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+$') then -- three or more character hostname.hostname or hostname.tld return true;it elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') 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 -- one character/digit .org hostname return true; elseif domain:match ('%f[%a][qxz]%.com$') then -html/std66#section- assigned one character .com hostname (x3.com times out 2015-12-10) return true; elseif domain1 which says:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) return true; elseif domain:match ('%f[%Scheme names consist of a%d][%sequence of characters beginning with a%d]%.%a%a$') then -- one character hostname letter and cctld (2 chars) return true;followed by any combination of letters, digits, plus elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a"+$'") then -- two character hostname and tld return true; elseif domain:match , period ('^%d%d?%d?%".%d%d?%d?%.%d%d?%d?%.%d%d?%d?'") then , or hyphen ("-- IPv4 address return true; else return false; endend").
returns true if it does, else false
--[[--------------------------< I S _ U R L >------------------------------------------------------------------]]
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. ]] local function is_url is_scheme (scheme, domain) if is_set (return scheme) then -- if scheme is set check it and domain return is_scheme (scheme) and is_domain_name :match (domain'^%a[%a%d%+%.%-]*:'); else return is_domain_name (domain); -- true if scheme not is set when url is protocol relative endand matches the pattern
end
--[=[--------------------------< I S P L _ D O M A I T N _ U R L N A M E >------------------------------------------------------------
Split Does this thing that purports to be a url into domain name seem to be a scheme, authority indicator, and valid domain.name?
First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(Syntax defined here: http:/), query(?) or fragment(/tools.ietf.org/html/rfc1034#)section-3.5BNF defined here: https://tools.ietf.org/html/rfc4234Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; see also [[Single-letter second-level domain]]list of tlds: https://www.iana.org/domains/root/db
If protocol relative urlrfc952 (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, return nil scheme and domain else return nil for both scheme and domainthe hyphen.
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 Also allowed are only 2IPv4 addresses.IPv6 not supported
Strip off domain is expected to be stripped of any port and 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 digitlocal function split_url (url_str) single-letter/digit second-level domains in the .org TLD local schemeq, authorityx, domain;and z SL domains in the .com TLD i and q SL domains in the .net TLD url_str = url_str:gsub single-letter SL domains in the ccTLDs ('where the ccTLD is two letters) two-character SL domains in gTLDs ([%a%d]where the gTLD is two or more letters)%.?[/%?#].*$', '%1'); three-plus- strip FQDN terminator and pathcharacter SL domains in gTLDs (/where the gTLD is two or more letters) IPv4 dot-decimal address format; TLD not allowed returns true if domain appears to be a proper name and tld or IPv4 address, query(?), fragment (#) (the capture prevents else false replacement of '//') ]=]
if url_str:match local function is_domain_name ('^//%S*') then -- if there is what appears to be a protocol relative url domain = url_str:match ('^//(%S*)') elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and not domain namethen scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothingreturn false; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return scheme; -- return scheme only making domain nil which will cause an error message end domain = domain:gsub ('(%a):%d+'not set, '%1'); -- strip port number if presentabandon
end
return schemedomain = domain:gsub ('^//', ''); -- strip '//' from domainname if present;done here so we only have to do it once if not domain:match ('^[%a%d]') then -- first character must be letter or digit return false; end if domain:match ('%f[%a%d][%a%d]%.org$') then --one character .org hostname return true; elseif domain:match ('%f[%a][qxz]%.com$') then --assigned one character .com hostname (x.com times out 2015-12-10) return true; elseif domain:match ('%f[%a][iq]%.net$') then --assigned one character .net hostname (q.net registered but not active 2015-12-10) return true; elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then --internationalized domain name with ACE prefix return true; elseif domain:match ('%f[%a%d][%a%d]%.cash$') then --one character/digit .cash hostname return true; elseif domain:match ('%f[%a%d][%a%d]%.%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 ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then --three or more character hostname.hostname or hostname.tld return true; elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then ----< L I N K _ P A R A M _ O K >---------------------------------------------------IPv4 address return true; else return false; endchecks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urlsend
Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
# < > [ ] | { } _
except the underscore which is used as a space in wiki urls and # which is used for section links
--[[--------------------------< I S _ U R L >------------------------------------------------------------------ returns false when true if the value contains any scheme and domain parts of these charactersa url appear to be a valid url; else false.
When This function is the last step in the validation process. This function is separate because there are no illegal characterscases thatare not covered by split_url(), this function returns TRUE if value DOES NOT appear to be a valid url for example is_parameter_ext_wikilink(the|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter which is NOT ok)looking for bracketted externalwikilinks.
]]
local function link_param_ok is_url (value) local scheme, domain;) if value:find is_set ('[<>%[%]|{}]'scheme) then -- if any prohibited charactersscheme is set check it and domain return is_scheme (scheme) and is_domain_name (domain); else return falseis_domain_name (domain); -- scheme not set when url is protocol relative
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 P L I N K T _ T I T U R L E _ O K >------------------------------------------------------------
Use link_param_ok() to validate |<param>-link= value Split a url into a scheme, authority indicator, and its matching |<title>= valuedomain.If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
|<title>= may be wikilinked but When not when |<param>-link= has a valueprotocol relative, get scheme, authority indicator, and domain. This function emits If there is an error message whenauthority indicator (oneor more '/' characters following the scheme's colon), make sure that condition existsthere are only 2.
]]
local function link_title_ok split_url (linkurl_str) local scheme, lorigauthority, titledomain; url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', torig'%1')local orig; -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
if is_set url_str:match (link'^//%S*') then -- don't bother if <param>-link doesn't have there is what appears to be a valueprotocol relative url if not link_param_ok domain = url_str:match ('^//(%S*)') elseif url_str:match (link'%S-:/*%S+') then -- check |<param>-link= markupif there is what appears to be a scheme, optional authority indicator, and domain name orig scheme, authority, domain = lorigurl_str:match ('(%S-:)(/*)(%S+)'); -- identify extract the failing link parameterscheme, authority indicator, and domain portions elseif titleauthority = authority:find gsub ('%[%[//', '', 1); -- replace place 1 pair of '/'with nothing; if is_set(authority) then -- check |title= for wikilink markupif anything left (1 or 3+ '/' where authority should be) then orig = torigreturn scheme; -- identify the failing |title= parameterreturn 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 is_set (orig) then table.insert( z.message_tail, { set_error( 'bad_paramlink'return scheme, orig)}); -- url or wikilink in |title= with |title-link=domain; end
end
--[[--------------------------< 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 Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed: # < > [ ] | { } _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. When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok). ]] local function link_param_ok (value) local scheme, domain; if value:find ('[<>%[%]|{}]') then -- if any prohibited characters 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 urlend --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
Determines whether a URL string appears to be valid.
portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two
portions of the url. If both are valid, 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 links
that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
]]
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url; if 'news:' == scheme then -- special case for newsgroups return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$'); end
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
local 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 '//')
if value:match ('%f[%[]%[%a%S*:%S+.*%]') 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*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] scheme, domain = split_url (value:match ('%f[%[]%[(//(%S*%.%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*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text scheme, domain = split_url (value:match ('(//(%S*%.%S+)')); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a url
--[[--------------------------< S A F E _ F O R _ U R I T A L I C S >------------------------------------------------------ Protects a string that will be wrapped in wiki italic markup '' ... ''
Escape sequences Note: We cannot use <i> for content italics, as the expected behavior for italics specified by ''...'' in the title is that they will be used for URL descriptionsinverted (i.e. unitalicized) in the resulting references. In addition, <i> and '' tend to interactpoorly under Mediawiki's HTML tidy.
]]
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 --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------ Escape sequences for content that will be used for URL descriptions ]] local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
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 one
argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason
this function is similar to but separate from wrap_msg().
]]
local function wrap_style (key, str)
if not is_set( str ) then
return "";
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
str = safe_for_italics( str );
end
return substitute( cfg.presentation[key], {str} );
end
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
]]
local function external_link( URL, label, source, access)
local error_str = "";
local domain;
local path;
local base_url;
if not is_set( label ) then
label = URL;
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
domainreturn table.concat({ "[", path = URL:match , " ", safe_for_url('^([/%.%-%+:%a%d]+label )([/%?#, "].*)$'", error_str }); -- split the url into scheme plus domain and path if path then end -- if there is a path portion path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values URL=domain..path; -- and reassemble----------------------< E X T E R N A L _ L I N K _ I D >---------------------------------------------- end Formats a wiki style external link if is_set (access) then -- access level (subscription, registration, limited) label = safe_for_url (label); -- replace square brackets and newlines]]
base_url = table.concat local function external_link_id( -- assemble external link with access signaloptions) { '<span class local url_string ="plainlinks">[', -- opening css and url markup URL, -- the url ' ', -- the required space label, '<span style="padding-left:0.15em">', -- signal spacing css cfgoptions.presentation[access], -- the appropriate icon '</span>', -- close signal spacing span ']</span>' -- close url markup and plain links span })id; elseif options.encode == true or options.encode == nil then base_url url_string = tablemw.uri.concatencode({ "[", URL, " ", safe_for_url( label ), "]" }url_string ); -- no signal markup
end
return tablemw.ustring.concatformat({ base_url'[%s%s%s \<span title\=\"%s\"\>%s%s%s\<\/span\>]', options.prefix, url_string, options.suffix or "", error_str } options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) );
end
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated
parameters in the citation.
added_deprecated_cat is a boolean declared in page scope variables above
]]
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local function deprecated_parameter(name)
if not added_deprecated_cat page_in_deprecated_cat then added_deprecated_cat 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
end
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
--[=[-------------------------< 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. 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.
Replaces unicode quotemarks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
Call this function for chapter titles, for website titles, etc; not for book titles.
]=]
local function kern_quotes (str)
local cap='';
local cap2='';
local wl_type, label, link;
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
if 1 cap, cap2 == wl_type then -- [[D]] simple wikilink with or without quote marks if mw.ustring.str:match (str, '%[%[[\" “”\'‘’].+^([\" “”\' ‘’]%]%]') then -- leading and trailing quote marks str = substitute (cfg.presentation['kern-wl-both'], str); elseif mw.ustring.match (str, '%[%[[\"“”^\' ‘’].+%]%]') then "); -- match leading double or single quote marksbut not double single quotes str = substitute (cfg.presentation['kern-wl-left'], str); elseif mw.ustring.match if is_set (str, '%[%[.+[\"“”\'‘’]%]%]'cap) then -- trailing quote marks str = substitute (cfg.presentation['kern-wl-rightleft'], str{cap, cap2}); end 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.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) if is_set (cap) then label = substitute (cfg.presentation['kern-left'], {cap, cap2}); end cap, cap2 = mw.ustring.str:match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) if is_set (cap) then label str = substitute (cfg.presentation['kern-right'], {cap, cap2}); end if 2 == wl_type then str = make_wikilink (link, label); -- reassemble the wikilink else str = label; end
end
return str;
end
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
end
-- if we get this far we have prefix and script
name = mw.language.fetchLanguageName( lang, "en" mw.getContentLanguage():getCode() ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, cfg.script_lang_codes{'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
lang = ''; -- invalid so set lang to empty string
end
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 T E N A T E >------------------------------------------
local function script_concatenate (title, script)
if is_set(title) then
title = '-{zh;zh-hans;zh-hant|' .. title .. '}-';
end
if is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
--[[--------------------------< F O R M I S _ A T _ C H L I A P T E R S _ T I T L U S E D >----------------------------------------------------- This function is used by select_one() 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, 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
Format the four chapter parametersReturns: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-parameter (chapter_url_source used for error messages). 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 format_chapter_title is_alias_used (scriptchapterargs, chapteralias, transchapterindex, chapterurlenumerated, chapter_url_sourcevalue, no_quotesselected, accesserror_list) local chapter_error = ''; if not is_set (chapter) enumerated then -- is this a test for an enumerated parameters? chapter alias = alias:gsub ('#', index); -- to be safe for concatenationreplace '#' with the value in index
else
if false alias == no_quotes then chapter = kern_quotes alias:gsub (chapter'#', ''); -- if necessary, separate chapter titleremove 's leading and trailing quote marks from Module provided quote marks chapter = wrap_style (#'quoted-title', chapter); endif it exists
end
chapter = script_concatenate if is_set(chapter, scriptchapterargs[alias]) then -- <bdi> tags, lang atribute, categorization, etc; must be done after title alias is wrappedin the template's argument list if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases if is_set local skip; for _, v in ipairs(transchaptererror_list) do -- spin through the error list to see if we've added this alias if v == alias then transchapter skip = wrap_style ('transtrue; break; -quoted-title', transchapter);has been added so stop looking end end if is_set not skip then -- has not been added so table.insert(chaptererror_list, alias ) then; -- add error alias to the error list chapter = chapter .. ' ' .. transchapter;end else -- here when transchapter without chapter or script-chapter chapter value = transchapterargs[alias]; -- not yet selected an alias, so select this one chapter_error selected = ' ' .. set_error ('trans_missing_title', {'chapter'})alias;
end
end
return value, selected; -- return newly selected alias, or previously selected alias
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_error;end--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just
names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
--[[--------------------------Because enumerated parameter |< H A S _ I N V I S I B L E _ C H A R S param>----------------------------------------1= is an alias of |<param>= we must test for both possibilities.
This function searches a parameter's value for nonprintable or invisible characters. The search stops at the
first match.
This function will detect the visible replacement character when it Generates an error if more than one match is part of the wikisourcepresent.
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().]]
Detects but ignores local function select_one( args, aliases_list, error_condition, index ) local value = nil; -- the character pattern that results from value assigned to the transclusion selected parameter local selected = ''; -- the name of the parameter we have chosen local error_list = {{'}} 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 if index ~= nil then index = tostring(or, for multi-byte characters, the position of its first byteindex) in theparameter value.; end
]] for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list if alias:match ('#') then -- if this alias can be enumerated if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases value, selected = 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 else value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias end end
local function has_invisible_chars (param, v) local position = if #error_list > 0 and 'none'; ~= error_condition then -- position of invisible char or starting position of stripmarker local dummy; -- end of matching string; not used but required to hold end position when a capture for cases where this code is returned local capture; -- used by stripmarker detection to hold name outside of the stripmarkerextract_names() local ierror_str =1""; local stripmarker for _, apostrophe; capture = string.match k in ipairs(v, '[%w%p ]*'error_list ); -- Test for values that are simple ASCII text and bypass other tests if truedo if capture error_str ~="" then error_str = v then -- if same there are no unicode characters return; end while cfgerror_str ..invisible_chars[i] do local char=cfg.invisible_charsmessages[i][1] 'parameter-- the character or group name local pattern=cfg.invisible_chars[iseparator'][2] -- the pattern used to find itend position, dummy, capture error_str = mwerror_str .ustring.find wrap_style (v'parameter', patternk) -- see if the parameter value contains characters that match the pattern; end if position and (char =#error_list > 1 then error_str = error_str .. cfg.messages['zero width joiner') then parameter-final- if we found a zero width joiner characterseparator']; else if mwerror_str = error_str .ustring.find (v, cfg.indic_script) then messages['parameter-pair- its ok if one of the indic scripts position = nilseparator']; -- unset position end
end
if position then if 'nowiki' error_str == capture or error_str .. wrap_style ('mathparameter' == capture then -- nowiki, math stripmarker (not an error conditionselected) stripmarker = true; -- set a flag elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset else local err_msg; if capture then err_msg = capture .. ' ' .. char; else err_msg = char .. ' ' .. 'character'; end table.insert( z.message_tail, { set_error( 'invisible_char'error_condition, {err_msg, wrap_style ('parameter', param), positionerror_str}, true ) } ); -- add error message return; -- and done with this parameter end end i=i+1; -- bump our index
end
return value, selected;
end
--[[--------------------------< A F O R G U M E N A T _ W R C H A P P T E R _ T I T L E >----------------------------------------------
Argument wrapper. This function provides support for argument mapping defined in Format the configuration file so thatfour chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-multiple names can be transparently aliased to single internal variableparameter (chapter_url_source used for error messages).
]]
local function argument_wrapperformat_chapter_title ( args scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) local origin chapter_error = {}'';
return setmetatableif not is_set ({chapter) then chapter = ''; -- to be safe for concatenation else ORIGIN if false = function( self, k )= no_quotes then local dummy chapter = self[k]kern_quotes (chapter); --force the variable to be loaded.if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks return origin[k]chapter = wrap_style ('quoted-title', chapter);
end
},end { __index chapter = function script_concatenate ( tblchapter, k scriptchapter) if origin[k] ~= nil then return nil; end local args -- <bdi> tags, listlang atribute, v = argscategorization, cfg.aliases[k]etc;must be done after title is wrapped if typeis_set ( list transchapter) == 'table' then v, origin[k] transchapter = select_onewrap_style ( args, list, 'redundant_parameterstrans-quoted-title' , transchapter); if origin[k] == nil is_set (chapter) then origin[k] chapter = chapter .. ''.. transchapter; else -- Empty string, not nil endhere when transchapter without chapter or script-chapter elseif list ~chapter = nil then v, origin[k] = args[list], listtranschapter; else -- maybe let through instead of raising an error? -- v, origin[k] chapter_error = args[k]' ' .. set_error ('trans_missing_title', k; error( cfg.messages[{'unknown_argument_mapchapter'] }); end end -- Empty strings, not nil; if v == nil is_set (chapterurl) then v = cfg.defaults[k] or ''; origin[k] = ''; end tbl chapter = rawsetexternal_link ( tblchapterurl, kchapter, v chapter_url_source); -- adds bare_url_missing_title error if appropriate return v; end end, })return chapter .. chapter_error;
end
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------This function searches a parameter's value for nonprintable or invisible characters. The search stops at thefirst match.
Looks for a parameter's name in one This function will detect the visible replacement character when it is part of several whiteliststhe wikisource.
Parameters in the whitelist can have three values: true - activeDetects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, supported parameters false - deprecatedpre, supported parametersref) nil - unsupported parametersand identifies them with a slightly different error message. See also coins_cleanup(). ]]Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
local Output of this function validate( nameis an error message that identifies the character or the Unicode group, cite_class ) local name = tostring( name ); local state;or the stripmarker if in_array that was detected along with its position (cite_classor, {'arxiv', 'biorxiv'for multi-byte characters, 'citeseerx'}the position of its first byte) then -- limited in theparameter sets allowed for these templates state = whitelistvalue.limited_basic_arguments[ name ]; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end
if 'arxiv' == cite_class then -- basic parameters unique to these templates state = whitelist.arxiv_basic_arguments[name]; end if 'biorxiv' == cite_class then state = whitelist.biorxiv_basic_arguments[name]; end if 'citeseerx' == cite_class then state = whitelist.citeseerx_basic_arguments[name]; end
if true local function has_invisible_chars (param, v) local position == state then return true''; end -- valid actively supported parameter if false == state thenposition of invisible char or starting position of stripmarker deprecated_parameter (name) local dummy; -- parameter is deprecated end of matching string; not used but still supported return true; required to hold endposition when a capture is returned -- limited enumerated parameters list name = name:gsub( "%d+", "#" ) local capture; -- replace digit(s) with # (last25 becomes last#) state = whitelist.limited_numbered_arguments[ used by stripmarker detection to hold name ];of the stripmarker if true = local i= state then return true1; end -- valid actively supported parameter if false == state then deprecated_parameter (name) local stripmarker, apostrophe; -- parameter is deprecated but still supported return true; end
while cfg.invisible_chars[i] do return false; local char=cfg.invisible_chars[i][1] -- not supported because not found the character or group name is set local pattern=cfg.invisible_chars[i][2] -- the pattern used to nilfind it end position, dummy, capture = mw.ustring.find (v, pattern) -- end limited see if the parameter-set templatesvalue contains characters that match the pattern
state = whitelist.basic_arguments[ name ]; if position then-- all other templates; all normal parameters allowed if true 'nowiki' == capture or 'math' == capture or ('ref' == capture and 'quote' == state param) then return true; end -- valid actively supported parameternowiki, math, or quote param and ref stripmarker (not an error condition) if false 'nowiki' == capture or 'math' == state capture then deprecated_parameter -- nowiki, math stripmarker (namenot an error condition) stripmarker = true; -- parameter is deprecated but still supportedset a flag return elseif true== stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset end elseif 'apostrophe' == char then --apostrophe template uses ‍, hair space and zero- all enumerated parameters allowedwidth space name apostrophe = true; elseif true == name:gsubapostrophe and in_array ( "%d+"char, {'zero width joiner', 'zero width space', "#" 'hair space'})then position = nil; -- replace digit(s) with # (last25 becomes last#unset else local err_msg; if capture then err_msg = capture .. ' ' .. cfg.invisible_chars[i][3] or char; else state err_msg = whitelistcfg.numbered_argumentsinvisible_chars[i][ name 3]or (char .. ' character'); end
if table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true == state then ) } ); -- add error message return true; end -- valid actively supported and done with this parameter if false == state then end end deprecated_parameter (name)i=i+1; -- parameter is deprecated but still supported return true;bump our index
end
return false; -- not supported because not found or name is set to nil
end
--[[--------------------------< A R G U M E N O T _ W R A P _ D A T P E R >--------------------------------------------------------
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>Argument wrapper. When date is DD MMMM YYYY or isMMMM DD, YYYY then wrap This function provides support for argument mapping defined in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYYthe configuration file so thatDOES NOT yet support MMMM YYYY or any of the date rangesmultiple names can be transparently aliased to single internal variable.
]]
local function nowrap_date argument_wrapper(dateargs ) local caporigin =''; local cap2=''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date){};
elseif date:matchreturn setmetatable("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then{ cap, cap2 ORIGIN = string.match function(dateself, "^(.*k )%s+(%d%d%d%d)$"); date local dummy = substitute (cfg.presentationself['nowrap2'k], {cap, cap2}); end return date;end --[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.Also handles force the special case where it is desirable variable to omit the title type from the rendered citation (|type=none)be loaded. ] return origin[k] local function set_titletype (cite_class, title_type) if is_set(title_type) then if "none" == title_type then title_type = ""; -- if |type=none then type parameter not displayed
end
}, { __index = function ( tbl, k ) if origin[k] ~= nil then return title_typenil; end local args, list, v = args, cfg.aliases[k]; if type( list ) == 'table' then v, origin[k] = select_one( args, list, 'redundant_parameters' ); if origin[k] == nil then origin[k] = ''; -- if |typeEmpty string, not nil end elseif list ~= nil then v, origin[k] = args[list], list; else -- maybe let through instead of raising an error? -- v, origin[k] = has been set to any other value use that valueargs[k], k; error( cfg.messages['unknown_argument_map'] ); end -- Empty strings, not nil; if v == nil then return v = cfg.title_types defaults[cite_classk] or ''; -- set template origin[k] = ''s default title type; else empty string for concatenation end tbl = rawset( tbl, k, v ); return v; end, });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 -[[--------------------------< H Y P H E N _ T O _ D A S H >-----------------------------------------------deprecated, supported parameters nil --- Converts a hyphen to a dashunsupported parameters
]]
local function hyphen_to_dashvalidate( str name ) local name = tostring( name ); local state = whitelist.basic_arguments[ name ]; -- Normal arguments if not is_settrue == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (strname) or str; -- parameter is deprecated but still supported return true; end -- Arguments with numbers in them name = name:matchgsub( "[%d+", "#" ); -- replace digit(s) with # (last25 becomes last# state = whitelist.numbered_arguments[%name ]{}<>]" ) ~; if true == state then return true; end -- valid actively supported parameter if false == nil state then deprecated_parameter (name); -- parameter is deprecated but still supported return strtrue; end return str:gsubfalse; -- Not supported because not found or name is set to nilend -- Formats a wiki style internal linklocal function internal_link_id(options) return mw.ustring.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
--[[--------------------------< S N O W R A P _ D A F T E _ J O I N >-------------------------------------------------------- When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or isMMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
Joins a sequence DOES NOT yet support MMMM YYYY or any of strings together while checking for duplicate separation charactersthe date ranges.
]]
local function safe_joinnowrap_date ( tbl, duplicate_char date) local cap=''; local cap2=''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation[[ Note: we use string functions here'nowrap1'], rather than ustring functions.date);
This has considerably faster performance and should work correctly as elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then long as the duplicate_char is strict ASCII cap, cap2 = string.match (date, "^(. The strings*)%s+(%d%d%d%d)$"); in tbl may be ASCII or UTF8 date = substitute (cfg.presentation['nowrap2'], {cap, cap2}); ]]end
local str = ''return date; end --[[--------------------------< IS _ V A L I D _ I S X N >----------------------------------------------------- ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().If the output stringnumber 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. ]] local function is_valid_isxn (isxn_str, len) local comp temp = 0; isxn_str = ''{ isxn_str:byte(1, len) }; -- what does make a table of byte values 'comp0' mean? local end_chr = → 0x30 .. '9' → 0x39, 'X';→ 0x58 local trimlen = len+1; -- adjust to be a loop counter for _i, value v in ipairs( tbl isxn_str ) do -- loop through all of the bytes and calculate the checksum if value v == nil string.byte( "X" ) then -- if checkdigit is X (compares the byte value = 'of '; end if str == X'' then -- if output string which is empty0x58) str temp = valuetemp + 10*( len - i ); -- assign value to it (first time through the loop)represents 10 decimal elseif value ~= '' thenelse if value:subtemp = temp + tonumber(1,1) == '<' then -- Special case of values enclosed in spans and other markupstring. comp = value:gsubchar( "%b<>", "" v) ); -- remove html markup *(<span>string</span> len-> stringi); else end end comp return temp % 11 == value0; -- returns true if calculation result is zero 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 .. "<HERE(enchr=" .. end_chr.. ")" IS _ V A L I D _ I S X N _ 1 3 >-- 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 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; endISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit. elseif end_chr == " " then -- if last char of output string If the number is a space if str:sub(-2valid,-1) == duplicate_char the result will be 0.. " " then Before calling this function, isbn-- if last two chars 13/ismn must be checked for lengthand stripped of str are <sepc><space> str = str:sub(1dashes,spaces and other non-3); isxn-- remove them both end end13 characters.
if trim then]] if value ~= comp then -- value does not equal comp when value contains html markup local dup2 function is_valid_isxn_13 (isxn_str) local temp= duplicate_char0; if dup2 isxn_str = { isxn_str:matchbyte( "%A" 1, 13) then dup2 = "%" .. dup2}; end -- if duplicate_char not make a letter then escape ittable of byte values '0' → 0x30 .. '9' → 0x39 for i, v in ipairs( isxn_str ) do value temp = value:gsubtemp + ( "3 - 2*(i %b<>2))" * tonumber( string.. dup2, "%1", 1 char(v) -- 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 .. valuemultiply odd index digits by 1, even index digits by 3 and sum; --add it to the output string endincludes check digit
end
return strtemp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correctend
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------Determines whether an ISBN string is valid
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.]]
local function check_isbn( isbn_str ) if 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 = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces local len = isbn_str:len(); if len ~= 10 and len ~= 13 then return false; end
local function is_suffix if len == 10 then if isbn_str:match(suffix"^%d*X?$" )== nil then return false; end if in_array return is_valid_isxn(suffixisbn_str, {'Jr', 'Sr', '2nd', '3rd'}10) or suffix; else local temp = 0; if isbn_str:match ('"^97[89]%dthd*$'" ) == nil thenreturn false; end -- isbn13 begins with 978 or 979; ismn begins with 979 return trueis_valid_isxn_13 (isbn_str);
end
return false;
end
--[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
section 2, pages 9–12.
]]
--local function ismn (id) local handler = cfg.id_handlers[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------'ISMN']; local text; local valid_ismn = true;
For Vancouver Style id=id:gsub( "[%s-–]", author/editor names are supposed to be rendered in Latin (read ASCII"" ) characters. When a nameuses characters that contain diacritical marks; -- strip spaces, those characters are to converted to the corresponding Latin character.When a name is written using a non-Latin alphabet or logogramhyphens, that name is to be transliterated into Latin characters.These things are not currently possible in this module so are left to and endashes from the editor to do.ismn
This test allows |first if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and |lastbegin 9790 valid_ismn = false; else valid_ismn=is_valid_isxn_13 (id); -- validate ismn end -- text = internal_link_id({link = handler.link, label = names handler.label, -- use this (or external version) when there is some place to link to contain any of the letters defined in the four Unicode Latin character sets-- [http://wwwprefix=handler.unicodeprefix,id=id,separator=handler.org/charts/PDF/U0000separator, encode=handler.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007Aencode}) text="[[http://www" .. handler.link .. "|" .. handler.unicodelabel .org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement"]] 00C0–00D6, 00D8–00F6, 00F8–00FF [http://www" .. handler.unicodeseparator .org/charts/PDF/U0100.pdf Latin Extendedid; -A] 0100–017F- because no place to link to yet [http://wwwif false == valid_ismn then text = text ..unicode' ' .org/charts/PDF/U0180.pdf Latin Extendedset_error( 'bad_ismn' ) -B] 0180–01BF, 01C4–024F- add an error message if the issn is invalid end return text;end
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods--[[--------------------------< I S S N >----------------------------------------------------------------------
Validate and format an issn. This original test: if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") thenwas written ouside of code fixes the code case where an editor and pasted here because has included an ISSN in the code editor gets confused between character insertion point and cursor position.The test citation but has been rewritten to use decimal character escape sequence for separated the individual bytes two groups of fourdigits with a space. When that condition occurred, the unicode characters so that it is not necessaryto use an external editor to maintain resulting link looked like this code.:
\195\128|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -\195\150 – À- Ö (U+00C0–U+00D6 – C0 controls)can't have spaces in an external link \195\152-\195\182 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. Ø-ö Incorrect length (U+00D8-U+00F6 – C0 controls8 digits) \195\184, characters other than 0-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls9 and X, Latin extended A & B)or checkdigit / calculated value mismatch will all cause a check issn \199\132-\201\143 error message. – DŽ-ɏ (U+01C4-U+024F – Latin extended B)The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
]]
local function is_good_vanc_name issn(lastid, firste) local first, suffix issn_copy = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or firstid; -- save a copy of unadulterated issn; use this version for display if first has something that looks like a generational suffix, get itissn does not validate local handler; local text; local valid_issn = true; if is_set (suffix) e then if not is_suffix (suffix) then add_vanc_error (handler = cfg.id_handlers['suffixEISSN')]; return false; -- not a name with an appropriate suffix else endhandler = cfg.id_handlers['ISSN'];
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
add_vanc_error ('non-Latin character');
return false; -- not a string of latin characters; Vancouver requires Romanization
end;
return true;
end
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >-------------------------------------validate the issn: 8 digits long, containing only 0-9 or X in the last position valid_issn=false; --wrong length or improper character else valid_issn=is_valid_isxn(id, 8); --validate issn end
Attempts to convert names to initials in support of |name if true == valid_issn then id = string.sub( id, 1, 4 ) .. "-list" .. string.sub( id, 5 ); -format- if valid, display correctly formatted version else id = issn_copy; -- if not valid, use the show the invalid issn with error message end text =vancexternal_link_id({link = handler. link, label = handler.label,Names in |firstn prefix= may be separated by spaces or hyphenshandler.prefix, or for initialsid=id, a periodseparator=handler. See http://wwwseparator, encode=handler.ncbiencode}) if false == valid_issn then text = text .nlm.nih' ' .gov/books/NBK7271/box/A35062/.set_error( 'bad_issn' ) -- add an error message if the issn is invalid end return textend
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.--[[--------------------------< A M A Z O N >------------------------------------------------------------------
This function uses ustring functions because firstname initials may Formats a link to Amazon. Do simple error checking: asin must be any mix of the unicode Latin 10 numeric or uppercase alphacharacters accepted by is_good_vanc_name (). If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digitisbn. If 10-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.
]]
local function reduce_to_initialsamazon(firstid, domain) local name, suffix err_cat = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
if not name id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then err_cat = ' ' .. set_error ('bad_asin'); -- if asin is not initials a mix of 10 uppercase alpha and a suffixnumeric characters else name if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X) if check_isbn( id ) then -- see if asin value is isbn10 add_maint_cat ('ASIN'); elseif not is_set (err_cat) then err_cat = mw ' ' .ustring.set_error ('bad_asin'); -- asin is not isbn10 end elseif not id:match(first, "^(%u[%d%u]+)$") then err_cat = ' ' .. set_error ('bad_asin'); -- is it just intials?asin doesn't begin with uppercase alpha end
end
if not is_set(domain) then
domain = "com";
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
domain = "co." .. domain;
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
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
if name then -- if first is initials with or without suffix if 3 [[--------------------------< A R X I V > mw.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----------------------------------------------------
See: http://arxiv.org/help/arxiv_identifier
format and error check arXiv identifier. There are three valid forms of the identifier:the first form, valid only between date codes 9108 and 0703 is: local initials, names = {}, {}arXiv:<archive>.<class>/<date code><number><version>where: <archive> is a string of alpha characters - may be hyphenated; no other punctuation <class> is a string of alpha characters -may be hyphenated; no other punctuation <date code> is four digits in the form YYMM where YY is the last two digits of the four- tables to hold name parts digit year and initialsMM is the month number January = 01 first digit of YY for this form can only 9 and 0 local i = <number> is a three-digit number <version> is a 1or 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: <date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01 <number> is a four- counter for digit number <version> is a 1 or more digit number of initialspreceded with a lowercase v; no spaces
the third form, valid from January 2015 is: names = mwarXiv:<date code>.text.split (first, '[%s,]+'); <number><version>where: <date code> and <version> are as defined for 0704-1412 <number> is a five- split into a table of names and possible suffixdigit number]]
local function arxiv (id, class) while nameslocal handler = cfg.id_handlers[i'ARXIV'] do -- loop through the table; local year, month, version; local err_cat = ''; local text; if 1 < i and namesid:match("^%a[%a%.%-]+/[90]%d[i01]%d%d%d%d$") or id:match ('"^%a[%dJSa%.%-]+/[90]%drndthd[01]%d%d%d%dv%d+%.?$'") then -- if not test for the first name9108-0703 format w/ & w/o version year, and looks like month = id:match("^%a[%a suffix %.%-]+/(may have trailing dot[90]%d) names([i01] = names%d)%d%d%d[iv%d]:gsub *$"); year = tonumber(year); month = tonumber('%.', ''month); if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- remove terminal dot if presentinvalid year or invalid month if is_suffix (names[i](91 == year and 7 > month) or (7 == year and 3 < month)) then -- if a legitimate suffixyears ok, are starting and ending months ok? tableerr_cat = ' ' ..insert set_error(initials, ' bad_arxiv' .. names[i]); -- add a separator space, insert at end of initials table break; -- and done because suffix must fall at the end of a name end -- no set error message if not a suffix; possibly because of Romanization
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); year = tonumber(year); month = tonumber(month); if 3 ((7 > year) or (14 < year) or (1 > i thenmonth or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years) table.insert (initials(7 == year) and (4 > month)) then --or -- when year is 07, mwis month invalid (before April)? err_cat = ' ' .ustring.subset_error(names[i],1,1)'bad_arxiv' ); -- insert the intial at end of initials tableset error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); year = tonumber(year); i month = i+tonumber(month); if ((15 > year) or (1> month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years) err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message end else err_cat = ' ' .. set_error( 'bad_arxiv' ); -- bump the counterarXiv id doesn't match any format
end
text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; return table.concatif is_set (initialsclass) then class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- Vancouver format does external link within square brackets, not include spaceswikilink else class = ''; -- empty string for concatenation end return text ..class;
end
--[[
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
1. Remove all blanks.
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
3. If there is a hyphen in the string:
a. Remove it.
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
1. All these characters should be digits, and there should be six or less. (not done in this function)
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
--[[--------------------------< L I S T Returns a normalized lccn for lccn() to validate. _ P E O P L E >-------------------------------------------------------There is no error checking (step 3.b.1) performed in this function.]]
Formats a list of people local function normalize_lccn (elccn) lccn = lccn:gsub ("%s", ""); -- 1.g. authors / editors) strip whitespace
]] if nil ~= string.find (lccn,'/') then lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it end
local function list_people(control, people, etal) local sep;prefix local namesep;suffix local format prefix, suffix = controllccn:match ("(.format local maximum = control+)%-(.maximum local lastauthoramp = control+)"); -- 3.lastauthoramp; local text = {}a remove hyphen by splitting the string into prefix and suffix
if nil ~= suffix then -- 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 end return lccn; 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/ length = 8 then all digitslength = 9 then lccn[1] is lower case alphalength = 10 then lccn[1] and lccn[2] are both lower case alpha or both digitslength = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digitslength = 12 then lccn[1] and lccn[2] are both lower case alpha ]] local function lccn(lccn) local handler = cfg.id_handlers['vancLCCN' ]; local err_cat = ''; -- presume that LCCN is valid local id = format lccn; -- local copy of the lccn id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) local len = id:len(); -- get the length of the lccn if 8 == len then if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message end elseif 9 == len then -- VancouverLCCN should be adddddddd if nil == id:match("%l%d%d%d%d%d%d%d%d") then -like author/editor name styling- does it match our pattern? err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message sep end elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... if nil == 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' ); -- no match,set an error message end end elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd if not (id: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 -- see if it matches one of our patterns err_cat = ' ' .. set_error( 'bad_lccn'); -- nameno match, set an error message end elseif 12 == len then --list separator between authors is a commaLCCN should be aadddddddddd namesep if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern err_cat = ' '.. set_error( 'bad_lccn' ); -- last/first separator is a spaceno match, set an error message end
else
sep err_cat = '' .. set_error( 'bad_lccn' );' -- name-list separator between authors is a semicolonwrong length, set an error message end if not is_set (err_cat) and nil ~= lccn:find ('%s') then namesep err_cat = ', ' .. set_error( 'bad_lccn' ); -- last/first separator is <comma><lccn 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
--[[
Format PMID and do simple error checking. PMIDs are sequential numbers beginning at 1 and counting up. This code checks the PMID to see that it
contains 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.
]]
local function pmid(id)
local test_limit = 30000000; -- update this value as PMIDs approach
local handler = cfg.id_handlers['PMID'];
local err_cat = ''; -- presume that PMID is valid
if sepid:submatch(-1,-1) ~= " [^%d]" ) then sep -- if PMID has anything but digits err_cat = sep ' ' .. " " endset_error( 'bad_pmid' ); -- set an error message if is_set else -- PMID is only digits local id_num = tonumber(maximumid) and maximum ; -- convert id to a number for range testing if 1 > id_num or test_limit < 1 id_num then return "", 0; end -- returned 0 if PMID is for EditorCountoutside test limit boundaries err_cat = ' ' .. set_error( 'bad_pmid' ); not used for authors-- set an error message end end
for ireturn external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator,person in ipairs(peopleencode=handler.encode}) do.. err_cat; end --[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------ Determines if is_set(persona PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.last) then If embargo date isin the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because local mask |embargo= personwas not set in this cite.mask local one ]] local sep_one = sep;function is_embargoed (embargo) if is_set (maximumembargo) and i > maximum then etal local lang = truemw.getContentLanguage(); break local good1, embargo_date, good2, todays_date; elseif good1, embargo_date = pcall(mask ~= nillang.formatDate, lang, 'U', embargo ) then; local n good2, todays_date = tonumberpcall(masklang.formatDate, lang, 'U' ); if good1 and good2 then -- if embargo date and today's date are good dates if tonumber(n ~= nilembargo_date ) then one >= string.reptonumber("—",ntodays_date )then -- is embargo date is in the future? else one = mask; sep_one = " "return embargo; end -- still embargoed
else
one = person.last local first = person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub add_maint_cat ('%.embargo', ''); -- 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 tested 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 ~= control.page_name then one = make_wikilink (person.link, one)return ''; -- link author/editor if this page is not the author's/editor's page endunset because embargo has expired
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
return ''; -- |embargo= not set return empty string
end
--[[--------------------------< P M C >------------------------------------------------------------------------
Format a PMC, do simple error checking, and check for embargoed articles.
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 The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not etal then text[#text-2] = " & "; -- replace last separator with ampersand text end text[#text] = nil; -- erase be linked to the last separator end local result = tablearticle.concat(text) -- construct list If the embargo date is today or in the past, or if etal and is_set (result) it is empty or omitted, then -- etal may be set by |display-authors=etal but we might not have a last-first listthe result = result .. sep .. ' ' .. PMC identifier is linked to the article through the link at cfg.messagesid_handlers['et alPMC']; -- we've go a last-first list and etal so add et al. end return result, countendprefix.
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link. Function is_embargoed ()
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------PMCs 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.
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 pmc(id, authorembargo) local test_limit = 6000000; -, or editor-name lists chosen in that orderupdate this value as PMCs approach local handler = cfg. id_handlers['PMC']; local err_cat = year ''; -- presume that PMC is Year or anchor_year.valid local text;
if id:match("[^%d]]") then -- if PMC has anything but digitslocal function anchor_id err_cat = ' ' .. set_error(namelist, year'bad_pmc' ); -- set an error message else -- PMC is only digits local namesid_num ={}tonumber(id); -- convert id to a table number for the one to four names and yearrange testing if 1 > id_num or test_limit < id_num then for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last namesif PMC is outside test limit boundaries names[i] err_cat = v' ' .last . set_error( 'bad_pmc' ); -- set an error message 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 (idembargo) then -- if concatenation is not an empty stringPMC is still embargoed? return text="CITEREF[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id.. err_cat; -- add the CITEREF portionstill embargoed so no external link
else
return ''; text = external_link_id({link = handler.link, label = handler.label, -- return an empty string; no reason embargo date or embargo has expired, ok to include CITEREF link to article prefix=handler.prefix,id in this citation=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
return text;
end
-- Formats a DOI and checks for DOI errors.
--[[--------------------------< N A M E _ H A S _ E T A L >------------------------------------------------DOI names contain two parts: prefix and suffix separated by a forward slash.-- Prefix: directory indicator '10.' followed by a registrant code-- Suffix: character string of any length chosen by the registrant
Evaluates the content of author and editor -- This function checks a DOI name parameters for variations on the theme of et al: prefix/suffix. If foundthe doi name contains spaces or endashes,the et al. is removed-- or, if it ends with a flag is set to true and the period or a comma, this function returns the modified name and the flagwill emit a bad_doi error message.
This function never sets -- DOI names are case-insensitive and can incorporate any printable Unicode characters so the flag to false but returns it's previous state because it may have been set bytest for spaces, endash,previous passes through this function or by the parameters |display-authors=etal or |display-editors=etaland terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
local function doi(id, inactive) local cat = "" local handler = cfg.id_handlers['DOI']; local text; if is_set(inactive) then local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id; if is_set(inactive_year) then table.insert( z.error_categories, "自" .. inactive_year .. "年含有不活躍DOI的頁面"); else table.insert( z.error_categories, "含有不活躍DOI的頁面" ); -- when inactive doesn't contain a recognizable year end inactive = " (" .. cfg.messages['inactive'].. " " .. inactive .. ")" else local function name_has_etal text = external_link_id(name{link = handler.link, etallabel = handler.label, nocat prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) inactive = "" end
if is_set (name) then -- name can be nil in which case just return local etal_pattern = = id:match("[;,]? *[\"']*^10%f.[^%as–]-/[Ee][Tt] *[Aa][Ll^%s–]-[^%.\"',]*$" ) then -- variations on the doi must begin with 'et al10.' theme local others_pattern = "[;,]? *%f[%must contain a]and [Oo]thers"; -- and alternate to et al. if name:match (etal_pattern) then -- variants on et al. name = name:gsub (etal_patternfwd slash, ''); -- if foundmust not contain spaces or endashes, remove etal = true; -- set flag (may have been set previously here or by |display-authors=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat ('etal'); -- and add a category if must not already added endwith period or comma elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? name cat = name:gsub (others_pattern, ''); -- if found, remove etal = true; -- set flag (may have been set previously here or by |display-authors=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat .. set_error('etalbad_doi'); -- and add a category if not already added end end
end
return name, etal; -- text .. inactive .. cat
end
--[[--------------------------< O P E N A M E _ H A S _ E D _ M L I B R A R K U P Y >--------------------------------------------------------
Evaluates the content of author Formats an OpenLibrary link, and editor parameters checks for extranious editor annotations: ed, ed., eds, (Ed.), etc.These annotation do not belong in author parameters and are redundant in editor parameters. If found, the functionadds the editor markup maintenance categoryassociated errors.
]]
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];
local function name_has_ed_markup if (name, list_namecode == "A" ) local _, pattern; local patterns = { -- these patterns match annotations at end of namethen '%f[%return external_link_id(%[][%(%[]%s*[Ee][Dd][Ss]?%{link=handler.?%s*[%)%]]?$'link, -- (ed) or (eds): leading '('label=handler.label, case insensitive 'ed', optional 's', ' prefix=handler.prefix ..' andauthors/or ')OL', '[ id=id,%separator=handler.%s]%f[e]eds?%separator, encode = handler.?$', -- ed or eds: without '('or 'encode})'; case sensitive elseif (ED could be initials Ed could be namecode == "M" )then '%f[%return external_link_id(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%{link=handler.?%s*[%)%]]?$'link, -- (editor) or (editors): leading '('label=handler.label, case insensitive, optional ' prefix=handler.prefix ..' andbooks/or ')OL', '[ id=id,%separator=handler.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%separator, encode = handler.?$', -- editor or editors: without 'encode}) elseif ('or 'code == "W" )'; case insensitivethen -- these patterns match annotations at beginning of name '^eds?[%return external_link_id({link=handler.link,;]'label=handler.label, -- ed prefix=handler.prefix . or eds.: lower case only, optional 'sworks/OL', requires '.' '^[%(%[]%s*[Ee][Dd][Ss]?% id=id, separator=handler.?%s*[%)%]]'separator, -- (edencode = handler.encode}) or (eds): also sqare brackets, case insensitive, optional 's', '.' else '^[%return external_link_id(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A'{link=handler.link, -- (editor or (editors: also sq brackets, case insensitive, optional bracketslabel=handler.label, 's' prefix=handler.prefix .. '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%AOL', -- (edited: also sq brackets id=id, case insensitiveseparator=handler.separator, optional brackets encode = handler.encode} if is_set (name) then for _, pattern in ipairs (patterns) do -- spin through patterns table and if name:match (pattern) then add_maint_cat .. ' ' .. set_error('extra_text_namesbad_ol', cfg.special_case_translation [list_name]); -- add a maint cat for this template break; end end
end
return name; -- and done
end
--[[--------------------------< N A M E _ H A S _ M U L T _ N S A M G E S _ I D >----------------------------------------------------------
Evaluates the content of author Validate and editor (surnames only) parameters for multiple namesformat a usenet message id. Multiple names areSimple error checking, looks for 'id-left@id-right' not enclosed inindicated if there is more than one comma '<' and /or semicolon. If found, the function adds the multiple name(author or editor) maintenance category'>' angle brackets.
]]
local function name_has_mult_names message_id (name, list_nameid) local count, _handler = cfg.id_handlers['USENETID']; if is_set text = external_link_id(name) then{link = handler.link, label = handler.label, _prefix=handler.prefix,id=id, count separator= namehandler.separator, encode=handler.encode}) if not id:match('^.+@.+$') or not id:gsub match('^[;,^<].*[^>]', '$'); -- count the number of separator-like characters if 1 < count then -- param could be |author= doesn't have '@' or |editor= so has one separator or first or last character is acceptable'< or '>' add_maint_cat text = text .. ' ' .. set_error('mult_namesbad_message_id', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this templatean error message if the message id is invalid end end return name; -- and donetext
end
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
--[[--------------------------This function sets default title types (equivalent to the citation including |type=< N A M E _ C H E C K S default value>--------------------------------------------------------) for those templates that have defaults.This function calls various name checking functions used Also handles the special case where it is desirable to validate omit the content of title type from the various name-holdingparametersrendered citation (|type=none).
]]
local function name_checks set_titletype (lastcite_class, first, list_nametitle_type) if is_set (lasttitle_type) then if last:match ('^%(%(.*%)%)$') "none" == title_type then -- if wrapped in doubled parentheses, accept as written last title_type = last:match ('^%(%((.*)%)%)$')""; -- strip parens else last if |type= name_has_mult_names (last, list_name); -- check for multiple names in the none then type parameter (last only) last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotationnot displayed
end
return title_type; -- if |type= has been set to any other value use that value
end
if is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
else
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
end
end
return last, first; -- done
end
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------Removes irrelevant text and dashes from ISBN numberGets name list from the input argumentsSimilar to that used for Special:BookSources
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.]]
This local function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last namesclean_isbn( isbn_str ) return isbn_str:gsub( "[^-0-9X]", |last1= and |last3="" );are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.end
When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returnedthat will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the template's metadata. When this occurs, the page is added to a maintenance category.--[[--------------------------< 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 like
string.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
local function extract_names(args, list_name) local names = {}; -- table of names local last; [[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >-------------------------- individual name components local first; local link; local mask; local i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; -- used Strip 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 to count the number of times we havenmarkup a title have, as a result, provided valid markup. When they don't found a |last= (or alias for authors, |editor-last or alias for editors) local etal=false; -- return value set to true when we find some form of et alsingle apostrophes are left behind. in an author parameter
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary while true do last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ); link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
last, etal = name_has_etal local function strip_apostrophe_markup (last, etal, falseargument); -- find and remove variations on et al. first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al. last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks if first and not last then -- if there is a firstn without a matching lastn table.insertis_set ( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } argument); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1return argument; -- 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 link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup
while true do if argument:match ("%'%'%'%'%'") then -- bold italic (5) names[n] argument= {last = lastargument:gsub("%'%'%'%'%'", first = first, link = link, mask = mask, corporate=false}""); -- remove all instances of it elseif argument:match ("%'%'%'%'") then -- add this name to our names list italic start and end without content (corporate for |vauthors= only4) n argument= n + 1argument:gsub("%'%'%'%'", ""); elseif argument:match ("%'%'%'") then -- point to next location in the names tablebold (3) if 1 argument== count argument:gsub("%'%'%'", ""); elseif argument:match ("%'%'") then -- if the previous name was missingitalic (2) table.insert( z.message_tail, { set_error argument=argument:gsub( "%'missing_name%'", {err_msg_list_name, i-1}, true ) } ""); -- add this error message end else count = 0break; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
return names, etalargument; -- all done, return our list of names
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--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------script pairs)
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 codeApostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with stringsof %27%27...]]
Returns the language name and associated twolocal function make_coins_title (title, script) if is_set (title) then title = strip_apostrophe_markup (title); - or three-character code. Because case of the source may be incorrectstrip any apostrophe markup elseor different from the case that WikiMedia uses title=''; -- if not set, the name comparisons are done in lower case and when a match make sure title isan empty string end if is_set (script) thenfound script = script:gsub ('^%l%l%s*:%s*', the Wikimedia version ''); -- remove language prefix if present (assumed to script value may now be correctempty string) script = strip_apostrophe_markup (script); -- strip any apostrophe markup else script=''; -- if not set, make sure script is returned along with the codean empty string end if is_set (title) and is_set (script) then script = ' ' .. When there is no match, script; -- add a space before weconcatenate end return title .. script; -- return the original language name string.concatenationend
mw.language.fetchLanguageNames(--[[--------------------------<local wiki languageG E T _ C O I N S _ P A G E S >, 'all') returns a list of languages that in some cases may includeextensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not supportcode 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, 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/LocalNamesEn.php---------------------------------------------
Names but that are included in the list will be found if that name is provided Extract page numbers from external wikilinks in any of the |languagepage= parameter. For example,if |languagepages=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are foundand the associated code is not two or three characters, this function returns only the Wikimedia language name. Adapted from code taken from Module:Check ISO 639-1|at= parameters for use in COinS.
]]
local function get_iso639_code get_coins_pages (lang, this_wiki_codepages) local remap = {pattern; ['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla if not is_set (the endonym) but we want Bengali (the exonympages)then return pages; here we remap ['bengali'] = {'Bengali', 'bn'}, end -- MediaWiki doesn't use exonym so here if no page numbers then 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 }re done
if remap[langwhile true do pattern = pages:lowermatch()] then return remap"%[lang(%w*:lower(?//[^ ]+%s+)[%w%d][1.*%]"); -- pattern is the opening bracket, remapthe url and following space(s): "[lang:lowerurl " if nil == pattern then break; end -- no more urls pattern = escape_lua_magic_chars (pattern)][2]; -- for this language 'namepattern is not a literal string; escape lua's magic pattern characters pages = pages:gsub(pattern, return a possibly new name and appropriate code""); -- 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
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get Gets the display text for a list of language names known to Wikimediawikilink like [[A|B]] or [[B]] gives B -- local function remove_wiki_link('all' is required for North Ndebele, South Ndebele, and Ojibwastr ) local langlc = mw.ustring.lowerreturn (str:gsub( "%[%[(lang[^%[%]]*); -- lower case version for comparisons for code%]%]", name in pairsfunction(languagesl) do -- scan the list to see if we can find our language if langlc == mwreturn l:gsub( "^[^|]*|(.ustring.lower(name*)$", "%1" ) then if 2 ~= code:lengsub() and 3 ~= code:len"^%s*(.-) then -- two- or three-character codes only; extensions not supported return name; -- so return the name but not the code end return name%s*$", code"%1"); -- 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 code
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
--[[--------------------------< L S A N G U A G F E _ P A R A M E T E R J O I N >------------------------------------------------------------
Gets language name from Joins a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki,use the returned name; if not, then use the value that was provided with the language parametersequence of strings together while checking for duplicate separation characters.
When |language= contains a recognized language (either code or name), the page is assigned to the category forthat code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assignedto the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources.]]
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-characterequivalents of two-character codes: code 'ar' is recognized bit code 'ara' is not. This function supports multiple languages in the form |language=nb, Frenchsafe_join( tbl, th where the language names or codes areseparated from each other by commas. ]] local function language_parameter (langduplicate_char ) local code; -- the two- or three-character language code local name; -- the language name local language_list = {}; -- table of language names to be rendered local names_table = {}; -- table made from the value assigned to |language= local this_wiki = mw.getContentLanguage(); -- get a language object for this wiki local this_wiki_code = this_wiki:getCode() -- get this wiki's language code local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name local remap = { ['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org ['bn'] = 'Bengali', -- MediaWiki returns Bangla } names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list for _Note: we use string functions here, lang in ipairs (names_table) do -- reuse lang if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? end if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code name = mw.languagerather than ustring functions.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code end
if is_set (name) then -- if |language= specified a valid code This has considerably faster performance and should work correctly as code = lang:lower(); -- save it long as the duplicate_char is strict ASCII. The strings else in tbl may be ASCII or UTF8. name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) end ]]
if is_set (code) then -- only 2- or 3-character codes name local str = remap[code] or name''; -- override wikimedia when they misuse language codes/namesthe output string if this_wiki_code ~ local comp = code then ''; -- when the language is not the same as this wikiwhat does 'comp's languagemean? if 2 = local end_chr = 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) local trim; add_prop_cat for _, value in ipairs('foreign_lang_source_2' .. code, {code}tbl ) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template end enddo else add_maint_cat (if value == nil then value = 'unknown_lang'); -- add maint category if not already added end
table.insert (language_list, name); name if str == ''; then -- so we can reuse itif output string is empty end code str = #language_list value; -- reuse code as number of languages in assign value to it (first time through the listloop) if 2 > elseif value ~= code '' then name = table.concat if value:sub(language_list1, ' and '1) -- insert == '<space>and<space>' between two language names elseif 2 < code then language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'Special case of values enclosed in spans and<space>'other markup. name comp = table.concat value:gsub(language_list"%b<>", ', '"" ) ; -- and concatenate with 'remove html markup (<commaspan>string<space/span> ->' separatorsstring) else comp = value; end -- typically duplicate_char is sepc if this_wiki_name comp:sub(1,1) == name duplicate_char then -- is first charactier same as duplicate_char? why test first character? return ''; -- if one language and that language is this wiki's return an empty Because individual string segments often (no annotationalways?)begin with terminal punct for th end return (" " -- preceding segment: 'First element' .. wrap_msg ('languagesepc next element'.. etc? trim = false; end_chr = str:sub(-1, name)-1); -- get the last character of the output string -- otherwise wrap with 'str = str .. "<HERE(in enchr=" ..end_chr..")'" -- debug stuff? if end_chr == duplicate_char then --[[ TODOif same as separator str = str: should only return blank or name rather than full list so we can clean up the bunched parenthetical elements Language, Typesub(1, Format ]]end -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 end elseif end_chr == "]" then --if it might be wikimarkup if str:sub(-3,-< S E T _ C S 1 _ S T Y L E >---------------------------------) == duplicate_char .. "]]" then --if last three chars of str are sepc]] wikilink 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 endSet style settings for CS1 citation templates. Returns separator and postscript settings end
]] if trim then if value ~= comp then -- value does not equal comp when value contains html markup local function set_cs1_style dup2 = duplicate_char; if dup2:match(ps"%A" )then dup2 = "%" .. dup2; end -- if duplicate_char not is_set a letter then escape it value = value:gsub(ps"(%b<>) then " .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup else value = value:sub( 2, -1 ); -- unless explicitely set to somethingremove duplicate_char when it is first character end end end ps str = 'str .'. value; -- terminate add it to the rendered citation with a periodoutput string end end return '.', psstr; end --[[------------ separator --------------< I S _ G O O D _ V A N C _ N A M E >-------------------------------------------- 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 corresponding Latin character.When a name is written using a full stopnon-Latin alphabet or logogram, that name is to be transliterated into Latin characters.endThese things are not currently possible in this module so are left to the editor to do.
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
[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, 00D8–00F6, 00F8–00FF
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
Set style settings for CS2 citation templatesAt the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it herebecause the code editor gets confused between character insertion point and cursor position. Returns separator, postscript, ref settings
]]
local function set_cs2_style is_good_vanc_name (pslast, reffirst) if not is_set nil == mw.ustring.find (ps) then last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%- if |postscript%s%']*$") or nil == has not been setmw.ustring.find (first, set cs2 default ps = ''; "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%- make sure it isn%s%'t nil%.]*$") then end if not is_set add_vanc_error (ref) then -- if |ref= is not set; ref = "harv"return false; -- set default |ref=harvnot a string of latin characters; Vancouver required Romanization end; return ',', ps, reftrue; end --[[- separator is a comma-------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ endAttempts to convert names to initials in support of |name-list-format=vanc.
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/.
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is notcurrently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establishrendered styleThis function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
]]
local function get_settings_from_cite_class reduce_to_initials(psfirst) if mw.ustring.match(first, ref"^%u%u$") then return first end; -- when first contains just two upper-case letters, cite_class)nothing to do local initials = {} local sepi = 0; -- counter for number of initials if for word in mw.ustring.gmatch(cite_class == first, "citation[^%s%.%-]+") then do -- for citation templates (CS2)names separated by spaces, hyphens, or periods septable.insert(initials, psmw.ustring.sub(word, ref = set_cs2_style (ps1, ref1)) -- Vancouver format does not include full stops. i = i + 1; else -- not a citation template so CS1bump the counter sep, ps if 2 <= set_cs1_style (ps)i then break; end -- only two initials allowed in Vancouver system;if 2, quit
end
return sep, ps, ref table.concat(initials) -- return them allVancouver format does not include spaces.
end
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ Establish basic style settings to be used when rendering the citationFormats a list of people (e. Uses |mode= if set and valid or usesconfig.CitationClass from the template's #invoke: to establish styleg.authors / editors)
]]
local function set_style list_people(modecontrol, pspeople, refetal, cite_classlist_name) -- TODO: why is list_name here? not used in this function
local sep;
if 'cs2' local namesep; local format =control.format local maximum = mode then -- if this template is to be rendered in CS2 (citation) stylecontrol.maximum sep, ps, ref local lastauthoramp = set_cs2_style (ps, ref)control.lastauthoramp; elseif local text = {} if 'cs1vanc' == mode format then -- if this template is to be rendered in CS1 (cite xxx) styleVancouver-like author/editor name styling? sep= ', ps = set_cs1_style (ps)'; else --name- anything but cs1 or cs2list separator between authors is a comma sep, ps, ref namesep = get_settings_from_cite_class (ps, ref, cite_class)' '; -- get settings based on the template's CitationClasslast/first separator is a space endelse if sep = 'none;' == ps:lower() then --name- if assigned value list separator between authors is 'none' thena semicolon ps namesep = ', '; -- set to empty stringlast/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors for i,person in ipairs(people) do if 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 one = string.rep("—", ps, refn) else one = mask; sep_one = " "; end else one = person.last local first = person.first if is_set(first) then if ( "vanc" == format ) then --[if vancouver format one =[-------------------------< I S _ P D F >------------------------------------------------------------one:gsub ('%.', ''); --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 tested first = reduce_to_initials(first) --attempt to convert first name(s) to initials end end one = one .. namesep .. first endDetermines if a url has the file extension that is is_set(person.link) and person.link ~= control.page_name then one of the pdf file extensions used by = "[[MediaWiki:Common" .. person.link .. "|" .. one ..css"]] when" -- link author/editor if this page is not the author's/editor's pageapplying the pdf icon to external links end end table.insert( text, one ) table.insert( text, sep_one ) end end
returns true local count = #text / 2; -- (number of names + number of separators) divided by 2 if file extension is one of the recognized extensions, else falsecount > 0 then if count > 1 and is_set(lastauthoramp) and not etal then text[#text-2]=" & "; -- replace last separator with ampersand text end text[#text]= nil; -- erase the last separator end local function is_pdf result = table.concat(urltext) -- construct list return url:match 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 ..pdf$') or url:match ('%.PDF$') or url:match ('%.pdfcfg.messages[%?#]') or url:match (et al'%.PDF[%?#]; -- we');ve go a last-first list and etal so add et al. end return result, count
end
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
Applies css style to |format=namelist is one of the contributor-, |chapterauthor-format=, etc. Also emits an error message if the format parameter doesnot have a matching url parameteror editor-name lists chosen in that order. If the format parameter is not set and the url contains a file extension thatyear is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) withthe appropriate stylingYear 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
end
end
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parentheses, resize
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
return format;
end
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
Returns a number that defines This function never sets the number of names displayed for author and editor name lists and a boolean flagto false but returns it's previous state because it may have been set byto indicate when et al. should be appended to previous passes through this function or by the name list.parameters |display-authors=etal or |display-editors=etal
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number andthe previous state of the 'etal' flag (false by default but may have been set to true if the name list containssome variant of the text 'et al.').]]
When the value assigned to |display-xxxxors= is the keyword 'local function name_has_etal (name, etal', return a number that is one greater than thenumber of authors in the list and set the 'etal' flag true. This will cause the list_people(nocat) to display all ofthe names in the name list followed by 'et al.'
In all other cases, returns if is_set (name) then -- name can be nil and the previous state of the 'etal' flag.in which case just return inputs: max: A local etal_pattern = "['DisplayAuthors';,] or A? *['DisplayEditors\"']; *%f[%a number or some flavor of etal count: #a or #e list_name: ][Ee][Tt] *[Aa][Ll][%.\"'authors]*$" -- variations on the ' or 'editorset al'theme etal: author_etal or editor_etal local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. local function get_display_authors_editors (max, count, list_name, etal) if is_set (max) then if 'etal' == maxname:lowermatch ():gsub("[ '%.]", ''etal_pattern) then -- the :gsub() portion makes 'etal' from a variety of 'variants on et al.' spellings and stylings max name = count + 1name:gsub (etal_pattern, ''); -- number of authors + 1 so display all author name plus et al.if found, remove etal = true; -- overrides value set flag (may have been set previously here or by extract_names|display-authors=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat ('etal'); -- and add a category if not already added end elseif maxname:match ('^%d+$'others_pattern) then -- if is a string of numbersnot 'et al.', then 'and others'? max name = tonumber name:gsub (maxothers_pattern, ''); -- make it a numberif found, remove if max >etal = count then true; -- if set flag (may have been set previously here or by |display-xxxxorsauthors=etal) if not nocat then -- no categorization for |vauthors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_edetal', cfg.special_case_translation [list_name]); -- and add a category if not already added
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; as if |display-xxxxors= had not been set
end
end
return maxname, etal; --
end
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------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.
Adds page to Category:CS1 maint: extra text if This function emits an error message when there is a |pagefirstn= or without a matching |pageslastn= has what appears to be some form of p. or pp. abbreviation When there are 'holes' in the first characters list of the parameter contentlast names, |last1= and |last3=are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
check Page and Pages for extraneous p, pWhen an author or editor parameter contains some form of 'et al.', pp, and ppthe 'et al. at start of ' is stripped from the parameter value:and a flag (etal) returned good patternthat will cause list_people() to add the static 'et al.' text from Module: Citation/CS1/Configuration. This keeps '^P[^%et al.P%l]' matches when |out of the template's metadata. When this occurs, the page(s)= begins PX or P# but not Px where x and X are letters and # is added to a dgiit bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PPmaintenance category.
]]
local function extra_text_in_page_check extract_names(pageargs, list_name) local good_pattern names = '^P[^%.Pp]'{}; -- table of names local last; -- individual name components local first; local link; local mask; local i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; -- ok used to begin with uppercase P: P7 (pg 7 count the number of section P) but not p123 times we haven't found a |last= (page 123) TODO: add Gg or alias for PG authors, |editor-last or Pg?alias for editors) local bad_pattern etal= '^[Pp]?[Pp]%false; -- return value set to true when we find some form of et al.?[ %d]';in an author parameter
if not pagelocal err_msg_list_name = list_name:match (good_pattern"(%w+) and (page:match (bad_patternList") .. 's list'; -- modify AuthorList or page:match EditorList for use in error messages if necessary while true do last = select_one(args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters'^, i ); -- search through args for name components beginning at 1 first = select_one( args, cfg.aliases[Pplist_name .. '-First']ages?, 'redundant_parameters', i ); link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) then; add_maint_cat mask = select_one(args, cfg.aliases[list_name .. '-Mask'], 'extra_textredundant_parameters', i ); endend
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
if first and not last then --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- split apart if there is a firstn without a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubledmatching lastnparentheses to also have commas; in the old version of the code, the doubled parnetheses were included in therendered citation and in the metadata table. Individual author names may be wikilinked |vauthors=Jones AB, [[Einsert( z. B. White|White EB]]message_tail, { set_error((Black'first_missing_last', Brown{err_msg_list_name, and Co.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 local function get_v_name_table (vparam, output_table, output_link_table) local name_table if 2 <= mw.text.split(vparam, "%s*,%s*"); count then -- two missing names are separated by commasand we give up local wl_type, label, link break; -- wl_type not used here; just normal exit or there is a place holder local i = 1two-name hole in the list;can't tell which while name_table[i] do end if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then else -- first segment of corporate we have last with one or more commas; this segment has the opening doubled parenswithout a first local name if is_set (link) and false == name_table[i];link_param_ok (link) then i=i+1; -- bump indexer to next segment while name_table[i] dothis test here in case link is missing last name = name table.insert( z. message_tail, { set_error( 'bad_paramlink', ' .. name_table[i]; -- concatenate with previous segments if name_table[i]list_name:match ('^.*"(%w+)%List"):lower()$.. '-link'.. i )}) then -- if this table member has the closing doubled parens break; -- and done reassembling so end i=i+1url or wikilink in author link; -- bump indexer
end
table.insert (output_tablenames[n] = {last = last, first = first, link = link, mask = mask, name)corporate=false}; -- and add corporate this name to the output table table.insert our names list (output_link_table, ''corporate for |vauthors= only); -- no wikilink else wl_type, label, link n = is_wikilink (name_table[i])n + 1; -- wl_type is: 0, no wl (text point to next location in label variable); 1, [[D]]; 2, [[L|D]] the names table.insert (output_table, label); -- add this name if 1 == wl_type count then -- if the previous name was missing table.insert (output_link_tablez.message_tail, { set_error( 'missing_name', {err_msg_list_name, label); i-- simple wikilink [[D]] else table.insert (output_link_table1}, linktrue ) } ); -- no wikilink or [[L|D]]; add this link if there is one, else empty stringerror 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 output_tablenames, etal; -- all done, return our list of names
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for
any of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value to
the identifier list. Emits redundant error message is more than one alias exists in args
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------]]
This local function extracts author / editor names from |vauthorsextract_ids( args ) local id_list = or |veditors= and finds matching |xxxxor{}; --maskn= andlist of identifiers found in args|xxxxor for k, v in pairs( cfg.id_handlers ) do --linknk is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table v = in select_one( args, v. It then returns parameters, 'redundant_parameters' ); -- v.parameters is a table of assembled names just as extract_namesaliases for k; here we pick one from args if present if is_set(v) does.then id_list[k] = v; end -- if found in args, add identifier to our list end return id_list;end
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.--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
Supports generational suffixes Jr, 2nd, 3rd, 4th–6thTakes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.inputs: id_list – table of identifiers built by extract_ids() options – table of various template parameter values used to modify some manually handled identifiers
]]
local function parse_vauthors_veditors build_id_list(argsid_list, vparam, list_nameoptions ) local names = {}; -- table of names assembled from |vauthors=new_list, |author-maskn=, |author-linkn= local v_name_table = {}; local v_link_table handler = {}; -- 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;
vparam, etal function fallback(k) return { __index = name_has_etal function(vparamt, etali) return cfg.id_handlers[k][i] end } end; for k, truev in pairs( id_list ); do -- find and remove variations on et alk is uc identifier name as index to cfg.id_handlers; e.g. do not categorize (do it here because et alcfg. might have id_handlers['ISBN'], v is a period)table -- fallback to read-only cfg v_name_table handler = get_v_name_table setmetatable(vparam{ ['id'] = v }, v_name_table, v_link_tablefallback(k) ); -- names are separated by commas if handler.mode == 'external' then for i table.insert( new_list, {handler.label, v_name in ipairsexternal_link_id(v_name_tablehandler ) do} ); if v_name:match (elseif handler.mode == 'internal'^%then table.insert(%new_list, {handler.label, internal_link_id(.+%handler )%} )$; elseif handler.mode ~= 'manual') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection first = error( cfg.messages['unknown_ID_mode'] ); -- set to empty string for concatenation and because it may have been set for previous author/editor last elseif k == v_name:match ('^%(%DOI' then table.insert(new_list, {handler.label, doi(v, options.+DoiBroken )%} )%)$; elseif k == 'ARXIV') -- remove doubled parnthesesthen corporate = true; -- flag used in list_peopletable.insert( new_list, {handler.label, arxiv(v, options.Class ) } ); elseif stringk == 'ASIN' then table.findinsert(v_namenew_list, "%s"{handler.label, amazon( v, options.ASINTLD ) } ) ; elseif k == 'LCCN' then if v_name:findtable.insert('[;%new_list, {handler.]'label, lccn( v ) } ) then -- look for commonly occurring punctuation characters; add_vanc_error ( elseif k == 'OL' or k == 'punctuationOLA'then table.insert( new_list, {handler.label, openlibrary( v ) } ); end local lastfirstTable elseif k == {}'PMC' then lastfirstTable = mwtable.textinsert( new_list, {handler.splitlabel, pmc(v_namev, "%s"options.Embargo ) } ); elseif k == 'PMID' then first = table.removeinsert( new_list, {handler.label, pmid(lastfirstTablev ) } ); -- removes and returns value of last element in table which should be author intials elseif k == 'ISMN' then if is_suffix table.insert( new_list, {handler.label, ismn(firstv ) then -- if a valid suffix} ); suffix elseif k == first -- save it as a suffix and'ISSN' then first = table.removeinsert( new_list, {handler.label, issn(lastfirstTablev ) } ); -- get what should be the initials from the table end -- no suffix error message here because letter combination may be result of Romanization; check for digits? elseif k == 'EISSN' then last = table.concatinsert( new_list, {handler.label, issn(lastfirstTablev, " "true ) } ) ; -- returns a string that is the concatenation of all other names that are not initialstrue distinguishes eissn from issn if mw.ustring.match (last, elseif k == '%a+%s+%u+%s+%a+ISBN') then add_vanc_error local ISBN = internal_link_id('missing comma'handler ); -- matches last II last; the case when a comma is missing end if mwnot check_isbn( v ) and not is_set(options.ustring.match (v_name, ' %u %u$'IgnoreISBN) then -- this test is in the wrong place TODO: move or replace with a more appropriate test add_vanc_error ISBN = ISBN .. set_error('namebad_isbn', {}, false, " ", "" ); -- matches a space between two intiials
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
first = error( cfg.messages['unknown_manual_ID'] ); -- 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
function comp( a, b ) -- used in following table.sort() return namesa[1] < b[1]; end table.sort( new_list, etalcomp ); -- all done for k, v in ipairs( new_list ) do new_list[k] = v[2]; end return our list of namesnew_list;
end
--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities.
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the source of the author name list orappropriate contentselect one of |editors=, |editorn= when it shouldn't. See https:/ editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name listphabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29
Only one of these appropriate three will be used. The hierarchy isTODO: |authorn= (and aliases) highest and |authors= lowest move the replacement patterns andreplacement values into a table in /Configuration similar to the invisiblecharacters table?similarly, |editorn= (and aliases) highest and |editors= lowest]]
When looking for |authornlocal 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</ |editornspan>', "'s"); -- replace {{'s}} template with simple apostrophe-s value = parametersvalue:gsub ('‍\226\128\138\039\226\128\139', test |xxxxor1"'"); -- replace {{'}} with simple apostrophe value = and |xxxxor2value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11) value = value:gsub (and all of their aliases' ', ' '); -- replace entity with plain space value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space value = value:gsub ('‍', ''); stops after the second -- remove ‍ entitiestest which mimicks the test used in extract_names value = value:gsub ('[\226\128\141\226\128\139]', '') when looking for a hole in the author name list. There may be a better -- remove zero-width joiner, zero-width spaceway to do this value = value:gsub ('[\194\173\009\010\013]', I just haven't discovered what that way is.'); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space return value;end
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate--[[--------------------------< C O I N S >-------------------------------------------------------------------- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
]]
local function select_author_editor_source COinS(vxxxxorsdata, xxxxors, args, list_nameclass)local lastfirst = false; if select_one( args, cfg.aliases[list_name .. '-Lasttable'], 'none', 1 ~= type(data) or -- do this twice incase we have a |first1nil = without a |last1=; this ...next(data) then select_one( args, cfg.aliases[list_name .. return '-First']; end for k, 'none', 1 v in pairs (data) or do -- ... also catches spin through all of the case where |first= is used with |vauthors=metadata parameter values select_one( args, cfg.aliases[list_name .. if '-LastID_list'], ~= k and 'noneAuthors', 2 ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) or select_one( args, cfg.aliases data[list_name .. '-First'k], 'none', 2 = coins_cleanup (v) then; lastfirst=true; end
end
local 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 (vxxxxorsvalue) and true then rawset( self, #self+1, table.concat{ key, '== lastfirst', mw.uri.encode( remove_wiki_link( value ) ) } ) or -- these are the three error conditions; end end }); if in_array (is_set class, {'arxiv', 'journal', 'news'}) or (in_array (vxxxxorsclass, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set (xxxxorsdata.Periodical)) or (true 'citation' == lastfirst class and is_set (xxxxorsdata.Periodical) and not is_set (data.Encyclopedia)) then local err_nameOCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier if 'AuthorListarxiv' == 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' == list_name class then OCinSoutput["rft.genre"] = "unknown"; -- figure out which name should be 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 error messagebook 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"; err_name -- book metadata identifier if 'report' = = class or 'authortechreport'== 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
err_name if 'map' == class or 'interview' == class then OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview else OCinSoutput["rft.genre"] = 'editorbook'; -- 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'} tableOCinSoutput["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.insertTitle; -- dissertation ( zalso patent but that is not yet supported) OCinSoutput["rft.degree"] = data.message_tailDegree; -- 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, { set_errorv in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? if k == 'redundant_parametersISBN',then v = clean_isbn( v ) end {err_name local id = cfg.id_handlers[k]. COinS; if string.sub( id or "", 1, 4 ) == 'info'then -name-list parameters'for ids that are in the info:registry OCinSoutput["rft_id"] = table.concat{ id, "/", v }; elseif string.sub (id or "", 1, true 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords OCinSoutput[ id ] = v; elseif id then -- when cfg.id_handlers[k].COinS is not nil OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v } ); -- add error messageothers; 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.id_handlers[k].COinS; if true k == lastfirst 'ISBN' then return value = clean_isbn( v ); else value = v; end if string.sub( id or "", 1 , 4 ) == 'info' then OCinSoutput["rft_id"] = table.concat{ id, "/", v }; else OCinSoutput[ id ] = 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(first) then -- return a number indicating which set these COinS values if |first= and |last= specify the first author name source to OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation elseif is_set(last) then OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise usethis form for the first name end else -- for all other authors if is_set (vxxxxorslast) and is_set(first) then return 2 end OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation if elseif is_set (xxxxorslast) then return 3 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 ); return table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); --such as "Z39.88- no authors so 2004" return 1table.concat(OCinSoutput, "&"); this allows missing author name test to run in case there is a first without last
end
--[[--------------------------< G E T _ I S O 6 3 9 _ V A L I C O 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 numberof allowable values (yes, y, true, no, etc). When the Validates language names provided in |language= parameter value has if not been assigned a value (missing or emptyin the source template) the function returns truean ISO639-1 code. If Handles the parameter value special case that is one of the list of allowed values returnsNorwegian wheretrue; else, emits an error message and returns falseISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
]]Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimediauses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned alongwith the code. When there is no match, we return the original language name string.
local function is_valid_parameter_value (value, name, possible) if not is_set mw.language.fetchLanguageNames(value) then will return true; a list of languages that aren't part of ISO639-1. Names that aren't ISO639- an empty 1 but that are includedin the list will be found if that name is provided in the |language= parameter is ok elseif in_array(value:lower(). For example, if |language=Samaritan Aramaic, possible) then return true;that name will be else table.insert( z.message_tail, { set_error( found with the associated code 'invalid_param_valsam', {name, value}, true ) } ); -not an ISO639- 1 code. When names are found and the associated code is not an allowed value so add error messagetwo characters, this function return false endendreturns only the Wikimedia language name.
Adapted from code taken from Module:Check ISO 639-1.
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------]]
This local function terminates get_iso639_code (lang) if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized end local languages = mw.language.fetchLanguageNames(mw.getContentLanguage():getCode(), 'all') -- get a name list of language names known to Wikimedia -- (author'all' is required for North Ndebele, contributorSouth Ndebele, editorand Ojibwa) with a separator character 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 language if langlc == mw.ustring.lower(name) then if 2 ~= code:len(sepc) and a spacethen -- ISO639-1 codes onlywhen return name; -- so return the last character is name but not a sepc character or when the last three characters are code end return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code end end return lang; -- not sepc followed by twovalid language; return language in original case and nil for ISO639-1 codeendclosing square brackets (close of a wikilink)--[[--------------------------< 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. When either of these If a code is truevalid use the returned name; if not, then use the name_list is terminated value that was provided with asingle space characterthe 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') andNorwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appearsthat 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 function terminate_name_list (name_list, sepc) if (string.sub (name_list,-3Because Norwegian Bokmål is the most common language variant,Media wiki has been modified to return Norwegian Bokmål for ISO639-1) == sepc .. code 'no'. ') then -- if already properly terminatedHere we undo that and return name_list; -- just return the name list elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]Norwegian') then -- if last name in list ends with sepc char return name_list .when editors use |language=no. " "; -- We presume that editors don't add another else return name_list .. sepc .know about the variants or can't descriminate between them. ' '; -- otherwise terninate the name list endend
See Help talk:Citation Style_1#An ISO 639-1 language name test
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------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.
returns This function supports multiple languages in the concatenation of form |language=nb, French, th where the formatted volume and issue parameters as a single string; or formatted volumeor formatted issue, language names or an empty string if neither codes are setseparated from each other by commas.
]]
local function language_parameter (lang)
local code; -- the ISO639-1 two character code
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_table = {}; -- table made from the value assigned to |language=
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
for _, lang in ipairs (names_table) do -- reuse lang
if lang:match ('^%a%a%-') or 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
if lang:match ('^zh-') then
name = mw.language.fetchLanguageName( lang:lower(), lang:lower() );
else
name = mw.language.fetchLanguageName( lang:lower(), mw.getContentLanguage():getCode() ); -- get ISO 639-1 language name if Language is a proper code
end
end
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) if not is_set (volume) and not is_set (issuename) then return ''; end -- if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then if is_set (volume) and is_set (issue) thenLanguage specified a valid ISO639-1 code return wrap_msg ('vol-no', {sepc, volume, issue}, code = lang:lower); elseif is_set (volume) then return wrap_msg ('vol', {sepc, volume}, lower); -- save it
else
return wrap_msg name, code = get_iso639_code ('issue', {sepc, issue}, lowerlang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
end local vol = ''; if is_set (volumecode) then if (4 < mw.ustring.len(volume)) 'no' == code thenname = '挪威语' end; -- override wikimedia when code is 'no' vol if 'zh' ~= substitute code and not code:match (cfg.messages['j^zh-vol']) then -- English not the language add_prop_cat ('foreign_lang_source', {sepcname, volumecode}); end
else
vol = substitute add_maint_cat (cfg.presentation['vol-boldunknown_lang'], {sepc, hyphen_to_dash(volume)}); -- 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 is_set 2 >= code then name = table.concat (issuelanguage_list, '及') -- insert '<space>及<space>' between two language names elseif 2 < code then return vol language_list[code] = '及' .. substitute (cfg.messageslanguage_list[code]; -- prepend last name with 'j-issue及<space>'] name = table.concat (language_list, issue'，'); -- and concatenate with '<comma><space>' separators
end
return vol(" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
Set style settings for CS1 citation templates. Returns separator and postscript settings ]] local function set_cs1_style (ps) if not is_set (ps) then --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-------------------------------------unless explicitely set to something ps = '.'; --terminate the rendered citation with a period end return '.', ps; --separator is a full stopend
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.The return order is: page, pages, sheet, sheets--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
Singular has priority over plural when both are providedSet style settings for CS2 citation templates.Returns separator, postscript, ref settings
]]
local function format_pages_sheets set_cs2_style (pageps, pages, sheet, sheets, cite_class, origin, sepc, nopp, lowerref) if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators if not is_set (sheetps) then -- if 'journal' |postscript=has not been set, set cs2 default ps = origin then return '', '', wrap_msg ('j; --sheetmake sure it isn', sheet, lower), '';t nil else return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; end elseif if not is_set (sheetsref) then -- if 'journal' |ref=is not set ref = origin then return '', '', '', wrap_msg ('j"harv"; --sheets', sheets, lower); else return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower); end endset default |ref=harv
end
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin); if is_set (page) then if is_journal then return substitute (cfg.messages['j-page(s)'], page), '', ''ps, ''ref; elseif not nopp then return substitute (cfg.messages['p -prefix'], {sepc, page}), '', '', ''; else return substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; end elseif is_set(pages) then if is_journal then return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; elseif tonumber(pages) ~= nil and not nopp then -- if pages separator is only digits, assume a single page number return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; elseif not nopp then return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; else return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; end end return '', '', '', ''; -- return empty stringscomma
end
--[[--------------------------< 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 |mode=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------is not set or when its value is invalid, use config.CitationClass and parameter values to establishrendered style.
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...)archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allowunwitting readers to do.]]
When the archive.org url does not have a complete timestamplocal function get_settings_from_cite_class (ps, ref, archive.org chooses a snapshot according to its ownalgorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results. This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and|archive-date= and an error message when:cite_class) |archive-url= holds an archive.org save command urllocal sep; |archive-url= is an archive.org url that does not have a complete timestamp if (YYYYMMDDhhmmss 14 digits) in the correct placeotherwise returns |archive-urlcite_class = and |archive-date= There are two mostly compatible archive.org urls: //web.archive.org/<timestamp>... -- the old form //web.archive.org/web/<timestamp>... "citation") then -- the new form 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_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)we don't check for these specific flags but we do check the form. This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modifiedarchive url: for save command errors, return undated wildcard citation templates (/*/CS2) for timestamp errors when the timestamp has a wildcard sep, return the url unmodified for timestamp errors when the timestamp does not have a wildcardps, return with timestamp limited to six digits plus wildcard (/yyyymm*/) ]ref =] local function archive_url_check set_cs2_style (urlps, dateref) local err_msg = ''; -- start with the error message empty local path, timestamp, flag; else -- portions of the archive.or url if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine urla citation template so CS1 return urlsep, dateps = set_cs1_style (ps); -- not an archive.org archive, return ArchiveURL and ArchiveDate
end
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page err_msg = 'save command'; url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL elseif url:match('//liveweb%.archive%.org/') then err_msg = 'liveweb'; else path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here err_msg = 'timestamp'; if '*' ~= flag then url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat) 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, date; -- return archiveURL and ArchiveDate end end -- if here, something not right so table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}sep, true ) } ); -- add error message and if is_set (Frame:preprocess('{{REVISIONID}}')) then return ''ps, ''; ref -- return empty strings for archiveURL and ArchiveDate else return url, date; -- preview mode so return archiveURL and ArchiveDate endthem all
end
--[[--------------------------< S E T _ 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 parameter. If the content has a string of characters and digits followed by an equalsign, compare the alphanumeric string Establish basic style settings to be used when rendering the list of cs1|2 parameterscitation. If found, then the string is possibly aparameter that is missing its pipe: {{cite ... Uses |titlemode=Title access-date=2016-03-17}}if set and valid or usescs1|2 shares some parameter names with xml/html atributes: class=, title=, etcconfig. To prevent false positives xml/htmltags are removed before CitationClass from the search. If a missing pipe is detected, this function adds the missing pipe maintenance categorytemplate's #invoke: to establish style.
]]
local function missing_pipe_check set_style (valuemode, ps, ref, cite_class) local capturesep; value = value:gsub (if '%b<>cs2', ''); == mode then -- remove xml/html tags because attributes: class=if this template is to be rendered in CS2 (citation) style sep, ps, titleref =set_cs2_style (ps, etc ref); capture elseif 'cs1' == value:match ('%s+mode then -- if this template is to be rendered in CS1 (%a[%a%d]+cite xxx)%s*style sep, ps ='set_cs1_style (ps) ; else -- anything but cs1 or value:match cs2 sep, ps, ref = get_settings_from_cite_class ('^(%a[%a%d]+)%s*='ps, ref, cite_class); -- find and categorize parameters with possible missing pipesget settings based on the template's CitationClass end if capture and validate 'none' == ps:lower(capture) then -- if the capture assigned value is a valid parameter name'none' then add_maint_cat (ps = 'missing_pipe'); -- set to empty string end return sep, ps, refend
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
--Determines if a url has the file extension that is one of the pdf file extensions used by [[--------------------------< C I T A T I O N 0 >------------------------------------------------------------MediaWiki:Common.css]] whenapplying the pdf icon to external links.
This returns true if file extension is the main function doing the majority one of the citation formatting.recognized extension, else false
]=]
local function citation0is_pdf ( config, argsurl) --return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[ Load Input Parameters The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. %?#]] local A = argument_wrapper( args ?'); local i end
-- Pick out the relevant fields from the arguments. Different citation templates [[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ define different field names for the same underlying things.
Applies css style to |format=, |chapter-- set default format=, etc. Also emits an error message if the format parameter values defined by |mode= doesnot have a matching url parameter. If the format parameter is not set and the url contains a file extension that local Mode = A[is recognized as a pdf document by MediaWiki'Mode']; if not is_valid_parameter_value s commons.css, this code will set the format parameter to (Mode, 'mode', cfg.keywords['mode']PDF) thenwith Mode = ''; endthe appropriate styling.
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 style_format (A['Vauthors']format, A['Authors']url, argsfmt_param, 'AuthorList'url_param); if 1 == selected then a, author_etal = extract_names is_set (args, 'AuthorList'format); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=then elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might be a, author_etal = parse_vauthors_veditors wrap_style (args, args.vauthors, 'AuthorListformat', format); -- fetch author list from |vauthors=add leading space, |author-linkn=parenthases, and |author-maskn=resize elseif 3 == selected then Authors = A['Authors']; -- use content of |authors= if 'authors' == A:ORIGINnot is_set ('Authors'url) then -- but add a maint cat if the parameter is |authors format = add_maint_cat format .. set_error('authorsformat_missing_url', {fmt_param, url_param} ); -- 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; -- so that |display-authors=etal not requiredadd an error message
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
return format;
end
local Others = --[[--------------------------< G E T _ D I S P L A Y _ A['Others'];U T H O R S _ E D I T O R S >------------------------
local editor_etal; local e = {}; -- editors list from |editor-lastn= / |Returns a number that may or may not limit the length of the author or editor-firstn= pairs or |veditors= local Editors;name lists.
do -- When the value assigned 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= / |editordisplay-lastn= / |editor-firstn=, |editor-linknauthors=is a number greater than or equal to zero, return the number and |editor-maskn= elseif 2 == selected then NameListFormat = the previous state of the 'vancetal'; -- override whatever |flag (false by default but may have been set to true if the name-list-format= might becontains e, editor_etal = parse_vauthors_veditors (args, argssome variant of the text 'et al.veditors, 'EditorList'); -- fetch editor list from . When the value assigned to |veditors=, |editordisplay-linknauthors=is the keyword 'etal', return a number that is one greater than thenumber of authors in the list and |editor-maskn= elseif 3 == selected then Editors = A[set the 'Editorsetal']; -- use content flag true. This will cause the list_people() to display all of |editors= add_maint_cat (the names in the name list followed by 'editorset al.'); -- but add a maint cat because use of this parameter is discouraged end end
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs local Translators; -- assembled translators name list t = extract_names (argsIn all other cases, returns nil and the previous state of the 'TranslatorListetal'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=flag.
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 c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairsfunction get_display_authors_editors (max, count, list_name, etal) local Contributors; -- assembled contributors name listif is_set (max) then local Contribution if 'etal' == Amax:lower():gsub("['Contribution'%.]; if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites c = extract_names the :gsub(args, ) portion makes 'ContributorListetal'); -- fetch contributor list from |contributorna variety of 'et al.' spellings and stylings max = / |contributorcount + 1; -lastn=, -firstnnumber of authors + 1 so display all author name plus et al. etal =, true; -linkn=, -maskn= if 0 < #c then if not is_set overrides value set by extract_names(Contribution) then -- |contributor= requires |contribution= table.insert elseif max:match ( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution^%d+$')}); then -- add missing contribution error messageif is a string of numbers c max = {}tonumber (max); -- blank the contributors' table; make it is used as a flag later endnumber if 0 max >= count and 'authors' == #a list_name then -- AUTHORS ONLY -- if |contributor= requires |authordisplay-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( 'contributor_missing_required_paraminvalid_param_val', {'authordisplay-'.. list_name, max}, true )}); -- add missing author error message c max = {}nil; -- blank the contributors' table; it is used as a flag later endunset
end
else -- if not a book cite if select_one (args, cfg.aliases['ContributorList-Lastelseif '], authors'redundant_parameters', 1 ) == list_name then -- are there contributor name list parameters? table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error messageAUTHORS ONLY need to clear implicit et al category end Contribution max = nilcount + 1; -- unsetnumber of authors + 1
end
return max, etal;
end
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------list-format']) then -- only accepted value for this parameter is 'vanc'--------------------- NameListFormat Adds page to Category:CS1 maint: extra text if |page= or |pages= ''; -- anything else, set has what appears to empty stringbe some form of p. or pp. endabbreviation in the first characters of the parameter content.
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: local Year = Agood pattern: '^P[^%.P%l]'Yearmatches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit bad pattern: '^[Pp]; local PublicationDate = A[Pp]'PublicationDate'matches matches when |page(s)= begins pp or pP or Pp or PP ]]; local OrigYear = A['OrigYear'];function extra_text_in_page_check (page) -- local Date good_pattern = A'^P[^%.P%l]'Date']; local LayDate good_pattern = A'^P[^%.Pp]'LayDate']; -------------------- --ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?--------------------------- Get title data local Title bad_pattern = A'^['Title'Pp]; local ScriptTitle = A['ScriptTitle'Pp]; local BookTitle = A['BookTitle']; local Conference bad_pattern = A['Conference']; local TransTitle = A^['TransTitle'Pp]; local TitleNote = A?['TitleNote'Pp]; local TitleLink = A%.?['TitleLink'%d]; link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
local Chapter = Aif not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?'Chapter'];)) then local ScriptChapter = A[ add_maint_cat ('ScriptChapterextra_text']); local ChapterLink end-- = A if Page:match ('^[Pp]?[Pp]%.?[ %d]'ChapterLink) or Page:match ('^[Pp]; ages?[ %d]') or-- deprecated as a parameter but still used internally by cite episode local TransChapter = A Pages:match ('^[Pp]?['TransChapter'Pp]; local TitleType = A%.?[%d]'TitleType) or Pages:match ('^[Pp]; local Degree = Aages?[%d]'Degree'];) then local Docket = A[-- add_maint_cat ('Docketextra_text']);-- local ArchiveFormat = A['ArchiveFormat'];endend
local ArchiveDate;
local ArchiveURL;
ArchiveURL, ArchiveDate = archive_url_check (A--[['ArchiveURL'], --------------------------< P A['ArchiveDate']) local DeadURL = R S E _ V A['DeadURL'] if not is_valid_parameter_value (DeadURL, 'deadU T H O R S _ V E D I T O R S >----------------------------url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string end
local URL This function extracts author / editor names from |vauthors= A['URL'] local URLorigin or |veditors= A:ORIGIN('URL'); -and finds matching |xxxxor- get name of parameter that holds URL local ChapterURL maskn= A['ChapterURL'];and local ChapterURLorigin |xxxxor-linkn= A:ORIGINin args. It then returns a table of assembled names just as extract_names('ChapterURL'); -- get name of parameter that holds ChapterURLdoes. local ConferenceFormat Author / editor names in |vauthors= A['ConferenceFormat']; local ConferenceURL or |veditors= A['ConferenceURL'];must be in Vancouver system style. Corporate or institutional names local ConferenceURLorigin = A:ORIGINmay sometimes be required and because such names will often fail the is_good_vanc_name('ConferenceURL'); -- get name of parameter that holds ConferenceURLand other format compliance local Periodical = A['Periodical']; local Periodical_origin = A:ORIGINtests, are wrapped in doubled paranethese (('Periodical'corporate name)); -- get to suppress the name of format tests. This function sets the periodical parametervancouver error when a reqired comma is missing and when there is a space between an author's initials. ]]
local Series = A['Series']; function parse_vauthors_veditors (args, vparam, list_name) local Volumenames = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= local Issuev_name_table = {}; local Pageetal = false; -- return value set to true when we find some form of et al. vauthors parameter local Pageslast, first, link, mask; local Atcorporate = false;
if in_array vparam, etal = name_has_etal (config.CitationClassvparam, etal, cfg.templates_using_volumetrue) then Volume = A['Volume']; end -- conference & map books find and remove variations on et al. do not support issuecategorize (do it here because et al. might have a period) if in_array vparam:find (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', %[%['map'}) and not is_set or vparam:find (Periodical))then Issue = A['Issue'%]%]; end local Position = ''; if not in_array (config.CitationClass, cfg.templates_not_using_page) then -- no wikilinking vauthors names Page = A['Page']; Pages = hyphen_to_dashadd_vanc_error ( A['Pages'] ); At = A['At'];
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
local Edition for i, v_name in ipairs(v_name_table) do if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection first = A['Edition']; -- set to empty string for concatenation and because it may have been set for previous author/editor local PublicationPlace last = A[v_name:match ('PublicationPlace^%(%((.+)%)%)$']) local Place corporate = A['Place']true; elseif string.find(v_name, "%s") then lastfirstTable = {} lastfirstTable = mw.text.split(v_name, "%s") local PublisherName first = A['PublisherName']table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials local RegistrationRequired last = A['RegistrationRequired'];table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials if not is_valid_parameter_value mw.ustring.match (RegistrationRequiredlast, 'registration%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, cfg.keywords ['yes_true_y%u %u$']) then add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials RegistrationRequiredend else first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor last =nilv_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
local SubscriptionRequired = A['SubscriptionRequired']; if is_set (first) and not is_valid_parameter_value mw.ustring.match (SubscriptionRequired, 'subscription'first, cfg.keywords ['yes_true_y']"^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else SubscriptionRequired=niladd_vanc_error ();
end
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', 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 names, etal; -- all done, return our list of names
end
local UrlAccess = --[[--------------------------< S E L E C T _ A['UrlAccess']; if not is_valid_parameter_value (UrlAccess, 'urlU T H O R _ E D I T O R _ S O U R C E >-----------------------access', cfg.keywords ['url-access']) then UrlAccess = nil; end if not is_set(URL) and is_set(UrlAccess) then UrlAccess = nil; table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } ); end
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliasesSelect one of |authors=, these are much the same so if both are set table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message SubscriptionRequired |authorn= nil; -- unset; prefer / |accesslastn / firstn= over , or |subscriptionvauthors= end if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not as the source of the same but contradictory so if both are setauthor name list or table.insert( z.message_tailselect one of |editors=, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url|editorn= / editor-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message RegistrationRequired lastn= nil; / |editor-- unset; prefer |accessfirstn= over or |registrationveditors= endas the source of the editor name list.
local ChapterUrlAccess = A['ChapterUrlAccess']; if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', cfgOnly one of these appropriate three will be used.keywords ['url-access']) then -- same as url-access ChapterUrlAccess The hierarchy is: |authorn= nil; end if not is_set(ChapterURLand aliases) highest and is_set(ChapterUrlAccess) then ChapterUrlAccess |authors= nil;lowest and table.insert( z.message_tailsimilarly, { set_error|editorn= ( 'param_access_requires_param', {'chapter-url'}, true and aliases) } ); endhighest and |editors= lowest
local Via When looking for |authorn= A['Via']/ |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases);stops after the second local AccessDate = A['AccessDate'];test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better local Agency = A[way to do this, I just haven'Agency'];t discovered what that way is.
local Language = A['Language']; local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local DoiBroken = A['DoiBroken']; local ID = A['ID']; local ASINTLD = A['ASINTLD']; local IgnoreISBN = A['IgnoreISBN']; if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-Emits an error', cfgmessage when more than one xxxxor name source is provided.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 In this function, vxxxxors = extract_ids( args )vauthors or veditors; local ID_access_levels xxxxors = extract_id_access_levels( args, ID_list );authors or editors as appropriate.
local Quote = A['Quote'];]
local LayFormat = A['LayFormat'];function select_author_editor_source (vxxxxors, xxxxors, args, list_name) local LayURL lastfirst = A['LayURL']false; local LaySource = Aif select_one( args, cfg.aliases[list_name .. 'LaySource-Last']; local Transcript = A[, 'Transcriptnone'];, 1 ) or -- do this twice incase we have a first 1 without a last1 local TranscriptFormat = A select_one( args, cfg.aliases[list_name .. 'TranscriptFormat-Last']; local TranscriptURL = A[, 'TranscriptURLnone'] , 2 ) then local TranscriptURLorigin lastfirst= A:ORIGIN('TranscriptURL')true; -- get name of parameter that holds TranscriptURL end
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions (is_set (vxxxxors) and is_set (xxxxors)) or (true == lastfirst and is_set (xxxxors)) then local LastAuthorAmp err_name; if 'AuthorList' == list_name then -- figure out which name should be used in error message err_name = 'author'; else err_name = A['LastAuthorAmpeditor']; if not is_valid_parameter_value end table.insert(LastAuthorAmpz.message_tail, { set_error( 'last-author-ampredundant_parameters', cfg {err_name ..keywords ['yes_true_y-name-list parameters']}, true ) } ) then; LastAuthorAmp = nil; -- set to empty stringadd error message end
local no_tracking_cats if true = A['NoTracking']= lastfirst then return 1 end; -- return a number indicating which author name source to use if is_set (vxxxxors) then return 2 end; if not is_valid_parameter_value is_set (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']xxxxors) thenreturn 3 end; no_tracking_cats = nil return 1; -- set no authors so return 1; this allows missing author name test to empty stringrun in case there is a first without last end
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- 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
local DF = --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A['DF']; L U E >------------------------- date format set in cs1|2 template if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword DF = ''; -- not valid, set to empty string end
local sepc; -- separator between citation elements for CS1 This function is used to validate a period, parameter's assigned value for CS2, those parameters that have only a commalimited number local PostScript; local Ref; sepcof allowable values (yes, PostScripty, Ref = set_style (Mode:lower()true, A['PostScript']no, A['Ref'], configetc).CitationClass 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; use_lowercase = ( sepc == 'else,' ); -- used to control capitalization for certain static textemits an error message and returns false.
--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 -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end end]]
-- check for extra |page=local function is_valid_parameter_value (value, name, |pages= or |at= parameters. (also sheet and sheets while we're at itpossible) select_oneif not is_set ( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' value)then return true; -- this an empty parameter is a dummy call simply to get the error message and categoryok local NoPP = A['NoPP'] if is_set elseif in_array(value:lower(NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']possible) then NoPP = return true;
else
NoPP = niltable.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- unset, used as a flag laternot an allowed value so add error message return false
end
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 this page to maint cat if |page= value begins with what looks like p. or pp.
elseif is_set(Pages) then
if is_set(At) then
At = ''; -- unset
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
-- both |publication[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >------------------------------place= and |place= (|location=) allowed if different if not is_set(PublicationPlace) and is_set(Place) then PublicationPlace = Place; -- promote |place= (|location=) to |publication-place 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 |encyclopediaThis function terminates a name list (author, |titlecontributor, editor) with a separator character (sepc) and |article a spacewhen the last character is not a sepc character or when the last three characters are not modifiedsepc followed by two closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a ]]single space character.
local Encyclopedia = A['Encyclopedia'];]
local function terminate_name_list (name_list, sepc) if ( configstring.CitationClass == "encyclopaedia" ) or sub ( config.CitationClass == "citation" and is_set (Encyclopedia)) then name_list,-1,- test code for citation if is_set(Periodical1) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then if not is_set(Chapter) then Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; if not is_set (ChapterURLsepc) and is_set or (TitleLink) then Chapter = make_wikilink string.sub (TitleLinkname_list, Chapter); end Title = Periodical; ChapterFormat = Format; Periodical = ''; -3,- redundant so unset TransTitle 1) = ''; URL = sepc .. ']]'; Format = ''; TitleLink = ''; ScriptTitle = ''; end else ) then -- |title not setif last name in list ends with sepc char Title = Periodical return name_list .. " "; -- |encyclopedia set and |article set or not set so map |encyclopedia to |titledon't add another else Periodical = return name_list .. sepc .. ''; -- redundant so unset end endotherwise terninate the name list
end
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(ID) then -- can we use ID for the "number"?
ID = A['Number']; -- 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 mailing list if (config.CitationClass == "mailinglist") then Periodical = [[-------------------------< F O R M A ['MailingList'];T _ V O L U M E _ I S S U E >---------------------------------------- elseif 'mailinglist' == A:ORIGIN('Periodical') then Periodical = ''returns the concatenation of the formatted volume and issue parameters as a single string; -- unset because mailing list is only used for cite mailing listor formatted volume endor formatted issue, or an empty string if neither are set.
]] -- Account for the oddity that is {{cite conference}}local function format_volume_issue (volume, before generation of COinS data.issue, cite_class, origin, sepc, lower) if 'conference' == config.CitationClass then if not is_set (volume) and not is_set(BookTitleissue) then Chapter = Title;-- ChapterLink = TitleLink; -- |chapterlink= is deprecated ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = URLorigin; URLorigin = return ''; ChapterFormat = Format; TransChapter = TransTitle; Title = BookTitle; Format = '';-- TitleLink = ''; TransTitle = ''; URL = ''; end elseif 'speech' ~= config.CitationClass then Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities local Cartography if 'magazine' = ""; local Scale = ""; local Sheet = A['Sheet'] 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
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local SeriesLink = A['SeriesLink'];
link_title_ok (SeriesLink, --[[-------------------------< F O R M A T _ P A:ORIGIN ('SeriesLink'), Series, 'series'); G E S _ S H E E T S >--------------------------------------- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
local Network adds static text to one of |page(s)= A['Network']; local Station = A['Station']; local or |sheet(s, n )= {}, {};values and returns it with all of the others set to empty strings. -- do common parameters firstThe return order is: if is_set(Network) then table.insert(n page, Network); end if is_set(Station) then table.insert(npages, Station); end ID = table.concat(nsheet, sepc .. ' ');sheets if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = AirDate; endSingular has priority over plural when both are provided.
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Season = A['Season']; local SeriesNumber = A['SeriesNumber'];
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) if is_set 'map' == cite_class then -- only cite map supports sheet(Seasons) and as in-source locators if is_set (SeriesNumbersheet) then -- these are mutually exclusive so if both are set'journal' == origin then table.insert( z.message_tailreturn '', { set_error( 'redundant_parameters', {wrap_style wrap_msg ('parameterj-sheet', sheet, lower), 'season') .. ; else return ' and ' .. wrap_style (, 'parameter', wrap_msg ('seriesnosheet'), {sepc, sheet}, true lower) } ); -- add error message SeriesNumber = , ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series if elseif is_set(Seasonsheets) 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-sheets', Issuesheets, use_lowercase)lower); end Issue = else return ''; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = A:ORIGIN(, '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'sheets', Chapter); elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set{sepc, URL links episode; Series = make_wikilink (ChapterLinksheets}, Serieslower);
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']; -- TODO: make |episode= available to cite episode someday? if is_set (Series) and is_set (SeriesLink) then Series = make_wikilink (SeriesLink, Series); 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}}local is_journal = 'journal' == cite_class or (in_array (cite_class, {{cite biorxiv}}'citation', {{cite citeseerx'map'}}, before generation of COinS data.) and 'journal' == origin); doif is_set (page) then if in_array is_journal then return substitute (configcfg.CitationClassmessages['j-page(s)'], page), {'arxiv', 'biorxiv', 'citeseerx'}) then; if elseif not is_set (ID_list[config.CitationClass:upper()]) nopp then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates table.insert return substitute ( z.message_tail, { set_error( config.CitationClass .cfg. messages['_missingp-prefix'], {}sepc, true ) page} ); -- add error message end if , '', 'arxiv' == config.CitationClass then Periodical = , 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string end else if return substitute (cfg.messages['biorxivnopp' == config.CitationClass then Periodical = ], {sepc, page}), 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string end if '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
end if not is_set(error_message) then -- error free dates only local modified Coauthors = falseA['Coauthors']; -- flag if is_set (DF) then -- if we need to reformat dates modified local Others = reformat_dates (date_parameters_list, DF, false)A['Others']; -- 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 local editor_etal; modified local e = true; add_maint_cat ('date_format'){}; -- hyphens were converted so add maint category end editors list from |editor-lastn= / |editor- for those wikis that can and want to have English date names translated to the local language,firstn= pairs or |veditors= -- uncomment these three lines. Not supported by en.wiki (for obvious reasons)-- if date_name_xlate (date_parameters_list) then-- modified = truelocal Editors;-- end
if modified then do -- if the date_parameters_list values were modifiedto limit scope of selected AccessDate local selected = date_parameters_listselect_author_editor_source (A['access-dateVeditors']; -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list, A['archive-dateEditors'], args, 'EditorList'); Date if 1 == date_parameters_list[selected then e, editor_etal = extract_names (args, 'dateEditorList']); DoiBroken -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn= date_parameters_list['doi, |editor-brokenlinkn=, and |editor-date'];maskn= elseif 2 == selected then LayDate NameListFormat = date_parameters_list['lay-datevanc']; -- override whatever |name-list-format= might be PublicationDate e, editor_etal = date_parameters_list[parse_vauthors_veditors (args, args.veditors, 'publication-dateEditorList']); end-- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= elseelseif 3 == selected then table.insert( z.message_tail, { set_error( Editors = A['bad_dateEditors', {error_message}, true ) } )]; -- add this error messageuse content of |editors=
end
end -- end of do
local t = {}; -- Account for the oddity that is {{cite journal}} with translators list from |pmctranslator-lastn= set and |url/ translator-firstn= not set. Do this after date check but before COInS.pairs local Translators; -- Here we unset Embargo if PMC not embargoed assembled translators name list t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |embargotranslator-lastn=, -firstn=, -linkn= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date-maskn= Embargo local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= is_embargoed (Embargo)pairs local Contributors; -- assembled contributors name list local Contribution = A['Contribution']; if in_array(config.CitationClass == , {"book"journal," citation"}) and not is_set(URLA['Periodical']) then -- |contributor= and is_set|contribution= only supported in book cites c = extract_names (ID_list[args, 'PMCContributorList']) ; -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= if 0 < #c then if not is_set (EmbargoContribution) then -- if not embargoed or embargo has expired|contributor= requires |contribution= URL=cfg table.insert( z.id_handlers[message_tail, { set_error( 'PMCcontributor_missing_required_param'].prefix .. ID_list[, 'PMCcontribution'])}); -- set url to be the same as the PMC external link if not embargoedadd missing contribution error message URLorigin c = cfg.id_handlers['PMC'].parameters[1]{}; -- set URLorigin to parameter name for use in error message if citation blank the contributors' table; it is missing used as a |title=flag later end if is_set(AccessDate) 0 == #a then -- access date requires |urlcontributor=; pmc created url is not requires |urlauthor= table.insert( z.message_tail, { set_error( 'accessdate_missing_urlcontributor_missing_required_param', {}, true 'author') } );-- add missing author error message AccessDate c = ''{}; -- unsetblank the contributors' table; it is used as a flag later
end
end
else -- if not a book cite
if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters?
table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message
end
Contribution = nil; -- unset
end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not is_setis_valid_parameter_value (Title) and not is_set(TransTitle) and not is_set(ScriptTitle) then if 'episodeNameListFormat, ' == config.CitationClass then name-list- special case for cite episode; TODO: is there a better way to do this? table.insert( z.message_tail, { set_error( 'citation_missing_titleformat', {'series'}, true ) } ); else tablecfg.insert( z.message_tail, { set_error( keywords['citation_missing_title', {'title'}, true ) } ); end end if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodicalname-list-format']) then -- special case only accepted value for journal citesthis parameter is 'vanc' Title NameListFormat = ''; -- anything else, set title to empty string add_maint_cat ('untitled'); end
check_for_url ({ local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- add error message when any of these parameters contains a URLGet title data local Title = A['titleTitle']; local ScriptTitle =Title,A['ScriptTitle']; local BookTitle = A['BookTitle']; local Conference = A:ORIGIN(['ChapterConference')]; local TransTitle =Chapter,A['TransTitle']; local TitleNote = A['TitleNote']; local TitleLink = A:ORIGIN(['PeriodicalTitleLink']; if is_set (TitleLink)]and false ==Periodicallink_param_ok (TitleLink) then table.insert( z.message_tail, { set_error( 'bad_paramlink', [A:ORIGIN('PublisherNameTitleLink')] )}); -- url or wikilink in |title-link= PublisherName; });end
local Chapter = A['Chapter']; local ScriptChapter = A['ScriptChapter']; local ChapterLink -- COinS metadata = 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(see <http://ocoins.info/>'URL') for automated parsing ; -- get name of citation information.parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- handle the oddity get name of parameter that is cite encyclopedia and {{citation |encyclopediaholds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL =something}}. Here we presume thatA['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- when get name of parameter that holds ConferenceURL local Periodical, Title, and Chapter are all set, then = A['Periodical is the book ']; local Periodical_origin = A:ORIGIN(encyclopedia'Periodical') title, Title ; -- is get the article title, and Chapter is a section within name of the article. So, we remap periodical parameter local Series = A['Series'];
local coins_chapter = ChapterVolume; local Issue; local Page; local Pages; -- default assuming that remapping not required local coins_title = TitleAt; -- et tu if 'encyclopaedia' == in_array (config.CitationClass or , cfg.templates_using_volume) and not ('citationconference' == config.CitationClass and not is_set (EncyclopediaPeriodical)) then if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then coins_chapter Volume = TitleA['Volume']; -- remap coins_title = Periodical; end
end
local coins_author = a; -- default for coins rftif in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.au if 0 < #c CitationClass, {'conference', 'map'}) and not is_set (Periodical))then -- but if contributor list coins_author Issue = cA['Issue']; -- use that instead
end
-- this is the function call to COinS() local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, ['Chapter'] Position = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Degree'] = Degree; -- cite thesis only ['Title'] = make_coins_title if not in_array (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_dateconfig.rftdate, -- COinS_date has correctly formatted date if Date is valid; ['Season'] = COinS_date.rftssnCitationClass, ['Chron'] = COinS_datecfg.rftchron or (not COinS_date.rftdate and Datetemplates_not_using_page) or '', -- chron but if not set and invalid date format use Date; keep this last bit?then ['Series'] Page = Series, A['VolumePage'] = Volume, ['Issue'] = Issue,; ['Pages'] = get_coins_pages (first_set hyphen_to_dash({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links A['Edition'] = Edition, ['PublisherName'] = PublisherName, ['URLPages'] = first_set ({ChapterURL, URL}, 2),; ['Authors'] At = coins_author, A['ID_list'] = ID_list, ['RawPageAt'] = this_page.prefixedText, }, config.CitationClass); -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite citeseerx}} AFTER generation of COinS data. if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
end
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static textlocal Edition = A['Edition']; local PublicationPlace = A['PublicationPlace'] if local Place = A['newsgroupPlace' ]; local PublisherName =A['PublisherName']; local RegistrationRequired = config.CitationClass thenA['RegistrationRequired']; if is_set not is_valid_parameter_value (PublisherNameRegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then PublisherName RegistrationRequired=nil; end local SubscriptionRequired = substitute A['SubscriptionRequired']; if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.messageskeywords ['newsgroupyes_true_y'], external_link( ) then SubscriptionRequired=nil; end local Via = A['Via']; local AccessDate = A['AccessDate']; local ArchiveDate = A['ArchiveDate']; local Agency = A['news:Agency' .. PublisherName, PublisherName, ]; local DeadURL = A:ORIGIN['DeadURL'] if not is_valid_parameter_value (DeadURL, 'PublisherNamedead-url'), nil )cfg.keywords ['deadurl'])then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string
end
end
local Language = A['Language'];
local Format = A['Format'];
local ChapterFormat = A['ChapterFormat'];
local DoiBroken = A['DoiBroken'];
local ID = A['ID'];
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.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 = extract_ids( args );
-- Now perform various field substitutions. -- 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 EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list do local last_first_list; local control = { format Quote = NameListFormat, -- empty string or 'vancA[' 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 donQuote't wikilink to it via editorlinkn mode = Mode }];
do -- do editor name list first because the now unsupported coauthors used to modify control table local LayFormat = A['LayFormat']; local LayURL = A['LayURL']; local LaySource = A['LaySource']; control.maximum , editor_etal local Transcript = get_display_authors_editors (A['DisplayEditorsTranscript'], #e, ; local TranscriptFormat = A['editorsTranscriptFormat', editor_etal)]; last_first_list, EditorCount local TranscriptURL = list_peopleA['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN(control, e, editor_etal'TranscriptURL'); -- get name of parameter that holds TranscriptURL
if is_set (Editors) then if editor_etal then Editors local LastAuthorAmp = Editors .. ' ' .. cfg.messagesA['et alLastAuthorAmp']; if not is_valid_parameter_value (LastAuthorAmp, 'last-author- add et al. to editors parameter beause |display-editors=etal EditorCount = 2; -- with et al.amp', |editors= is multiple names; spoof to display (edscfg.) annotation else EditorCount = 2; -- we donkeywords ['yes_true_y't know but assume |editors= is multiple names; spoof to display (eds.]) annotation endthen else Editors LastAuthorAmp = last_first_listnil; -- either an author name list or an set to empty string end if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then EditorCount = 2; -- spoof to display (eds.) annotation end
end
do -- now do interviewers control.maximum local no_tracking_cats = #interviewers_listA['NoTracking']; -- number of interviewerss Interviewers = list_people if not is_valid_parameter_value (controlno_tracking_cats, interviewers_list'no-tracking', falsecfg.keywords ['yes_true_y'])then no_tracking_cats = nil; -- et al not currently supportedset to empty string
end
do -- now do translators
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false); -- et al not currently supported
end
do -- now do contributors
control.maximum = #c; -- number of contributors
Contributors = list_people(control, c, false); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
last_first_list --these are used by cite interview local Callsign = list_people(control, a, author_etal)A['Callsign']; local City = A['City']; local Program = A['Program'];
if is_set (Authors) then--local variables that are not cs1 parameters Authors, author_etal = name_has_etal (Authors, author_etal, false) local use_lowercase; -- find and remove variations on et al.controls capitalization of certain static text if author_etal then Authors local this_page = Authors mw.title. ' ' .. cfg.messages['et al']getCurrentTitle(); -- add et al. to authors parameteralso used for COinS and for language end else Authors = last_first_list local anchor_year; -- either an author name list or an empty string end end -- end of doused in the CITEREF identifier if is_set (Authors) and is_set (Collaboration) then Authors local COinS_date = Authors .. ' (' .. Collaboration .. ')'{}; -- add collaboration after et al. endholds 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 not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
-- apply |[xx-]format= styling; at check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the end, these parameters hold correctly styled format annotation,error categories if not is_set (no_tracking_cats) then -- an error message ignore if the associated url is we are already not setgoing to categorize this page if in_array (this_page.nsText, or an empty string for concatenationcfg.uncategorized_namespaces) then ArchiveFormat no_tracking_cats = style_format "true"; -- set no_tracking_cats end for _,v in ipairs (ArchiveFormat, ArchiveURL, 'archivecfg.uncategorized_subpages) do -format', 'archive-url'cycle through page name patterns if this_page.text:match (v)then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end ConferenceFormat end -- check for extra |page= style_format , |pages= or |at= parameters. (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-urlalso sheet and sheets while we're at it); Format = style_format select_one(Formatargs, URL{'page', 'formatp', 'urlpp'); LayFormat = style_format (LayFormat, LayURL'pages', 'lay-formatat', 'lay-urlsheet'); TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-formatsheets'}, 'transcripturlredundant_parameters'); -- this is a dummy call simply to get the error message and category
-- special case for chapter format so no error message or cat when chapter not supportedlocal NoPP = A['NoPP'] if not is_set (in_arrayNoPP) and is_valid_parameter_value (config.CitationClassNoPP, {'web', 'news', 'journal', 'magazinenopp', cfg.keywords ['pressreleaseyes_true_y', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}]) orthen ('citation' NoPP == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) thentrue; else ChapterFormat NoPP = style_format (ChapterFormat, ChapterURL, 'chapternil; --format'unset, 'chapter-url');used as a flag later
end
if not is_set(URLPage) then if in_arrayis_set(Pages) or is_set(config.CitationClass, {"web","podcast", "mailinglist"}At) then Pages = ''; -- |url= required for cite web, cite podcast, and cite mailinglistunset the others table.insert( z.message_tail, { set_error( At = 'cite_web_url', {}, true ) } );
end
extra_text_in_page_check (Page); -- do we have add this page to maint cat if |accessdate= without either |urlpage= value begins with what looks like p. or |chapter-url=?pp. if elseif is_set(AccessDatePages) and not then if is_set(ChapterURLAt)then -- ChapterURL may be set when URL is not set; table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); AccessDate At = ''; -- unset
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
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 OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; DeadURL = DeadURL:lower(); -- used later when assembling archived text if is_set( 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 chapter's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages OriginalFormat = ChapterFormat; -- and original |format= if 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url ChapterURLorigin Encyclopedia = A:ORIGIN(['ArchiveURLEncyclopedia') -- name of archive-url parameter for error messages ChapterFormat = ArchiveFormat or ''; -- swap in archive's format end elseif 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= OriginalAccess = UrlAccess; if 'no' ~= DeadURL then -- if URL set then archive-url applies to it URL = ArchiveURL -- swap-in the archive's url URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages Format = ArchiveFormat or ''; -- swap in archive's format UrlAccess = nil]; -- restricted access levels do not make sense for archived urls end end end
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}== "encyclopaedia" ) or -- if any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation if is_set (Periodical) and not then -- Periodical is set when |encyclopedia is set if is_set (EncyclopediaTitle)or is_set (ScriptTitle) then local chap_param; if not is_set (Chapter) then Chapter = Title; -- get a parameter name from one of these chapter related meta-parameters|encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; TransChapter = TransTitle; chap_param ChapterURL = A:ORIGIN URL; if not is_set ('Chapter'ChapterURL) elseif and is_set (TransChapterTitleLink) then chap_param Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]'; end Title = Periodical; ChapterFormat = Format; Periodical = ''; -- redundant so unset TransTitle = A:ORIGIN ('TransChapter'); elseif is_set (ChapterURL) then URL = ''; chap_param Format = A:ORIGIN ('ChapterURL'); elseif is_set (ScriptChapter) then TitleLink = ''; chap_param ScriptTitle = A:ORIGIN ('ScriptChapter'); end else is_set (ChapterFormat) -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title chap_param Periodical = A:ORIGIN ('ChapterFormat'); -- redundant so unset
end
end
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 (chap_paramID) then -- if can we found oneuse ID for the "number"? ID = A['Number']; -- yes, use it else -- ID has a value so emit error message table.insert( z.message_tail, { set_error( 'chapter_ignoredredundant_parameters', {chap_paramwrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true ) } ); end end end -- add error messagespecial case for cite interview Chapter if (config.CitationClass == ''; -- and set them to empty string to be safe with concatenation"interview") then if is_set(Program) then TransChapter ID = ''.. Program; end if is_set(Callsign) then if is_set(ID) then ChapterURL ID = ID .. sepc .. ''.. Callsign; ScriptChapter = ''; else ChapterFormat ID = ''.. Callsign;
end
else -- otherwise, format chapter / article title local no_quotes = false; -- default assume that we will be quoting the chapter parameter valueend if is_set (ContributionCity) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:loweris_set(ID), cfgthen ID = ID .. sepc ..keywords' ' .contribution) then -- and a generic contribution title. City; else no_quotes ID = true' ' .. City; -- then render it unquoted
end
end
Chapter = format_chapter_title if is_set(ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccessOthers); -- Contribution is also in Chapterthen if is_set (ChapterTitleType) then Chapter Others = Chapter ' ' .. ChapterFormat TitleType .. ' with ' .. Others; if TitleType = 'map' == config.CitationClass and is_set (TitleType) then; else Chapter Others = Chapter ' ' .. ' Interview with ' .. TitleType; -- map annotation hereOthers; not after title
end
else Chapter Others = Chapter.. sepc .. ' '; elseif is_set (ChapterFormatInterview) 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.special case for cite mailing list if '..(config.' CitationClass == Title:sub (-3"mailinglist") then -- if elipsis is the last three characters of |title= Title Periodical = mw.ustring.gsub (Title, A ['(%.%.%.)%.+$', '%1MailingList')]; -- limit the number of dots to three elseif not mw.ustring.find 'mailinglist' == A:ORIGIN(Title, '%.%s*%a%.Periodical') then -- end of title is not a 'dot-(optional space-)letter-dot' initialism Title Periodical = 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);unset because mailing list is only used for cite mailing list
end
if in_array(config.CitationClass, -- Account for the oddity that is {{'web'cite conference}}, 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) orbefore generation of COinS data. ( if 'citationconference' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) orthen ('map' == config.CitationClass and if is_set (Periodical)BookTitle) then Chapter = Title;-- ChapterLink = TitleLink; -- special case for cite map when the map |chapterlink= is in a periodical treat as an articledeprecated ChapterURL = URL; Title ChapterURLorigin = kern_quotes (Title)URLorigin; -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title URLorigin = wrap_style ('quoted-title', Title); ChapterFormat = Format; TransChapter = TransTitle; Title = script_concatenate (Title, ScriptTitle)BookTitle; -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitleFormat = wrap_style ('trans-quoted-title', TransTitle ); elseif 'report' == config.CitationClass then -- no styling for cite report Title TitleLink = 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 URL = wrap_style ('italic-title', Title); Title end elseif 'speech' ~= script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrappedconfig.CitationClass then TransTitle Conference = wrap_style ('trans'; -italic-title', TransTitle);not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities local TransError Cartography = ""; local Scale = ""; local Sheet = A['Sheet'] or ''; local Sheets = A['Sheets'] or ''; if is_setconfig.CitationClass == "map" then Chapter = A['Map']; ChapterURL = A['MapURL']; TransChapter = A['TransMap']; ChapterURLorigin = A:ORIGIN(TransTitle'MapURL') then; ChapterFormat = A['MapFormat']; Cartography = A['Cartography']; if is_set(TitleCartography ) then TransTitle Cartography = sepc .. " " .. TransTitlewrap_msg ('cartography', Cartography, use_lowercase); elseend Scale = A['Scale']; if is_set( Scale ) then TransError Scale = sepc .. " " .. set_error( 'trans_missing_title', {'title'} )Scale;
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 = ''; -- unset these because no longer needed
Format = "";
else
Title = Title .. TransTitle .. TransError;
end
else
Title = TransTitle .. TransError;
end
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. if 'episode' == config.CitationClass or 'serial' == config.CitationClass then local AirDate = A['AirDate']; local SeriesLink = A['SeriesLink']; if is_set(PlaceSeriesLink) and false == link_param_ok (SeriesLink) then Place = " " table.insert( z. wrap_msg message_tail, { set_error('writtenbad_paramlink', Place, use_lowercaseA:ORIGIN('SeriesLink'))}) .. sepc .. " "; end local Network = A['Network']; local Station = A['Station']; local s, n = {}, {}; -- do common parameters first if is_set (ConferenceNetwork) thentable.insert(n, Network); end if is_set (ConferenceURLStation) thentable.insert(n, Station); end Conference ID = external_linktable.concat( ConferenceURLn, Conference, ConferenceURLorigin, nil sepc .. ' '); if not is_set (Date) and is_set (AirDate)then -- promote airdate to date Date = AirDate;
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
end
if not is_set(Position) 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Minutes Season = A['MinutesSeason']; local Time SeriesNumber = A['TimeSeriesNumber'];
if is_set(MinutesSeason) then if and is_set (TimeSeriesNumber) then -- these are mutually exclusive so if both are set table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutesseason') .. ' and ' .. wrap_style ('parameter', 'timeseriesno')}, true ) } ); -- add error message SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series Position = " " if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table. Minutes 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 Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterURLorigin = A:ORIGIN('URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table. " " concat(s, sepc .. cfg.messages['minutes']); -- this is concatenation of season, seriesno, episode number else if is_set(TimeChapterLink) and not is_set (ChapterURL) then -- link but not URL local TimeCaption Chapter = A'[['TimeCaption.. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink if not elseif is_set (ChapterLink) and is_set(TimeCaptionChapterURL) then -- if both are set, URL links episode; TimeCaption Series = cfg'[[' ..messages[ChapterLink .. '|'event.. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; if sepc ~ else -- now oddities that are cite serial Issue = '.' then; -- unset because this parameter no longer supported by the citation/core version of cite serial TimeCaption Chapter = TimeCaptionA['Episode']; -- TODO:lowermake |episode= available to cite episode someday? if is_set (Series) and is_set (SeriesLink); endthen end Position Series = " " '[[' .. TimeCaption SeriesLink .. " " '|' .. TimeSeries .. ']]';
end
end else Position Series = " " .. Positionwrap_style ('italic-title', Series); -- series is italicized At = '';end
end
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. Page, Pages, Sheet, Sheets if 'arxiv' == format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);then At = if not is_set(AtID_list['ARXIV']) and then -- |arxiv= or |eprint= required for cite arxiv table.insert(sepc z.. " " .. Atmessage_tail, { set_error( 'arxiv_missing', {}, true ) } ) or ""; -- add error message Position = elseif is_set(PositionSeries) and (sepc .. " " .. Position) or "";then -- series is an alias of version if config.CitationClass == ID_list['mapARXIV' then local Section ] = AID_list['SectionARXIV'].. Series; -- concatenate version onto the end of the arxiv identifier local Sections Series = A['Sections']; -- unset local Inset = A[ deprecated_parameter ('Insetversion']); -- deprecated parameter but only for cite arxiv end
if is_setfirst_set ( Inset {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'], ID_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']},27) then Inset = sepc table.insert( z. " " .. wrap_msg message_tail, { set_error('insetarxiv_params_not_supported', Inset{}, use_lowercasetrue ) } ); end -- add error message
if is_set( Sections ) then AccessDate= ''; -- set these to empty string; not supported in cite arXiv Section PublisherName = sepc .. " " .. wrap_msg ('sections'; -- (if the article has been published, Sectionsuse cite journal, use_lowercaseor other) Chapter = ''; elseif is_set( Section ) then URL = ''; Format = ''; Section Page = ''; Pages = ''; At = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
At Periodical = At .. Inset .. Section'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_set in_array(Languageconfig.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then Language TitleType = language_parameter set_titletype (Languageconfig.CitationClass, TitleType); -- format, categories, name from ISO639-1, etc else Language=if is_set(Degree) and "Thesis"; == TitleType then -- language not specified so make sure this is an empty string;special case for cite thesis --[[ TODO: need to extract the wrap_msg from language_parameter so that we can solve parentheses bunching problem with Format/Language/ TitleType= Degree .. "论文"; ]] end
end
Others = is_set(Others) and (sepc .. " " .. Others) or ""; if is_set (TranslatorsTitleType) then -- if type parameter is specified Others TitleType = sepc .substitute( cfg. messages[' type' .. wrap_msg ('translated', Translators], use_lowercaseTitleType) .. Others; -- 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 (InterviewersDate) then Others Date = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. OthersYear; -- promote Year to Date end Year = nil; -- make nil so Year as empty string isn't used for CITEREF TitleNote = if not is_set(TitleNoteDate) and (sepc .. " " .. TitleNote) or ""; if is_set (EditionPublicationDate) then -- use PublicationDate when |date= and |year= are not set if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then Date = PublicationDate; -- promote PublicationDate to Date add_maint_cat (PublicationDate = 'extra_text'; -- unset, 'edition');no longer needed
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
Series if PublicationDate = is_set(Series) and (sepc .. " " .. Series) or ""; OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""Date then PublicationDate = ''; end -- TODO: presentationif PublicationDate is same as Date, don't display in rendered citation
Agency = is_set(Agency) --[[Go test all of the date-holding parameters for valid MOS:DATE format and (sepc 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. " " .. Agency) or "";
Date validation supporting code is in Module:Citation/CS1/Date_validation]] Volume do -- create defined block to contain local variables error_message and mismatch local error_message = format_volume_issue ''; -- AirDate has been promoted to Date so not necessary to check it anchor_year, error_message = dates(Volume{['access-date']=AccessDate, Issue['archive-date']=ArchiveDate, config.CitationClass['date']=Date, Periodical_origin['doi-broken-date']=DoiBroken, sepc ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, use_lowercaseCOinS_date);
if is_set (Year) and is_set (Date) then --both |date= and |year= not normally needed; local mismatch = year_date_check (Year, Date) if 0 == mismatch then --|year= does not match a year-------------------------------- totally unrelated datavalue in |date= if is_set(Viaerror_message) then -- if there is already an error message Via error_message = error_message .. ', '; -- tack on this additional message end error_message = " " error_message .. wrap_msg '|year= / |date= mismatch'; elseif 1 == mismatch then -- |year= matches year-value in |date= add_maint_cat ('viadate_year', Via); end end
--[[ Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link note is displayed. There are no error messages for this condition. ]] if is_set (SubscriptionRequirederror_message) then SubscriptionRequired = sepc table.insert( z. " " .. cfg.messages[message_tail, { set_error( 'subscriptionbad_date'], {error_message}, true ) } ); -- subscription required add this error message elseif is_set (RegistrationRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required messageend else SubscriptionRequired = ''; end -- either or both might be set to something other than yes true y 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 is_setPMC not embargoed (AccessDate|embargo= not set in the citation) thenor if the embargo time has expired. Otherwise, holds embargo date local retrv_text Embargo = " " .. cfg.messages['retrieved']is_embargoed (Embargo); --
AccessDate if config.CitationClass == nowrap_date "journal" and not is_set(URL) and is_set(AccessDateID_list['PMC']); -- wrap in nowrap span if date in appropriate formatthen if not is_set (sepc ~= "."Embargo) then retrv_text -- if not embargoed or embargo has expired URL= retrv_text:lower() end cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if mode is cs2, lower casenot embargoed AccessDate URLorigin = substitute (retrv_text, AccessDate)cfg.id_handlers['PMC'].parameters[1]; -- add retrieved textset URLorigin to parameter name for use in error message if citation is missing a |title= end end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not is_set(Title) and not is_set(TransTitle) and AccessDate not is_set(ScriptTitle) then if 'episode' = substitute = config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? table.insert(cfgz.presentation[message_tail, { set_error( 'accessdatecitation_missing_title'], {sepc'series'}, AccessDatetrue ) }); -- allow editors to hide accessdates else table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); end
end
if is_set(ID) then ID = sepc .." ".. ID; end if "thesis" 'none' == Title and in_array (config.CitationClass , {'journal', 'citation'}) and is_set(DocketPeriodical) then ID = sepc .." Docket ".. Docket .. ID; end if "report" and 'journal' == config.CitationClass and is_setA:ORIGIN(Docket'Periodical') then -- special case for cite report when |docket= is setjournal cites ID Title = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is settitle to empty string add_maint_cat ('untitled');
end
ID_list = build_id_listcheck_for_url ( ID_list, {IdAccessLevels -- add error message when any of these parameters contains a URL ['title']=ID_access_levelsTitle, DoiBroken [A:ORIGIN('Chapter')]= DoiBrokenChapter, ASINTLD [A:ORIGIN('Periodical')]= ASINTLDPeriodical, IgnoreISBN = IgnoreISBN, Embargo [A:ORIGIN('PublisherName')] =EmbargoPublisherName, Class = Class } );
if is_set-- COinS metadata (URLsee <http://ocoins.info/>) thenfor automated parsing of citation information. URL -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia= " " something}}.. external_linkHere we presume that -- when Periodical, Title, and Chapter are all set, then Periodical is the book ( URLencyclopedia) title, nilTitle -- is the article title, URLoriginand Chapter is a section within the article. So, UrlAccess we remap local coins_chapter = Chapter; -- default assuming that remapping not required local coins_title = Title; -- et tu if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then if is_set (Chapter) and is_set (Title)and is_set (Periodical) then -- if all are used then coins_chapter = Title; -- remap coins_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
if is_set-- this is the function call to COinS(Quote) then local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, if Quote:sub['Chapter'] = make_coins_title (1coins_chapter,1ScriptChapter) , -- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Map'] =Map, ['Degree'] = Degree; -- cite thesis only ['"Title' and Quote:sub] = make_coins_title (coins_title, ScriptTitle), --1Title and ScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, --1) COinS_date has correctly formatted date if Date is valid; ['Season'] =COinS_date.rftssn, ['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '"' then , -- chron but if first not set and invalid date format use Date; keep this last characters of quote are quote marksbit? ['Series'] = Series, ['Volume'] = Volume, ['Issue'] = Issue, Quote ['Pages'] = Quote:subget_coins_pages (first_set (2{Sheet, Sheets, Page, Pages, At},-25)); , -- strip them offpages stripped of external links end['Edition'] = Edition, ['PublisherName'] = PublisherName, Quote ['URL'] = sepc .." " .. wrap_style first_set ({ChapterURL, URL}, 2), ['Authors'] = coins_author, ['ID_list'quoted-text] = ID_list, ['RawPage'] = this_page.prefixedText, Quote }, config.CitationClass); -- wrap in <q>Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data. if 'arxiv' == config.CitationClass then -- we have set rft.</q> tagsjtitle in COinS to arXiv, now unset so it isn't displayed PostScript Periodical = ""''; -- cs1|2 does periodical not supply terminal punctuation when |quote= is setallowed in cite arxiv; if article has been published, use cite journal end local Archived-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text if is_set(ArchiveURL) 'newsgroup' == config.CitationClass then if not is_set(ArchiveDatePublisherName) then ArchiveDate PublisherName = set_errorsubstitute (cfg.messages['newsgroup'], external_link('archive_missing_datenews:'.. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
end
end -- Now perform various field substitutions. -- 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 EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list do local last_first_list; local maximum; if "no" local control == DeadURL then{ local arch_text format = cfg.messages[NameListFormat, -- empty string or 'archivedvanc']; maximum = nil, -- as if sepc ~display-authors or display-editors not set lastauthoramp = "LastAuthorAmp, page_name = this_page." then arch_text = arch_text:lower() endtext -- get current page name so that we don't wikilink to it via editorlinkn }; do -- do editor name list first because coauthors can modify control table Archived maximum , editor_etal = sepc .. " " .. substituteget_display_authors_editors ( cfg.messagesA['archived-not-deadDisplayEditors'], { external_link( ArchiveURL#e, arch_text, A:ORIGIN('ArchiveURLeditors'), nil editor_etal) ; --[[ 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 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 --2017. ArchiveFormat, ArchiveDate } );6.23 shizhao if not is_set(OriginalURLmaximum) and #e == 4 then Archived maximum = Archived .. " " 3; table.insert( z. message_tail, { set_error('archive_missing_urlimplict_etal_editor', {}, true) } );
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' ]] local arch_text control.maximum = cfg.messages['archived-dead']maximum; if sepc ~= "." then arch_text = arch_text:lower() end if in_array last_first_list, EditorCount = list_people(DeadURLcontrol, {'unfit'e, 'usurped'editor_etal, 'bot: unknowneditor'}); if is_set (Editors) then Archived if editor_etal then Editors = sepc Editors .. " " ' ' ..cfg. messages['Archived from the original on et al' .. ArchiveDate]; -- format already styled if 'bot: unknown' =add et al. to editors parameter beause |display-editors= DeadURL thenetal add_maint_cat ('bot:_unknown')EditorCount = 2; -- and add a category if not already addedwith et al., |editors= is multiple names; spoof to display (eds.) annotation
else
add_maint_cat ('unfit')EditorCount = 2; -- and add a category if not already addedwe don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else Editors = last_first_list; -- DeadURL is either an author name list or an empty, 'yes', 'string end if 1 == EditorCount and (true', == editor_etal or 'y'1 < #e) then -- only one editor displayed but includes etal then Archived EditorCount = sepc .. " " .. substitute2; -- spoof to display ( arch_text, { external_link( OriginalURL, cfgeds.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styledannotation end elseend local arch_text = cfg.messages['archived do --missing'];now do translators if sepc ~= "control." then arch_text maximum = arch_text:lower() end#t; -- number of translators Archived Translators = sepc .. " " .. substitutelist_people( arch_textcontrol, t, false, { set_error('archive_missing_urltranslator'), ArchiveDate } ); -- et al not currently supported
end
elseif is_set (ArchiveFormat) then do -- now do contributors Archived control.maximum = ArchiveFormat#c; -- if set and ArchiveURL not set ArchiveFormat has error messagenumber of contributors else Archived = "" end local Lay Contributors = ''; if is_set(LayURL) then if is_setlist_people(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – control, c, false, 'contributor'" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; -- et al not currently supported
end
if sepc == '.' thendo -- now do authors Lay control.maximum , author_etal = sepc .. " " .. external_linkget_display_authors_editors ( LayURL, cfg.messagesA['lay summaryDisplayAuthors'], A:ORIGIN(#a, 'LayURLauthors', author_etal); if is_set(Coauthors) then -- if the coauthor field is also used, nil ) prevent ampersand and et al.formatting. LayFormat control.lastauthoramp = nil; control. LaySource .. LayDatemaximum = #a + 1; end else Lay last_first_list = sepc .. " " .. external_linklist_people( LayURLcontrol, a, author_etal, cfg.messages['lay summaryauthor']:lower); if is_set (Authors)then Authors, A:ORIGINauthor_etal = name_has_etal ('LayURL')Authors, author_etal, nil false) ; -- find and remove variations on et al. if author_etal then Authors = Authors . LayFormat .' ' . LaySource .cfg. LayDatemessages['et al']; -- add et al. to authors parameter end elseif is_set (LayFormat) then else Authors = last_first_list; -- Test if |lay-format= is given without giving a |lay-url=either an author name list or an empty string end Lay = sepc .. LayFormat; end -- if set and LayURL not set, then LayFormat has error message endof do
if not is_set(TranscriptAuthors) then if and is_set(TranscriptURLCoauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified Transcript = external_linktable.insert( TranscriptURLz.message_tail, Transcript{ set_error('coauthors_missing_author', TranscriptURLorigin{}, nil true) } );-- emit error message
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
end
-- apply |[xx-]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 (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); Format = style_format (Format, URL, 'format', 'url'); LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); local PublisherTranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); -- special case for chapter format so no error message or cat when chapter not supported if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set(PublicationDateEncyclopedia))) then PublicationDate ChapterFormat = wrap_msg style_format (ChapterFormat, ChapterURL, 'publishedchapter-format', PublicationDate'chapter-url');
end
if not is_set(PublisherNameURL) then--and if is_setin_array(PublicationPlace) then Publisher = sepc .config. CitationClass, {" web" .. PublicationPlace .. ,": podcast" .. PublisherName .. PublicationDate; else Publisher = sepc .. , " mailinglist" .. PublisherName .. PublicationDate; end elseif is_set(PublicationPlace}) then -- Test if cite web or cite podcast |url= is missing or empty Publisher= sepc table.insert( z. " " .. PublicationPlace .. PublicationDatemessage_tail, { set_error( 'cite_web_url', {}, true ) } ); else Publisher = PublicationDate; end -- Several of the above rely upon detecting this as nil, so do it last. Test if is_set(Periodical) thenaccessdate is given without giving a URL if is_set(TitleAccessDate) or and not is_set(TitleNoteChapterURL) then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test? Periodical = sepc table.insert( z. " " .. wrap_style message_tail, { set_error('italic-titleaccessdate_missing_url', Periodical{}, true ) else } ); Periodical AccessDate = wrap_style ('italic-title', Periodical);
end
end
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set? DeadURL = DeadURL:lower(); --[[used later when assembling archived text Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote if is_set(through |department=ArchiveURL ) and forces it to be " then if is_set (SpeechURL)" so thatthen OriginalURL = URL; -- save copy of original source URL the annotation directly follows the |title OriginalURLorigin = URLorigin; -- name of url parameter value in the citation rather than the for error messages OriginalFormat = Format; -- and original |eventformat= parameter value (if provided). ]] if "speech" 'no' ~=DeadURL then -- if URL set then archive-url applies to it URL = config.CitationClass then ArchiveURL --swap- cite speech onlyin the archive's url TitleNote URLorigin = " A:ORIGIN(Speech'ArchiveURL')" -- name of archive url parameter for error messages Format = ArchiveFormat or ''; -- annotate the citationswap in archive's format end if elseif is_set (PeriodicalChapterURL) then -- URL not set so if Periodical, perhaps because chapter-url is set apply archive url to it OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of an included |websitechapter-url parameter for error messages OriginalFormat = or ChapterFormat; -- and original |journalformat= parameter if is_set 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url ChapterURLorigin = A:ORIGIN(Conference'ArchiveURL') then -- and if |event= is setname of archive-url parameter for error messages Conference ChapterFormat = Conference .. sepc .. " "ArchiveFormat or ''; -- then add appropriate punctuation to the end of the Conference variable before renderingswap in archive's format
end
end
end
-- Piece all bits together at lastif in_array(config. HereCitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', all should be non'arxiv'}) or --nilif any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then local chap_param; if is_set (Chapter) then --get a parameter name from one of these chapter related meta- We build things this way because it is more efficient in LUAparameters chap_param = A:ORIGIN ('Chapter') elseif is_set (TransChapter) then chap_param = A:ORIGIN ('TransChapter') elseif is_set (ChapterURL) then chap_param = A:ORIGIN ('ChapterURL') elseif is_set (ScriptChapter) then chap_param = A:ORIGIN ('ScriptChapter') else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat') -- not to keep reassigning to the same string variable over and over. end
local tcommon; local tcommon2; if is_set (chap_param) then -- used for book cite when |contributor= is setif we found one if in_array table.insert(configz.CitationClassmessage_tail, { set_error( 'chapter_ignored', {"journal"chap_param},"citation"true ) }) ; -- add error message Chapter = ''; -- and is_set(Periodical) thenset them to empty string to be safe with concatenation TransChapter = ''; ChapterURL = ''; if is_set(Others) then Others ScriptChapter = Others .. sepc .. " " end''; tcommon ChapterFormat = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc )''; end elseif in_array(config.CitationClasselse -- otherwise, {"book","citation"}) and not is_set(Periodical) then format chapter / article title local no_quotes = false; -- special cases for book citesdefault assume that we will be quoting the chapter parameter value if is_set (ContributorsContribution) and 0 < #c then -- when we are citing foreword, preface, introduction, etcif this is a contribution with contributor(s) tcommon = safe_joinif in_array (Contribution:lower( {Title), TitleNote}, sepc cfg.keywords.contribution); then -- author and other stuff will come after this and before tcommon2a generic contribution title tcommon2 no_quotes = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc )true; else -- then render it unquoted tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );end end
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); elseif -- Contribution is also in Chapter if is_set (Chapter) then if 'map' == config.CitationClass then -- special cases for cite map if and is_set (ChapterTitleType) then -- map in a book Chapter = Chapter .. ' ' .. TitleType; TitleType is part of Chapter tcommon end Chapter = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, Chapter .. ChapterFormat .. sepc ).. ' '; elseif is_set (PeriodicalChapterFormat) then --|chapter= not set but |chapter- map in a periodicalformat= is so ... tcommon Chapter = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, ChapterFormat .. sepc ).. ' '; else -- a sheet or stand-alone map tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}... ChapterFormat has error message, sepc );we want to see it
end
elseif 'episode' == config.CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );end
else -- all other CS1 templatesFormat main title. if is_set(TitleLink) and is_set(Title) then tcommon Title = safe_join( {"[[" .. TitleLink .. "|" .. Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );.. "]]"
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);
if #ID_list Title = script_concatenate (Title, ScriptTitle); -- <bdi> 0 thentags, lang atribute, categorization, etc; must be done after title is wrapped ID_list TransTitle= safe_joinwrap_style ( { sepc .. " "'trans-quoted-title', tableTransTitle ); elseif 'report' == config.concatCitationClass then -- no styling for cite report Title = script_concatenate ( ID_listTitle, sepc .. " " ScriptTitle); -- <bdi> tags, ID }lang atribute, sepc 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
ID_list Title = IDwrap_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
local idcommon Title = safe_joinTitle .. TransTitle; if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title = external_link( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }Title, sepc URLorigin ).. TransError .. Format; URL = ""; local text Format = ""; local pgtext else Title = Position Title .. Sheet TransError; end end if is_set(Place) then Place = " " .. Sheets wrap_msg ('written', Place, use_lowercase) .. Page sepc .. Pages .. At" "; end
if is_set(DateConference) then if is_set (Authors) or is_set (EditorsConferenceURL) then -- date follows authors or editors when authors not set Date Conference = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses else -- neither of authors and editors set if external_link(string.sub(tcommonConferenceURL,-1Conference,-1ConferenceURLorigin ) == sepc) then -- if the last character of tcommon is sepc Date = " " .. Date .. OrigYear; -- Date does not begin with sepc else Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc end
end
end Conference = sepc .. " " .. Conference .. ConferenceFormat; if elseif is_set(AuthorsConferenceURL) then if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination Authors Conference = terminate_name_list sepc .. " " .. external_link(AuthorsConferenceURL, sepcnil, ConferenceURLorigin ); -- when no date, terminate with 0 or 1 sepc and a space end if not is_set(EditorsPosition) then local in_text Minutes = " "A['Minutes']; local post_text Time = ""A['Time']; if is_set(Minutes) then if is_set(ChapterTime) and 0 == #c then in_text = in_text table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') . cfg.messages['inand '] .. " " if wrap_style (sepc ~= '.parameter', 'time') then in_text = in_text:lower(}, true ) } ) -- lowercase for cs2; end else if EditorCount <= 1 then post_text Position = ", " .. Minutes .. " " .. cfg.messages['editorminutes']; else if is_set(Time) then elselocal TimeCaption = A['TimeCaption'] if not is_set(TimeCaption) then post_text TimeCaption = ", " .. cfg.messages['editorsevent']; if sepc ~= '.' then TimeCaption = TimeCaption:lower(); end
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 Position = sepc .. ' ' ." " . cfg.messages['by'] TimeCaption .. ' '; 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)Time; -- 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'];
end
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if in_array(config.CitationClass, {Position = "journal","citation"}) and is_set(Periodical) then text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ).. Position; else text At = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc )''; 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 the whole thing in a <cite/> element local options Page, Pages, Sheet, Sheets = {}; if is_setformat_pages_sheets (Page, Pages, Sheet, Sheets, 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 ('harv' == Ref ) then local namelist = {}; -- holds selected contributor, authorPeriodical_origin, editor name list local year = first_set ({Yearsepc, anchor_year}NoPP, 2use_lowercase); -- Year first for legacy citations and for YMD dates that require disambiguation
At = is_set(At) and (sepc .. " " .. At) or ""; Position = is_set(Position) and (sepc .. " " .. Position) or ""; if #c > 0 config.CitationClass == 'map' then -- if there is a contributor list namelist local Section = cA['Section']; -- select it elseif #a > 0 then -- or an author list local Sections = A['Sections']; namelist local Inset = aA['Inset']; elseif #e > 0 if is_set( Inset ) then -- or an editor list namelist Inset = esepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end if #namelist > 0 is_set( Sections ) then -- if there are names in namelist id Section = anchor_id sepc .. " " .. wrap_msg (namelist'sections', yearSections, use_lowercase); -- go make the CITEREF anchor elseif is_set( Section ) then else id Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); -- unset end
end
optionsAt = At .id . Inset .. Section; end if is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language= id""; -- language not specified so make sure this is an empty string;
end
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsubis_set ("%b<>","")Translators) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains zOthers = sepc .. ' 由' .. Translators ..error_categories = {}; text = set_error('empty_citation翻译 '); z.message_tail = {}. Others;
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if TitleNote = is_set(options.idTitleNote) then -- here we wrap the rendered citation in <cite and (sepc .." " .>...</cite> tagsTitleNote) or ""; if is_set (Edition) then tableif Edition:match ('%f[%a][Ee]d%.insert ?$') or Edition:match (render, substitute '%f[%a][Ee]dition$') then add_maint_cat (cfg.presentation['cite-idextra_text'], {mw.uri.anchorEncode(options.id'edition'), mw; end Edition = " " .text.nowikiwrap_msg (options.class)'edition', text})Edition); -- when |ref= is set
else
tableEdition = ''; end Series = is_set(Series) and (sepc .insert . " " .. Series) or ""; OrigYear = is_set(render, substitute OrigYear) and (cfg" [" .. OrigYear ..presentation['cite'"], {mw") or ""; Agency = is_set(Agency) and (sepc .. " " .text.nowikiAgency) or ""; Volume = format_volume_issue (optionsVolume, Issue, config.class)CitationClass, Periodical_origin, sepc, text})use_lowercase); ---------------------------- all other cases-------- totally unrelated data if is_set(Via) then Via = " " .. wrap_msg ('via', Via); end
table--[[Subscription implies paywall; Registration does not.insert (render If both are used in a citation, substitute (cfgthe subscription required linknote is displayed. There are no error messages for this condition.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
]] if #zis_set (SubscriptionRequired) then SubscriptionRequired = sepc .. " " .. cfg.message_tail ~messages['subscription']; -- subscription required message elseif is_set (RegistrationRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message else SubscriptionRequired = 0 ''; -- either or both might be set to something other than yes true y end if is_set(AccessDate) then tablelocal retrv_text = " " ..insert cfg.messages['retrieved'] AccessDate = nowrap_date (render, AccessDate); -- wrap in nowrap span if 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 for iAccessDate = substitute (cfg.presentation['accessdate'], {sepc,v in ipairsAccessDate}); -- allow editors to hide accessdates end if is_set( zID) then ID = sepc ..message_tail " ".. ID; end if "thesis" == config.CitationClass and is_set(Docket) dothen ID = sepc .." Docket ".. Docket .. ID; end if "report" == config.CitationClass and is_set(v[1]Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if i |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 = #z" " .message_tail . external_link( URL, nil, URLorigin ); end if is_set(Quote) then table.insert if Quote:sub(render1, error_comment1) == '"' and Quote:sub( v[-1,-1]) == '"' then -- if first and last characters of quote are quote marks Quote = Quote:sub(2, v[-2] )); -- strip them off else end table Quote = sepc .." " ..insert wrap_style (render'quoted-text', error_commentQuote ); -- wrap in <q>...</q> tags PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set end local Archived if is_set(ArchiveURL) then if not is_set( vArchiveDate) then ArchiveDate = set_error('archive_missing_date'); end if "no" == DeadURL then local arch_text = cfg.messages[1'archived'] ; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. "; ", v.. substitute( cfg.messages[2'archived-not-dead'] , { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL')) .. ArchiveFormat, ArchiveDate } ); if not is_set(OriginalURL) then endArchived = 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 .. " " .. 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 ~= "." 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 #zis_set(LayURL) then if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; end if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource ..maintenance_cats ~LayDate else Lay = 0 sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= tableLay = sepc ..insert LayFormat; -- 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(renderTranscriptURL, Transcript, TranscriptURLorigin ); end Transcript = sepc .. '<span class' .. 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","citation-commentpodcast" style}) then if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher =PublicationPlace .. "display:none" .. PublisherName; else Publisher = PublisherName; end elseif is_set(PublicationPlace) then Publisher= PublicationPlace; else Publisher = ""; end if is_set(Publisher) then Publisher = " (" .. Publisher .. ")"; color end else if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ":#33aa33" .. PublisherName; else Publisher = sepc .. " " .. PublisherName; end elseif is_set(PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace; else Publisher = ''; margin end end -left:0- 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, Via, SubscriptionRequired, Lay, Language, Quote }, vsepc ); 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 tableend Editors = 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, make_wikilink preface, 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 local 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; tableelseif #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