' .. set_error( 'bad_pmc' ); -- reset the counter, we're looking for two consecutive missing namesset an error message
end
i = i + 1; -- point to next args location
end
return namesif is_set (embargo) then -- is PMC is still embargoed? text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link else text = external_link_id({link = handler.link, label = handler.label, etal; -- all doneno embargo date or embargo has expired, ok to link to article prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; end return our list of namestext;
end
-- Formats a DOI and checks for DOI errors.
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------DOI names contain two parts: prefix and suffix separated by a forward slash.Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 Prefix: directory indicator '10.' followed by a registrant code. Returns the language name and associated two- or three- Suffix: character code. Because case string of any length chosen by the source may be incorrector different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match isfound, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, wereturn the original language name string.registrant
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns -- This function checks a list of languages that in some cases may includeextensionsDOI name for: prefix/suffix. For example, code 'cbk-zam' and its associated If the doi name 'Chavacano de Zamboanga' (MediaWiki does not supportcode 'cbk' contains spaces or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per seendashes, rather theyare used as sub-domain names: cbk-zam.wikipedia.org. These names can be found (for the time being) athttps://phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEnor, if it ends with a period or a comma, this function will emit a bad_doi error message.php
Names but that -- DOI names are included in case-insensitive and can incorporate any printable Unicode characters so the list will be found if that name is provided in the |language= parameter. For exampletest for spaces, endash,if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found- and the associated code is terminal punctuation may not two or three be technically correct but it appears, that in practice these characters, this function returns only the Wikimedia language nameare rarely if ever used in doi names.
Adapted from code taken from Module:Check ISO 639-1. ]] local function get_iso639_code doi(langid, this_wiki_codeinactive) local remap cat = {"" local handler = cfg.id_handlers['banglaDOI'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap ['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide 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 }
local text; if remap[lang:loweris_set(inactive)] then return remap[langlocal inactive_year = inactive:lowermatch("%d%d%d%d")or ''; -- try to get the year portion from the inactive date text = "[[" .. handler.link .. "|" .. handler.label .. "][1]:" .. id; if is_set(inactive_year) then table.insert( z.error_categories, remap[lang:lower"Pages with DOIs inactive since " .. inactive_year ); else table.insert(z.error_categories, "Pages with inactive DOIs" )][2]; -- for this language when inactive doesn't contain a recognizable year end inactive = " (" .. cfg.messages['nameinactive'] .. " " .. inactive .. ")" else text = external_link_id({link = handler.link, label = handler.label, return a possibly new name and appropriate code prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) inactive = ""
end
local languages if nil = mw= id:match("^10%.language[^%s–]-/[^%s–]-[^%.fetchLanguageNames(this_wiki_code, 'all']$") then -- get a list of language names known to Wikimedia -- (doi must begin with 'all10.' is required for North Ndebele, South Ndebelemust contain a fwd slash, must not contain spaces or endashes, and Ojibwa) local langlc = mw.ustring.lower(lang); -- lower case version for comparisons for code, name in pairs(languages) do -- scan the list to see if we can find our languagemust not end with period or comma if langlc cat == mw' ' .ustring.lowerset_error(name'bad_doi' ) then if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported return name; -- so return the name but not the code end return name, code; -- found it, return name to ensure proper capitalization and the the code end
end
return lang; -- not valid language; return language in original case and nil for the codetext .. inactive .. cat
end
--[[--------------------------< O P E N L A N G U A G E _ P A I B R A M E T E R Y >--------------------------------------------------------
Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWikiFormats an OpenLibrary link,use the returned name; if not, then use the value that was provided with the language parameterand checks for associated errors.
When |language= contains a recognized language ]]local function openlibrary(either code or nameid), the page is assigned to the category forthat local code= id: Category:Norwegian-language sources match("^%d+(no[AMW])$"). For valid three; --character code languagesonly digits followed by 'A', 'M', the page is assignedor 'W'to the single category for local handler = cfg.id_handlers['639-2OL' codes: Category:CS1 ISO 639-2 language sources.];
Languages that are the same as the local wiki are not categorized if ( code == "A" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. MediaWiki does not recognize three-character'authors/OL',equivalents of two-character codes: id=id, separator=handler.separator, encode = handler.encode}) elseif ( code == "M" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'arbooks/OL' is recognized bit , id=id, separator=handler.separator, encode = handler.encode}) elseif ( code == "W" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'araworks/OL' is not, id=id, separator=handler.separator, encode = handler.encode}) else return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'OL', id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' ); endend
This function supports multiple languages --[[--------------------------< M E S S A G E _ I D >---------------------------------------------------------- Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in the form |language=nb, French, th where the language names '<' and/or codes areseparated from each other by commas'>' angle brackets.
]]
local function language_parameter message_id (langid) local code; -- the two- or three-character language code local name; -- the language name local language_list handler = {}cfg.id_handlers['USENETID']; -- table of language names to be rendered local names_table = {}; -- table made from the value assigned to |language=
local this_wiki text = mwexternal_link_id({link = handler.link, label = handler.label, prefix=handler.getContentLanguage(prefix,id=id,separator=handler.separator, encode=handler.encode}); -- get a language object for this wiki local this_wiki_code = this_wikiif not id:match('^.+@.+$') or not id:getCodematch('^[^<].*[^>]$') then -- get this wikidoesn't have '@' or has one or first or last character is '< or '>'s language code local this_wiki_name text = mwtext .. ' ' .language.fetchLanguageNameset_error(this_wiki_code, this_wiki_code'bad_message_id' ); -- get this wiki's language nameadd an error message if the message id is invalid end return textend
local remap = { --['bh'] = 'Bihari', [--------------------------< S E T _ T I T L E T Y P E >-------------------------------------------------- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org ['bn'] = 'Bengali', -- MediaWiki returns Bangla }
names_table This function sets default title types (equivalent to the citation including |type= mw<default value>) for those templates that have defaults.text.split Also handles the special case where it is desirable to omit the title type from the rendered citation (lang, '%s*,%s*'|type=none); -- names should be a comma separated list.
for _, lang in ipairs (names_table) do -- reuse lang]]
local function set_titletype (cite_class, title_type) if lang:match is_set('^%a%a%-'title_type) then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? if "none" == title_type then lang title_type = lang:match ('(%a%a)%""; -') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?if |type=none then type parameter not displayed
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)return title_type; -- get language name if |language= is a proper code end if is_set (name) then -- if |languagetype= specified a valid code code = lang:lower(); -- save it else name, code = get_iso639_code (lang, this_wiki_code); -- attempt has been set to get code from name (assign name here so any other value use that we are sure of proper capitalization)value end if is_set (code) then -- only 2- or 3-character codes name = remapreturn cfg.title_types [codecite_class] or name''; -- override wikimedia when they misuse language codes/namesset template's default title type; else empty string for concatenationend
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language if 2 == code:len() then [[--------- and is a two-character code add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it else -- or is a recognized language (but has a three-character code) add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template end end else add_maint_cat ('unknown_lang'); -- add maint category if not already added end table.insert (language_list, name); name = ''; -- so we can reuse it end code = #language_list -- reuse code as number of languages in the list if 2 >= code then name = table.concat (language_list, ' and ') -- insert '<spaceC L E A N _ I S B N >and<space>' between two language names elseif 2 < code then language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>' name = table.concat (language_list, ', ') -- ------------------------------------------------------ Removes irrelevant text and concatenate with '<comma><space>' separatorsdashes from ISBN numberSimilar to that used for Special:BookSources end]] if this_wiki_name == name then return ''; -- if one language and that language is this wiki's return an empty string local function clean_isbn(no annotationisbn_str ) end return isbn_str:gsub(" [^-0-9X]" .. wrap_msg ('language', name)"" ); -- otherwise wrap with '(in ...)' --[[ TODO: should only return blank or name rather than full list so we can clean up the bunched parenthetical elements Language, Type, Format ]]
end
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
Returns a string where all of lua's magic characters have been escaped. This is important because functions likestring.gsub() treat their pattern and replace strings as patterns, not literal strings.]]local function escape_lua_magic_chars (argument) argument = argument:gsub("%%", "%%%%"); -- replace % with %% argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters return argument;end --[[--------------------------< S E T R I P _ C S 1 _ A P O S T Y L R O P H E _ M A R K U P >----------------------------------------------------
Set style settings for CS1 citation templatesStrip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.This function strips common patterns of apostrophe markup. We presume that editors who have taken the time tomarkup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind. Returns separator and postscript settings
]]
local function set_cs1_style strip_apostrophe_markup (psargument) if not is_set (psargument) then return argument; end while true do if argument:match ("%'%'%'%'%'") then -- bold italic (5) argument=argument:gsub("%'%'%'%'%'", ""); -- unless explicitely set to somethingremove all instances of it ps elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4) argument= argument:gsub("%'.%'%'%'", ""); elseif argument:match ("%'%'%'") then -- terminate the rendered citation with a periodbold (3) argument=argument:gsub("%'%'%'", ""); elseif argument:match ("%'%'") then -- italic (2) argument=argument:gsub("%'%'", ""); else break; end
end
return '.', psargument; -- separator is a full stopdone
end
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
Makes a title for COinS from Title and / or ScriptTitle (or any other name--[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- Set style settings for CS2 citation templates. Returns separator, postscript, ref settingsscript pairs)
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
of %27%27...
]]
local function set_cs2_style make_coins_title (pstitle, refscript) if not is_set (pstitle) then title = strip_apostrophe_markup (title); -- strip any apostrophe markup else title=''; -- if |postscript= has not been set, set cs2 defaultmake sure title is an empty string end if is_set (script) then script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string) script = strip_apostrophe_markup (script); -- strip any apostrophe markup else ps script= ''; -- if not set, make sure it isn't nilscript is an empty string
end
if not is_set (reftitle) and is_set (script) then -- if |ref= is not set ref script = "harv"' ' .. script; -- set default |ref=harvadd a space before we concatenate
end
return ',', ps, reftitle .. script; -- separator is a commareturn the concatenation
end
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- When Extract page numbers from external wikilinks in any of the |modepage= is not set , |pages=, or when its value is invalid, |at= parameters for use config.CitationClass and parameter values to establishrendered stylein COinS.
]]
local function get_settings_from_cite_class get_coins_pages (ps, ref, cite_classpages) local seppattern; if not is_set (cite_class =pages) then return pages; end -- if no page numbers then we're done while true do pattern = pages:match("citation%[(%w*:?//[^ ]+%s+)[%w%d].*%]") then ; -- for citation templates pattern is the opening bracket, the url and following space(CS2s): "[url " if nil == pattern then break; end -- no more urls sep, ps, ref pattern = set_cs2_style escape_lua_magic_chars (ps, refpattern); else -- pattern is not a citation template so CS1literal string; escape lua's magic pattern characters sep, ps pages = set_cs1_style pages:gsub(pspattern, ""); -- remove as many instances of pattern as possible
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like?
return pages;
end
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives Blocal function remove_wiki_link( str ) return sep(str:gsub( "%[%[([^%[%]]*)%]%]", psfunction(l) return l:gsub( "^[^|]*|(.*)$", ref "%1" ):gsub("^%s*(.-- return them all)%s*$", "%1"); end));
end
-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end
--[[--------------------------< S A F E T _ S T Y L E J O I N >------------------------------------------------------------
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or usesconfig.CitationClass from the template's #invoke: to establish styleJoins a sequence of strings together while checking for duplicate separation characters.
]]
local function set_style safe_join(modetbl, ps, ref, cite_classduplicate_char ) local sep; if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style[[ sep Note: we use string functions here, ps, ref = set_cs2_style (ps, ref);rather than ustring functions. elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style sep, ps = set_cs1_style (ps); else -- anything but cs1 or cs2This has considerably faster performance and should work correctly as sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on long as the template's CitationClassduplicate_char is strict ASCII. The strings end if 'none' == ps:lower() then -- if assigned value is 'none' then ps = ''; -- set to empty stringin tbl may be ASCII or UTF8. end]]
return sep, ps, refend local str = ''; --[the output string local comp =[''; -------------------------< I S what does 'comp' mean? local end_chr = ''; local trim; for _ P D F >------------------------------------------------------------------, value in ipairs( tbl ) do Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] whenvalue == nil then value = ''; endapplying the pdf icon to external links. returns true if str == '' then -- if file extension output string is one of the recognized extensions, else falseempty ] str =] local function is_pdf value; -- assign value to it (urlfirst time through the loop) return url:match ( elseif value ~= '%.pdf$') or urlthen if value:match sub(1,1) == '<'%then -- Special case of values enclosed in spans and other markup.PDF$') or url comp = value:match gsub('"%.pdf[%?#]'b<>", "" ) or url:match ; -- remove html markup ('%.PDF[%?#]'<span>string</span> -> string) else comp = value; end --[[------------ --typically duplicate_char is sepc if comp:sub(1,1) == duplicate_char then --is first charactier same as duplicate_char? why test first character? -- Because individual string segments often (always?) begin with terminal punct for th -- preceding segment: 'First element' .. 'sepc next element' .. etc? trim = false; end_chr = str:sub(-1,-1); --get the last character of the output string --str = str .. "< S T Y L E _ F O R M A T >--------------------------HERE(enchr=" .. end_chr.. ")" --debug stuff? if end_chr == duplicate_char then --if same as separator str = str:sub(1,-2); --remove it elseif end_chr == "'" then --if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "''" then --if last three chars of str are sepc'' str = str:sub(1, -4) .. "''"; --remove them and add back '' elseif str:sub(-5,-1) == duplicate_char .. "]]''" then --if last five chars of str are sepc]]'' trim = true; --why? why do this and next differently from previous? elseif str:sub(-4,-1) == duplicate_char .. "]''" then --if last four chars of str are sepc]'' trim = true; --same question endApplies css style to |format elseif end_chr ==, |chapter"]" then --format=, etc. Also emits an error message if the format parameter doesit might be wikimarkupnot have a matching url parameter. If the format parameter is not set and the url contains a file extension thatis recognized as a pdf document by MediaWiki's commons.css if str:sub(-3, this code will set the format parameter to (PDF-1) withthe appropriate styling== duplicate_char .. "]]" then -- if last three chars of str are sepc]]wikilink trim = true;local function style_format elseif str:sub(format-2, url, fmt_param, url_param-1) == duplicate_char .. "]" then -- if is_set (format) thenlast two chars of str are sepc] external link format trim = wrap_style true; elseif str:sub('format'-4, format); -- add leading space, parentheses, resize if not is_set (url1) then format = format = duplicate_char .. set_error( "'format_missing_url', {fmt_param, url_param} ); ]" then -- add an error messagenormal case when |url=something & |title=Title. trim = true; end elseif is_pdf (url) end_chr == " " then -- format is not set so if url last char of output string is a pdf file thenspace format = wrap_style if str:sub('format'-2, 'PDF'-1); == duplicate_char .. " " then -- set format to pdfif last two chars of str are <sepc><space> else format str = ''str:sub(1,-3); -- empty string for concatenationremove them both end return format; end
if trim then
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; --add it to the output string
end
end
return str;
end
--[[--------------------------< I S _ G E T O O D _ D I S P L V A Y N C _ N A U T H O R S _ M E D I T O R S >------------------------ Returns a number that defines the number of names displayed for author and editor name lists and a boolean flagto indicate when et al. should be appended to the name list.--------------------
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a nameuses characters that contain diacritical marks, those characters are to converted to the value assigned to |display-xxxxors= corresponding Latin character.When a name is written using a number greater than non-Latin alphabet or equal logogram, that name is to zero, return the number andbe transliterated into Latin characters.These things are not currently possible in this module so are left to the previous state of the 'etal' flag (false by default but may have been set editor to true if the name list containssome variant of the text 'et al.')do.
When the value assigned to This test allows |first= and |display-xxxxorslast= is names to contain any of the letters defined in the keyword 'etal'four Unicode Latin character sets [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, return a number that is one greater than the0061–007Anumber of authors in the list [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and set the 'etal' flag trueLatin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF [http://www.unicode.org/charts/PDF/U0100. This will cause the list_people() to display all ofpdf Latin Extended-A] 0100–017Fthe names in the name list followed by 'et al [http://www.unicode.org/charts/PDF/U0180.'pdf Latin Extended-B] 0180–01BF, 01C4–024F
In all other cases|lastn= also allowed to contain hyphens, spaces, returns nil and the previous state of the 'etal' flagapostrophes.(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
inputs: max: A[At the time of this writing, I had to write the 'DisplayAuthorsif nil == mw.ustring.find ...'] or A['DisplayEditors']; a number or some flavor test ouside of etal count: #a or #e list_name: 'authors' or 'editors'the code editor and paste it here etal: author_etal or editor_etalbecause the code editor gets confused between character insertion point and cursor position.
]]
local function get_display_authors_editors is_good_vanc_name (maxlast, count, list_name, etalfirst) if is_set (max) then if 'etal' nil == max:lower():gsubmw.ustring.find (last, "^[ '%.]", '') then A-Za-zÀ- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; ÖØ-öø- number of authors + 1 so display all author name plus et al. etal = true; ƿDŽ-ɏ%- overrides value set by extract_names(%s%']*$") elseif max:match or nil == mw.ustring.find ('first, "^%d+$') then [A-Za- if is a string of numbers max = tonumber (max); zÀ-ÖØ- make it a number if max >= count then öø-ƿDŽ- if |displayɏ%-xxxxors= value greater than or equal to number of authors/editors add_maint_cat (%s%'disp_auth_ed', cfg%.special_case_translation [list_name]*$"); endthen else -- not a valid keyword or number table.insert( z.message_tail, { set_erroradd_vanc_error ( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message max = nil return false; -- unsetnot a string of latin characters; as if |display-xxxxors= had not been set endVancouver required Romanization end ; return max, etaltrue;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-format=vanc.
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears Vancouver style requires family rank designations (Jr, II, III, etc) to be some rendered as Jr, 2nd, 3rd, etc. This form of pis notcurrently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. or ppSee http://www. abbreviation in the first characters of the parameter contentncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
check Page and Pages for extraneous p, p., pp, and pp. at start This function uses ustring functions because firstname initials may be any of parameter value: good pattern: '^P[^%.P%l]' matches when |pagethe unicode Latin characters accepted by is_good_vanc_name (s)= begins PX or P# but not Px where x and X are letters and # is a dgiit bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP.
]]
local function extra_text_in_page_check reduce_to_initials(pagefirst) local good_pattern = '^P[if mw.ustring.match(first, "^%.Pp]'u%u$") then return first end; --when first contains just two upper- ok case letters, nothing to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?do local initials = {} local bad_pattern i = '0; -- counter for number of initials for word in mw.ustring.gmatch(first, "[^[Pp]?[Pp]%s%.?[ %d-]';+") do -- names separated by spaces, hyphens, or periods if not page:match table.insert(good_pattern) and initials, mw.ustring.sub(page:match (bad_patternword,1,1) or page:match ('^[Pp]ages?')) then -- Vancouver format does not include full stops. i = i + 1; -- bump the counter add_maint_cat ('extra_text')if 2 <= i then break; end -- only two initials allowed in Vancouver system;if 2, quit
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------Formats a list of people (e.g. authors / editors)
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubledparentheses to also have commas; in the old version of the code, the doubled parnetheses were included in therendered citation and in the metadata. Individual author names may be wikilinked]]
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function |vauthorslocal sep; local namesep; local format =Jones AB, [[Econtrol. Bformat local maximum = control. White|White EB]], ((Black, Brown, and Comaximum local lastauthoramp = control.))lastauthoramp; local text = {}
] if 'vanc' ==]format then -- Vancouver-like author/editor name styling? local function get_v_name_table (vparam sep = ', output_table, output_link_table)'; -- name-list separator between authors is a comma local name_table namesep = mw.text.split(vparam, "%s*,%s*")' '; -- names are separated by commaslast/first separator is a space local wl_type, label, linkelse sep = '; ' --name- wl_type not used here; just list separator between authors is a place holdersemicolon namesep = ', ' -- last/first separator is <comma><space> end
local i if sep:sub(-1,-1) ~= " " then sep = sep .. " " end if is_set (maximum) and maximum < 1then return "", 0; end -- returned 0 is for EditorCount;not used for authors
while name_table[for i] ,person in ipairs(people) do if name_table[i]:match is_set('^%person.last) then local mask = person.mask local one local sep_one = sep; if is_set (%maximum) and i > maximum then etal = true; break; elseif (.*[^%mask ~= nil)][^%then local n = tonumber(mask)]$' if (n ~= nil) then -- first segment of corporate with one or more commas= string.rep("— this segment has the opening doubled parens",n) else local name one = name_table[i]mask; i sep_one =i+1" "; -- bump indexer to next segment end while name_table[i] doelse one = person.last name local first = name person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub ('%. ', ' '); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person. name_table[i]corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested first = reduce_to_initials(first) -- concatenate with previous segmentsattempt to convert first name(s) to initials end end one = one .. namesep .. first end if name_table[i]:match is_set('^person.*%)%)$'link) and person.link ~= control.page_name then one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this table member has page is not the closing doubled parens break; -- and done reassembling soauthor's/editor's page
end
i=i+1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
i text[#text] = i+1nil; -- erase the last separator end local result = table.concat(text) -- construct list if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al. end return output_table;result, count
end
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string. namelist is one of the contributor-, author-[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >---------------, or editor-name lists chosen in that order. year is Year or anchor_year. ]]local function anchor_id (namelist, year) local names={}; --a table for the one to four names and year for i,v in ipairs (namelist) do --loop through the list and take up to the first four last names names[i] = v.last if i == 4 then break end --if four then done end table.insert (names, year); --add the year at the end local id = table.concat(names); --concatenate names and year for CITEREF id if is_set (id) then --if concatenation is not an empty string return "CITEREF" .. id; --add the CITEREF portion else return ''; --return an empty string; no reason to include CITEREF id in this citation endend
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional namesmay sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliancetests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
Supports generational suffixes JrEvaluates the content of author and editor name parameters for variations on the theme of et al. If found, 2ndthe et al. is removed, 3rd, 4th–6tha flag is set to true and the function returns the modified name and the flag.
This function never sets the vancouver error when a reqired comma is missing and when there is a space between an authorflag to false but returns it's initials.previous state because it may have been set byprevious passes through this function or by the parameters |display-authors=etal or |display-editors=etal
]]
local function parse_vauthors_veditors name_has_etal (args, vparam, list_name) local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = {}; local v_link_table = {}; -- when name is wikilinked, targets go in this table local etal = false; -- return value set to true when we find some form of et al. vauthors parameter local last, first, link, mask, suffix; local corporate = false;nocat)
vparam, etal = name_has_etal if is_set (vparam, etal, truename)then -- name can be nil in which case just return local etal_pattern = "[; ,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- find and remove variations on the 'et al. do not categorize (do it here because et al. might have a period)' theme v_name_table local others_pattern = get_v_name_table (vparam"[;, v_name_table, v_link_table)]? *%f[%a]and [Oo]thers"; -- names are separated by commasand alternate to et al. for i, v_name in ipairs(v_name_table) do if v_namename:match ('^%(%(.+%)%)$'etal_pattern) then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editorvariants on et al. last name = v_namename:match gsub (etal_pattern, '^%(%((.+)%)%)$') ; -- if found, remove doubled parntheses corporate etal = true; -- set flag used in list_people(may have been set previously here or by |display-authors=etal) elseif string.find(v_name, "%s") then if v_name:find('[;%.]') not nocat then -- look no categorization for commonly occurring punctuation characters; |vauthors= add_vanc_error add_maint_cat ('punctuationetal'); -- and add a category if not already added
end
local lastfirstTable = {} lastfirstTable = mw elseif name:match (others_pattern) then -- if not 'et al.text.split(v_name', "%s")then 'and others'? first name = table.removename:gsub (lastfirstTableothers_pattern, ''); -- removes and returns value of last element in table which should be author intialsif found, remove if is_suffix (first) then etal = true; -- if a valid suffix suffix = first set flag (may have been set previously here or by |display-- save it as a suffix and first authors= table.remove(lastfirstTableetal); -- get what should be the initials from the table end if not nocat then -- no suffix error message here because letter combination may be result of Romanization; check categorization for digits? last |vauthors= table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then add_vanc_error add_maint_cat ('missing commaetal'); -- matches last II last; the case when and add a comma is missingcategory if not already added
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error ('name'); -- matches a space between two intiials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
if is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit
if is_set (suffix) then
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
suffix = ''; -- unset so we don't add this suffix to all subsequent names
end
else
if not corporate then
is_good_vanc_name (last, '');
end
end
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[i];
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
return namesname, etal; -- all done, return our list of names
end
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn'tfind |last4= and |last5= then the search is done.
Select one of This function emits an error message when there is a |authorsfirstn=, without a matching |authornlastn= / . When there are 'holes' in the list of last names, |lastn / firstnlast1=, or and |vauthorslast3= as the source of the author name list orselect one of are present but |editorslast2=is missing, an error message is emitted. |editorn= / editor-lastn= / is not required to have a matching |editor-firstn= or |veditors= as the source of the editor name list.
Only one When an author or editor parameter contains some form of these appropriate three will be used'et al.', the 'et al. The hierarchy ' is: |authorn= (stripped from the parameter and aliases) highest and |authors= lowest andsimilarly, |editorn= a flag (and aliasesetal) highest and |editors= lowestreturned When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= that will cause list_people(and all of their aliases); stops after to add the secondtest which mimicks the test used in extract_names() when looking for a hole in the author name liststatic 'et al.' text from Module:Citation/CS1/Configuration. There may be a betterway to do this, I just havenThis keeps 't discovered what that way iset al.' out of the Emits an error message when more than one xxxxor name source is providedtemplate's metadata. In When this functionoccurs, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriatethe page is added to a maintenance category.
]]
local function select_author_editor_source extract_names(vxxxxors, xxxxors, args, list_name) local lastfirst names = false{}; -- table of names if select_one( args, cfg.aliases[list_name .. 'local last; --Last'], 'none', individual name components local first; local link; local mask; local i = 1 ) or ; -- loop counter/indexer local n = 1; -- do this twice incase we have a |first1= without a |last1output table indexer local count =0; this ... select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches used to count the case where number of times we haven't found a |firstlast= is used with |vauthors= select_one( argsor alias for authors, cfg.aliases[list_name .. '|editor-Last'], 'none', 2 last or alias for editors) or local etal=false; select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then lastfirst=- return value set to true; endwhen we find some form of et al. in an author parameter
if local err_msg_list_name = list_name:match (is_set "(vxxxxors%w+) and true == lastfirstList") or .. 's list'; -- these are the three modify AuthorList or EditorList for use in error conditionsmessages if necessary (is_set (vxxxxors) and is_set (xxxxors)) or while true do (true last == lastfirst and is_set select_one(xxxxorsargs, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i )) then local err_name; if 'AuthorList' == list_name then -- figure out which search through args for name should be used in error messagecomponents beginning at 1 err_name first = select_one( args, cfg.aliases[list_name .. 'author-First'; else err_name = ], 'editorredundant_parameters', i ); end table link = select_one( args, cfg.aliases[list_name .insert( z.message_tail'-Link'], { set_error( 'redundant_parameters',i ); {err_name mask = select_one( args, cfg.aliases[list_name .. '-name-list parametersMask'], 'redundant_parameters'}, true ) } i ); -- add error message end
if true last, etal == lastfirst then return 1 endname_has_etal (last, etal, false); -- return a number indicating which author name source to usefind and remove variations on et al. if is_set first, etal = name_has_etal (vxxxxors) then return 2 end; if is_set (xxxxorsfirst, etal, false) then return 3 end; return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last endfind and remove variations on et al.
if first and not last then -- if there is a firstn without a matching lastn table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1; -- number of times we haven't found last and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there is a two-name hole in the list; can't tell which end else -- we have last with or without a first if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link; end names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message end count = 0; -- reset the counter, we're looking for two consecutive missing names end i = i + 1; -- point to next args location end return names, etal; -- all done, return our list of namesend --[[--------------------------< B U I S L D _ V A L I D _ P A R A M E L I S T E R _ V A L U E >-------------------------------------------------------- This function is used to validate a parameter's assigned value Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for those parameters that have only a limited numberany of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or emptyparameters listed in the source template) the function returns trueeach cfg.id_handlers['...'].parameters. If found, adds the parameter and value is one of tothe identifier list of allowed values returnstrue; else, emits an . Emits redundant error message and returns false.is more than one alias exists in args
]]
local function is_valid_parameter_value extract_ids(value, name, possibleargs ) if not is_set (value) then return truelocal id_list = {}; -- an empty parameter is oklist of identifiers found in args elseif in_array(value:lowerfor k, v in pairs(cfg.id_handlers )do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], possible) thenv is a table return true; else table.insertv = select_one( zargs, v.message_tailparameters, { set_error( 'invalid_param_valredundant_parameters', {name, value}, true ) } ; -- v.parameters is a table of aliases for k; here we pick one from args if present if is_set(v)then id_list[k] = v; end -- not an allowed value so if found in args, add error message return falseidentifier to our list
end
return id_list;
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a spaceinputs:when the last character is not a sepc character or when the last three characters are not sepc followed id_list – table of identifiers built by twoclosing square brackets extract_ids(close of a wikilink). options When either – table of these is true, the name_list is terminated with asingle space character.various template parameter values used to modify some manually handled identifiers
]]
local function terminate_name_list build_id_list(name_listid_list, sepcoptions ) if local new_list, handler = {}; function fallback(k) return { __index = function(stringt,i) return cfg.sub id_handlers[k][i] end } end; for k, v in pairs(name_listid_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'],v is a table -3- fallback to read-only cfg handler = setmetatable( { ['id'] = v }, fallback(k) ); if handler.mode == 'external' then table.insert( new_list,-1{handler.label, external_link_id( handler ) } ) ; elseif handler.mode == sepc 'internal' then table.insert( new_list, {handler. label, internal_link_id( handler ) } ); elseif handler.mode ~= 'manual'then error( cfg. messages['unknown_ID_mode'] ) ; elseif k == 'DOI' then -- if already properly terminated table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } ); return name_listelseif k == 'ARXIV' then table.insert( new_list, {handler.label, arxiv( v, options.Class ) } ); -- just return the name list elseif k == 'ASIN' then table.insert(stringnew_list, {handler.label, amazon( v, options.ASINTLD ) } ); elseif k == 'LCCN' then table.sub insert(name_listnew_list,-1{handler.label,-1lccn( v ) } ) ; elseif k == sepc'OL' or k == 'OLA' then table.insert( new_list, {handler.label, openlibrary( v ) or } ); elseif k == 'PMC' then table.insert( new_list, {handler.label, pmc(stringv, options.sub Embargo ) } ); elseif k == 'PMID' then table.insert(name_listnew_list,-3{handler.label,-1pmid( v ) } ) ; elseif k == sepc 'ISMN' then table.insert( new_list, {handler. label, ismn( v ) } ); elseif k == ']]ISSN'then table.insert( new_list, {handler.label, issn( v ) } ); elseif k == 'EISSN' then table.insert( new_list, {handler.label, issn( v, true ) } ); -- true distinguishes eissn from issn elseif k == 'ISBN' then local ISBN = internal_link_id( handler ); if last name in list ends with sepc charnot check_isbn( v ) and not is_set(options.IgnoreISBN) then return name_list ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", " "); -- don't add another else end table.insert( new_list, {handler.label, ISBN } ); return name_list elseif k == 'USENETID' then table.insert( new_list, {handler. sepc .label, message_id( v ) } ); else error( cfg. messages[' unknown_manual_ID'] ); end end function comp( a, b ) -- otherwise terninate the name listused in following table.sort() return a[1] < b[1]; end table.sort( new_list, comp ); for k, v in ipairs( new_list ) do new_list[k] = v[2];
end
return new_list;
end
--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------
Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities. 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate contentwhen it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisiblecharacters table?]] local function coins_cleanup (value) value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s value = value:gsub ('‍\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11) value = value:gsub (' ', ' '); -- replace entity with plain space value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space value = value:gsub ('‍', ''); -- remove ‍ entities value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space return value;end --[[--------------------------< F O R M A T _ V C O L U M E _ I N S S U E >--------------------------------------------------------------------
returns COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the concatenation of the formatted volume and issue parameters as a single string; or formatted volumeor formatted issue, or an empty string if neither are setcitation information.
]]
local function format_volume_issue COinS(volume, issue, cite_class, origin, sepcdata, lowerclass) if not is_set 'table' ~= type(volumedata) and not is_set or nil == next(issuedata) then
return '';
end
for k, v in pairs (data) do -- spin through all of the metadata parameter values if 'magazineID_list' ~== cite_class or (in_array (cite_class, {'citation', 'map'}) k and 'magazineAuthors' ~== origin) k then if is_set (volume) -- except the ID_list and is_set Author tables (issueauthor nowiki stripmarker done when Author table processed) then return wrap_msg data[k] = coins_cleanup ('vol-no', {sepc, volume, issue}, lower); elseif is_set (volume) then return wrap_msg ('vol', {sepc, volume}, lower); else return wrap_msg ('issue', {sepc, issue}, lowerv);
end
end
local vol ctx_ver = "Z39.88-2004"; -- treat table strictly as an array with only set values. local OCinSoutput = setmetatable( {}, { __newindex = function(self, key, value) if is_set(value) then rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } ); end end }); if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or ('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier if 'arxiv' == class then -- set genre according to the type of citation template we are rendering OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv elseif 'conference' == class then OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set) elseif 'web'== class then OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set) else OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles end OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only if is_set (data.Map) then OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical else OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles end -- these used onlu for periodicals OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall OCinSoutput["rft.chron"] = data.Chron; -- free-form date components OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books OCinSoutput["rft.issue"] = data.Issue; OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier if 'report' == class or 'techreport' == class then -- cite report and cite techreport OCinSoutput["rft.genre"] = "report"; elseif 'conference' == class then -- cite conference when Periodical not set OCinSoutput["rft.genre"] = "conference"; elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then if is_set (data.Chapter) then OCinSoutput["rft.genre"] = "bookitem"; OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title else if 'map' == class or 'interview' == class then OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview else OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia end end else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'} OCinSoutput["rft.genre"] = "unknown"; end OCinSoutput["rft.btitle"] = data.Title; -- book only OCinSoutput["rft.place"] = data.PublicationPlace; -- book only OCinSoutput["rft.series"] = data.Series; -- book only OCinSoutput["rft.pages"] = data.Pages; -- book, journal OCinSoutput["rft.edition"] = data.Edition; -- book only OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported) OCinSoutput["rft.degree"] = data.Degree; -- dissertation only OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation end -- and now common parameters (as much as possible) OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? if is_set k == 'ISBN' then v = clean_isbn(volumev ) thenend local id = cfg.id_handlers[k].COinS; if string.sub(id or "", 1, 4 < mw) == 'info' then -- for ids that are in the info:registry OCinSoutput["rft_id"] = table.ustringconcat{ id, "/", v }; elseif string.lensub (volume)id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords vol OCinSoutput[ id ] = substitute v; elseif id then -- when cfg.id_handlers[k].COinS is not nil OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v }; -- others; provide a url end end --[[ for k, v in pairs(data.ID_list ) do -- what to do about these? For now assume that they are common to all? local id, value = cfg.messagesid_handlers[k].COinS; if k == 'ISBN'j-volthen value = clean_isbn( v ); else value = v; end if string.sub( id or "", 1, 4 ) == 'info'then OCinSoutput["rft_id"]= table.concat{ id, {sepc"/", volumev });
else
vol = substitute (cfg.presentationOCinSoutput['vol-bold'id ], {sepc, hyphen_to_dash(volume)})= value;
end
end
]] local last, first; for k, v in ipairs( data.Authors ) do last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers if k == 1 then -- for the first author name only if is_set(last) and is_set (issuefirst) then -- set these COinS values if |first= and |last= specify the first author name return vol OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation OCinSoutput["rft. substitute aufirst"] = first; -- book, journal, dissertation elseif is_set(cfglast) then OCinSoutput["rft.messagesau"] = last; -- book, journal, dissertation -- otherwise use this form for the first name end else -- for all other authors if is_set(last) and is_set(first) then OCinSoutput['j"rft.au"] = table.concat{ last, ", ", first }; --issue']book, journal, issuedissertation elseif is_set(last)then OCinSoutput["rft.au"] = last; -- book, journal, dissertation end end
end
OCinSoutput.rft_id = data.URL; OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage }; OCinSoutput = setmetatable( OCinSoutput, nil ); -- sort with version string always first, and combine. table.sort( OCinSoutput ); table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004" return voltable.concat(OCinSoutput, "&");
end
--[[--------------------------< F O R M A G E T _ P A G E I S O 6 3 9 _ S H C O D E E T S >------------------------------------------------ Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian whereISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
adds static text to one Returns the language name and associated ISO639-1 code. Because case of |page(s)= the source may be incorrect or |sheetdifferent from the case that Wikimediauses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (sassumed to be correct)= values and returns it is returned alongwith all of the others set to empty stringscode. When there is no match, we return the original language name string.The mw.language.fetchLanguageNames() will return order a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are includedin the list will be found if that name is:provided in the |language= parameter. For example, if |language=Samaritan Aramaic, that name will be pagefound with the associated code 'sam', pagesnot an ISO639-1 code. When names are found and the associated code is not two characters, sheet, sheetsthis functionreturns only the Wikimedia language name.
Singular has priority over plural when both are providedAdapted from code taken from Module:Check ISO 639-1.
]]
local function format_pages_sheets get_iso639_code (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lowerlang) if 'mapnorwegian' == cite_class lang:lower() then -- only cite map supports sheet(s) as in-source locators if is_set (sheet) then if special case related to Wikimedia remap of code 'journalno' == origin thenat Extension:CLDR return 'Norwegian', 'no', wrap_msg ; -- Make sure rendered version is properly capitalized end local languages = mw.language.fetchLanguageNames(mw.getContentLanguage():getCode('j-sheet', sheet, lower), 'all';) else-- get a list of language names known to Wikimedia return '', '', wrap_msg -- ('sheetall'is required for North Ndebele, {sepc, sheet}South Ndebele, and Ojibwa) local langlc = mw.ustring.lower(lang), ''; -- lower case version for comparisons end for code, name in pairs(languages) do -- scan the list to see if we can find our language elseif is_set if langlc == mw.ustring.lower(sheetsname) then if 'journal' 2 ~== origin code:len() then -- ISO639-1 codes only return '', '', '', wrap_msg ('jname; --sheets', sheets, lower); else so return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Get language name from ISO639-1 code value provided. If a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and
Norwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appears
that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation'Because Norwegian Bokmål is the most common language variant, 'map'}) and 'journal' == origin); if is_set (page) then if is_journal then Media wiki has been modified to return substitute (cfg.messages['jNorwegian Bokmål for ISO639-page(s)'], page), '', '', 1 code 'no'; elseif not nopp then return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; elseHere we undo that and return substitute (cfg.messages['nopp'], {sepc, page}), 'Norwegian', '', ''; end elseif is_set(pages) then if is_journal then return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; elseif tonumber(pages) ~when editors use |language= nil and not nopp then -- if pages is only digits, assume a single page number return '', substitute (cfgno.messages[ We presume that editors don'p-prefix'], {sepc, pages}), '', ''; elseif not nopp then return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; else return t know about the variants or can'', substitute (cfgt descriminate between them.messages['nopp'], {sepc, pages}), '', ''; end end return '', '', '', ''; -- return empty stringsend
See Help talk:Citation Style_1#An ISO 639-1 language name test
--[When |language=[-------------------------< A R C H I V E _ U R L _ C H E C K >-----------------------------------------contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) ifthe page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way.
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to This function supports multiple languages in the save snapshot url or to calendar pages. When form |language=nb, French, th where the archive url is 'https://web.archive.org/save/' (language names or http://...)archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allowunwitting readers to docodes are separated from each other by commas.
When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its ownalgorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
This local function looks at language_parameter (lang) local code; -- the value assigned to |archiveISO639-url= and returns empty strings for |archive1 two character code local name; -url= and|archive-date= and an error message when:the language name |archivelocal language_list = {}; --url= holds an archive.org save command urltable of language names to be rendered |archivelocal names_table = {}; --url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in table made from the correct placeotherwise returns value assigned to |archive-url= and |archive-datelanguage=
There are two mostly compatible archive.org urls: //web.archive.org/<timestamp>... -- the old form //web.archive.org/web/<timestamp>.names_table = mw.text. split (lang, '%s*,%s*'); -- the new formnames should be a comma separated list
The old form does not support or map to the new form when it contains a display flag. There are four identified flags('id_', 'js_', 'cs_' for _, 'im_') but since archive.org ignores others following the same form lang in ipairs (two letters and an underscorenames_table)we don't check for these specific flags but we do check the form. -- reuse lang
This function supports if lang:match ('^%a preview mode. When the article is rendered in preview mode, this funct may return %a modified%-') or 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)archive url if lang:match ('^zh-') then for save command errors, return undated wildcard name = mw.language.fetchLanguageName( lang:lower(/*/) for timestamp errors when the timestamp has a wildcard, return the url unmodified for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard lang:lower(/yyyymm*/)); else] name =] local function archive_url_check mw.language.fetchLanguageName( lang:lower(url), datemw.getContentLanguage():getCode() ) local err_msg = ''; --get ISO 639- start with the error message empty1 language name if Language is a proper code local path, timestamp, flag; -- portions of the archive.or url end end
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate end if url:matchis_set ('//web%.archive%.org/save/'name) then -- if Language specified a save command url, we don't want to allow saving of the target page valid ISO639-1 code err_msg code = 'save command'; url = urllang:gsub lower('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL elseif url:match('//liveweb%.archive%.org/') thensave it err_msg = 'liveweb'; else path name, timestamp, flag code = url:match('//web%.archive%.org/get_iso639_code ([^%d]*)(%d+)([^/]*)/'lang); -- split out some attempt to get code from name (assign name here so that we are sure of the url parts for evaluationproper capitalization) end if not is_set(timestamp) or 14 ~= timestamp:len(code) then -- path and flag optional, must have 14-digit timestamp here err_msg if 'no' == code then name = 'timestamp挪威语'end; -- override wikimedia when code is 'no' if '*zh' ~= flag then url=urlcode and not code:gsub match ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?zh-')[^/]*then -- English not the language add_prop_cat (', '%1*foreign_lang_source', 1) -- for preview{name, modify ts to be yearmo* max (0-6 digits plus splatcode})
end
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
err_msg = 'path';
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
err_msg = 'flag';
elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = 'flag';
else
return url, dateadd_maint_cat ('unknown_lang'); -- return archiveURL and ArchiveDateadd maint category if not already added
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
code = #language_list -- reuse code as number of languages in the list if here, something not right so2 >= code then name = table.insertconcat ( z.message_taillanguage_list, { set_error( 'archive_url及', {err_msg}, true ) } ); -- add error message andinsert '<space>及<space>' between two language names if is_set (Frame:preprocess('{{REVISIONID}}')) elseif 2 < code then return '', language_list[code] = '及'.. language_list[code]; -- return empty strings for archiveURL and ArchiveDate elseprepend last name with '及<space>' return urlname = table.concat (language_list, date; '，') -- preview mode so return archiveURL and ArchiveDateconcatenate with '<comma><space>' separators
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ Look at the contents of a parameterSet style settings for CS1 citation templates. If the content has a string of characters Returns separator 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.postscript settings
]]
local function missing_pipe_check set_cs1_style (valueps) local capture; value = value:gsub if not is_set ('%b<>', ''ps); then -- remove xml/html tags because attributes: class=, title=, etc unless explicitely set to something capture = value:match ('%s+(%a[%a%d]+)%s* ps =') or value:match ('^(%a[%a%d]+)%s*=.'); -- find and categorize parameters terminate the rendered citation with possible missing pipes if capture and validate (capture) then -- if the capture is a valid parameter name add_maint_cat ('missing_pipe');period
end
return '.', ps; -- separator is a full stop
end
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ This is the main function doing the majority of the Set style settings for CS2 citation formattingtemplates.Returns separator, postscript, ref settings
]]
local function citation0set_cs2_style ( configps, argsref) if not is_set (ps) then --[[ if |postscript= has not been set, set cs2 default ps = ''; -- make sure it isn't nil Load Input Parametersend The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.if not is_set (ref) then -- if |ref= is not set ref = "harv"; -- set default |ref=harv ]]end local A = argument_wrapper( args )return ',', ps, ref; -- separator is a comma local i end
-- Pick out the relevant fields from the arguments. Different citation templates [[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- define different field names for the same underlying things.
-- set default parameter values defined by When |mode= parameter. local Mode = A['Mode']; if is not is_valid_parameter_value (Modeset or when its value is invalid, 'mode', cfguse config.keywords['mode']) thenCitationClass and parameter values to establish Mode = ''; endrendered style.
local author_etal; local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authors; local NameListFormat = A['NameListFormat']; local Collaboration = A['Collaboration'];
do -- to limit scope of selected local selected = select_author_editor_source function get_settings_from_cite_class (A['Vauthors'], A['Authors']ps, argsref, 'AuthorList'cite_class) local sep; if 1 (cite_class == selected then a, author_etal = extract_names (args, 'AuthorList'"citation"); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might befor citation templates (CS2) a sep, ps, author_etal ref = parse_vauthors_veditors set_cs2_style (argsps, args.vauthors, 'AuthorList'ref); else -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=not a citation template so CS1 elseif 3 == selected then Authors = A['Authors']; -- use content of |authors= if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authorssep, ps = add_maint_cat set_cs1_style ('authors'ps); -- because use of this parameter is discouraged; what to do about the aliases is a TODO: end end if is_set (Collaboration) then author_etal = true; return sep, ps, ref -- so that |display-authors=etal not required endreturn them all end
local Others = A--['Others'];[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
local editor_etal; local e = {}; -- editors list from |editor-lastn= / Establish basic style settings to be used when rendering the citation. Uses |editor-firstnmode= pairs if set and valid or |veditors=uses local Editors;config.CitationClass from the template's #invoke: to establish style.
do -- to limit scope of selected local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList'); if 1 == selected then e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might be e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= elseif 3 == selected then Editors = A['Editors']; -- use content of |editors= add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged end end
local function set_style (mode, ps, ref, cite_class) local t sep; if 'cs2' = {}; = mode then -- translators list from |translatorif this template is to be rendered in CS2 (citation) style sep, ps, ref = set_cs2_style (ps, ref); elseif 'cs1' == mode then -lastn= / translator-firstnif this template is to be rendered in CS1 (cite xxx) style sep, ps = pairsset_cs1_style (ps); local Translators; else -- assembled translators name listanything but cs1 or cs2 t sep, ps, ref = extract_names get_settings_from_cite_class (argsps, ref, cite_class); -- get settings based on the template'TranslatorLists CitationClass end if 'none' == ps:lower(); then -- fetch translator list from |translatornif assigned value is 'none' then ps = / |translator''; --lastn=set to empty string end return sep, ps, refend --firstn[=, [-------------------------< I S _ P D F >------------------------------------------------------------------linkn= Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] whenapplying the pdf icon to external links. returns true if file extension is one of the recognized extension, -maskn=else false
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 discouraged else interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters end
local function is_pdf (url) local c = {}return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?'); end --[[--------------------------< S T Y L E _ F O R M A T >--------------------------------------------------- contributors list from --- Applies css style to |contributor-lastnformat= / contributor, |chapter-firstnformat= pairs, etc. Also emits an error message if the format parameter does local Contributors; -- assembled contributors name listnot have a matching url parameter. If the format parameter is not set and the url contains a file extension that local Contribution = A['Contributionis recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) withthe appropriate styling. ]]; if in_arraylocal function style_format (config.CitationClassformat, url, {"book"fmt_param,"citation"}url_param) and not if is_set(A['Periodical']format) then -- |contributor= and |contribution= only supported in book cites c format = extract_names wrap_style (args, 'ContributorListformat', format); -- fetch contributor list from |contributorn= / |contributor-lastn=add leading space, -firstn=parenthases, -linkn=, -maskn=resize if 0 < #c then if not is_set (Contributionurl) then -- |contributor= requires |contribution format = tableformat .insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message c = {}; -- blank the contributorsformat_missing_url' table; it is used as a flag later end if 0 == #a then -- |contributor= requires |author= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param'fmt_param, 'author')url_param}); -- add missing author an error message c = {}; -- blank the contributors' table; it is used as a flag later end
end
else elseif is_pdf (url) then -- format is not set so if not url is a book citepdf file then if select_one format = wrap_style (args, cfg.aliases['ContributorList-Lastformat'], 'redundant_parametersPDF', 1 ) then -- are there contributor name list parameters? table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error messageset format to pdf end else Contribution format = nil''; -- unsetempty string for concatenation
end
return format;
end
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >-------------------list-format']) then -- only accepted value for this parameter is 'vanc' NameListFormat = ''; -- anything else, set to empty string end
local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- Get title data local Title = A['Title']; local ScriptTitle = A['ScriptTitle']; local BookTitle = A['BookTitle']; local Conference = A['Conference']; local TransTitle = A['TransTitle']; local TitleNote = A['TitleNote']; local TitleLink = A['TitleLink']; link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= Returns a number that may or wikimarkup in |title= when |title-link= is setmay not limit the length of the author or editor name lists.
local Chapter = A['Chapter']; local ScriptChapter = A['ScriptChapter']; local ChapterLink -When the value assigned to |display- authors= A['ChapterLink']; -- deprecated as is a parameter but still used internally by cite episodenumber greater than or equal to zero, return the number and local TransChapter = A[the previous state of the 'TransChapteretal']; local TitleType = A['TitleType'];flag (false by default but may have been set to true if the name list contains local Degree = A['Degree']; local Docket = A['Docket']; local ArchiveFormat = A[some variant of the text 'ArchiveFormatet al.'];).
local ArchiveDate;When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the local ArchiveURL;number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all ofthe names in the name list followed by 'et al.'
ArchiveURLIn all other cases, ArchiveDate = archive_url_check (A[returns nil and the previous state of the 'ArchiveURLetal'], A['ArchiveDate']) local DeadURL = A['DeadURL'] if not is_valid_parameter_value (DeadURL, 'dead-url', cfgflag.keywords ['deadurl']) then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string end
local URL = A['URL'] local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local function get_display_authors_editors (max, count, list_name, etal) local Series if is_set (max) then if 'etal' == Amax:lower():gsub("['Series%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; -- number of authors + 1 so display all author name plus et al. etal = true; -- overrides value set by extract_names() elseif max:match ('^%d+$') then -- if is a string of numbers max = tonumber (max); -- make it a number if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed', list_name); end else -- not a valid keyword or number table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-'].. list_name, max}, true ) } ); -- add error message max = nil; -- unset end elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category max = count + 1; -- number of authors + 1 end
local Volumereturn max, etal; local Issue;end local Page; local Pages; local At;--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Adds page to Category:CS1 maint: extra text if in_array (config.CitationClass, cfg.templates_using_volume) then Volume |page= or |pages= A['Volume']; end -- conference & map books do not support issue if in_array (config.CitationClass, cfghas what appears to be some form of p.templates_using_issue) and not (in_array (configor pp.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then Issue = A['Issue']; end local Position = ''; if not in_array (config.CitationClass, cfgabbreviation in the first characters of the parameter content.templates_not_using_page) then Page = A['Page']; Pages = hyphen_to_dash( A['Pages'] ); At = A['At']; end
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: local Edition = Agood pattern: '^P[^%.P%l]'Edition'];matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit local PublicationPlace = A[bad pattern: 'PublicationPlace'] local Place = A^['Place'Pp]; local PublisherName = A['PublisherName'Pp]; local RegistrationRequired = A['RegistrationRequired']; if not is_valid_parameter_value matches matches when |page(RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']s) then RegistrationRequired=nil; endbegins pp or pP or Pp or PP
local SubscriptionRequired = A['SubscriptionRequired']; if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then SubscriptionRequired=nil; end
local UrlAccess function extra_text_in_page_check (page)-- local good_pattern = A'^P[^%.P%l]'UrlAccess']; if not is_valid_parameter_value (UrlAccess, local good_pattern = 'url-access', cfg^P[^%.keywords [Pp]'url; -access']- ok to begin with uppercase P: P7 (pg 7 of section P) then UrlAccess = nil; end if but not is_set(URL) and is_setp123 (UrlAccesspage 123) thenTODO: add Gg for PG or Pg? UrlAccess -- local bad_pattern = nil'^[Pp][Pp]'; table local bad_pattern = '^[Pp]?[Pp]%.insert( z.message_tail, { set_error( 'param_access_requires_param', {?[ %d]'url'}, true ) } ); end
if is_set not page:match (UrlAccessgood_pattern) and is_set (SubscriptionRequiredpage:match (bad_pattern) then -- while not aliases, these are much the same so if both are set table.insert( z.message_tail, { set_erroror page:match ( 'redundant_parameters', {wrap_style ('parameter', 'url-access^[Pp]ages?') .. ' and ' .. wrap_style ) then add_maint_cat ('parameter', 'subscriptionextra_text')}, true ) } ); -- add error messageend SubscriptionRequired = nil; -- unset; prefer |access= over |subscription= end if is_set Page:match (UrlAccess'^[Pp]?[Pp]%.?[ %d]') and is_set or Page:match (RegistrationRequired'^[Pp]ages?[ %d]') then or-- these are not the same but contradictory so if both are set table.insert Pages:match ( z'^[Pp]?[Pp]%.message_tail, { set_error( ?[ %d]'redundant_parameters', {wrap_style ) or Pages:match ('parameter^[Pp]ages?[ %d]', 'url) then--access') .. ' and ' .. wrap_style add_maint_cat ('parameter', 'registrationextra_text')}, true ) } ); -- add error message RegistrationRequired = nil; -- unset; prefer |access= over |registration= end end
local ChapterUrlAccess = A['ChapterUrlAccess'];
if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', cfg.keywords ['url-access']) then -- same as url-access
ChapterUrlAccess = nil;
end
if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then
ChapterUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'chapter-url'}, true ) } );
end
local Via = A--[['Via']; local AccessDate = --------------------------< P A['AccessDate']; local Agency = R S E _ V A['Agency'];U T H O R S _ V E D I T O R S >--------------------------------
local Language This function extracts author / editor names from |vauthors= A['Language']; local Format or |veditors= A['Format']; local ChapterFormat and finds matching |xxxxor-maskn= A['ChapterFormat'];and local DoiBroken |xxxxor-linkn= A['DoiBroken']; local ID = A['ID']; local ASINTLD = A['ASINTLD']; local IgnoreISBN = A['IgnoreISBN']; if not is_valid_parameter_value in args. It then returns a table of assembled names just as extract_names(IgnoreISBN, 'ignore-isbn-error', cfg) does.keywords ['yes_true_y']) then IgnoreISBN = nil; -- anything else, set to empty string end local Embargo = A['Embargo']; local Class = A['Class']; -- arxiv class identifier
local ID_list Author / editor names in |vauthors= extract_idsor |veditors= must be in Vancouver system style. Corporate or institutional namesmay sometimes be required and because such names will often fail the is_good_vanc_name( args );and other format compliance local ID_access_levels = extract_id_access_levelstests, are wrapped in doubled paranethese (( args, ID_list corporate name));to suppress the format tests.
local Quote = A[This function sets the vancouver error when a reqired comma is missing and when there is a space between an author'Quote'];s initials.
local LayFormat = A['LayFormat']; local LayURL = A['LayURL']; local LaySource = A['LaySource']; local Transcript = A['Transcript']; local TranscriptFormat = A['TranscriptFormat']; local TranscriptURL = A['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
local function parse_vauthors_veditors (args, vparam, list_name) local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = {}; local etal = false; -- return value set to true when we find some form of et al. vauthors parameter local last, first, link, mask; local LastAuthorAmp corporate = false; vparam, etal = Aname_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) if vparam:find ('%[%['LastAuthorAmp) or vparam:find ('%]%]') then -- no wikilinking vauthors names add_vanc_error (); end v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas for i, v_name in ipairs(v_name_table) do if not is_valid_parameter_value v_name:match ('^%(%(LastAuthorAmp, .+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor last= v_name:match ('^%(%((.+)%)%)$') corporate = true; elseif string.find(v_name, "%s") then lastfirstTable = {} lastfirstTable = mw.text.split(v_name, "%s") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be authorintials last = table.concat(lastfirstTable, " ") --ampreturns a string that is the concatenation of all other names that are not initials if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, cfg.keywords ['yes_true_y%u %u$']) then add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials LastAuthorAmp end else first = nil''; -- set to empty stringfor concatenation and because it may have been set for previous author/editor last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
local no_tracking_cats = A['NoTracking']; if is_set (first) and not is_valid_parameter_value mw.ustring.match (no_tracking_catsfirst, 'no"^%u?%u$") then -tracking'- first shall contain one or two upper-case letters, cfg.keywords ['yes_true_y']) thennothing else no_tracking_cats = niladd_vanc_error (); -- set to empty string
end
--local variables that are not cs1 parameters local use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.getCurrentTitlethis from extract_names (); -- also used for COinS and for language local anchor_year; -- used in the CITEREF identifier local COinS_date link = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification local DF = Aselect_one( args, cfg.aliases[list_name .. 'DF-Link'], 'redundant_parameters', i ); -- date format set in cs1|2 template if not is_valid_parameter_value mask = select_one(DF, 'df'args, cfg.keywordsaliases[list_name .. 'date-formatMask'], 'redundant_parameters', i ) then -- validate reformatting keyword; DF names[i] = {last = last, first = first, link = link, mask = mask, corporate= ''corporate}; -- not valid, set add this assembled name to empty stringour names list
end
return names, etal; -- all done, return our list of names
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ local PostScript; local Ref; sepcSelect one of |authors=, PostScript|authorn= / |lastn / firstn=, Ref or |vauthors= set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);as the source of the author name list or use_lowercase select one of |editors= ( sepc , |editorn=/ editor-lastn= ',' ); / |editor-- used to control capitalization for certain static textfirstn= or |veditors= as the source of the editor name list.
--check this page to see if it is in Only one of the namespaces that cs1 these appropriate three will be used. The hierarchy is not supposed to add to the error categories if not is_set : |authorn= (no_tracking_catsand aliases) then -- ignore if we are already not going to categorize this pagehighest and |authors= lowest and if in_array (this_page.nsTextsimilarly, cfg.uncategorized_namespaces) then no_tracking_cats |editorn= "true"; -- set no_tracking_cats end for _,v in ipairs (cfg.uncategorized_subpagesand aliases) do -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats highest and |editors= "true"; -- set no_tracking_cats break; -- bail out if one is found end end endlowest
-- check When looking for extra |pageauthorn=/ |editorn= parameters, test |pagesxxxxor1= or and |atxxxxor2= parameters. (also sheet and sheets while we're at itall of their aliases); stops after the second select_onetest which mimicks the test used in extract_names( args, {'page') when looking for a hole in the author name list. There may be a betterway to do this, I just haven'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this t discovered what that way is a dummy call simply to get the error message and category.
local NoPP = A['NoPP'] if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfgEmits an error message when more than one xxxxor name source is provided.keywords ['yes_true_y']) then NoPP = true; else NoPP = nil; -- unset, used as a flag later end
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 In this page to maint cat if |pagefunction, vxxxxors = value begins with what looks like p. vauthors or pp. elseif is_set(Pages) then if is_set(At) then At = ''veditors; -- unset end extra_text_in_page_check (Pages); -- add this page to maint cat if |pagesxxxxors = value begins with what looks like p. authors or ppeditors as appropriate. end ]]
-- both |publication-place= and |place= local function select_author_editor_source (|locationvxxxxors, xxxxors, args, list_name)local lastfirst =) allowed if differentfalse; if not is_setselect_one(PublicationPlaceargs, cfg.aliases[list_name .. '-Last'], 'none', 1 ) and is_setor -- do this twice incase we have a first 1 without a last1 select_one(Placeargs, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then PublicationPlace lastfirst= Placetrue; -- promote |place= (|location=) to |publication-place
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title
|trans-title maps to |trans-chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped
All other combinations of |encyclopedia, |title, and |article are not modified
]]
local Encyclopedia = A['Encyclopedia']; if ( config.CitationClass is_set (vxxxxors) and true == "encyclopaedia" lastfirst) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citationthese are the three error conditions if (is_set(Periodicalvxxxxors) then -- Periodical is set when |encyclopedia is set if and is_set(Titlexxxxors)) or is_set (ScriptTitle) then if not is_set (Chapter) then Chapter true == Title; -- |encyclopedia and |title are set so map |title to |article lastfirst and |encyclopedia to |title ScriptChapter = ScriptTitle; TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; if not is_set (ChapterURLxxxxors) and is_set (TitleLink) then Chapter = make_wikilink (TitleLink, Chapter) local err_name; end Title if 'AuthorList' = Periodical; ChapterFormat = Format; Periodical = ''; list_name then -- redundant so unsetfigure out which name should be used in error message TransTitle = ''; URL = ''; Format = ''; TitleLink = ''; ScriptTitle err_name = 'author'; end else -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical err_name = 'editor'; -- redundant so unset
end
end table.insert( z.message_tail, { set_error( 'redundant_parameters', {err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
if true == lastfirst then return 1 end; -- Special case for cite techreport.return a number indicating which author name source to use if is_set (config.CitationClass == "techreport"vxxxxors) then -- special case for cite techreportreturn 2 end; if is_set(A['Number']xxxxors) then return 3 end; return 1; -- cite techreport uses no authors so return 1; this allows missing author name test to run in case there is a first without last end --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------ This function is used to validate a parameter's assigned value for those parameters that have only a limited number'of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or emptyin the source template) the function refurns true. If the parameter value is one of the list of allowed values returnstrue; else, emits an error message and returns false. ]] local function is_valid_parameter_value (value, name, which other citations alias to 'issue'possible) if not is_set(IDvalue) then -- can we use ID for the "number"? ID = A['Number'] return true; -- yesan empty parameter is ok elseif in_array(value:lower(), use itpossible) then return true; else -- ID has a value so emit error message table.insert( z.message_tail, { set_error('redundant_parametersinvalid_param_val', {wrap_style ('parameter'name, 'id') .. ' and ' .. wrap_style ('parameter', 'number')value}, true )}); end-- not an allowed value so add error message end return false
end
end
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
-- Account for [[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a spacewhen the oddity that last character is {{cite conference}}, before generation not a sepc character or when the last three characters are not sepc followed by twoclosing square brackets (close of COinS dataa wikilink). When either of these is true, the name_list is terminated with a if 'conference' == configsingle space character.CitationClass then if is_set]] local function terminate_name_list (BookTitlename_list, sepc) then Chapter = Title; if (string.sub (name_list,-1,- ChapterLink 1) == TitleLink; sepc) or (string.sub (name_list,-3,- |chapterlink1) = is deprecated ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = URLorigin; URLorigin = sepc .. ']]';) then -- if last name in list ends with sepc char ChapterFormat = Format; TransChapter = TransTitle; Title = BookTitle; Format = '' return name_list .. " "; -- TitleLink = don'';t add another TransTitle = ''; URL = ''; else end elseif 'speech' ~= configreturn name_list .. sepc ..CitationClass then Conference = ''; -- not cite conference or cite speech so make sure this is empty stringotherwise terninate the name list
end
end
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- cite map oddities returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volumeor formatted issue, or an empty string if neither are set. ]] local Cartography = ""function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) if not is_set (volume) and not is_set (issue) then return ''; local Scale = "";end local Sheet = A[if 'Sheetmagazine'] == cite_class or (in_array (cite_class, {'citation'; local Sheets = A[, 'Sheetsmap'] or }) and 'magazine'; if config.CitationClass == "map" origin) then Chapter = A['Map'];if is_set (volume) and is_set (issue) then ChapterURL = A[ return wrap_msg ('MapURLvol-no'], {sepc, volume, issue}, lower); ChapterUrlAccess = UrlAccess;elseif is_set (volume) then TransChapter = A[ return wrap_msg ('TransMapvol'], {sepc, volume}, lower); ChapterURLorigin = A:ORIGINelse return wrap_msg ('MapURLissue', {sepc, issue}, lower); ChapterFormat end end local vol = A['MapFormat'];
Cartography = A['Cartography']; if is_set (volume) then if is_set( Cartography 6 < mw.ustring.len(volume)) then Cartography vol = sepc substitute (cfg.. " " .. wrap_msg (messages['cartographyj-vol'], Cartography{sepc, use_lowercasevolume}); end else Scale vol = A[wrap_style ('Scalevol-bold']; if is_set, hyphen_to_dash( Scale volume)) then Scale = sepc .. " " .. Scale;
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation adds static text to one of COinS data. if 'episode' |page(s)== config.CitationClass or 'serial' |sheet(s)== configvalues and returns it with all of the others set to empty strings.CitationClass then local AirDate = A['AirDate'];The return order is: local SeriesLink = A['SeriesLink']; link_title_ok (SeriesLink page, A:ORIGIN ('SeriesLink')pages, Seriessheet, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is setsheets
local Network = A['Network']; local Station = A['Station']; local s, n = {}, {}; -- do common parameters first if is_set(Network) then tableSingular has priority over plural when both are provided.insert(n, Network); end if is_set(Station) then table.insert(n, Station); end ID = table.concat(n, sepc .. ' '); if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = AirDate; end
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Season = A['Season']; local SeriesNumber = A['SeriesNumber'];
if is_set local function format_pages_sheets (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set table.insert( z.message_tailpage, pages, sheet, sheets, { set_error( 'redundant_parameters'cite_class, {wrap_style ('parameter'origin, 'season') .. ' and ' .. wrap_style ('parameter'sepc, 'seriesno')}nopp, true lower) } ); -- add error message SeriesNumber = if 'map'; -- unset; prefer |season= over |seriesno= end cite_class then --only cite map supports sheet(s) as in- assemble a table of parts concatenated later into Seriessource locators if is_set(Seasonsheet) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) 'journal' == origin then table.insert(s return '', wrap_msg ('series', SeriesNumber, use_lowercase)); end if is_set(Issue) then table.insert(s, wrap_msg ('episodej-sheet', Issuesheet, use_lowercaselower)); end Issue = , ''; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapterelse ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = A:ORIGIN( return 'URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number if is_set wrap_msg (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = make_wikilink (ChapterLink'sheet', Chapter); elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set{sepc, URL links episode; Series = make_wikilink (ChapterLinksheet}, Serieslower), '';
end
elseif is_set (sheets) then URL if 'journal' == origin then return ''; -- unset TransTitle = , '', ''; ScriptTitle = , wrap_msg ('j-sheets', sheets, lower); else -- now oddities that are cite serial Issue = return '', ''; -- unset because this parameter no longer supported by the citation/core version of cite serial Chapter = A[, 'Episode']; -- TODO: make |episode= available to cite episode someday? if is_set , wrap_msg (Series) and is_set (SeriesLink) then Series = make_wikilink (SeriesLink'sheets', {sepc, sheets}, Serieslower);
end
Series = wrap_style ('italic-title', Series); -- series is italicized end
end
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. do if in_array (config.CitationClass, {local is_journal = 'arxivjournal', 'biorxiv', 'citeseerx'}) then if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= = cite_class or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates table.insert( z.message_tailin_array (cite_class, { set_error( config.CitationClass .. '_missingcitation', {'map'}, true ) } ); -- add error message end if and 'arxivjournal' == config.CitationClass then Periodical = 'arXiv'origin); -- set to arXiv for COinS; after that, must be set to empty string end
if is_set (page) then if is_journal then if return substitute (cfg.messages['j-page(s)'], page), '', '', 'biorxiv' == config.CitationClass ; elseif not nopp then Periodical = return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string end else if return substitute (cfg.messages['nopp'], {sepc, page}), '', 'citeseerx' == config.CitationClass then Periodical = , 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string end
end
endelseif is_set(pages) then if is_journal then -- handle type parameter for those CS1 citations that have default values if in_array return substitute (configcfg.CitationClass, {"AVmessages['j-media-notes"page(s)'], "interview"pages), "mailinglist"'', "map"'', "podcast"''; elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, "pressrelease"assume a single page number return '', "report"substitute (cfg.messages['p-prefix'], "techreport"{sepc, "thesis"pages}) , '', ''; elseif not nopp then TitleType = set_titletype return '', substitute (configcfg.CitationClassmessages['pp-prefix'], TitleType{sepc, pages}), '', ''; if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesiselse TitleType = Degree .. return ' ' .. , substitute (cfg.title_types messages['thesisnopp']:lower(, {sepc, pages}), '', '';
end
end
return '', '', '', ''; -- return empty strings
end
if is_set(TitleType) then -- if type parameter is specified TitleType = substitute( cfg.messages['type'], TitleType); [--------------------------< C I T A T I O N 0 >---------------------------------------------------------- display it in parentheses -- TODO: Hack on TitleType to fix bunched parentheses problem end
-- legacy: promote PublicationDate to Date if neither Date nor Year are setThis is the main function doing the majority of the citation formatting. if not is_set (Date) then Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set Date = PublicationDate; -- promote PublicationDate to Date PublicationDate = ''; -- unset, no longer needed end end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation]]
local function citation0( config, args) --[[ Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is whereLoad Input Parameters we get The argument_wrapper facilitates the date used in the metadatamapping of multiple aliases to single internal variable. Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch local error_message A = ''argument_wrapper( args ); -- AirDate has been promoted to Date so not necessary to check it local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};i
anchor_year, Embargo, error_message -- Pick out the relevant fields from the arguments. Different citation templates -- define different field names for the same underlying things. local author_etal; local a = dates(date_parameters_list, COinS_date){}; -- start temporary Julian authors list from |lastn= / Gregorian calendar uncertainty categorization|firstn= pairs or |vauthors= if COinS_date.inter_cal_cat then local Authors; add_prop_cat ( local NameListFormat = A['jul_greg_uncertaintyNameListFormat')]; end-- end temporary Julian / Gregorian calendar uncertainty categorization
if is_set (Year) and is_set (Date) then do -- both |date= and |year= not normally needed; to limit scope of selected local mismatch selected = year_date_check select_author_editor_source (YearA['Vauthors'], A['Authors'], args, Date'AuthorList'); if 0 1 == mismatch selected then a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |yearauthorn= does not match a year/ |lastn= / |firstn=, |author-value in linkn=, and |dateauthor-maskn= if is_set (error_message) elseif 2 == selected then -- if there is already an error message error_message NameListFormat = error_message .. ', vanc'; --override whatever |name- tack on this additional messagelist-format= might be end error_message a, author_etal = error_message .parse_vauthors_veditors (args, args. vauthors, '|year= / |date= mismatchAuthorList'); elseif 1 == mismatch then -- fetch author list from |yearvauthors= matches year, |author-value in linkn=, and |dateauthor-maskn= add_maint_cat ( elseif 3 == selected then Authors = A['date_yearAuthors')]; end -- use content of |authors=
end
if not is_set(error_message) then -- error free dates only local modified = false; -- flag if is_set (DF) then -- if we need to reformat dates modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate end
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate modified local Coauthors = true; add_maint_cat (A['date_formatCoauthors')]; -- hyphens were converted so add maint category end -- for those wikis that can and want to have English date names translated to the local language, -- uncomment these three lines. Not supported by en.wiki (for obvious reasons)-- if date_name_xlate (date_parameters_list) then-- modified Others = trueA['Others'];-- end
if modified then -- if the date_parameters_list values were modified AccessDate = date_parameters_list['access-date'] local editor_etal; -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list['archive-date']; Date = date_parameters_list['date']; DoiBroken = date_parameters_list['doi-broken-date']; LayDate local e = date_parameters_list['lay-date']; PublicationDate = date_parameters_list['publication-date']; end else table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message end end editors list from |editor-- end of do -- Account for the oddity that is {{cite journal}} with |pmclastn= set and / |url= not set. Do this after date check but before COInS. -editor- Here we unset Embargo if PMC not embargoed (|embargofirstn= not set in the citation) pairs or if the embargo time has expired. Otherwise, holds embargo date Embargo |veditors= is_embargoed (Embargo); if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then if not is_set (Embargo) then -- if not embargoed or embargo has expired URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed URLorigin = cfg.id_handlers['PMC'].parameters[1]local Editors; -- set URLorigin to parameter name for use in error message if citation is missing a |title= if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url= table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); AccessDate = ''; -- unset end
do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
if 1 == selected then
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
elseif 2 == selected then
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
end
end
local t = {}; -- At this point fields may be nil if they weren't specified in the template use. We can use that fact.translators list from |translator-lastn= / translator-firstn= pairs local Translators; -- Test if citation has no titleassembled translators name list if not is_set(Title) and not is_set(TransTitle) and not is_set(ScriptTitle) then if 'episode' =t = config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? table.insert( z.message_tail, { set_errorextract_names ( 'citation_missing_title'args, {'seriesTranslatorList'}, true ) } ); else table.insert( z.message_tail -- fetch translator list from |translatorn= / |translator-lastn=, { set_error( 'citation_missing_title'-firstn=, {'title'}-linkn=, true ) } ); end end-maskn=
if local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs local Contributors; -- assembled contributors name list local Contribution = A['noneContribution' == Title and ]; if in_array (config.CitationClass, {'journal'"book", '"citation'"}) and not is_set (Periodical) and 'journal' == A:ORIGIN(['Periodical']) then -- special case for journal |contributor= and |contribution= only supported in book cites Title c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, - set title to empty stringmaskn= add_maint_cat ('untitled'); end if 0 < #c then check_for_url if not is_set ({ Contribution) then -- add error message when any of these parameters contains a URL ['title']|contributor= requires |contribution=Title, [A:ORIGIN table.insert('Chapter')]=Chapterz.message_tail, [A:ORIGIN{ set_error('Periodicalcontributor_missing_required_param')]=Periodical, [A:ORIGIN('PublisherNamecontribution')] = PublisherName }); -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.add missing contribution error message c = {}; -- handle blank the oddity that contributors' table; it is cite encyclopedia and {{citation used as a flag later end if 0 == #a then -- |contributor= requires |encyclopediaauthor=something}} table.insert( z. Here we presume that -- when Periodicalmessage_tail, Title{ set_error( 'contributor_missing_required_param', and Chapter are all set, then Periodical is the book (encyclopedia'author')}) title, Title; -- add missing author error message c = {}; -- is blank the article title, and Chapter contributors' table; it is used as a section within the article. So, we remap flag later end end local coins_chapter = Chapter; else -- default assuming that remapping if not requireda book cite local coins_title = Title; -- et tu if select_one (args, cfg.aliases['encyclopaediaContributorList-Last' == config.CitationClass or (], 'citationredundant_parameters' == config.CitationClass and is_set (Encyclopedia), 1 ) then-- are there contributor name list parameters? if is_set table.insert(Chapter) and is_set z.message_tail, { set_error(Title'contributor_ignored') and is_set (Periodical}) then -- if all are used then coins_chapter = Title; -- remap coins_title = Periodical;add contributor ignored error message
end
end local coins_author = a; -- default for coins rft.au if 0 < #c then -- but if contributor list coins_author Contribution = cnil; -- use that insteadunset
end
-- this is the function call to COinSif not is_valid_parameter_value () local OCinSoutput = COinS({ ['Periodical'] = PeriodicalNameListFormat, ['Encyclopedia'] = Encyclopedia, ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), name-list- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Degree'] = Degree; -- cite thesis only ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup [format'PublicationPlace'] = PublicationPlace, ['Date'] = COinS_datecfg.rftdate, -- COinS_date has correctly formatted date if Date is valid; keywords['Season'] = COinS_date.rftssn, ['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', name-list- chron but if not set and invalid date format use Date; keep this last bit? ['Series'] = Series, ['Volume'] = Volume, ['Issue'] = Issue, ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external linksthen ['Edition'] = Edition, ['PublisherName'] = PublisherName, ['URL'] = first_set ({ChapterURL, URL}, 2), ['Authors'] = coins_author, ['ID_list'] = ID_list, ['RawPage'] = this_page.prefixedText, }, config.CitationClass); -- Account only accepted value for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite citeseerx}} AFTER generation of COinS data. if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerxthis parameter is '}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isnvanc't displayed Periodical NameListFormat = ''; -- periodical not allowed in these templates; if article has been publishedanything else, use cite journal end -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername set to include some static text if 'newsgroup' == config.CitationClass then if is_set (PublisherName) then PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil )); endempty string
end
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local Date = A['Date'];
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
end
local Chapter = A['Chapter'];
local ScriptChapter = A['ScriptChapter'];
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
local Degree = A['Degree'];
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
local ArchiveURL = A['ArchiveURL'];
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local ChapterURL = A['ChapterURL'];
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
-- Now perform various field substitutions.local Series = A['Series']; -- We also add leading spaces and surrounding markup and punctuation to the -- various parts of the citation, but only when they are non-nil.local Volume; local EditorCountIssue; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list dolocal Page; local last_first_listPages; local control = { format = NameListFormat, -- empty string or 'vanc' maximum = nil, -- as if display-authors or display-editors not set lastauthoramp = LastAuthorAmp, page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn mode = Mode }At;
do -- do editor name list first because the now unsupported coauthors used to modify control table control if in_array (config.maximum CitationClass, editor_etal cfg.templates_using_volume) and not ('conference' = get_display_authors_editors = config.CitationClass and not is_set (Periodical)) then Volume = A['DisplayEditorsVolume']; end if in_array (config.CitationClass, #ecfg.templates_using_issue) and not (in_array (config.CitationClass, {'editorsconference', editor_etal'map'})and not is_set (Periodical))then Issue = A['Issue']; end local Position = ''; last_first_list if not in_array (config.CitationClass, EditorCount cfg.templates_not_using_page) then Page = A['Page']; Pages = list_peoplehyphen_to_dash(control, e, editor_etalA['Pages'] ); At = A['At']; end
if is_set (Editors) then if editor_etal then Editors local Edition = Editors .. A[' Edition' .. cfg.messages]; local PublicationPlace = A['et alPublicationPlace']; -- add et al. to editors parameter beause |display-editors=etal EditorCount local Place = 2A['Place']; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation else EditorCount local PublisherName = 2; -- we donA['PublisherName't know but assume |editors= is multiple names]; spoof to display (eds.) annotation end else Editors local RegistrationRequired = last_first_listA['RegistrationRequired']; -- either an author name list or an empty string end if 1 == EditorCount and not is_valid_parameter_value (true == editor_etal or 1 < #eRegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then -- only one editor displayed but includes etal then EditorCount RegistrationRequired= 2nil; -- spoof to display (eds.) annotation end
end
do -- now do interviewers control.maximum local SubscriptionRequired = #interviewers_listA['SubscriptionRequired']; -- number of interviewerss Interviewers = list_people if not is_valid_parameter_value (controlSubscriptionRequired, interviewers_list'subscription', falsecfg.keywords ['yes_true_y'])then SubscriptionRequired=nil; -- et al not currently supported
end
do -- now do translators control.maximum local Via = A['Via']; local AccessDate = A['AccessDate']; local ArchiveDate = A['ArchiveDate']; local Agency = #tA['Agency']; -- number of translators Translators local DeadURL = list_peopleA['DeadURL'] if not is_valid_parameter_value (controlDeadURL, t'dead-url', falsecfg.keywords ['deadurl'])then -- set in config.defaults to 'yes' DeadURL = ''; -- et al not currently supportedanything else, set to empty string
end
do -- now do contributors control.maximum local Language = A['Language']; local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local DoiBroken = A['DoiBroken']; local ID = A['ID']; local ASINTLD = #cA['ASINTLD']; -- number of contributors Contributors local IgnoreISBN = list_peopleA['IgnoreISBN']; if not is_valid_parameter_value (controlIgnoreISBN, c'ignore-isbn-error', falsecfg.keywords ['yes_true_y'])then IgnoreISBN = nil; -- et al not currently supportedanything else, set to empty string
end
do -- now do authors control.maximum , author_etal local Embargo = get_display_authors_editors (A['DisplayAuthorsEmbargo'], #a, ; local Class = A['authorsClass', author_etal)]; -- arxiv class identifier
last_first_list local ID_list = list_peopleextract_ids(control, a, author_etalargs );
if is_set (Authors) then Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. if author_etal then Authors local Quote = Authors .. ' ' .. cfg.messagesA['et alQuote']; -- add et al. to authors parameter end else Authors = last_first_list; -- either an author name list or an empty string end end -- end of do if is_set (Authors) and is_set (Collaboration) then Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. end
endlocal LayFormat = A['LayFormat']; local LayURL = A['LayURL']; local LaySource = A['LaySource']; local Transcript = A['Transcript']; local TranscriptFormat = A['TranscriptFormat']; local TranscriptURL = A['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
-- apply |local LastAuthorAmp = A[xx-'LastAuthorAmp']format= styling; at the end, these parameters hold correctly styled format annotation, -- an error message if the associated url is not set, or an empty string for concatenation ArchiveFormat = style_format is_valid_parameter_value (ArchiveFormat, ArchiveURLLastAuthorAmp, 'archivelast-formatauthor-amp', cfg.keywords ['archive-urlyes_true_y']);then ConferenceFormat LastAuthorAmp = style_format (ConferenceFormat, ConferenceURL, 'conferencenil; -format', 'conference-url');set to empty string end Format local no_tracking_cats = style_format (Format, URL, A['formatNoTracking', 'url')]; LayFormat = style_format if not is_valid_parameter_value (LayFormat, LayURLno_tracking_cats, 'layno-formattracking', cfg.keywords ['lay-urlyes_true_y']);then TranscriptFormat no_tracking_cats = style_format (TranscriptFormat, TranscriptURL, 'transcriptnil; --format', 'transcripturl');set to empty string end
-- special case for chapter format so no error message or cat when chapter not supportedthese are used by cite interview if not (in_array(config.CitationClass, {local Callsign = A['webCallsign', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or]; ( local City = A['citationCity' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then]; ChapterFormat local Program = style_format (ChapterFormat, ChapterURL, 'chapter-format', A['chapter-urlProgram')]; end
--local variables that are not cs1 parameters if not is_setlocal use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.getCurrentTitle(URL) then; -- also used for COinS and for language local anchor_year; -- used in the CITEREF identifier local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification -- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values local Mode = A['Mode']; if in_arraynot is_valid_parameter_value (config.CitationClassMode, {"web"'mode',"podcast", "mailinglist"}cfg.keywords['mode']) then Mode = ''; end local sepc; -- |url= required separator between citation elements for cite webCS1 a period, cite podcastfor CS2, and cite mailinglista comma local PostScript; local Ref; table.insert sepc, PostScript, Ref = set_style (Mode:lower( z.message_tail), A['PostScript'], { set_error( A['cite_web_urlRef'], {}config.CitationClass); use_lowercase = ( sepc == ', true ' ); -- used to control capitalization for certain static text --check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories if not is_set (no_tracking_cats) } then -- ignore if we are already not going to categorize this page if in_array (this_page.nsText, cfg.uncategorized_namespaces)then no_tracking_cats = "true"; -- set no_tracking_cats
end
for _,v in ipairs (cfg.uncategorized_subpages) do -- do we have |accessdate= without either |url= or |chapter-url=?cycle through page name patterns if is_setthis_page.text:match (AccessDate) and not is_set(ChapterURLv)then -- test page name against each pattern no_tracking_cats = "true"; -- ChapterURL may be set when URL is not set;no_tracking_cats table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ) break; -- bail out if one is found AccessDate = '';end
end
end
local OriginalURL-- check for extra |page=, OriginalURLorigin, OriginalFormat, OriginalAccess; DeadURL |pages= or |at= DeadURL:lowerparameters. (also sheet and sheets while we're at it); -- used later when assembling archived text if is_setselect_one( ArchiveURL ) then if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it OriginalURL = ChapterURL; -- save copy of source chapterargs, {'page', 'p', 'pp', 'pages', 'at', 's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages OriginalFormat = ChapterFormat; -- and original |format= if sheet'no, ' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archivesheets's url ChapterURLorigin = A:ORIGIN(}, 'ArchiveURLredundant_parameters') ; -- name of archive-url parameter for this is a dummy call simply to get the error messagesmessage and category ChapterFormat local NoPP = ArchiveFormat or A['NoPP'; -- swap in archive's format] end elseif if is_set (URLNoPP) then OriginalURL = URL; -- save copy of original source URL OriginalURLorigin = URLorigin; -- name of url parameter for error messages OriginalFormat = Format; -- and original |format= OriginalAccess = UrlAccess; if is_valid_parameter_value (NoPP, 'nonopp' ~= DeadURL then -- if URL set then archive-url applies to it URL = ArchiveURL -- swap-in the archive's url URLorigin = A:ORIGIN(, cfg.keywords ['ArchiveURLyes_true_y']) -- name of archive url parameter for error messagesthen Format NoPP = ArchiveFormat or ''true; -- swap in archive's format UrlAccess else NoPP = nil; -- restricted access levels do not make sense for archived urls end endunset, used as a flag later
end
if in_arrayis_set(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}Page) or -- if any of the 'periodical' cites except encyclopediathen ('citation' == config.CitationClass and if is_set (PeriodicalPages) and not or is_set (Encyclopedia)At) then local chap_paramPages = ''; if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parametersunset the others chap_param At = A:ORIGIN ('Chapter'); end elseif is_set extra_text_in_page_check (TransChapterPage) then chap_param ; -- add this page to maint cat if |page= A:ORIGIN ('TransChapter')value begins with what looks like p. or pp. elseif is_set (ChapterURLPages) then chap_param = A:ORIGIN ('ChapterURL') elseif if is_set (ScriptChapterAt) then chap_param At = A:ORIGIN ('ScriptChapter'); -- unset end else is_set extra_text_in_page_check (ChapterFormatPages) chap_param ; -- add this page to maint cat if |pages= A:ORIGIN ('ChapterFormat')value begins with what looks like p. or pp. end
if is_set -- both |publication-place= and |place= (chap_param|location=) then -- allowed if we found onedifferent table.insert if not is_set( z.message_tail, { set_errorPublicationPlace) and is_set( 'chapter_ignored', {chap_param}, true Place) } ); -- add error messagethen Chapter PublicationPlace = ''Place; -- and set them promote |place= (|location=) to empty string to be safe with concatenation|publication-place end TransChapter = ''; ChapterURL if PublicationPlace = ''; ScriptChapter = ''; ChapterFormat Place then Place = ''; end else -- otherwise, format chapter / article titledon't need both if they are the same local no_quotes = false; -- default assume that we will be quoting [[Parameter remapping for cite encyclopedia:When the chapter parameter valuecitation has these parameters: if is_set (Contribution) |encyclopedia and 0 < #c |title then -- if this is a contribution with contributor(s)map |title to |article and |encyclopedia to |title if in_array (Contribution:lower(), cfg.keywords.contribution) |encyclopedia and |article then -- and a generic contribution map |encyclopedia to |title no_quotes = true; -- |encyclopedia then render it unquoted end endmap |encyclopedia to |title
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution |trans_title maps to |trans_chapter when |title is also in Chapter if is_set (Chapter) then Chapter = Chapter .. ChapterFormat ; if 'map' == config.CitationClass and is_set (TitleType) then Chapter = Chapter .. ' ' .. TitleType; re-- map annotation here; not after titlemapped end Chapter = Chapter.. sepc .. ' '; elseif is_set (ChapterFormat) then -- |url maps to |chapter= not set but chapterurl when |chapter-format= title is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it end endremapped
-- Format main title. if '...' == Title:sub (-3) then -- if elipsis is the last three characters All other combinations of |title= Title = mw.ustring.gsub (Titleencyclopedia, '(%.%.%.)%.+$', '%1'); -- limit the number of dots to three elseif not mw.ustring.find (Title, '%.%s*%a%.') then -- end of |title is not a 'dot-(optional space-)letter-dot' initialism Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character end if is_set(TitleLink) and is_set(Title) then Title = make_wikilink (TitleLink, Title); end|article are not modified
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); elseif 'report' == config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle = wrap_style ('trans-italic-title', TransTitle); end]]
local TransError = ""; if is_set(TransTitle) then if is_set(Title) then TransTitle = " " .. TransTitle; else TransError = " " .. set_error( 'trans_missing_title', {'title'} ); end end if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format; URL Encyclopedia = A['Encyclopedia']; -- unset these because no longer needed Format = ""; else Title = Title .. TransTitle .. TransError; end else Title = TransTitle .. TransError; end
if is_set(Place) then Place config.CitationClass == " encyclopaedia" .. wrap_msg ) or ('written', Place, use_lowercase) .. sepc .config. CitationClass == " citation";and is_set (Encyclopedia)) then -- test code for citation end if is_set(Periodical) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then if not is_set (ConferenceChapter) then Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; TransChapter = TransTitle; ChapterURL = URL; if not is_set (ConferenceURLChapterURL) and is_set (TitleLink) then Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]'; end Title = Periodical; ChapterFormat = Format; Periodical = ''; -- redundant so unset TransTitle = ''; URL = ''; Format = ''; TitleLink = ''; ScriptTitle = ''; end Conference else -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil )''; -- redundant so unset end
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
end
-- Special case for cite techreport. if (config.CitationClass == "techreport") then -- special case for cite techreport if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' if not is_set(PositionID) then -- can we use ID for the "number"? local Minutes ID = A['MinutesNumber']; -- yes, use it else -- ID has a value so emit error message table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )}); end end end -- special case for cite interview if (config.CitationClass == "interview") then if is_set(Program) then ID = ' ' .. Program; end if is_set(Callsign) then if is_set(ID) then ID = ID .. sepc .. ' ' .. Callsign; else ID = ' ' .. Callsign; end end local Time if is_set(City) then if is_set(ID) then ID = ID .. sepc .. ' ' .. City; else ID = A['Time'].. City; end end
if is_set(MinutesOthers) then if is_set (TimeTitleType) then tableOthers = ' ' .. TitleType .insert( z.message_tail, { set_error( 'redundant_parameterswith ', {wrap_style (.. Others; TitleType = 'parameter', ; else Others = 'minutes') .. ' and Interview with ' .. wrap_style ('parameter', 'time')}, true ) } )Others;
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if is_set(Time) then local TimeCaption Others = A['TimeCaption'] if not is_set(TimeCaptionInterview) then TimeCaption = cfg.messages['event']; if sepc ~= '.' then TimeCaption = TimeCaption:lower(); end end Position = " " .. TimeCaption .. " " .. Time; end
end
else
Position = " " .. Position;
At = '';
end
-- special case for cite mailing list Page, Pages, Sheet, Sheets = format_pages_sheets if (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); At = is_set(At) and (sepc .. " " .. At) or ""; Position = is_set(Position) and (sepc .. " mailinglist" .. Position) or ""; if config.CitationClass == 'map' then local Section Periodical = A['SectionMailingList']; local Sections = A[ elseif 'Sectionsmailinglist']; local Inset == A['Inset']; if is_set( Inset ) then Inset = sepc .. " " .. wrap_msg :ORIGIN('insetPeriodical', Inset, use_lowercase); end if is_set( Sections ) then Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); elseif is_set( Section ) then Section Periodical = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end if is_set (Language) then Language = language_parameter (Language); - - format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this unset because mailing list is an empty string; --[[ TODO: need to extract the wrap_msg from language_parameter so that we can solve parentheses bunching problem with Format/Language/TitleType ]]only used for cite mailing list
end
-- Account for the oddity that is {{cite conference}}, before generation of COinS data. Others if 'conference' == is_set(Others) and (sepc config.. " " .. Others) or "";CitationClass then if is_set (TranslatorsBookTitle) then Chapter = Title;-- Others ChapterLink = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. OthersTitleLink; -- |chapterlink= is deprecated end ChapterURL = URL; if is_set (Interviewers) then ChapterURLorigin = URLorigin; Others URLorigin = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others; end ChapterFormat = Format; TransChapter = TransTitle; TitleNote Title = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""BookTitle; if is_set (Edition) then Format = '';-- if Edition:match (TitleLink = '%f[%a][Ee]d%.?$') or Edition:match (; TransTitle = '%f[%a][Ee]dition$') then; add_maint_cat (URL = 'extra_text', 'edition');
end
Edition elseif 'speech' ~= " " .config. wrap_msg ('edition', Edition); elseCitationClass then Edition Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities Series local Cartography = ""; local Scale = is_set(Series) and (sepc .. " " ; local Sheet = A['Sheet'] or ''; local Sheets = A['Sheets'] or ''; if config.. Series) or CitationClass == "map"then Chapter = A['Map']; ChapterURL = A['MapURL']; TransChapter = A['TransMap']; OrigYear ChapterURLorigin = is_setA:ORIGIN(OrigYear'MapURL') and (" ; ChapterFormat = A[" .. OrigYear .. "'MapFormat']") or ""; -- TODO: presentation Agency Cartography = A['Cartography']; if is_set(AgencyCartography ) and (then Cartography = sepc .. " " .. Agency) or ""; Volume = format_volume_issue wrap_msg (Volume, Issue, config.CitationClass'cartography', Periodical_origin, sepcCartography, use_lowercase); end ------------------------------------ totally unrelated data Scale = A['Scale']; if is_set(ViaScale ) then Via Scale = sepc .. " " .. wrap_msg ('via', Via)Scale; end
end
--[[ Subscription implies paywall; Registration does not. If both Account for the oddities that are used in a citation{{cite episode}} and {{cite serial}}, the subscription required linkbefore generation of COinS data. note is displayedif 'episode' == config. There are no error messages for this conditionCitationClass or 'serial' == config.CitationClass then local AirDate = A['AirDate']; ] local SeriesLink = A['SeriesLink']; if is_set (SubscriptionRequiredSeriesLink) and false == link_param_ok (SeriesLink) then SubscriptionRequired = sepc table.insert( z. " " .. cfg.messages[message_tail, { set_error( 'bad_paramlink', A:ORIGIN('subscriptionSeriesLink']))}); -- subscription required message elseif is_set (RegistrationRequired) then end SubscriptionRequired local Network = sepc .. " " .. cfg.messagesA['registrationNetwork']; -- registration required message else SubscriptionRequired local Station = A['Station']; local s, n = {}, {}; -- either or both might be set to something other than yes true ydo common parameters first if is_set(Network) then table.insert(n, Network); end if is_set(AccessDateStation) thentable.insert(n, Station); end local retrv_text ID = " " table.concat(n, sepc . cfg.messages['retrieved']); if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = AirDate; end
AccessDate if 'episode' = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format if (sepc ~= "config.") CitationClass then retrv_text = retrv_text:lower() end -- if mode is cs2, lower casehandle the oddities that are strictly {{cite episode}} local Season = A['Season']; AccessDate local SeriesNumber = substitute (retrv_text, AccessDate)A['SeriesNumber']; -- add retrieved text
AccessDate = substitute if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set table.insert(cfgz.presentation[message_tail, { set_error( 'accessdateredundant_parameters'], {sepcwrap_style ('parameter', AccessDate'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) }); -- allow editors to hide accessdatesadd error message SeriesNumber = ''; -- unset; prefer |season= over |seriesno= end -- assemble a table of parts concatenated later into Series if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ''; -- unset because this is not a unique parameter
if is_set Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterURLorigin = A:ORIGIN(ID'URL') then ID ; Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .." ".. ID' '); end -- this is concatenation of season, seriesno, episode number if "thesis" == config.CitationClass is_set (ChapterLink) and not is_set(DocketChapterURL) then -- link but not URL ID Chapter = sepc '[[' .. ChapterLink .." Docket "'|' .. Docket Chapter .. ID']]'; end-- ok to wikilink if "report" == config.CitationClass elseif is_set (ChapterLink) and is_set(DocketChapterURL) then -- for cite report when |docket= is if both are set, URL links episode; ID Series = sepc '[[' .. ChapterLink .. ' |' .. DocketSeries .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; else -- now oddities that are cite serial Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial Chapter = A['Episode']; -- overwrite ID even TODO: make |episode= available to cite episode someday? if is_set (Series) and is_set (SeriesLink) then Series = '[[' .. SeriesLink .. '|id' .. Series .. ']]'; end Series = wrap_style ('italic-title', Series); -- series is setitalicized end
end
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. if 'arxiv' == config.CitationClass then if not is_set (ID_list ['ARXIV']) then -- |arxiv= or |eprint= build_id_listrequired for cite arxiv table.insert( ID_listz.message_tail, { set_error( 'arxiv_missing', {IdAccessLevels}, true ) } ); -- add error message elseif is_set (Series) then -- series is an alias of version ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier Series =ID_access_levels''; -- unset deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv end if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'], ID_list['JFM'], ID_list['JSTOR'], DoiBroken = DoiBrokenID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'], ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']}, ASINTLD = ASINTLD27) then table.insert( z.message_tail, IgnoreISBN = IgnoreISBN{ set_error( 'arxiv_params_not_supported', Embargo=Embargo{}, Class = Classtrue ) } ); -- add error message
if is_set(URL) then AccessDate= ''; -- set these to empty string; not supported in cite arXiv URL PublisherName = " " .. external_link''; -- ( URLif the article has been published, niluse cite journal, URLorigin, UrlAccess or other) Chapter = ''; URL = ''; Format = ''; Page = ''; Pages = ''; At = ''; end Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
-- handle type parameter for those CS1 citations that have default values if is_setin_array(Quoteconfig.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then if Quote:subTitleType = set_titletype (1config.CitationClass,1TitleType) == '"' and Quote:sub; if is_set(-1,-1Degree) and "Thesis" == '"' TitleType then -- if first and last characters of quote are quote marksspecial case for cite thesis Quote TitleType = Quote:sub(2,-2)Degree .. "论文"; -- strip them off
end
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
if is_set(TitleType) then -- if type parameter is specified local ArchivedTitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses end -- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set. if not is_set(ArchiveURLDate) then Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not is_set(ArchiveDateDate) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set ArchiveDate Date = PublicationDate; -- promote PublicationDate to Date PublicationDate = set_error('archive_missing_date'); -- unset, no longer needed
end
end if "no" PublicationDate == DeadURL Date thenPublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation --[[Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is wherewe get the date used in the metadata. Date validation supporting code is in Module:Citation/CS1/Date_validation]] do -- create defined block to contain local variables error_message and mismatch local arch_text error_message = cfg.messages''; -- AirDate has been promoted to Date so not necessary to check it anchor_year, error_message = dates({['archivedaccess-date']; if sepc ~= "." then arch_text AccessDate, ['archive-date']= arch_text:lower() end Archived ArchiveDate, ['date']= sepc .. " " .. substitute( cfg.messagesDate, ['archiveddoi-notbroken-deaddate']=DoiBroken, { external_link( ArchiveURL ['embargo']=Embargo, ['lay-date']=LayDate, arch_text['publication-date']=PublicationDate, A:ORIGIN(['ArchiveURLyear']=Year}, COinS_date); if is_set (Year), nil and is_set (Date) .. ArchiveFormatthen -- both |date= and |year= not normally needed; local mismatch = year_date_check (Year, ArchiveDate } Date); if 0 == mismatch then -- |year= does not match a year-value in |date= if is_set(OriginalURLerror_message) then -- if there is already an error message Archived error_message = Archived error_message .. " " ', '; -- tack on this additional message end error_message = error_message .. set_error'|year= / |date= mismatch'; elseif 1 == mismatch then -- |year= matches year-value in |date= add_maint_cat ('archive_missing_urldate_year');
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
if 'bot: unknown' == DeadURL then
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
else
add_maint_cat ('unfit'); -- and add a category if not already added
end
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else
local arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( arch_text,
{ set_error('archive_missing_url'), ArchiveDate } );
end
elseif is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = "" end local Lay = ''; if is_set(LayURLerror_message) then if is_set table.insert(LayDate) then LayDate = " (" .. LayDate .z. ")" end if is_setmessage_tail, { set_error(LaySource) then LaySource = " – 'bad_date'" .. safe_for_italics(LaySource, {error_message}, true ) } ) .. "''"; else LaySource = "";-- add this error message
end
if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message endof do
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date Embargo = is_embargoed (Embargo); -- if config.CitationClass == "journal" and not is_set(TranscriptURL) and is_set(ID_list['PMC']) then if not is_set(TranscriptURLEmbargo) then -- if not embargoed or embargo has expired URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed Transcript URLorigin = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil )cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. local Publisher;-- Test if citation has no title if not is_set(PublicationDateTitle) thenand PublicationDate = wrap_msg ('published', PublicationDate); end if not is_set(PublisherNameTransTitle) thenand if not is_set(PublicationPlaceScriptTitle) then Publisher if 'episode' == sepc config.. " " .. PublicationPlace .. "CitationClass then -- special case for cite episode; TODO: " is there a better way to do this? table.insert( z. PublisherName .. PublicationDatemessage_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); else Publisher = sepc table.insert( z. " " .. PublisherName .. PublicationDate; end elseif is_setmessage_tail, { set_error(PublicationPlace'citation_missing_title', {'title'}, true ) } ) then Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; else Publisher = PublicationDate; end
end
-- Several of the above rely upon detecting this as nil, so do it last. if is_set'none' == Title and in_array (Periodicalconfig.CitationClass, {'journal', 'citation'}) then if and is_set(TitlePeriodical) or is_setand 'journal' == A:ORIGIN(TitleNote'Periodical') then -- special case for journal cites Periodical Title = sepc .. " " .. wrap_style ('italic'; -- set title', Periodical) to empty string else Periodical = wrap_style add_maint_cat ('italic-titleuntitled', Periodical) end;
end
check_for_url ({ --add error message when any of these parameters contains a URL ['title']=Title, [A:ORIGIN('Chapter')]=Chapter, [A:ORIGIN('Periodical')]=Periodical, [A:ORIGIN('PublisherName')] = PublisherName, }); Handle -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. -- handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through encyclopedia and {{citation |departmentencyclopedia=) something}}. Here we presume that -- when Periodical, Title, and forces it to be " Chapter are all set, then Periodical is the book (Speechencyclopedia)" so thattitle, Title -- is the annotation directly follows the |article title= parameter value in , and Chapter is a section within the citation rather than the |event= parameter value (if provided)article. So, we remap ]] if "speech" local coins_chapter == config.CitationClass then Chapter; -- cite speech onlydefault assuming that remapping not required TitleNote local coins_title = " (Speech)"Title; -- annotate the citationet tu if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (PeriodicalEncyclopedia)) then -- if Periodical, perhaps because of an included |website= or |journal= parameter if is_set (ConferenceChapter) and is_set (Title) and is_set (Periodical) then -- and if |event= is setall are used then Conference coins_chapter = Conference .. sepc .. " "Title; -- then add appropriate punctuation to the end of the Conference variable before renderingremap endcoins_title = Periodical;
end
end
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
end
-- Piece all bits together at last. Here, all should be non-nil. -- We build things this way because it is more efficient in LUAthe function call to COinS() local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- not to keep reassigning to the same string variable over Chapter and over.ScriptChapter stripped of bold / italic wikimarkup ['Map'] = Map, local tcommon; local tcommon2 ['Degree'] = Degree; -- used for book cite when |contributorthesis only ['Title'] = is set if in_arraymake_coins_title (config.CitationClasscoins_title, {"journal"ScriptTitle),"citation"}) -- Title and is_set(Periodical) thenScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if is_set(Others) then Others Date is valid; ['Season'] = Others COinS_date.rftssn, ['Chron'] = COinS_date. sepc rftchron or (not COinS_date.. " " endrftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit? tcommon ['Series'] = safe_join( {OthersSeries, Title ['Volume'] = Volume, TitleNote ['Issue'] = Issue, Conference ['Pages'] = get_coins_pages (first_set ({Sheet, PeriodicalSheets, FormatPage, TitleTypePages, SeriesAt}, Language5)), -- pages stripped of external links ['Edition'] = Edition, Publisher ['PublisherName'] = PublisherName, Agency ['URL'] = first_set ({ChapterURL, VolumeURL}, sepc 2);, ['Authors'] = coins_author, ['ID_list'] = ID_list, ['RawPage'] = this_page.prefixedText, elseif in_array(}, config.CitationClass, {"book","citation"}) and not is_set(Periodical) then ; -- special cases Account for book citesthe oddities that are {{cite arxiv}}, AFTER generation of COinS data. if is_set (Contributors) 'arxiv' == config.CitationClass then -- when we are citing forewordhave set rft.jtitle in COinS to arXiv, preface, introduction, etcnow unset so it isn't displayed tcommon Periodical = safe_join( {Title''; -- periodical not allowed in cite arxiv; if article has been published, TitleNote}, sepc ); use cite journal end -- author and other stuff will come special case for cite newsgroup. Do this after this and before tcommon2COinS because we are modifying Publishername to include some static text tcommon2 if 'newsgroup' == safe_joinconfig.CitationClass then if is_set ( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc PublisherName); elsethen tcommon PublisherName = safe_joinsubstitute ( {Titlecfg.messages['newsgroup'], TitleNoteexternal_link( 'news:' .. PublisherName, ConferencePublisherName, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc A:ORIGIN('PublisherName') ));
end
end
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
end
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
else -- all other CS1 templates tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );Now perform various field substitutions. end-- We also add leading spaces and surrounding markup and punctuation to the -- various parts of the citation, but only when they are non-nil. if #ID_list > 0 then ID_list = safe_join( local EditorCount; -- used only for choosing { sepc ed.. " ", table.concat) or ( ID_list, sepc eds.. " " ), ID }, sepc );annotation at end of editor name-list elsedo ID_list = IDlocal last_first_list; end local maximum; local idcommon control = safe_join( { ID_list format = NameListFormat, URL -- empty string or 'vanc' maximum = nil, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote } -- as if display-authors or display-editors not set lastauthoramp = LastAuthorAmp, sepc ); local page_name = this_page.text; -- get current page name so that we don't wikilink to it via editorlinkn local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At };
if is_set(Date) then if is_set (Authors) or is_set (Editors) then do -- date follows authors or editors when authors not setdo editor name list first because coauthors can modify control table Date maximum , editor_etal = " get_display_authors_editors (" .. Date .."A['DisplayEditors'], #e, 'editors', editor_etal)" .. OrigYear .. sepc .. " "; -- [[ Preserve old-style implicit et al. 临时修复"Category:含有旧式缩略标签的引用的页面 in paranetheses else editors"的问题，中文版目前与英文版逻辑不一样，暂时不需要这个分类。等以后更新时再看怎么处理 -- neither of authors and editors set2017.6.23 shizhao if not is_set(string.sub(tcommon,-1,-1maximum) and #e == sepc) 4 then -- if the last character of tcommon is sepc Date maximum = " " .. Date .. OrigYear3; -- Date does not begin with sepc else Date = sepc table.insert( z. " " .. Date .. OrigYearmessage_tail, { set_error('implict_etal_editor', {}, true) } ); -- Date begins with sepc
end
end ]] end if is_set(Authors) then control.maximum = maximum; if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination Authors last_first_list, EditorCount = terminate_name_list list_people(Authorscontrol, sepce, editor_etal, 'editor'); -- when no date, terminate with 0 or 1 sepc and a space end if is_set(Editors) then local in_text = " "; local post_text = ""; if is_set(Chapter) and 0 == #c editor_etal then in_text Editors = in_text Editors .. ' ' .. cfg.messages['inet al'] ; -- add et al.. " " if (sepc ~to editors parameter beause |display-editors= '.') thenetal in_text EditorCount = in_text:lower() 2; -- lowercase for cs2 end else if EditorCount <with et al., |editors= 1 then post_text = ", " is multiple names; spoof to display (eds.. cfg.messages['editor'];) annotation
else
post_text EditorCount = ", " .. cfg.messages[2; -- we don't know but assume |editors']= is multiple names;spoof to display (eds.) annotation
end
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if is_set (Editors) and is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if (not is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif is_set(Editors) then
if is_set(Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
else
Editors = Editors .. ", " .. cfg.messages['editors']last_first_list; -- either an author name list or an empty string
end
else if 1 == EditorCount <and (true == editor_etal or 1 < #e) then Editors = Editors .. " (" .. cfg.messages[' -- only one editor'] .. ")" .. sepc .. " " elsedisplayed but includes etal then Editors EditorCount = Editors .. " 2; -- spoof to display (" eds.. cfg.messages['editors'] .. ")" .. sepc .. " "annotation
end
end
text do -- now do translators control.maximum = #t; -- number of translators Translators = safe_joinlist_people( {Editorscontrol, Datet, Chapterfalse, Place, tcommon'translator'); -- et al not currently supported end do -- now do contributors control.maximum = #c; -- number of contributors Contributors = list_people(control, pgtextc, idcommon}false, sepc 'contributor'); -- et al not currently supported else end if in_arraydo -- now do authors control.maximum , author_etal = get_display_authors_editors (config.CitationClassA['DisplayAuthors'], #a, {"journal"'authors',"citation"}author_etal) and ; if is_set(PeriodicalCoauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting. control.lastauthoramp = nil; control.maximum = #a + 1; end text last_first_list = safe_joinlist_people( {Chaptercontrol, Placea, tcommonauthor_etal, pgtext'author'); if is_set (Authors) then Authors, Dateauthor_etal = name_has_etal (Authors, idcommon}author_etal, sepc false);-- find and remove variations on et al. if author_etal then Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter end else Authors = last_first_list; -- either an author name list or an empty string text end end -- end of do if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors= safe_join( {Chapter, Placeauthorn=, tcommonor lastn= isn't specified table.insert( z.message_tail, Date{ set_error('coauthors_missing_author', pgtext{}, idcommontrue) }, sepc );-- emit error message
end
end
if is_set(PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1,-sepc:len()-1);
end
text = safe_join( {text, PostScript}, sepc );
-- Now enclose apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,-- an error message if the whole thing in a <cite/> elementassociated url is not set, or an empty string for concatenation local options ArchiveFormat = {}style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); if is_setFormat = style_format (config.CitationClassFormat, URL, 'format', 'url') and config.CitationClass ~= "citation" then; options.class LayFormat = config.CitationClassstyle_format (LayFormat, LayURL, 'lay-format', 'lay-url'); options.class TranscriptFormat = "citation " .. config.CitationClassstyle_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); -- class=citation required special case for blue highlight chapter format so no error message or cat when used with |ref=chapter not supported elseif not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or options('citation' == config.class CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then ChapterFormat = "citation"style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
if ('harv' == Ref ) then
local namelist = {}; -- holds selected contributor, author, editor name list
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
if #c > 0 not is_set(URL) then -- and if there is a contributor list namelist = c; -- select it elseif #a > 0 in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or an author list namelist cite podcast |url= a;is missing or empty elseif #e > 0 then -- or an editor list namelist = etable.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); end -- Test if accessdate is given without giving a URL if #namelist > 0 is_set(AccessDate) and not is_set(ChapterURL)then -- if there ChapterURL may be set when the others are names in namelistnot set; TODO: move this to a separate test? id = anchor_id table.insert( z.message_tail, { set_error(namelist'accessdate_missing_url', year{}, true ) } ); -- go make the CITEREF anchor else id AccessDate = ''; -- unset end
end
options.id = id;
end
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set? if string.lenDeadURL = DeadURL:lower(); -- used later when assembling archived text:gsub if is_set("<span[^>/]*>ArchiveURL ) then if is_set (.URL) then OriginalURL = URL; -- save copy of original source URL OriginalURLorigin = URLorigin; -- name of url parameter for error messages OriginalFormat = Format; -- and original |format= if 'no' ~= DeadURL then -)</span>", "%1")- if URL set then archive-url applies to it URL = ArchiveURL -- swap-in the archive's url URLorigin = A:gsubORIGIN("%b<>",""'ArchiveURL') -- name of archive url parameter for error messages Format = ArchiveFormat or ''; -- swap in archive's format end elseif is_set (ChapterURL) <= 2 then -- remove <span> tags and other htmlURL not set so if chapter-like markupurl is set apply archive url to it OriginalURL = ChapterURL; then get length -- save copy of source chapter's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of what remainschapter-url parameter for error messages z.error_categories OriginalFormat = {}ChapterFormat; -- and original |format= if 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url text ChapterURLorigin = set_errorA:ORIGIN('empty_citationArchiveURL') -- name of archive-url parameter for error messages ChapterFormat = ArchiveFormat or ''; -- swap in archive's format end z.message_tail = {};end
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if is_setin_array(optionsconfig.idCitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) then or -- here we wrap if any of the rendered citation in <cite ...>...</cite> tags'periodical' cites except encyclopedia table.insert (render, substitute (cfg.presentation['cite-idcitation'], {mw== config.uri.anchorEncodeCitationClass and is_set (options.idPeriodical), mw.text.nowikiand not is_set (options.classEncyclopedia), text})then local chap_param; if is_set (Chapter); then --get a parameter name from one of these chapter related meta- when |refparameters chap_param = is setA:ORIGIN ('Chapter') elseif is_set (TransChapter) then else chap_param = A:ORIGIN ('TransChapter') table.insert elseif is_set (render, substitute ChapterURL) then chap_param = A:ORIGIN (cfg.presentation['citeChapterURL'], {mw.text.nowiki) elseif is_set (ScriptChapter) then chap_param = A:ORIGIN (options.class'ScriptChapter'), text} else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat'); -- all other cases end if is_set (chap_param) then -- if we found one table.insert (renderz.message_tail, substitute { set_error(cfg.presentation['ocinschapter_ignored'], {OCinSoutputchap_param}, true )} ); -- append metadata add error message Chapter = ''; -- and set them to the citationempty string to be safe with concatenation TransChapter = ''; ChapterURL = ''; ScriptChapter = ''; ChapterFormat = ''; end else -- otherwise, format chapter / article title local no_quotes = false; -- default assume that we will be quoting the chapter parameter value if is_set (Contribution) and 0 < #zc then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(), cfg.keywords.message_tail ~contribution) then -- and a generic contribution title no_quotes = 0 true; -- thenrender it unquoted end end table.insert Chapter = format_chapter_title (renderScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, ' 'no_quotes); -- Contribution is also in Chapter for i,v in ipairs( z.message_tail ) do if is_set(v[1]Chapter) then if i 'map' == #zconfig.message_tail then table.insert (render, error_commentCitationClass and is_set ( v[1], v[2] TitleType));then else tableChapter = Chapter ..insert (render, error_comment( v[1] ' ' .. "; ", v[2] ))TitleType; end
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' '; elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it end end -- Format main title. if is_set(TitleLink) and is_set(Title) then Title = "[[" .. TitleLink .. "|" .. Title .. "]]" end if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); elseif 'report' == config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle = wrap_style ('trans-italic-title', TransTitle); end TransError = ""; if is_set(TransTitle) then if is_set(Title) then TransTitle = " " .. TransTitle; else TransError = " " .. set_error( 'trans_missing_title', {'title'} ); end end Title = Title .. TransTitle; if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title, URLorigin ) .. TransError .. Format; URL = ""; Format = ""; else Title = Title .. TransError; end end if #is_set(Place) then Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; end if is_set (Conference) then if is_set (ConferenceURL) then Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin ); end Conference = sepc .. " " .. Conference .. ConferenceFormat; elseif is_set(ConferenceURL) then Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin ); end if not is_set(Position) then local Minutes = A['Minutes']; local Time = A['Time']; if is_set(Minutes) then if is_set (Time) then table.insert( z.maintenance_cats message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } ); end Position = " " .. Minutes .. " " .. cfg.messages['minutes']; else if is_set(Time) then local TimeCaption = A['TimeCaption'] if not is_set(TimeCaption) then TimeCaption = cfg.messages['event']; if sepc ~= 0 '.' then TimeCaption = TimeCaption:lower(); end end Position = " " .. TimeCaption .. " " .. Time; end end else Position = " " .. Position; At = ''; end Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); At = is_set(At) and (sepc .. " " .. At) or ""; Position = is_set(Position) and (sepc .. " " .. Position) or ""; if config.CitationClass == 'map' then local Section = A['Section']; local Sections = A['Sections']; local Inset = A['Inset']; if is_set( Inset ) then Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end if is_set( Sections ) then Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); elseif is_set( Section ) then Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end if is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this is an empty string; end Others = is_set(Others) and (sepc .. " " .. Others) or ""; if is_set (Translators) then Others = sepc .. ' 由' .. Translators .. '翻译 ' .. Others; end TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; if is_set (Edition) then if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then add_maint_cat ('extra_text', 'edition'); end Edition = " " .. wrap_msg ('edition', Edition); else Edition = ''; end Series = is_set(Series) and (sepc .. " " .. Series) or ""; OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); ------------------------------------ totally unrelated data if is_set(Via) then tableVia = " " ..insert wrap_msg (render'via', Via); end --[[Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required linknote is displayed. There are no error messages for this condition. ]] if is_set (SubscriptionRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message elseif is_set (RegistrationRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message else SubscriptionRequired = ''; -- either or both might be set to something other than yes true y end if is_set(AccessDate) then local retrv_text = " " .. cfg.messages['<retrieved'] AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span classif date in appropriate format if (sepc ~=".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text -- neither of these work; don't know why; it seems that substitute() isn't being called AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates end if is_set(ID) then ID = sepc .." ".. ID; end if "thesis" == config.CitationClass and is_set(Docket) then ID = sepc .." Docket ".. Docket .. ID; end if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set end ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); if is_set(URL) then URL = " " .. external_link( URL, nil, URLorigin ); end if is_set(Quote) then if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks Quote = Quote:sub(2,-2); -- strip them off end Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags PostScript = ""; --commentcs1|2 does not supply terminal punctuation when |quote= is set end local Archived if is_set(ArchiveURL) then if not is_set(ArchiveDate) then ArchiveDate = set_error('archive_missing_date'); end if "no" == DeadURL then local arch_text = cfg.messages['archived']; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } ); if not is_set(OriginalURL) then Archived = Archived .. " " .. set_error('archive_missing_url'); end elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' local arch_text = cfg.messages['archived-dead']; if sepc ~= "." then arch_text = arch_text:lower() end if in_array (DeadURL, {'unfit', 'usurped'}) then Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " style.. substitute( arch_text, { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled end else local arch_text = cfg.messages['archived-missing']; if sepc ~="display." then arch_text = arch_text:nonelower() end Archived = sepc .. " " .. substitute( arch_text, { set_error('archive_missing_url'), ArchiveDate } ); end elseif is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = "" end local Lay = ''; if is_set(LayURL) then if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; color end if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:#33aa33ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; margin -left- if set and LayURL not set, then LayFormat has error message end if is_set(Transcript) then if is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin ); end Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; elseif is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin ); end local Publisher; if is_set(Periodical) and not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = PublicationPlace .. ": " .. PublisherName; else Publisher = PublisherName; end elseif is_set(PublicationPlace) then Publisher= PublicationPlace; else Publisher = ""; end if is_set(Publisher) then Publisher = " (" .. Publisher .. ")"; end else if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ":0" .. PublisherName; else Publisher = sepc .. " " .. PublisherName; end elseif is_set(PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace; else Publisher = ''; end end -- Several of the above rely upon detecting this as nil, so do it last. if is_set(Periodical) then if is_set(Title) or is_set(TitleNote) then Periodical = sepc ..3em">" .. wrap_style ('italic-title', Periodical) else Periodical = wrap_style ('italic-title', Periodical) end end --[[Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=)and forces it to be " (Speech)" so thatthe annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).]] 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 end end end -- Piece all bits together at last. Here, all should be non-nil. -- We build things this way because it is more efficient in LUA -- not to keep reassigning to the same string variable over and over. local tcommon; local tcommon2; -- used for book cite when |contributor= is set if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then if is_set(Others) then Others = Others .. sepc .. " " end tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Edition, Publisher, Agency}, sepc ); elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2 tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); else tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); end elseif 'map' == config.CitationClass then -- special cases for _cite map if is_set (Chapter) then -- map in a book; TitleType is part of Chapter tcommon = safe_join( {Title, Format, Edition, Scale, Series, Cartography, Others, Publisher, Volume}, v sepc ); elseif is_set (Periodical) then -- map in ipairsa periodical tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Cartography, Others, Publisher, Volume}, sepc ); else -- a sheet or stand-alone map tcommon = safe_join( z{Title, TitleType, Format, Edition, Scale, Series, Cartography, Others, Publisher}, sepc ); end elseif 'episode' == config.maintenance_cats CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Edition, Publisher}, sepc ) do ; else -- append maintenance categoriesall other CS1 templates tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); end if #ID_list > 0 then ID_list = safe_join( { sepc .. " ", table.insert concat( ID_list, sepc .. " " ), ID }, sepc ); else ID_list = ID; end -- LOCAL local xDate = Date local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; if ( is_set(Periodical) and Date ~= '' and not in_array(config.CitationClass, {"encyclopaedia","web"}) ) or ( in_array(config.CitationClass, {"book","news"}) ) then if in_array(config.CitationClass, {"journal","citation"}) and ( Volume ~= '' or Issue ~= '' ) then xDate = xDate .. ',' .. Volume end xDate = xDate .. pgtext pgtext = '' end if PublicationDate and PublicationDate ~= '' then xDate = xDate .. ' (' .. PublicationDate .. ')' end if OrigYear ~= '' then xDate = xDate .. OrigYear end if AccessDate ~= '' then xDate = xDate .. ' ' .. AccessDate end if xDate ~= '' then xDate = sepc .. ' ' .. xDate end -- END LOCAL local idcommon = safe_join(render{ URL, xDate, ID_list, Archived, vVia, SubscriptionRequired, Lay, Language, Quote }, sepc ); local text; if is_set(Authors) then if is_set(Coauthors)then if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator Authors = Authors .. ', ' .. Coauthors; tableelse Authors = Authors .. '; ' ..insert Coauthors; end end Authors = terminate_name_list (renderAuthors, sepc); -- when no date, terminate with 0 or 1 sepc and a space if is_set(Editors) then local in_text = " "; local post_text = ""; if is_set(Chapter) and 0 == #c then in_text = in_text .. cfg.messages[' in'] .. " " if (sepc ~= '.')then in_text = in_text:lower() end -- lowercase for cs2 else if EditorCount <= 1 then post_text = ", " .. cfg.messages['editor']; else post_text = ", " .. cfg.messages['editors']; end end tableEditors = terminate_name_list (in_text .. Editors ..insert post_text, sepc); -- terminate with 0 or 1 sepc and a space end if is_set (renderContributors) then -- book cite and we're citing the intro, preface, make_wikilink etc local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; if (sepc ~= '.') then by_text = by_text:Category:lower() end -- lowercase for cs2 Authors = by_text .. Authors; -- author follows title so tweak it here if is_set (Editors) then -- when Editors make sure that Authors gets terminated Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space end Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space text = safe_join( {Contributors, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); else text = safe_join( {Authors, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); end elseif is_set(Editors) then if EditorCount <= 1 then Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " else Editors = Editors .. " (" .. cfg.messages['editors' ] ..")" .. sepc .. " " end text = safe_join( {Editors, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); else if config.CitationClass=="journal" and is_set(Periodical) then text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); else text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); end end if is_set(PostScript) and PostScript ~= sepc then text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc. v text = text:sub(1,-sepc:len()-1); end text = safe_join( {text, PostScript}, sepc ); -- Now enclose the whole thing in a <cite/> element local options = {}; if is_set(config.CitationClass) and config.CitationClass ~= "citation" then options.class = config.CitationClass; options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref= else options.class = "citation"; end if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate local id = Ref if ('linkharv'== Ref )then local namelist = {}; -- holds selected contributor, author, editor name list-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation tablelocal year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation if #c > 0 then -- if there is a contributor list namelist = c; -- select it elseif #a > 0 then -- or an author list namelist = a; elseif #e > 0 then -- or an editor list namelist = e; end id = anchor_id (namelist, year); -- go make the CITEREF anchor end options.id = id; end if string.len(text:gsub("<span[^>/]*>.insert -</span>", ""):gsub(render"%b<>", "")) <= 2 then z.error_categories = {}; text = set_error('empty_citation') ; z.message_tail = {}; end if is_set(options.id) then text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class).. '">' .. text .. "</cite>"; else text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; end local empty_span = '<span style="display:none;"> </span>'; -- Note: Using display: none on the COinS span breaks some clients. local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>'; text = text .. OCinS; if #z.message_tail ~= 0 then tabletext = text .. " "; for i,v in ipairs( z.message_tail ) do if is_set(v[1]) then if i == #z.message_tail then text = text .. error_comment( v[1], v[2] ); else text = text ..insert error_comment(renderv[1] .. "; ", v[2] ); end end end end if #z.maintenance_cats ~= 0 then text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">'; for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])'; end text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now); end no_tracking_cats = no_tracking_cats:lower(); if in_array(no_tracking_cats, {"", "no", "false", "n"}) then for _, v in ipairs( z.error_categories ) do tabletext = text ..insert (render, make_wikilink ('[[Category:' .. v))..']]'; end for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories tabletext = text ..insert (render, make_wikilink ('[[Category:' .. v))..']]'; end for _, v in ipairs( z.properties_cats ) do -- append properties maintenance categories tabletext = text ..insert (render, make_wikilink ('[[Category:' .. v))..']]'; end end return textend --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- This function searches a parameter's value for nonprintable or invisible characters. The search stops at the first match. Sometime after this module is done with rendering a citation, some C0 control characters are replaced with thereplacement character. That replacement character is not detected by this test though it is visible to readersof the rendered citation. This function will detect the 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 that the characterbelongs to along with its position in the parameter value. ]]--[[local function has_invisible_chars (param, v) local position = ''; local i=1; while cfg.invisible_chars[i] do local char=cfg.invisible_chars[i][1] -- the character or group name local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it v = mw.text.unstripNoWiki( v ); -- remove nowiki stripmarkers position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern if position then table.concat insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style (render'parameter', param), position}, true ) } ); -- add error message return; -- and done with this parameter end i=i+1; -- bump our index endend]] --[[--------------------------< Z . C I T A T I O N >---------------------------------------------------------- This is used by templates such as {{cite book}} to create the actual citation text. ]] function z.citation(frame) local pframe = frame:getParent() local validation; 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 Configuration and Whitelist and ... whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
This is used by templates such as {{cite book}} to create the actual citation text.
]]
function cs1.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;
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');
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modulesConfiguration and Whitelist and ...
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');-- ... live version of date validation code
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;
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
extract_id_access_levels = identifiers.extract_id_access_levels;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
get_coins_pages = metadata.get_coins_pages;
COinS = metadata.COinS;
local args = {}; -- table where we store all of the template's arguments local suggestions = {}; -- table where we store suggestions if we need to loadData them
local error_text, error_state;
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
config[k] = v;
-- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}}
end
for k, v in pairs( pframe.args ) do
if v ~= '' then
if not validate( k, config.CitationClass ) then
error_text = "";
if type( k ) ~= 'string' then
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
else
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end
end
missing_pipe_check (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
end
return cs1;z