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
--[[--------------------------< D O I >------------------------------------------------------------------------
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------Formats a DOI and checks for DOI errors.
Evaluates the content of author DOI names contain two parts: prefix and editor name parameters for variations on the theme of et alsuffix separated by a forward slash. If found,the et al Prefix: directory indicator '10. is removed, ' followed by a flag is set to true and the function returns the modified name and registrant code Suffix: character string of any length chosen by the flag.registrant
This function never sets checks a DOI name for: prefix/suffix. If the flag to false but returns doi name contains spaces or endashes, or, if it's previous state because it may have been set byendsprevious passes through with a period or a comma, this function or by will emit a bad_doi error message. DOI names are case-insensitive and can incorporate any printable Unicode characters so the parameters |display-authors=etal or |display-editors=etaltest for spaces, endash,and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarelyif ever used in doi names.
]]
local function name_has_etal doi(nameid, etal, nocatinactive) if is_set (name) then -- name can be nil in which case just return local etal_pattern cat = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme local others_pattern handler = "cfg.id_handlers[;,]? *%f[%a]and [Oo'DOI']thers"; -- and alternate to et al. local text; if name:match is_set(etal_patterninactive) then -- variants on et al. name local inactive_year = nameinactive:gsub match(etal_pattern, ''"%d%d%d%d"); -- 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 ('etal'); -- and add a category if not already added endtry to get the year portion from the inactive date elseif name:match if is_set(others_patterninactive_year) then -- if not 'et al.', then 'and others'? name = name:gsub table.insert(others_patternz.error_categories, ''"自" .. inactive_year .. "年含有不活躍DOI的頁面" ); -- if found, remove etal = true; -- set flag (may have been set previously here or by |display-authors=etal) else if not nocat then -- no categorization for |vauthors= add_maint_cat table.insert('etal'z.error_categories, "含有不活躍DOI的頁面" ); -- and add when inactive doesn't contain a category if not already added endrecognizable year
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
end
return nametext = external_link_id({link = handler.link, label = handler.label, q = handler.q, etal; -- end prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. (inactive or '')
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
cat = ' ' .. set_error( 'bad_doi' );
end
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------ return text .. cat end
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
]]--[[--------------------------< H D L >------------------------------------------------------------------------
local function name_has_ed_markup (name, list_name) local _, pattern; local patterns = { -- these patterns match annotations at end of name '%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%Formats an HDL with minor error checking.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')' '[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name) '%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')' '[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive -- these patterns match annotations at beginning of name '^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.' '^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.' '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's' '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets }
HDL names contain two parts: prefix and suffix separated by a forward slash. if is_set (name) then for _, pattern Prefix: character string using any character in ipairs (patterns) do the UCS-- spin through patterns table and if name:match (pattern) then add_maint_cat (2 character set except 'extra_text_names/', cfg.special_case_translation [list_name]); -- add a maint cat for this template break; end end end return name; -Suffix: character string of any length using any character in the UCS- and doneend2 character set chosen by the registrant
This function checks a HDL name for: prefix/suffix. If the HDL name contains spaces, endashes, or, if it ends
with a period or a comma, this function will emit a bad_hdl error message.
HDL names are case--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------insensitive and can incorporate any printable Unicode characters so the test for endashes andterminal punctuation may not be technically correct but it appears, that in practice these characters are rarelyif ever used in HDLs.
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names areindicated if there is more than one comma and or semicolon. If found, the function adds the multiple name(author or editor) maintenance category.]]
local function hdl(id) local handler = cfg.id_handlers['HDL']]; local text = external_link_id({link = handler.link, label = handler.label, q = handler.q, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
local function name_has_mult_names (name, list_name)local count, _; if is_set (name) then _, count nil == nameid:gsub match('"^[^%s–]-/[^%s–]-[;^%.,]', ''$"); then -- count the number of separator-like characters hdl must contain a fwd slash, must not contain spaces, endashes, and must not end with period or comma if 1 < count then -- param could be |authortext = or |editor= so one separator character is acceptable add_maint_cat text .. ' ' .. set_error('mult_namesbad_hdl', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template end
end
return nametext; -- and done
end
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------This function calls various name checking functions used to validate the content of the various name-holdingparametersFormats an OpenLibrary link, and checks for associated errors.
]]
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];
local function name_checks (last, first, list_name) if is_set (lastcode == "A" ) then if last:match return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. '^%(%(.*%)%)$authors/OL') then -- if wrapped in doubled parentheses, accept as written last id= last:match ('^%(%((id, separator=handler.separator, encode = handler.*encode})% elseif ( code == "M" )%)$'); -- strip parensthen elsereturn external_link_id({link=handler.link, label=handler.label, last prefix= name_has_mult_names (lasthandler.prefix .. 'books/OL', list_name); -- check for multiple names in the parameter (last only) last id=id, separator= name_has_ed_markup (lasthandler.separator, list_nameencode = handler.encode}); -- check for extraneous 'editor' annotation end end if is_set elseif (firstcode == "W" ) then if first:match return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. '^%(%(.*%)%)$works/OL') then -- if wrapped in doubled parentheses, accept as written first id=id, separator=handler.separator, encode = first:match ('^%(%((handler.*encode})%)%)$'); -- strip parens else elsereturn external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'OL', first id= name_has_ed_markup (firstid, separator=handler.separator, list_nameencode = handler.encode}); -- check for extraneous .. ' ' .. set_error( 'editorbad_ol' annotation end end return last, first); -- done
end
end
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
'<' and/or '>' angle brackets.
]]
--local function message_id (id) local handler = cfg.id_handlers[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------Gets name list from the input arguments'USENETID'];
Searches through args in sequential order to find |lastn text = and |firstnexternal_link_id({link = parameters (or their aliases)handler.link, and their matching link and mask parameterslabel = handler.label,Stops searching when both |lastn prefix= and |firstn= are not found in args after two sequential attempts: found |last1handler.prefix,id=id, |last2separator=handler.separator, and |last3encode= but handler.encode}) if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn'thave '@' or has one or first or last character is '< or '>'find |last4 text = and |last5= then text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the search message id is done.invalid end return textend
This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
When an author or editor parameter contains some form of 'et al.', This function sets default title types (equivalent to the 'et al.' is stripped from the parameter and a flag (etalcitation including |type=<default value>) returnedfor those templates that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et alhave defaults.' out of the template's metadata. When this occurs, Also handles the page special case where it is added desirable to a maintenance categoryomit the title type from the rendered citation (|type=none).
]]
local function extract_namesset_titletype (argscite_class, list_nametitle_type) local names if is_set(title_type) then if "none" == {}; -- table of namestitle_type then local last title_type = ""; -- individual name componentsif |type=none then type parameter not displayed local first; end local link; local mask; local i = 1 return title_type; -- loop counter/indexerif |type= has been set to any other value use that value local n = 1; -- output table indexerend local count = 0return cfg.title_types [cite_class] or ''; -- used to count the number of times we havenset template't found a |last= (or alias s default title type; else empty string for authors, |editor-last or alias for editors)concatenation local etal=false; -- return value set to true when we find some form of et al. in an author parameterend
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 .. '[--------------------------< C L E A N _ I S B N >-----------------------------------------------------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 (last, etal, false); -- find Removes irrelevant text 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.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1; -- dashes from ISBN 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_nameSimilar to that used for Special:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkupBookSources
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)] n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing table.insertlocal function clean_isbn( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true isbn_str ) } ); return isbn_str:gsub( "[^-- add this error message end count = 0; -- reset the counter9X]", we're looking for two consecutive missing names end i = i + 1; -- point to next args location end return names, etal"" ); -- all done, return our list of names
end
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
Returns a string where all of lua's magic characters have been escaped. This is important because functions likestring.gsub() treat their pattern and replace strings as patterns, not literal strings.]]local function escape_lua_magic_chars (argument) argument = argument:gsub("%%", "%%%%"); --replace % with %% argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------replace all other lua magic pattern characters return argument;end
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
Returns the language name Strip wiki italic and associated two- or three-character code. Because case of the source may be incorrector different bold markup from the case argument so that WikiMedia uses, the name comparisons are done in lower case and when a match isfound, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, wereturn the original language name string. mw.language.fetchLanguageNames(<local wiki language>, it doesn'all') returns a list of languages that in some cases may includeextensionst contaminate COinS metadata. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not supportcode 'cbk' or name 'Chavacano'. Most (all?) This function strips common patterns of these languages are not used a 'language' codes per se, rather theyare used as sub-domain names: cbk-zam.wikipedia.orgapostrophe markup. These names can be found (for We presume that editors who have taken the time being) attohttps://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 in the |language= parameter. For examplemarkup a title have,if |language=Chavacano de Zamboangaas a result, that name will be found with the associated code 'cbk-zam'provided valid markup. When names they don't, some single apostrophes 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 639-1left behind.
]]
local function get_iso639_code strip_apostrophe_markup (lang, this_wiki_codeargument) local remap = { ['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap ['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code ['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replace 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found ['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org } if remap[lang:lowernot is_set (argument)] then return remap[lang:lower()][1], remap[lang:lower()][2]argument; -- for this language 'name', return a possibly new name and appropriate code end
local languages while true do if argument:match ("%'%'%'%'%'") then -- bold italic (5) argument= mw.language.fetchLanguageNamesargument:gsub(this_wiki_code, "%'%'%'%'all%'", "") ; -- get a list remove all instances of language names known to Wikimediait -- elseif argument:match ("%'%'%'all%' is required for North Ndebele, South Ndebele, ") then -- italic start and Ojibwaend without content (4) local langlc argument= mw.ustring.lowerargument:gsub(lang"%'%'%'%'", ""); -- lower case version for comparisons for code, name in pairs elseif argument:match (languages"%'%'%'") do then -- scan the list to see if we can find our language if langlc == mw.ustring.lowerbold (name3) then if 2 ~argument= codeargument:lengsub("%'%'%'", "") and 3 ~= code; elseif argument:lenmatch ("%'%'") then -- two- or three-character codes only; extensions not supporteditalic (2) return name argument=argument:gsub("%'%'", ""); -- so return the name but not the code end else return name, codebreak; -- found it, return name to ensure proper capitalization and the the code
end
end
return langargument; -- not valid language; return language in original case and nil for the codedone
end
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------ Gets language name Makes a title for COinS from a provided two- Title and / 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 parameter. When |language= contains a recognized language ScriptTitle (either code or any other name), the page is assigned to the category forthat code: Category:Norwegian-language sources (noscript pairs). 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, French, th where the language names or codes areseparated from each other by commas.
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
of %27%27...
]]
local function language_parameter make_coins_title (lang) 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*title,%s*'script); -- names should be a comma separated list for _, lang in ipairs (names_table) do -- reuse lang if lang:match is_set ('^%a%a%-'title) then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? lang title = lang:match ('strip_apostrophe_markup (%a%atitle)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? end if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code endstrip any apostrophe markup if is_set (name) then -- if |language= specified a valid code code = lang:lower(); -- save it else 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 = remap[code] or name; -- override wikimedia when they misuse language codes/names if this_wiki_code ~= code then -- when the language is not the same as this wiki's language if 2 =title= code:len() then -- and is a two-character code add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it else -- or is a recognized language (but has a three-character code) add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template end end else add_maint_cat ('unknown_lang'); -- add maint category if not already added end table.insert (language_listset, name); name = ''; -- so we can reuse itmake sure title is an empty string
end
code = #language_list -- reuse code as number of languages in the list if 2 >= code is_set (script) then name script = table.concat script:gsub (language_list'^%l%l%s*:%s*', ' and ') ; -- insert '<space>and<space>' between two remove language names elseif 2 < code thenprefix if present (script value may now be empty string) language_list[code] script = 'and ' .. language_list[code]strip_apostrophe_markup (script); -- prepend last name with 'and<space>'strip any apostrophe markup else name script= table.concat (language_list, ', ') ; -- and concatenate with '<comma><space>' separatorsif not set, make sure script is an empty string
end
if this_wiki_name == name is_set (title) and is_set (script) then return script = ''.. script; -- if one language and that language is this wiki's return an empty string (no annotation)add a space before we concatenate
end
return (" " title .. wrap_msg ('language', name))script; -- otherwise wrap with '(in ...)' --[[ TODO: should only return blank or name rather than full list so we can clean up the bunched parenthetical elements Language, Type, Format ]]concatenation
end
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
--[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- Set style settings Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for CS1 citation templatesuse in COinS. Returns separator and postscript settings
]]
local function set_cs1_style get_coins_pages (pspages) local pattern; if not is_set (pspages) then return pages; end -- unless explicitely set to somethingif no page numbers then we're done while true do ps pattern = 'pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].'*%]"); -- terminate pattern is the opening bracket, the rendered citation with url and following space(s): "[url " if nil == pattern then break; end -- no more urls pattern = escape_lua_magic_chars (pattern); -- pattern is not a periodliteral string; escape lua's magic pattern characters pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
return '.'pages = pages:gsub("[%[%]]", ""); -- remove the brackets pages = pages:gsub("–", "-" ); -- replace endashes with hyphens pages = pages:gsub("&%w+;", ps"-" ); -- separator is a full stopand replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like? return pages;
end
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
local function remove_wiki_link( str )
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end));
end
--[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- Set style settings for CS2 citation templates. Returns separator, postscript, ref settings ]]Converts a hyphen to a dashlocal function set_cs2_style hyphen_to_dash(ps, refstr ) if not is_set (psstr) or str:match( "[%[%]{}<>]" ) then -- if |postscript~= has not been set, set cs2 default ps = ''; -- make sure it isn't nil end if not is_set (ref) then -- if |ref= is not set ref = "harv"return str; -- set default |ref=harv end return str:gsub( '-',', ps, ref–' ); -- separator is a comma
end
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
--[[--------------------------< 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= is not set or when its value is invalid, use config.CitationClass and parameter values to establishrendered styleJoins a sequence of strings together while checking for duplicate separation characters.
]]
local function get_settings_from_cite_class safe_join(pstbl, ref, cite_class) local sep; if (cite_class == "citation") then -- for citation templates (CS2) sep, ps, ref = set_cs2_style (ps, ref); else -- not a citation template so CS1 sep, ps = set_cs1_style (psduplicate_char ); end return sep, ps, ref -- return them allend --[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or usesconfig.CitationClass from the template's #invoke: to establish style. ]] local function set_style (mode, ps, ref, cite_class) local sep; if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style sep, ps, ref = set_cs2_style (ps, ref); elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style sep, ps = set_cs1_style (ps); else -- anything but cs1 or cs2 sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass end if 'none' == psNote:lower() then -- if assigned value is 'none' then ps = ''; -- set to empty we use string endfunctions here, rather than ustring functions.
return sep, ps, refThis has considerably faster performance and should work correctly as long as the duplicate_char is strict ASCII. The stringsend in tbl may be ASCII or UTF8. ]] local str = ''; --[the output string local comp =[''; -------------------------< I S what does 'comp' mean? local end_chr = ''; local trim; for _ P D F >------------------------------------------------------------------, value in ipairs( tbl ) do Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] whenvalue == nil then value = ''; endapplying the pdf icon to external links. returns true if str == '' then -- if file extension output string is one of the recognized extensions, else falseempty ] str =] local function is_pdf value; -- assign value to it (urlfirst time through the loop) return url:match ( elseif value ~= '%.pdf$') or urlthen if value:match sub(1,1) == '<'%then -- Special case of values enclosed in spans and other markup.PDF$') or url comp = value:match gsub('"%.pdf[%?#]'b<>", "" ) or url:match ; -- remove html markup ('%.PDF[%?#]'<span>string</span> -> string) else comp = value; end --[[------------ --typically duplicate_char is sepc if comp:sub(1,1) == duplicate_char then --is first charactier same as duplicate_char? why test first character? -- Because individual string segments often (always?) begin with terminal punct for th -- preceding segment: 'First element' .. 'sepc next element' .. etc? trim = false; end_chr = str:sub(-1,-1); --get the last character of the output string --str = str .. "< S T Y L E _ F O R M A T >HERE(enchr=" .. end_chr.. ")" --debug stuff? if end_chr == duplicate_char then --if same as separator str = str:sub(1,-2); --remove it elseif end_chr == "'" then --if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "''" then --if last three chars of str are sepc'' str = str:sub(1, -4) .. "''"; --remove them and add back '' elseif str:sub(-5,-1) == duplicate_char .. "]]''" then --if last five chars of str are sepc]]'' trim = true; --why? why do this and next differently from previous? elseif str:sub(-4,-1) == duplicate_char .. "]''" then --if last four chars of str are sepc]'' trim = true; --same question 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(-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 -------------- Applies css style to normal case when |formaturl=, something & |chapter-formattitle=, etcTitle. Also emits an error message trim = true; end elseif end_chr == " " then -- if the format parameter doesnot have a matching url parameter. If the format parameter last char of output string is not set and the url contains a file extension thatspaceis recognized as a pdf document by MediaWiki's commons if str:sub(-2,-1) == duplicate_char ..css" " then -- if last two chars of str are <sepc><space> str = str:sub(1, this code will set the format parameter to (PDF-3) with; -- remove them both endthe appropriate styling. end
]] if trim then if value ~= comp then -- value does not equal comp when value contains html markup local function style_format dup2 = duplicate_char; if dup2:match(format, url, fmt_param, url_param"%A" )then dup2 = "%" .. dup2; end -- if is_set duplicate_char not a letter then escape it value = value:gsub( "(format%b<>)" .. dup2, "%1", 1 ) then -- remove duplicate_char if it follows html markup else format value = wrap_style value:sub('format'2, format-1 ); -- add leading space, parentheses, resizeremove duplicate_char when it is first character end end if not is_set (url) then end format str = format str .. set_error( 'format_missing_url', {fmt_param, url_param} )value; -- add an error messageit to the output string
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 formatstr;end
--[[--------------------------< 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 non--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------Latin alphabet or logogram, that name is to be transliterated into Latin characters.These things are not currently possible in this module so are left to the editor to do.
Returns a number that defines This test allows |first= and |last= names to contain any of the letters defined in the number of names displayed for author four Unicode Latin character sets [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and editor name lists and a boolean flagBasic Latin] 0041–005A, 0061–007Ato indicate when et al [http://www.unicode. should be appended to the name listorg/charts/PDF/U0080. When the value assigned to |displaypdf C1 Controls and Latin-xxxxors= is a number greater than or equal to zero1 Supplement] 00C0–00D6, 00D8–00F6, return the number and00F8–00FFthe previous state of the 'etal' flag (false by default but may have been set to true if the name list contains [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017Fsome variant of the text 'et al [http://www.unicode.')org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
When the value assigned to |display-xxxxorslastn= is the keyword 'etal'also allowed to contain hyphens, spaces, return a number that is one greater than thenumber of authors in the list and set the 'etal' flag trueapostrophes. This will cause the list_people(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |firstn= also allowed to display all ofthe names in the name list followed by 'et al.'contain hyphens, spaces, apostrophes, and periods
In all other cases, returns nil and At the previous state time of this writing, I had to write the 'etal' flagif nil == mw.ustring.find ... inputs: max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor test ouside of etalthe code editor and paste it here count: #a or #e list_name: 'authors' or 'editors' etal: author_etal or editor_etalbecause the code editor gets confused between character insertion point and cursor position.
]]
local function get_display_authors_editors is_good_vanc_name (maxlast, count, list_name, etalfirst) if is_set (max) then if 'etal' nil == max:lower():gsubmw.ustring.find (last, "^[ '%.]", '') then A-Za-zÀ- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; ÖØ-öø- number of authors + 1 so display all author name plus et al. etal = true; ƿDŽ-ɏ%- overrides value set by extract_names(%s%']*$") elseif max:match or nil == mw.ustring.find ('first, "^%d+$') then [A-Za- if is a string of numbers max = tonumber (max); zÀ-ÖØ- make it a number if max >= count then öø-ƿDŽ- if |displayɏ%-xxxxors= value greater than or equal to number of authors/editors add_maint_cat (%s%'disp_auth_ed', cfg%.special_case_translation [list_name]*$"); endthen else -- not a valid keyword or number table.insert( z.message_tail, { set_erroradd_vanc_error ( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message max = nil return false; -- unsetnot a string of latin characters; as if |display-xxxxors= had not been set endVancouver required Romanization end ; return max, etaltrue;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------format=vanc.
Adds page to Category:CS1 maint: extra text if Names in |pagefirstn= may be separated by spaces or |pages= has what appears to be some form of phyphens, or for initials, a period. See http://www.ncbi.nlm. or ppnih. abbreviation in the first characters of the parameter contentgov/books/NBK7271/box/A35062/.
check Page and Pages for extraneous pVancouver style requires family rank designations (Jr, II, III, p.etc) to be rendered as Jr, 2nd, pp3rd, and ppetc. at start of parameter value: This form is not good patterncurrently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http: '^P[^%//www.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiitncbi.nlm.nih.gov/books/NBK7271/box/A35085/. bad pattern: '^[Pp][Pp]' matches matches when |pageThis function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (s)= begins pp or pP or Pp or PP.
]]
local function extra_text_in_page_check reduce_to_initials(pagefirst) local good_pattern = '^P[if mw.ustring.match(first, "^%.Pp]'u%u$") then return first end; --when first contains just two upper- ok case letters, nothing to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?do local initials = {} local bad_pattern i = '0; -- counter for number of initials for word in mw.ustring.gmatch(first, "[^[Pp]?[Pp]%s%.?[ %d-]';+") do -- names separated by spaces, hyphens, or periods if not page:match table.insert(good_pattern) and initials, mw.ustring.sub(page:match (bad_patternword,1,1) or page:match ('^[Pp]ages?')) then -- Vancouver format does not include full stops. i = i + 1; -- bump the counter add_maint_cat ('extra_text')if 2 <= i then break; end -- only two initials allowed in Vancouver system;if 2, quit
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------Formats a list of people (e.g. authors / editors)
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubledparentheses to also have commas; in the old version of the code, the doubled parnetheses were included in therendered citation and in the metadata. Individual author names may be wikilinked]]
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function |vauthorslocal sep; local namesep; local format =Jones AB, [[Econtrol. Bformat local maximum = control. White|White EB]], ((Black, Brown, and Comaximum local lastauthoramp = control.))lastauthoramp; local text = {}
] if 'vanc' ==]format then -- Vancouver-like author/editor name styling? local function get_v_name_table (vparam sep = ', output_table, output_link_table)'; -- name-list separator between authors is a comma local name_table namesep = mw.text.split(vparam, "%s*,%s*")' '; -- names are separated by commaslast/first separator is a space local wl_type, label, linkelse sep = '; ' --name- wl_type not used here; just list separator between authors is a place holdersemicolon namesep = ', ' -- last/first separator is <comma><space> end
local i if sep:sub(-1,-1) ~= " " then sep = sep .. " " end if is_set (maximum) and maximum < 1then return "", 0; end -- returned 0 is for EditorCount;not used for authors
while name_table[for i] ,person in ipairs(people) do if name_table[i]:match ('^%(%is_set(person.*[^%)][^%)]$'last) then -- first segment of corporate with local mask = person.mask local one or more commas; this segment has the opening doubled parens local name sep_one = name_table[i]sep; if is_set (maximum) and i> maximum then etal =i+1true; break; -- bump indexer to next segment while name_table[i] doelseif (mask ~= nil) then name local n = name .. ', ' .. name_table[i]; -- concatenate with previous segmentstonumber(mask) if name_table[i]:match ('^n ~= nil) then one = string.*%rep("—",n)%)$') then else -- if this table member has the closing doubled parensone = mask; breaksep_one = " "; -- and done reassembling so
end
i=i+1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
tableone = person.insert last local first = person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub (output_link_table'%.', link''); -- 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) -- no wikilink or 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 = "[[L" .. person.link .. "|D" .. one .. "]]; add this " -- link author/editor if there this page is one, else empty stringnot the author's/editor's page end
end
table.insert( text, one )
table.insert( text, sep_one )
end
i = i+1; end return output_table;end
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
local result = table.concat(text) -- construct list
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
end
return result, count
end
--[[--------------------------< P A R S E _ V A U T N C H O R S _ V E I D I T O R S >-------------------------------- This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.--------------------------
Author / editor names in |vauthors= Generates a CITEREF anchor ID if we have at least one name or |veditors= must be in Vancouver system stylea date. 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 Otherwise returns an empty string.
Supports generational suffixes Jrnamelist is one of the contributor-, 2ndauthor-, 3rd, 4th–6thor editor-name lists chosen in that order. This function sets the vancouver error when a reqired comma year is missing and when there is a space between an author's initialsYear or anchor_year.
]]
local function parse_vauthors_veditors anchor_id (argsnamelist, vparam, list_nameyear) local names = {}; -- a table of for the one to four names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = {}; local v_link_table = {}; -- when name is wikilinked, targets go in this table local etal = false; -- return value set to true when we find some form of et al. vauthors parameter local last, first, link, mask, suffix; local corporate = false; vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commasyear for i, v_name v in ipairs(v_name_tablenamelist) do if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses loop through the list and take up to supress vanc formatting and error detection the first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor four last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses corporate = true; -- flag used in list_people()names elseif string.find(v_name, "%s") then if v_name:find('names[;%.i]') then -- look for commonly occurring punctuation characters; add_vanc_error ('punctuation'); end local lastfirstTable = {} lastfirstTable = mw.textv.split(v_name, "%s") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials if is_suffix (first) i == 4 then break end -- if a valid suffixfour then done suffix = first -- save it as a suffix and end first = table.removeinsert (lastfirstTablenames, year); -- get what should be add the initials from year at the table end -- no suffix error message here because letter combination may be result of Romanization; check for digits? last local id = table.concat(lastfirstTable, " "names) ; -- returns a string that is the concatenation of all other concatenate names that are not initialsand year for CITEREF id if mw.ustring.match is_set (last, '%a+%s+%u+%s+%a+'id) then add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing end if mw.ustring.match (v_name, ' %u %u$') then -- this test concatenation is in the wrong place TODO: move or replace with a more appropriate test add_vanc_error ('name'); -- matches a space between two intiials end else first = ''; -- set to not an empty string for concatenation and because it may have been set for previous author/editor last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end if is_set (first) then if not mw.ustring.match (first, return "^%u?%u$CITEREF") 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 = ''id; -- unset so we don't add this suffix to all subsequent namesthe CITEREF portion end else else if not corporate then is_good_vanc_name (last, return ''); 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 )return an empty string; names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add no reason to include CITEREF id in this assembled name to our names listcitation
end
return names, etal; -- all done, return our list of names
end
--[[--------------------------< S E L N A M E C T _ H A U T H O R S _ E D I T O R _ S O U R C E A L >----------------------------------------------------
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as Evaluates the source content of the author and editor name list orparameters for variations on the theme of et al. If found,select one of |editors=the et al. is removed, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as a flag is set to true and the source of function returns the editor modified name listand the flag.
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and This function never sets the flag to false but returns it's previous state because it may have been set byprevious passes through this function or by the parameters |display-authors= lowest andsimilarly, |editorn= (and aliases) highest and etal or |display-editors= lowestetal
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the secondtest which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a betterway to do this, I just haven't discovered what that way is.]]
Emits an error message when more than one xxxxor local function name_has_etal (name source is provided., etal, nocat)
In this function if is_set (name) then -- name can be nil in which case just return local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. if name:match (etal_pattern) then -- variants on et al. name = name:gsub (etal_pattern, vxxxxors ''); -- 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 or veditors= add_maint_cat ('etal'); -- and add a category if not already added end elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? name = name:gsub (others_pattern, ''); xxxxors -- if found, remove etal = true; -- set flag (may have been set previously here or by |display-authors or editors as appropriate.=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat ('etal'); -- and add a category if not already added end end end return name, etal; -- end
]]--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------Gets name list from the input arguments
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)local lastfirst = false; if select_one( Searches through args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a in sequential order to find |first1lastn= without a and |last1firstn=; this ... select_oneparameters ( args, cfg.or their aliases[list_name .. '-First']), 'none', 1 ) or -- and their matching link and mask parameters... also catches the case where Stops searching when both |firstlastn= is used with and |vauthorsfirstn= select_one( are not found in argsafter two sequential attempts: found |last1=, cfg.aliases[list_name .. '-Last']|last2=, and |last3= but doesn'none', 2 ) ort select_one( args, cfg.aliases[list_name .find |last4= and |last5= then the search is done. '-First'], 'none', 2 ) then lastfirst=true; end
if (is_set (vxxxxors) and true This function emits an error message when there is a |firstn=without a matching |lastn= lastfirst) or -- these . When there are 'holes' in the three error conditions (is_set (vxxxxors) list of last names, |last1= and is_set (xxxxors)) or (true |last3== lastfirst and is_set (xxxxors)) then local err_name; if 'AuthorList' are present but |last2== list_name then -- figure out which name should be used in is missing, an error message err_name is emitted. |lastn= 'author'; else err_name is not required to have a matching |firstn= 'editor'; end table.insert( z.message_tail, { set_error( 'redundant_parameters', {err_name .. '-name-list parameters'}, true ) } ); -- add error message end
if true == lastfirst then return 1 end; -- return a number indicating which When an author name source to use if is_set (vxxxxors) then return 2 end; if is_set (xxxxors) then return 3 end; return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last end --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------ This function is used to validate a or editor parametercontains some form of 'et al.'s assigned value for those parameters that have only a limited numberof allowable values (yes, y, true, no, etc)the 'et al. When ' is stripped from the parameter value has not been assigned and a value flag (missing or emptyetal) returnedin the source templatethat will cause list_people() to add the function returns truestatic 'et al.' text from Module:Citation/CS1/Configuration. If the parameter value is one This keeps 'et al.' out of the list of allowed values returnstrue; elsetemplate's metadata. When this occurs, emits an error message and returns falsethe page is added to a maintenance category.
]]
local function is_valid_parameter_value extract_names(value, nameargs, possiblelist_name) if not is_set (value) thenlocal names = {}; -- table of names return true local last; -- an empty parameter is okindividual name components local first; elseif in_array(value:lower(), possible) thenlocal link; return true local mask; elselocal i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; table.insert-- used to count the number of times we haven't found a |last= ( z.message_tailor alias for authors, { set_error( 'invalid_param_val', {name, value}, true ) } |editor-last or alias for editors) local etal=false; -- not return value set to true when we find some form of et al. in an allowed value so add error message return false endendauthor 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 (last, etal, false); --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >--------------------------------------find and remove variations on et al. first, etal = name_has_etal (first, etal, false); --find and remove variations on et al.
This function terminates if first and not last then -- if there is a firstn without a name list matching lastn table.insert( z.message_tail, { set_error(author'first_missing_last', {err_msg_list_name, contributori}, editortrue ) with a separator character (sepc} ) ; -- add this error message elseif not first and a spacenot last then -- if both firstn and lastn aren't found, are we done?when the count = count + 1; -- number of times we haven't found last character and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there is not a sepc character two-name hole in the list; can't tell which end else -- we have last with or when the without a first if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last three characters are not sepc followed by twoclosing square brackets table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower(close of a ) .. '-link' .. i )}); -- url or wikilinkin author link; end names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true )} ); -- add this error message end count = 0; -- reset the counter, we're looking for two consecutive missing names end i = i + 1; -- point to next args location end return names, etal; -- all done, return our list of namesend --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args forany of the parameters listed in each cfg.id_handlers['...'].parameters. When either of these is trueIf found, adds the name_list is terminated with aparameter and value tosingle space characterthe identifier list. Emits redundant error message is more than one alias exists in args
]]
local function terminate_name_list extract_ids(name_list, sepcargs ) if (string.sub (name_list,-3,-1) local id_list == sepc .. '. ') then -- if already properly terminated return name_list{}; -- just return the name listof identifiers found in args elseif for k, v in pairs(stringcfg.sub (name_list,id_handlers ) do --1k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'],-1) v is a table v == sepc) or select_one(stringargs, v.sub (name_list,-3parameters,-1) == sepc .. ']]redundant_parameters') then ; -- v.parameters is a table of aliases for k; here we pick one from args if last name in list ends with sepc charpresent return name_list .. " "if is_set(v) then id_list[k] = v; end -- don't if found in args, add another else return name_list .. sepc .. ' '; -- otherwise terninate the name identifier to our list
end
return id_list;
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
returns the concatenation inputs: id_list – table of the formatted volume and issue parameters as a single string; or formatted volumeidentifiers built by extract_ids()or formatted issue, or an empty string if neither are set. options – table of various template parameter values used to modify some manually handled identifiers
]]
local function build_id_list( id_list, options )
local new_list, handler = {};
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
local function format_volume_issue for k, v in pairs( id_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table -- fallback to read-only cfg handler = setmetatable( { ['id'] = v }, fallback(k) ); if handler.mode == 'external' then table.insert( new_list, {handler.label, external_link_id( handler ) } ); elseif handler.mode == 'internal' then table.insert( new_list, {handler.label, internal_link_id( handler ) } ); elseif handler.mode ~= 'manual' then error( cfg.messages['unknown_ID_mode'] ); elseif k == 'DOI' then table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } ); elseif k == 'HDL' then table.insert( new_list, {handler.label, hdl( v ) } ); elseif k == 'ARXIV' then table.insert( new_list, {handler.label, arxiv( v, options.Class ) } ); elseif k == 'ASIN' then table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } ); elseif k == 'LCCN' then table.insert( new_list, {handler.label, lccn( v ) } ); elseif k == 'OL' or k == 'OLA' then table.insert(volumenew_list, issue{handler.label, cite_classopenlibrary( v ) } ); elseif k == 'PMC' then table.insert( new_list, origin{handler.label, sepcpmc( v, loweroptions.Embargo ) } ); elseif k == 'PMID' then table.insert( new_list, {handler.label, pmid( v ) } ); elseif k == 'ISMN' then table.insert( new_list, {handler.label, ismn( v ) } ); elseif k == 'ISSN' then table.insert( new_list, {handler.label, issn( v ) } ); elseif k == 'EISSN' then table.insert( new_list, {handler.label, issn( v, true ) } ); -- true distinguishes eissn from issn elseif k == 'ISBN' then local ISBN = internal_link_id( handler ); if not is_set check_isbn(volumev ) and not is_set (issueoptions.IgnoreISBN) then ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" ); end table.insert( new_list, {handler.label, ISBN } ) ; elseif k == 'USENETID' then table.insert( new_list, {handler.label, message_id( v ) } ); return else error( cfg.messages['unknown_manual_ID'] ); end
end
if 'magazine' == cite_class or function comp(in_array (cite_classa, {'citation', 'map'}b ) and 'magazine' == origin) then if is_set (volume) and is_set (issue) then return wrap_msg ('vol-no', {sepc, volume, issue}, lower); elseif is_set - used in following table.sort(volume) then return wrap_msg ('vol', {sepc, volume}, lower); else return wrap_msg ('issue', {sepc, issue}, lower)a[1] < b[1]; end
end
local vol = ''table.sort( new_list, comp ); if is_set for k, v in ipairs(volumenew_list ) thendo if (4 < mw.ustring.len(volume)) then vol = substitute (cfg.messagesnew_list['j-vol'k], {sepc, volume}); else vol = substitute (cfg.presentationv['vol-bold'2], {sepc, hyphen_to_dash(volume)}); end
end
if is_set (issue) then return vol .. substitute (cfg.messages['j-issue'], issue); end return volnew_list;
end
--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------
Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities.
2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate content
when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29
TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible
characters table?
]]
local function coins_cleanup (value)
value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content
value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s
value = value:gsub ('‍\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe
value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11)
value = value:gsub (' ', ' '); -- replace entity with plain space
value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space
value = value:gsub ('‍', ''); -- remove ‍ entities
value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space
value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space
return value;
end
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
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--[[--------------------------< C O I N S >--------------------------------------------------------------------
Singular has priority over plural when both are providedCOinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
]]
local function format_pages_sheets COinS(pagedata, pages, sheet, sheets, cite_class, origin, sepc, nopp, lowerclass) if 'maptable' ~= type(data) or nil == cite_class next(data) then return ''; end for k, v in pairs (data) do -- only cite map supports sheetspin through all of the metadata parameter values if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) data[k] = coins_cleanup (sv) ; end end local ctx_ver = "Z39.88-2004"; -- treat table strictly as in-source locatorsan array with only set values. local OCinSoutput = setmetatable( {}, { __newindex = function(self, key, value) if is_set (sheetvalue) then rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } ); end end }); if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or ('citation' == origin class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then return OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier if 'arxiv', == class then -- set genre according to the type of citation template we are rendering OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv elseif 'conference', wrap_msg == class then OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set) elseif 'jweb' == class then OCinSoutput["rft.genre"] = "unknown"; --sheet', sheet, lowercite 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
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical';article titles
end
-- these used onlu for periodicals OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall OCinSoutput["rft.chron"] = data.Chron; -- free-form date components OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books OCinSoutput["rft.issue"] = data.Issue; OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata elseif is_set (sheets) 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier if 'journalreport' == origin class or 'techreport' == class then -- cite report and cite techreport return OCinSoutput["rft.genre"] = "report"; elseif 'conference'== class then -- cite conference when Periodical not set OCinSoutput["rft.genre"] = "conference"; elseif in_array (class, {'book', 'citation', wrap_msg ('j-sheetsencyclopaedia', sheets'interview', lower'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
return if 'map', == class or 'interview', == class then OCinSoutput["rft.genre"] = 'unknown', wrap_msg (; -- standalone map or interview else OCinSoutput["rft.genre"] = 'sheetsbook', {sepc, sheets}, lower); -- book and encyclopedia end
end
else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
OCinSoutput["rft.genre"] = "unknown";
end
OCinSoutput["rft.btitle"] = data.Title; -- book only
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
OCinSoutput["rft.series"] = data.Series; -- book only
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
OCinSoutput["rft.edition"] = data.Edition; -- book only
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
end
-- and now common parameters (as much as possible) local is_journal OCinSoutput["rft.date"] = 'data.Date; -- book, journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);dissertation
if is_set for k, v in pairs(pagedata.ID_list ) thendo -- what to do about these? For now assume that they are common to all? if is_journal k == 'ISBN' thenv = clean_isbn( v ) end return substitute ( local id = cfg.messagesid_handlers['j-pagek].COinS; if string.sub(s)']id or "", 1, page4 ), == 'info'then -- for ids that are in the info:registry OCinSoutput["rft_id"] = table.concat{ id, ''"/", ''v }; elseif not nopp then return substitute string.sub (cfg.messages['p-prefix']id or "", {sepc1, page}3 ), == 'rft'then -- for isbn, ''issn, eissn, ''etc that have defined COinS keywords OCinSoutput[ id ] = v; elseelseif id then -- when cfg.id_handlers[k].COinS is not nil return substitute (OCinSoutput["rft_id"] = table.concat{ cfg.messagesid_handlers['nopp'k].prefix, {sepc, pagev }), '', '', '';-- others; provide a url
end
elseif is_set(pages) thenend if is_journal then return substitute (cfg.messages--[['j-page(s)'], pages) for k, '', '', ''; elseif tonumberv in pairs(pagesdata.ID_list ) ~= nil and not nopp then do -- if pages is only digits, what to do about these? For now assume a single page numberthat they are common to all? return '' local id, substitute (value = cfg.messagesid_handlers[k].COinS; if k == 'p-prefixISBN']then value = clean_isbn( v ); else value = v; end if string.sub( id or "", {sepc1, pages}4 ), '', == 'info'; elseif not nopp then return '', substitute (cfg.messagesOCinSoutput['pp-prefix'"rft_id"]= table.concat{ id, {sepc"/", pagesv }), '', '';
else
return 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, substitute non-printing or invisible characers if k == 1 then -- for the first author name only if is_set(last) and is_set(cfgfirst) then -- set these COinS values if |first= and |last= specify the first author name OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation OCinSoutput["rft.messagesaufirst"] = first; -- book, journal, dissertation elseif is_set(last) then OCinSoutput['nopp'"rft.au"]= last; -- book, journal, dissertation -- otherwise use this form for the first name end else -- for all other authors if is_set(last) and is_set(first) then OCinSoutput["rft.au"] = table.concat{sepclast, ", ", pagesfirst }; -- book, journal, dissertation elseif is_set(last)then OCinSoutput["rft.au"] = last; -- book, ''journal, '';dissertation end
end
end
OCinSoutput.rft_id = data.URL;
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
return ''-- sort with version string always first, ''and combine. table.sort( OCinSoutput ); table.insert( OCinSoutput, ''1, ''"ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004" return empty stringstable.concat(OCinSoutput, "&");
end
--[=[--------------------------< A R C H I V G E T _ U R L I S O 6 3 9 _ C H O D E C K >------------------------------------------------
Check archive.org urls to make sure they at least look like they are pointing at valid archives and Validates language names provided in |language= parameter if not to the save snapshot url or to calendar pagesan ISO639-1 code. When Handles the archive url special case that is Norwegian whereISO639-1 code 'https://web.archive.org/save/no' (or http://...)archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allowunwitting readers mapped to dolanguage name 'Norwegian Bokmål' by Extention:CLDR.
When Returns the archivelanguage name and associated ISO639-1 code.org url does not have 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 complete timestampmatch is found, archive.org chooses a snapshot according the Wikimedia version (assumed to its ownbe correct) is returned alongalgorithm or provides a calendar 'search' resultwith the code. [[WP:ELNO]] discourages links to search resultsWhen there is no match, we return the original language name string.
This function looks at mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are includedin the list will be found if that name is provided in the value assigned to |archive-urllanguage= and returns empty strings for parameter. For example, if |archive-urllanguage= andSamaritan Aramaic, that name will be|archive-date= and found with the associated code 'sam', not an error message when: |archiveISO639-url= holds an archive1 code.org save command url |archive-url= When names are found and the associated code is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the correct placetwo characters, this functionotherwise returns |archive-url= and |archive-date=only the Wikimedia language name.
There are two mostly compatible archive.org urlsAdapted from code taken from Module: //web.archive.org/<timestamp>... Check ISO 639-- the old form //web1.archive.org/web/<timestamp>... -- 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 local function supports a preview mode. When the article is rendered in preview mode, this funct may return a modifiedget_iso639_code (lang)archive url if 'norwegian' == lang: for save command errors, return undated wildcard lower(/*/)then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR for timestamp errors when the timestamp has a wildcard return 'Norwegian', return the url unmodified'no'; -- Make sure rendered version is properly capitalized for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)end ] local languages =] local function archive_url_check mw.language.fetchLanguageNames(mw.getContentLanguage():getCode(url), date'all') -- get a list of language names known to Wikimedia local err_msg = -- ('all'; -- start with the error message emptyis required for North Ndebele, South Ndebele, and Ojibwa) local path, timestamp, flaglanglc = mw.ustring.lower(lang); -- portions of the archive.or urllower case version for comparisons
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url return urlfor code, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate end if url:matchname in pairs('//web%.archive%.org/save/'languages) then do -- scan the list to see if a save command url, we don't want to allow saving of the target page can find our language err_msg if langlc = 'save command'; url = url:gsub ('(//web%mw.archive%ustring.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL elseif url:matchlower('//liveweb%.archive%.org/'name) 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 2 ~= timestampcode:len() then -- path and flag optional, must have 14ISO639-digit timestamp here1 codes only err_msg = 'timestamp' return name; 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)so return the name but not the code
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 urlname, datecode; -- found it, return archiveURL name to ensure proper capitalization and ArchiveDatethe ISO639-1 code
end
end
-- if here, something not right so table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } )return lang; -- add error message and if is_set (Frame:preprocess('{{REVISIONID}}')) then return '', ''not valid language; -- return empty strings language in original case and nil for archiveURL and ArchiveDate else return url, date; ISO639-- preview mode so return archiveURL and ArchiveDate end1 codeend
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Get language name from ISO639--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ Look at the contents of a parameter1 code value provided. If the content has a string of characters and digits followed by an equalsign, compare code is valid use the alphanumeric string to the list of cs1|2 parameters. If foundreturned name; if not, then use the string is possibly aparameter value that is missing its pipe: {{cite ... |title=Title access-date=2016-03-17}} cs1|2 shares some parameter names was provided with xml/html atributes: class=, title=, etc. To prevent false positives xml/htmltags are removed before the search. If a missing pipe is detected, this function adds the missing pipe maintenance categorylanguage parameter. ]]
local function missing_pipe_check There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (valuecode 'nb')and local capture; value = value:gsub Norwegian Nynorsk (code '%b<>nn'). The third, code 'no'); , is defined by ISO639-- remove xml/html tags because attributes: class=1 as 'Norwegian' though in Norway this is pretty much meaningless. However, title=it appearsthat on enwiki, etc 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.
capture = value:match (Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'%s+(%a[%a%d]+)%s*=. Here we undo that andreturn ') or value:match (Norwegian'^(%a[%a%d]+)%s*when editors use |language=no. We presume that editors don'); -- find and categorize parameters with possible missing pipes if capture and validate (capture) then -- if t know about the capture is a valid parameter name add_maint_cat (variants or can'missing_pipe'); endendt descriminate between them.
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-[[--------------------------< C I T A T I O N 0 >-----------------------------------------------------------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.
This is the main function doing supports multiple languages in the majority of form |language=nb, French, th where the citation formattinglanguage names or codes are separated from each other by commas.
]]
local function citation0language_parameter ( config, argslang) local code; --the ISO639-[[ 1 two character code Load Input Parameterslocal name; -- the language name The argument_wrapper facilitates the mapping local language_list = {}; -- table of multiple aliases language names to single internal variable. ]]be rendered local A names_table = argument_wrapper( args ){}; local i -- table made from the value assigned to |language=
-- Pick out the relevant fields from the argumentsnames_table = mw.text. Different citation templates split (lang, '%s*,%s*'); -- define different field names for the same underlying things. should be a comma separated list
-- set default parameter values defined by |mode= parameter. local Mode = A['Mode']; if not is_valid_parameter_value for _, lang in ipairs (Mode, 'mode', cfg.keywords['mode']names_table) then Mode = ''; enddo -- reuse lang
local author_etal; local if lang:match ('^%a%a = {}; %-- authors list from |lastn= / |firstn= pairs ') or |vauthors2 = local Authors; local NameListFormat = A['NameListFormat'];lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes) local Collaboration = A[ if lang:match ('Collaboration^zh-'];) then do -- to limit scope of selected local selected name = select_author_editor_source mw.language.fetchLanguageName( lang:lower(A['Vauthors']), A['Authors'], args, 'AuthorList'lang:lower() ); if 1 == selected then else a, author_etal name = extract_names mw.language.fetchLanguageName( lang:lower(args), 'AuthorList'mw.getContentLanguage():getCode() ); -- fetch author list from |authorn= / |lastn= / |firstn=, |authorget ISO 639-linkn=, and |author-maskn=1 language name if Language is a proper code end end elseif 2 == selected if is_set (name) then -- if Language specified a valid ISO639-1 code NameListFormat code = 'vanc'lang:lower(); -- override whatever |name-list-format= might besave it else aname, author_etal code = parse_vauthors_veditors get_iso639_code (args, args.vauthors, 'AuthorList'lang); -- fetch author list attempt to get code from |vauthors=, |author-linkn=, and |author-maskn=name (assign name here so that we are sure of proper capitalization) end elseif 3 if is_set (code) then if 'no' == selected code then Authors name = A['Authors挪威语']end; -- use content of |authors=override wikimedia when code is 'no' if 'authorszh' ~== Acode and not code:ORIGINmatch ('Authors^zh-') then -- but add a maint cat if English not the parameter is |authors=language add_maint_cat add_prop_cat ('authorsforeign_lang_source', {name, code}); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
else
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
if is_set table.insert (Collaborationlanguage_list, name) then; author_etal name = true''; -- so that |displaywe can reuse it end code = #language_list -- reuse code as number of languages in the list if 2 >= code then name = table.concat (language_list, '及') -authors- insert '<space>及<space>' between two language names elseif 2 < code then language_list[code] =etal not required'及' .. language_list[code]; -- prepend last name with '及<space>' endname = table.concat (language_list, '，') -- and concatenate with '<comma><space>' separators
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
local Others = A--['Others'];[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
local editor_etal;Set style settings for CS1 citation templates. Returns separator and postscript settings local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= local Editors;]]
do -- to limit scope of selected local selected = select_author_editor_source function set_cs1_style (A['Veditors'], A['Editors'], args, 'EditorList'ps); if 1 == selected then e, editor_etal = extract_names not is_set (args, 'EditorList'ps); then -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=unless explicitely set to something elseif 2 == selected then NameListFormat ps = 'vanc'; -- override whatever |name-list-format= might be e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= elseif 3 == selected then Editors = A['Editors']; -- use content of |editors= add_maint_cat ('editors'); -- but add terminate the rendered citation with a maint cat because use of this parameter is discouraged endperiod
end
return '.', ps; -- separator is a full stop
end
local t = {}; -- translators list from |translator[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------lastn= / translator-firstn= pairs local Translators; -- assembled translators name list t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn= Set style settings for CS2 citation templates. Returns separator, -linkn=postscript, -maskn=ref settings
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= pairs local Contributors; -- assembled contributors name list local Contribution = A['Contribution'];function set_cs2_style (ps, ref) if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']ps) then -- if |contributorpostscript= and |contribution= only supported in book citeshas not been set, set cs2 default c ps = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=make sure it isn't nil end if 0 < #c then if not is_set (Contributionref) then -- |contributor= requires |contribution= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message c = {}; -- blank the contributors' table; it is used as a flag later end if 0 == #a then -- |contributor= requires |author= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message c ref= {}; -- blank the contributors' table; it is used as a flag later end end else -- if not a book citeset 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')})ref = "harv"; -- add contributor ignored error message end Contribution set default |ref= nil; -- unsetharv
end
return ',', ps, ref; -- separator is a comma
end
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >-------------------list-format']) then -- only accepted When |mode= is not set or when its value for this parameter is 'vanc' NameListFormat = ''; -- anything elseinvalid, set use config.CitationClass and parameter values to empty stringestablish endrendered style.
local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- Get title data local Title = A['Title']; local ScriptTitle = A['ScriptTitle']; local BookTitle = A['BookTitle']; local Conference = A['Conference']; local TransTitle = A['TransTitle']; local TitleNote = A['TitleNote']; local TitleLink = A['TitleLink']; link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
local Chapter = A['Chapter'];function get_settings_from_cite_class (ps, ref, cite_class) local ScriptChapter = A['ScriptChapter']sep; local ChapterLink -- if (cite_class == A['ChapterLink']; "citation") then -- deprecated as a parameter but still used internally by cite episodefor citation templates (CS2) local TransChapter sep, ps, ref = A['TransChapter']set_cs2_style (ps, ref); local TitleType = A['TitleType']; local Degree = A['Degree'];else -- not a citation template so CS1 local Docket sep, ps = A['Docket']set_cs1_style (ps); local ArchiveFormat = A['ArchiveFormat'];end
local ArchiveDate;return sep, ps, ref -- return them all local ArchiveURL;end
ArchiveURL, ArchiveDate = archive_url_check (A--['ArchiveURL'], A['ArchiveDate']) local DeadURL = A['DeadURL'] if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string end---------------------< S E T _ S T Y L E >------------------------------------------------------------
local URL Establish basic style settings to be used when rendering the citation. Uses |mode= A['URL']if set and valid or uses local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURLconfig.CitationClass from the template']; local ChapterURLorigin = As #invoke:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameterto establish style.
local Series = A['Series']; local Volume; local Issue; local Page; local Pages; local At;]
local function set_style (mode, ps, ref, cite_class) local sep; if in_array 'cs2' == mode then -- if this template is to be rendered in CS2 (config.CitationClasscitation) style sep, ps, ref = set_cs2_style (ps, cfg.templates_using_volumeref) ; elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style sep, ps = set_cs1_style (ps); else -- anything but cs1 or cs2 Volume sep, ps, ref = A[get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template'Volume'];s CitationClass
end
-- conference & map books do not support issue if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'mapnone'}) and not is_set (Periodical))then Issue = A['Issue']; end local Position = ''; if not in_array ps:lower(config.CitationClass, cfg.templates_not_using_page) then Page = A[ -- if assigned value is 'Pagenone'];then Pages ps = hyphen_to_dash( A['Pages'] ); At = A['At']; -- set to empty string
end
return sep, ps, ref
end
local Edition = A--['Edition']; local PublicationPlace = A['PublicationPlace'] local Place = A['Place']; local PublisherName = A['PublisherName']; local RegistrationRequired = A['RegistrationRequired']; if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then RegistrationRequired=nil; end-------------------------< I S _ P D F >------------------------------------------------------------------
local SubscriptionRequired = ADetermines if a url has the file extension that is one of the pdf file extensions used by ['SubscriptionRequired'[MediaWiki:Common.css];] when if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfgapplying the pdf icon to external links.keywords ['yes_true_y']) then SubscriptionRequired=nil; end
local UrlAccess = A['UrlAccess']; if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then UrlAccess = nil; end returns true if not is_set(URL) and is_set(UrlAccess) then UrlAccess = nil; table.insert( z.message_tailfile extension is one of the recognized extension, { set_error( 'param_access_requires_param', {'url'}, true ) } ); endelse false
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, 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 ]= nil; -- unset; prefer |access= over |subscription= end if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message RegistrationRequired = nil; -- unset; prefer |access= over |registration= end]
local ChapterUrlAccess = A['ChapterUrlAccess'];function is_pdf (url) if not is_valid_parameter_value return url:match (ChapterUrlAccess, 'chapter-url-access', cfg%.keywords pdf[%?#]?'url-access']) then -- same as or url-access ChapterUrlAccess = nil; end if not is_set:match (ChapterURL) and is_set(ChapterUrlAccess) then ChapterUrlAccess = nil; table'%.insert( z.message_tail, { set_error( PDF[%?#]?'param_access_requires_param', {'chapter-url'}, true ) } ); end
local Via = A--['Via']; local AccessDate = A['AccessDate']; local Agency = --------------------------< S T Y L E _ F O R M A['Agency'];T >------------------------------------------------------
local Language Applies css style to |format=, |chapter-format= A[, etc. Also emits an error message if the format parameter doesnot have a matching url parameter. If the format parameter is not set and the url contains a file extension thatis recognized as a pdf document by MediaWiki'Language'];s commons.css, this code will set the format parameter to (PDF) withthe appropriate styling. local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local DoiBroken = A['DoiBroken']; local ID = A['ID'];function style_format (format, url, fmt_param, url_param) local ASINTLD = A['ASINTLD'];if is_set (format) then local IgnoreISBN format = A[wrap_style ('IgnoreISBNformat'], format); -- add leading space, parenthases, resize if not is_valid_parameter_value is_set (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']url) then IgnoreISBN format = nilformat .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- anything else, set to empty stringadd an error message
end
local Embargo elseif is_pdf (url) then -- format is not set so if url is a pdf file then format = A[wrap_style ('format', 'EmbargoPDF']); -- set format to pdf local Class else format = A['Class']; -- empty string for concatenation end return format;end --[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------ arxiv class identifier
local ID_list = extract_ids( args ); local ID_access_levels = extract_id_access_levels( args, ID_list );Returns a number that may or may not limit the length of the author or editor name lists.
local Quote When the value assigned to |display-authors= A[is a number greater than or equal to zero, return the number andthe previous state of the 'Quoteetal'];flag (false by default but may have been set to true if the name list containssome variant of the text 'et al.').
local LayFormat When the value assigned to |display-authors= A[is the keyword 'LayFormatetal'];, return a number that is one greater than the local LayURL = A[number of authors in the list and set the 'LayURLetal'];flag true. This will cause the list_people() to display all of local LaySource = A[the names in the name list followed by 'LaySourceet al.']; local Transcript = A['Transcript']; local TranscriptFormat = A[In all other cases, returns nil and the previous state of the 'TranscriptFormatetal']; local TranscriptURL = A['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURLflag.
local LastAuthorAmp = A['LastAuthorAmp']; if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then LastAuthorAmp = nil; -- set to empty string end
local function get_display_authors_editors (max, count, list_name, etal) local no_tracking_cats if is_set (max) then if 'etal' == Amax:lower():gsub("['NoTracking%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.']spellings and stylings max = count + 1; -- number of authors + 1 so display all author name plus et al. etal = true; -- overrides value set by extract_names() elseif max:match ('^%d+$') then -- if is a string of numbers max = tonumber (max); -- make it a number if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed', list_name); end else -- not is_valid_parameter_value a valid keyword or number table.insert(no_tracking_catsz.message_tail, { set_error( 'no-trackinginvalid_param_val', cfg.keywords [{'yes_true_ydisplay-'].. list_name, max}, true ) } ) then; -- add error message no_tracking_cats max = nil; -- set to empty stringunset
end
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
return max, etal;
end
--local variables that are not cs1 parameters local use_lowercase; [[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------ 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 Adds page to Category:CS1 maint: extra text if |page= A['DF']; -- date format set in cs1or |2 template if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword DF pages= ''; -- not valid, set has what appears to empty stringbe some form of p. or pp. endabbreviation in the first characters of the parameter content.
local sepc; -- separator between citation elements check Page and Pages for CS1 a periodextraneous p, p., for CS2pp, a comma local PostScript;and pp. at start of parameter value: local Ref; sepc, PostScript, Ref = set_style (Modegood pattern:lower(), A'^P['PostScript'^%.P%l], A['Ref'], config.CitationClassmatches when |page(s);= begins PX or P# but not Px where x and X are letters and # is a dgiit use_lowercase = ( sepc == bad pattern: ',^[Pp][Pp]' matches matches when |page(s); -- used to control capitalization for certain static text= begins pp or pP or Pp or PP
--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]]
local function extra_text_in_page_check (page)-- check for extra |pagelocal good_pattern =, |pages'^P[^%.P%l]'; local good_pattern = or |at= parameters'^P[^%. Pp]'; -- ok to begin with uppercase P: P7 (also sheet and sheets while we're at itpg 7 of section P) select_onebut not p123 ( args, {'page123) TODO: add Gg for PG or Pg?-- local bad_pattern = ', ^[Pp][Pp]'p; local bad_pattern = ', 'pp', 'pages', 'at', ^[Pp]?[Pp]%.?[ %d]'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
local NoPP = A['NoPP'] if is_set not page:match (NoPPgood_pattern) and is_valid_parameter_value (NoPP, page:match (bad_pattern) or page:match ('nopp', cfg.keywords ^[Pp]ages?'yes_true_y'])) then NoPP = true; else NoPP = niladd_maint_cat ('extra_text'); -- unset, used as a flag later
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- 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[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >-------------------------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: This function extracts author / editor names from |encyclopedia and vauthors= or |title then map |title to |article veditors= and finds matching |encyclopedia to |title |encyclopedia xxxxor-maskn= and |article then map |encyclopedia to |title |encyclopedia xxxxor-linkn= in args. It then map |encyclopedia to |titlereturns a table of assembled names just as extract_names() does. Author / editor names in |trans-title maps to vauthors= or |trans-chapter when |title is re-mappedveditors= must be in Vancouver system style. Corporate or institutional names |url maps to |chapterurl when |title is remappedmay sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance All other combinations of |encyclopediatests, |title, and |article are not modified ]]wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
local Encyclopedia = A[This function sets the vancouver error when a reqired comma is missing and when there is a space between an author'Encyclopedia'];s initials.
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation if is_set(Periodical) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then if not is_set(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 local function parse_vauthors_veditors (ChapterURL) and is_set (TitleLink) then Chapter = make_wikilink (TitleLinkargs, vparam, Chapterlist_name); end Title local names = Periodical{}; ChapterFormat = Format; Periodical = ''; -- redundant so unset TransTitle table of names assembled from |vauthors= ''; URL , |author-maskn= ''; Format , |author-linkn= ''; TitleLink local v_name_table = ''{}; ScriptTitle local etal = ''false; end else -- |title not return value setto true when we find some form of et al. vauthors parameter Title = Periodical local last, first, link, mask; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical local corporate = ''false; -- redundant so unset end end end
vparam, etal = name_has_etal (vparam, etal, true); -- Special case for cite techreportfind and remove variations on et al. if do not categorize (configdo it here because et al.CitationClass == "techreport"might have a period) then -- special case for cite techreport if is_setvparam:find (A'%[%['Number) or vparam:find ('%]%]) then -- cite techreport uses 'number', which other citations alias to 'issue' if not is_set(ID) then -- can we use ID for the "number"?no wikilinking vauthors names 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 add_vanc_error ('parameter', 'number')}, true )}); end end
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
for i, v_name in ipairs(v_name_table) do if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection first = ''; -- special case set to empty string for concatenation and because it may have been set for cite mailing listprevious author/editor last = v_name:match ('^%(%((.+)%)%)$') corporate = true; elseif string.find(v_name, "%s") then lastfirstTable = {} lastfirstTable = mw.text.split(v_name, "%s") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials if mw.ustring.match (configlast, '%a+%s+%u+%s+%a+') or mw.CitationClass ustring.match (v_name, ' %u %u$') then add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials end else first =''; -- set to empty string for concatenation and because it may have been set for previous author/editor last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end if is_set (first) and not mw.ustring.match (first, "mailinglist^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else add_vanc_error (); Periodical end -- this from extract_names () link = A select_one( args, cfg.aliases[list_name .. 'MailingList-Link'], 'redundant_parameters', i ); elseif mask = select_one( args, cfg.aliases[list_name .. 'mailinglist-Mask' == A:ORIGIN(], 'Periodicalredundant_parameters', i ) then; Periodical names[i] = ''{last = last, first = first, link = link, mask = mask, corporate=corporate}; -- unset because mailing list is only used for cite mailing add this assembled name to our names list
end
return names, etal; -- all done, return our list of names
end
-- Account for [[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the oddity that is {{cite conference}}author name list orselect one of |editors=, before generation |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of COinS datathe editor name list. if 'conference' Only one of these appropriate three will be used. The hierarchy is: |authorn=(and aliases) highest and |authors= config.CitationClass thenlowest and if is_setsimilarly, |editorn= (BookTitleand aliases) thenhighest and |editors= lowest Chapter = Title;-- ChapterLink When looking for |authorn= TitleLink; -- / |chapterlinkeditorn= is deprecated ChapterURL parameters, test |xxxxor1= URL; ChapterUrlAccess and |xxxxor2= UrlAccess(and all of their aliases);stops after the second ChapterURLorigin = URLorigin;test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better URLorigin = way to do this, I just haven'';t discovered what that way is. Emits an error message when more than one xxxxor name source is provided. ChapterFormat In this function, vxxxxors = Formatvauthors or veditors;xxxxors = authors or editors as appropriate. TransChapter = TransTitle; Title ]] local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)local lastfirst = BookTitlefalse; Format = ' if select_one( args, cfg.aliases[list_name .. ';-- TitleLink = Last'], '; TransTitle = none'';, 1 ) or -- do this twice incase we have a first 1 without a last1 URL = select_one( args, cfg.aliases[list_name .. '-Last'; end elseif ], 'speechnone' ~= config.CitationClass , 2 ) then Conference lastfirst= ''true; -- not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities local Cartography if (is_set (vxxxxors) and true = ""; local Scale = ""; local Sheet = A['Sheet'] lastfirst) or ''; -- these are the three error conditions local Sheets = A['Sheets'] (is_set (vxxxxors) and is_set (xxxxors)) or ''; if config.CitationClass (true == "map" lastfirst and is_set (xxxxors)) then Chapter = A['Map'] local err_name; ChapterURL = A[ if 'MapURLAuthorList']; ChapterUrlAccess = UrlAccess; TransChapter = A['TransMap']; ChapterURLorigin = A:ORIGIN('MapURL');list_name then -- figure out which name should be used in error message ChapterFormat err_name = A['MapFormatauthor']; else Cartography err_name = A['Cartographyeditor']; if is_set( Cartography ) then end Cartography = sepc table.insert( z. " " .. wrap_msg message_tail, { set_error('cartographyredundant_parameters', Cartography, use_lowercase); end Scale = A[ {err_name .. 'Scale-name-list parameters']}, true ) } ); if is_set( Scale ) then Scale = sepc .. " " .. Scale; end-- add error message
end
if true == lastfirst then return 1 end; -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.return a number indicating which author name source to use if 'episode' == config.CitationClass or 'serial' == config.CitationClass is_set (vxxxxors) thenreturn 2 end; local AirDate = A['AirDate'] if is_set (xxxxors) then return 3 end; local SeriesLink = A['SeriesLink'] return 1; -- no authors so return 1;this allows missing author name test to run in case there is a first without last end
link_title_ok (SeriesLink, --[[--------------------------< I S _ V A:ORIGIN ('SeriesLink'), Series, 'series'); L I D _ P A R A M E T E R _ V A L U E >---------------------------- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
local Network = A[This function is used to validate a parameter'Network']s assigned value for those parameters that have only a limited numberof allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or emptyin the source template) the function refurns true. If the parameter value is one of the list of allowed values returnstrue;else, emits an error message and returns false. local Station = A['Station'];] local sfunction is_valid_parameter_value (value, n = {}name, {};possible) -- do common parameters first if not is_set(Networkvalue) then table.insert(n, Network) return true; end -- an empty parameter is ok if is_set elseif in_array(value:lower(Station) then table.insert(n, Stationpossible)then return true; end else ID = table.concatinsert(nz.message_tail, sepc .. { set_error( ' invalid_param_val', {name, value}, true ) } );-- not an allowed value so add error message return false if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = AirDate; end end
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); [[-- add error message SeriesNumber = ''; -- unset; prefer |season= over |seriesno= end -- assemble a table of parts concatenated later into Series if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ''; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = --------------< T E R M I N A T E _ N A:ORIGIN('URL'); Title = Series; M E _ L I S T >-------------------------------------- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
if is_set This function terminates a name list (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = make_wikilink (ChapterLinkauthor, contributor, Chaptereditor); elseif is_set with a separator character (ChapterLinksepc) and is_set (ChapterURL) then -- if both are set, URL links episode;a space Series = make_wikilink (ChapterLink, Series); end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; else -- now oddities that when the last character is not a sepc character or when the last three characters are cite serial Issue = ''; -- unset because this parameter no longer supported not sepc followed by the citation/core version of cite serialtwo Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? if is_set closing square brackets (Seriesclose of a wikilink) and is_set (SeriesLink) then Series = make_wikilink (SeriesLink. When either of these is true, Series); end Series = wrap_style ('italic-title', Series); -- series the name_list is italicized end terminated with a end -- end of {{cite episode}} stuffsingle space character.
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. do if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message end if 'arxiv' == config.CitationClass then Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string end]
local function terminate_name_list (name_list, sepc) if 'biorxiv' (string.sub (name_list,-1,-1) == configsepc) or (string.CitationClass then Periodical sub (name_list,-3,-1) == sepc .. 'bioRxiv]]') then -- if last name in list ends with sepc char return name_list .. " "; -- set to bioRxiv for COinS; after that, must be set to empty stringdon't add another end else if 'citeseerx' == config return name_list .. sepc ..CitationClass then Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string end endotherwise terninate the name list
end
end
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
end
end
if is_set(TitleType) then -- if type parameter is specified TitleType = substitute( cfg.messages['type'], TitleType); [-------------------------< F O R M A T _ V O L U M E _ I S S U E >-------------------------------------- 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 set. if not is_set (Date) then Date = Yearreturns the concatenation of the formatted volume and issue parameters as a single string; -- promote Year to Dateor formatted volume Year = nil; -- make nil so Year as or formatted issue, or an empty string isn't used for CITEREF if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= neither 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 --[[ 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 where we get the date used in the metadata.]]
Date validation supporting code is in Module:Citation/CS1/Date_validation ]] do -- create defined block to contain local variables error_messagefunction format_volume_issue (volume, issue, cite_class, date_parameters_listorigin, mismatchsepc, lower) if not is_set (volume) and not is_set (issue) then local error_message = return ''; -- AirDate has been promoted to Date so not necessary to check it end local date_parameters_list = {['access-date']=AccessDate, [ if 'archive-datemagazine']=ArchiveDate, ['date']=Datecite_class or (in_array (cite_class, [{'doi-broken-datecitation']=DoiBroken, ['embargomap']=Embargo, [}) and 'lay-datemagazine']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}; anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_dateorigin);-- start temporary Julian / Gregorian calendar uncertainty categorization if COinS_date.inter_cal_cat then add_prop_cat ('jul_greg_uncertainty'); end-- end temporary Julian / Gregorian calendar uncertainty categorization if is_set (Yearvolume) and is_set (Dateissue) then -- both |date= and |year= not normally needed; local mismatch = year_date_check return wrap_msg (Year'vol-no', {sepc, volume, Dateissue}, lower); if 0 == mismatch then -- |year= does not match a year-value in |date= if elseif is_set (error_messagevolume) then -- if there is already an error message error_message = error_message .. return wrap_msg ('vol', '{sepc, volume}, lower); -- tack on this additional message end error_message = error_message .. '|year= / |date= mismatch'; else elseif 1 == mismatch then -- |year= matches year-value in |date= add_maint_cat return wrap_msg ('date_yearissue', {sepc, issue}, lower); end
end
end
local vol = '';
if not is_set(error_messagevolume) then -- error free dates only local modified = false; -- flag if is_set (DF) then -- if we need to reformat dates modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate end if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate modified = true; add_maint_cat ('date_format'); -- hyphens were converted so add maint category end -- for those wikis that can and want to have English date names translated to the local language, -- uncomment these three lines6 < mw. Not supported by enustring.wiki len(for obvious reasonsvolume)-- if date_name_xlate (date_parameters_list) then-- modified vol = true;-- end if modified then -- if the date_parameters_list values were modified AccessDate = date_parameters_listsubstitute (cfg.messages['accessj-datevol'], {sepc, volume}); -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list['archive-date']; Date = date_parameters_list['date']; DoiBroken = date_parameters_list['doi-broken-date']; LayDate = date_parameters_list['lay-date']; PublicationDate = date_parameters_list['publication-date']; end
else
table.insert( z.message_tail, { set_errorvol = wrap_style ( 'bad_datevol-bold', {error_message}, true hyphen_to_dash(volume) } ); -- add this error message
end
end if is_set (issue) then return vol .. substitute (cfg.messages['j-issue'], issue); end return vol;end --[[------------------------- end < F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of dothe others set to empty strings.The return order is: page, pages, sheet, sheets
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS. -- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time Singular has expiredpriority over plural when both are provided. Otherwise, holds embargo date Embargo = is_embargoed (Embargo);
]] local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) if config.CitationClass 'map' == "journal" and not is_setcite_class then -- only cite map supports sheet(URLs) and is_set(ID_list['PMC']) thenas in-source locators if not is_set (Embargosheet) then -- if not embargoed or embargo has expired URLif 'journal' =cfg.id_handlers[= origin then return 'PMC'].prefix .. ID_list[, '', wrap_msg ('j-sheet', sheet, lower), 'PMC']; -- set url to be the same as the PMC external link if not embargoedelse URLorigin = cfg.id_handlers[ return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), 'PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title= if end elseif is_set(AccessDatesheets) then -- access date requires |url if 'journal' =; pmc created url is not |url=origin then table.insert( z.message_tailreturn '', '', '', { set_errorwrap_msg ( 'accessdate_missing_urlj-sheets', {}sheets, true ) } lower); else AccessDate = return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower); -- unset
end
end
end
-- At this point fields may be nil if they werenlocal is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal't specified in the template use. We can use that fact.== origin); -- Test if citation has no titleis_set (page) then if is_journal then return substitute (cfg.messages['j-page(s)'], page), '', '', ''; elseif not is_setnopp then return substitute (Titlecfg.messages['p-prefix'], {sepc, page}) and, '', '', ''; not is_setelse return substitute (TransTitlecfg.messages['nopp'], {sepc, page}) and, '', '', ''; not end elseif is_set(ScriptTitlepages) then if is_journal then if return substitute (cfg.messages['j-page(s)'], pages), '', '', 'episode' ; elseif tonumber(pages) ~== config.CitationClass nil and not nopp then -- special case for cite episode; TODO: if pages is there only digits, assume a better way to do this?single page number table.insert return '', substitute ( zcfg.message_tailmessages['p-prefix'], { set_errorsepc, pages}), '', ''; elseif not nopp then return '', substitute ( cfg.messages['citation_missing_titlepp-prefix'], {sepc, pages}), 'series'}, true ) } )''; else table.insert return '', substitute ( zcfg.message_tailmessages['nopp'], { set_error( sepc, pages}), 'citation_missing_title', {'title'}, true ) } ); end
end
if return 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites Title = , ''; -- set title to return empty string add_maint_cat ('untitled');strings end
check_for_url ({ -- add error message when any of these parameters contains a URL ['title']=Title, [--------------------------< C I T A:ORIGIN('Chapter')]=Chapter,T I O N 0 >------------------------------------------------------------ [A:ORIGIN('Periodical')]=Periodical, [A:ORIGIN('PublisherName')] = PublisherName });This is the main function doing the majority of the citation formatting.
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title -- is the article title, and Chapter is a section within the article. So, 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]]
local function citation0( config, args) -- this is [[ Load Input Parameters The argument_wrapper facilitates the function call mapping of multiple aliases to COinS()single internal variable. local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, ['Chapter'] local A = make_coins_title argument_wrapper(coins_chapter, ScriptChapterargs ), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Degree'] = Degree; -- cite thesis only ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup local i ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; ['Season'] = COinS_datePick out the relevant fields from the arguments.rftssn, Different citation templates ['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Datedefine different field names for the same underlying things. local author_etal; keep this last bit? ['Series'] = Series, ['Volume'] = Volume, ['Issue'] local a = Issue, ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), ; -- pages stripped of external links ['Edition'] authors list from |lastn= Edition, ['PublisherName'] / |firstn= PublisherName, ['URL'] pairs or |vauthors= first_set ({ChapterURL, URL}, 2), [' local Authors'] = coins_author,; ['ID_list'] local NameListFormat = ID_list, A['RawPageNameListFormat'] = this_page.prefixedText, }, config.CitationClass);
do -- Account for the oddities that are {{cite arxiv}}to limit scope of selected local selected = select_author_editor_source (A['Vauthors'], A['Authors'], {{cite biorxiv}}args, and {{cite citeseerx}} AFTER generation of COinS data.'AuthorList'); if in_array 1 == selected then a, author_etal = extract_names (config.CitationClassargs, {'arxivAuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then NameListFormat = 'biorxivvanc'; -- override whatever |name-list-format= might be a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'citeseerxAuthorList'}) then ; -- we have set rft.jtitle in COinS to arXivfetch author list from |vauthors=, bioRxiv|author-linkn=, or CiteSeerX now unset so it isn't displayedand |author-maskn= Periodical elseif 3 == selected then Authors = A['Authors']; -- periodical not allowed in these templates; if article has been published, use cite journalcontent of |authors= end
end
local Coauthors = A['Coauthors']; local Others = A['Others']; local editor_etal; local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= local Editors; do -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static textlimit scope of selected if local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'newsgroupEditorList' ); if 1 == config.CitationClass selected then if is_set e, editor_etal = extract_names (PublisherNameargs, 'EditorList') ; -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= elseif 2 == selected then PublisherName NameListFormat = substitute (cfg.messages['newsgroupvanc']; -- override whatever |name-list-format= might be e, external_linkeditor_etal = parse_vauthors_veditors ( args, args.veditors, 'news:EditorList' .. PublisherName); -- fetch editor list from |veditors=, PublisherName|editor-linkn=, and |editor-maskn= elseif 3 == selected then Editors = A:ORIGIN(['PublisherNameEditors'), nil ))]; -- use content of |editors=
end
end
local t = {}; -- Now perform various field substitutions. translators list from |translator-lastn= / translator- We also add leading spaces and surrounding markup and punctuation to the -- various parts of the citation, but only when they are non-nil.firstn= pairs local EditorCountTranslators; -- used only for choosing {ed.) or (eds.) annotation at end of editor assembled translators name-list do local last_first_list; local control t = { format = NameListFormatextract_names (args, -- empty string or 'vancTranslatorList' maximum = nil, ); -- as if displayfetch translator list from |translatorn= / |translator-authors or displaylastn=, -editors not set lastauthoramp firstn= LastAuthorAmp, page_name -linkn= this_page.text, -- get current page name so that we don't wikilink to it via editorlinknmaskn= mode local c = Mode {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs do local Contributors; -- do editor assembled contributors name list first because the now unsupported coauthors used to modify control table control local Contribution = A['Contribution']; if in_array(config.maximum CitationClass, {"book", editor_etal = get_display_authors_editors "citation"}) and not is_set(A['DisplayEditorsPeriodical'], #e) then -- |contributor= and |contribution= only supported in book cites c = extract_names (args, 'editorsContributorList', editor_etal); last_first_list -- fetch contributor list from |contributorn= / |contributor-lastn=, EditorCount -firstn= list_people(control, e-linkn=, editor_etal);-maskn= if 0 < #c then if not is_set (EditorsContribution) then -- |contributor= requires |contribution= if editor_etal then Editors = Editors table.insert( z. message_tail, { set_error( ' contributor_missing_required_param' .. cfg.messages[, 'et alcontribution'])}); -- add et al. to editors parameter beause |display-editors=etal EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotationmissing contribution error message else EditorCount c = 2{}; -- we donblank the contributors't know but assume |editors= table; it is multiple names; spoof to display (eds.) annotation end else Editors = last_first_list; -- either an author name list or an empty stringused as a flag later
end
if 1 0 == EditorCount and (true #a then -- |contributor=requires |author= editor_etal or 1 < #e table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}) then ; -- only one editor displayed but includes etal then add missing author error message EditorCount c = 2{}; -- spoof to display (eds.) annotationblank the contributors' table; it is used as a flag later
end
end
do else -- now do interviewersif not a book cite control if select_one (args, cfg.maximum = #interviewers_list; aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- number of interviewerssare there contributor name list parameters? Interviewers = list_peopletable.insert(controlz.message_tail, interviewers_list, false{ set_error( 'contributor_ignored')}); -- et al not currently supportedadd contributor ignored error message
end
do -- now do translators control.maximum Contribution = #tnil; -- number of translatorsunset end Translators = list_people if not is_valid_parameter_value (controlNameListFormat, t'name-list-format', false); cfg.keywords['name-list- et al not currently supportedformat']) then end do -- now do contributorsonly accepted value for this parameter is 'vanc' control.maximum NameListFormat = #c''; -- number of contributors Contributors = list_people(control, canything else, false); -- et al not currently supportedset to empty string end do -- now do authors control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
last_first_list local Year = A['Year']; local PublicationDate = list_people(control, a, author_etal)A['PublicationDate']; local OrigYear = A['OrigYear']; if is_set (Authors) then local Date = A['Date']; Authors, author_etal local LayDate = name_has_etal (Authors, author_etal, false)A['LayDate']; ------------------------------ find and remove variations on et al.------------------- Get title data if author_etal then local Title = A['Title']; Authors local ScriptTitle = Authors .. A[' ScriptTitle' .. cfg.messages]; local BookTitle = A['et alBookTitle']; -- add et al. to authors parameter end local Conference = A['Conference']; else local TransTitle = A['TransTitle']; Authors local TitleNote = last_first_listA['TitleNote']; -- either an author name list or an empty string end end -- end of do local TitleLink = A['TitleLink']; if is_set (AuthorsTitleLink) and is_set false == link_param_ok (CollaborationTitleLink) then Authors = Authors table.insert( z. message_tail, { set_error( ' bad_paramlink', A:ORIGIN(' .. Collaboration .. TitleLink')')}); -- add collaboration after et al.url or wikilink in |title-link=;
end
endlocal Chapter = A['Chapter']; local ScriptChapter = A['ScriptChapter']; local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode local TransChapter = A['TransChapter']; local TitleType = A['TitleType']; local Degree = A['Degree']; local Docket = A['Docket']; local ArchiveFormat = A['ArchiveFormat']; local ArchiveURL = A['ArchiveURL']; local URL = A['URL'] local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
-- apply |local Series = A[xx-'Series']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')local Volume; ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url')local Issue; Format = style_format (Format, URL, 'format', 'url')local Page; LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url')local Pages; TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl')local At;
-- 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', 'biorxiv', 'citeseerx'}cfg.templates_using_volume) or and not ('citationconference' == config.CitationClass and not is_set (Periodical) and not is_set (Encyclopedia))) then ChapterFormat Volume = style_format A['Volume']; end if in_array (ChapterFormatconfig.CitationClass, ChapterURLcfg.templates_using_issue) and not (in_array (config.CitationClass, {'chapter-formatconference', 'chapter-urlmap'})and not is_set (Periodical))then Issue = A['Issue'];
end
local Position = ''; if not is_set(URL) then if in_array(config.CitationClass, {"web","podcast", "mailinglist"}cfg.templates_not_using_page) then -- |url Page = required for cite web, cite podcast, and cite mailinglistA['Page']; Pages = hyphen_to_dash( A['Pages'] ); At = A['At']; end local Edition = A['Edition']; local PublicationPlace = A['PublicationPlace'] local Place = A['Place']; local PublisherName = A['PublisherName']; local RegistrationRequired = A['RegistrationRequired']; table.insert if not is_valid_parameter_value ( z.message_tailRegistrationRequired, { set_error( 'cite_web_urlregistration', {}, true ) } cfg.keywords ['yes_true_y'])then RegistrationRequired=nil;
end
-- do we have |accessdate local SubscriptionRequired = without either |url= or |chapter-url=?A['SubscriptionRequired']; if is_set(AccessDate) and not is_setis_valid_parameter_value (ChapterURL)then -- ChapterURL may be set when URL is not set; table.insert( z.message_tailSubscriptionRequired, { set_error( 'accessdate_missing_urlsubscription', {}, true cfg.keywords ['yes_true_y']) } );then AccessDate SubscriptionRequired= ''nil;
end
end
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; DeadURL Via = DeadURL:lower()A['Via']; -- 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 local AccessDate = ChapterURL; -- save copy of source chapterA['AccessDate's url for archive text OriginalURLorigin = ChapterURLorigin]; -- name of chapter-url parameter for error messages OriginalFormat local ArchiveDate = ChapterFormat; -- and original |format= if A['noArchiveDate' ~= DeadURL then]; ChapterURL = ArchiveURL -- swap-in the archive's url ChapterURLorigin local Agency = A:ORIGIN(['ArchiveURLAgency') -- name of archive-url parameter for error messages]; ChapterFormat local DeadURL = ArchiveFormat or A['DeadURL'; -- swap in archive's format end] elseif is_set if not is_valid_parameter_value (URL) then OriginalURL = URL; -- save copy of original source URL OriginalURLorigin = URLorigin; -DeadURL, 'dead- name of url parameter for error messages OriginalFormat = Format; -- and original |format= OriginalAccess = UrlAccess; if 'no, cfg.keywords ['deadurl' ~= DeadURL ]) then -- if URL set then archive-url applies in config.defaults to it URL = ArchiveURL -- swap-in the archive's url URLorigin = A:ORIGIN('ArchiveURLyes') -- name of archive url parameter for error messages Format DeadURL = ArchiveFormat or ''; -- swap in archive's formatanything else, set to empty string UrlAccess = nil; -- restricted access levels do not make sense for archived urls end end end
if in_array(config.CitationClass, {local Language = A['webLanguage',]; local Format = A['newsFormat',]; local ChapterFormat = A['journalChapterFormat', ]; local DoiBroken = A['magazineDoiBroken', ]; local ID = A['pressreleaseID', ]; local ASINTLD = A['podcastASINTLD', ]; local IgnoreISBN = A['newsgroup', 'arxivIgnoreISBN']; if not is_valid_parameter_value (IgnoreISBN, 'biorxiv', 'citeseerx'}) or ignore-isbn- if any of the error'periodical, cfg.keywords [' cites except encyclopedia (yes_true_y'citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)]) then local chap_paramIgnoreISBN = nil; if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parametersanything else, set to empty string chap_param = A:ORIGIN ('Chapter') end elseif is_set (TransChapter) then chap_param local Embargo = A:ORIGIN (['TransChapterEmbargo')]; elseif is_set (ChapterURL) then chap_param local Class = A:ORIGIN (['ChapterURLClass') elseif is_set (ScriptChapter) then chap_param = A:ORIGIN ('ScriptChapter') else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat') end]; -- arxiv class identifier
if is_set (chap_param) then -- if we found one table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message Chapter = ''; -- and set them to empty string to be safe with concatenation TransChapter = ''; ChapterURL = ''; ScriptChapter = ''; ChapterFormat = ''; end else -- otherwise, format chapter / article title local no_quotes ID_list = false; -- default assume that we will be quoting the chapter parameter value if is_set extract_ids(Contributionargs ) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title no_quotes = true; -- then render it unquoted end end
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter if is_set (Chapter) then Chapter = Chapter .. ChapterFormat ; if 'map' == config.CitationClass and is_set (TitleType) then Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title end Chapter = Chapter.. sepc .. ' '; elseif is_set (ChapterFormat) then -- |chapterlocal Quote = not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. A[' Quote']; -- ... ChapterFormat has error message, we want to see it end end
-- Format main title.local LayFormat = A['LayFormat']; if local LayURL = A['...LayURL' == Title:sub (-3) then -- if elipsis is the last three characters of |title=]; Title local LaySource = mw.ustring.gsub (Title, A['(%.%.%.)%.+$LaySource', ]; local Transcript = A['%1Transcript')]; -- limit the number of dots to three elseif not mw.ustring.find (Title, local TranscriptFormat = A['%.%s*%a%.TranscriptFormat') then -- end of title is not a ]; local TranscriptURL = A['dot-(optional space-)letter-dotTranscriptURL' initialism] Title local TranscriptURLorigin = mw.ustring.gsubA:ORIGIN(Title, '%'..sepc..'$', 'TranscriptURL'); -- remove any trailing separator character end if is_set(TitleLink) and is_set(Title) then Title = make_wikilink (TitleLink, Title); endget name of parameter that holds TranscriptURL
if in_array(config.CitationClass, {local LastAuthorAmp = A['webLastAuthorAmp', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or]; ('citation' == config.CitationClass and is_set (Periodical) and if not is_set (Encyclopedia)) or is_valid_parameter_value (LastAuthorAmp, 'map' == config.CitationClass and is_set (Periodical)) then -last- 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 ('quotedauthor-titleamp', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style (cfg.keywords ['trans-quoted-titleyes_true_y', TransTitle ]); elseif 'report' == config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = wrap_style ('italic-title', Title); Title LastAuthorAmp = script_concatenate (Title, ScriptTitle)nil; -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle = wrap_style ('trans-italic-title', TransTitle); end local TransError = ""; if is_set(TransTitle) then if is_set(Title) then TransTitle = " " .. TransTitle; else TransError = " " .. set_error( 'trans_missing_title', {'title'} );set to empty string
end
end if is_set(Title) thenlocal no_tracking_cats = A['NoTracking']; if not is_setis_valid_parameter_value (TitleLink) and is_set(URL) then Title = external_link( URLno_tracking_cats, Title'no-tracking', URLorigin, UrlAccess cfg.keywords ['yes_true_y']) .. TransTitle .. TransError .. Format;then URL no_tracking_cats = ''nil; -- unset these because no longer needed Format = ""; else Title = Title .. TransTitle .. TransError;set to empty string
end
else
Title = TransTitle .. TransError;
end
--these are used by cite interview local Callsign = A['Callsign']; local City = A['City']; if is_setlocal Program = A['Program']; --local variables that are not cs1 parameters local use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.getCurrentTitle(Place) then; -- also used for COinS and for language local anchor_year; -- used in the CITEREF identifier local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification Place -- set default parameter values defined by |mode= " " parameter.. wrap_msg If |mode= is empty or omitted, use CitationClass to set these values local Mode = A['Mode']; if not is_valid_parameter_value (Mode, 'writtenmode', Place, use_lowercasecfg.keywords['mode']) .. sepc .. " "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
--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 (Conferenceno_tracking_cats) then -- ignore if we are already not going to categorize this page if is_set in_array (ConferenceURLthis_page.nsText, cfg.uncategorized_namespaces) then Conference no_tracking_cats = external_link"true"; -- set no_tracking_cats end for _,v in ipairs ( ConferenceURL, Conference, ConferenceURLorigin, nil 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
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
end
if not is_set-- check for extra |page=, |pages= or |at= parameters. (Positionalso sheet and sheets while we're at it) then local Minutes = A[ select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'Minutessheets']; local Time = A[}, 'Timeredundant_parameters']); -- this is a dummy call simply to get the error message and category
if is_set(Minutes) then local NoPP = A['NoPP'] if is_set (Time) then table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes'NoPP) .. ' and ' .. wrap_style is_valid_parameter_value ('parameter'NoPP, 'timenopp')}, true ) } ); end Position = " " .. Minutes .. " " .. cfg.messageskeywords ['minutesyes_true_y']; else if is_set(Time) then local TimeCaption NoPP = A['TimeCaption'] if not is_set(TimeCaption) then TimeCaption = cfg.messages['event']true; if sepc ~= '.' then TimeCaption = TimeCaption:lower(); end end Position = " " .. TimeCaption .. " " .. Time; end end
else
Position NoPP = " " .. Position; At = ''nil; -- unset, used as a flag later
end
if is_set(Page, ) then if is_set(Pages) or is_set(At) then Pages, Sheet, Sheets = format_pages_sheets ''; -- 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, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. end
At -- both |publication-place= is_set(At) and |place= (sepc .. " " .. At|location=) or "";allowed if different Position = if not is_set(PositionPublicationPlace) and is_set(sepc .. " " .. PositionPlace) or ""then PublicationPlace = Place; -- promote |place= (|location=) to |publication-place end if config.CitationClass PublicationPlace == 'map' Place then local Section Place = A['Section'];end -- don't need both if they are the same local Sections = A--[['Sections']; local Inset = A['Inset'];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 if is_set( Inset ) |encyclopedia thenmap |encyclopedia to |title Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end |trans_title maps to |trans_chapter when |title is re-mapped |url maps to |chapterurl when |title is remapped
if is_set( Sections ) then Section = sepc .. " " .. wrap_msg ('sections'All other combinations of |encyclopedia, Sections|title, use_lowercase); elseif is_set( Section ) then Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end and |article are not modified
if is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this is an empty string; --[[ TODO: need to extract the wrap_msg from language_parameter so that we can solve parentheses bunching problem with Format/Language/TitleType ]] end
local Encyclopedia = A['Encyclopedia']; Others = is_set(Others) and if (sepc .config. CitationClass == " encyclopaedia" .. Others) or ( config.CitationClass == "citation";and is_set (Encyclopedia)) then -- test code for citation if is_set(Periodical) then -- Periodical is set when |encyclopedia is set if is_set (TranslatorsTitle) or is_set (ScriptTitle) then Others = sepc .. ' ' .. wrap_msg if not is_set('translated', Translators, use_lowercaseChapter) .. Othersthen Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; TransChapter = TransTitle; end ChapterURL = URL; if not is_set (InterviewersChapterURL) and is_set (TitleLink) then Others Chapter= sepc '[[' .. TitleLink .. ' |' .. wrap_msg (Chapter .. 'interview]]', Interviewers, use_lowercase) .. Others; end Title = Periodical; ChapterFormat = Format; Periodical = ''; -- redundant so unset TitleNote TransTitle = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""''; if is_set (Edition) then URL = ''; if Edition:match ( Format = '%f[%a][Ee]d%.?$') or Edition:match (; TitleLink = '%f[%a][Ee]dition$') then; add_maint_cat ( ScriptTitle = 'extra_text', ; end else -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical = 'edition'); -- redundant so unset end
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
-- Special case for cite techreport. Series = is_set(Series) and if (sepc .config. CitationClass == " techreport" .. Series) or "";then -- special case for cite techreport OrigYear = if is_set(OrigYearA['Number']) and 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') . OrigYear .' and ' . "]". wrap_style ('parameter', 'number')}, true )}) or ""; end end -- TODO: presentationend
-- special case for cite interview Agency if (config.CitationClass == "interview") then if is_set(Program) then ID = ' ' .. Program; end if is_set(AgencyCallsign) and then if is_set(ID) then ID = ID .. sepc .. " " ' ' .. Callsign; else ID = ' ' .. AgencyCallsign; end end if is_set(City) or ""then if is_set(ID) then ID = ID .. sepc .. ' ' .. City; else ID = ' ' .. City; end end
Volume if is_set(Others) then if is_set(TitleType) then Others = ' ' .. TitleType .. ' with ' .. Others; TitleType = ''; else Others = ' ' .. 'Interview with ' .. Others; end else Others = format_volume_issue '(Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercaseInterview)'; end end
------------------------------------ totally unrelated dataspecial case for cite mailing list if is_set(Viaconfig.CitationClass == "mailinglist") then Via Periodical = A ['MailingList']; elseif 'mailinglist' == " " .. wrap_msg A:ORIGIN('viaPeriodical', Via)then Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
--[[ Subscription implies paywall; Registration does not. If both are used in a citation, Account for the subscription required link note oddity that is displayed. There are no error messages for this condition{{cite conference}}, before generation of COinS data. if 'conference' == config.CitationClass then ]] if is_set (SubscriptionRequiredBookTitle) then Chapter = Title;-- SubscriptionRequired ChapterLink = TitleLink; -- |chapterlink= is deprecated ChapterURL = URL; ChapterURLorigin = URLorigin; URLorigin = ''; ChapterFormat = Format; TransChapter = TransTitle; Title = BookTitle; Format = sepc .. " " .. cfg.messages['subscription']; -- subscription required message TitleLink = ''; elseif is_set (RegistrationRequired) then TransTitle = ''; SubscriptionRequired URL = sepc .. " " .. cfg.messages['registration']; -- registration required message end elseelseif 'speech' ~= config.CitationClass then SubscriptionRequired Conference = ''; -- either not cite conference or both might be set to something other than yes true ycite speech so make sure this is empty string
end
-- cite map oddities if is_set(AccessDate) thenlocal Cartography = ""; local retrv_text Scale = " " .. cfg.messages; local Sheet = A['retrievedSheet']or ''; AccessDate local Sheets = nowrap_date (AccessDate)A['Sheets'] or ''; -- wrap in nowrap span if date in appropriate format if (sepc ~config.CitationClass == ".map") then retrv_text Chapter = A['Map']; ChapterURL = A['MapURL']; TransChapter = A['TransMap']; ChapterURLorigin = retrv_textA:lowerORIGIN('MapURL') end -- if mode is cs2, lower case; AccessDate ChapterFormat = substitute (retrv_text, AccessDate)A['MapFormat']; -- add retrieved text AccessDate Cartography = substitute (cfg.presentationA['accessdateCartography'], {sepc, AccessDate}); -- allow editors to hide accessdates end if is_set(IDCartography ) then ID Cartography = sepc .." ".. IDwrap_msg ('cartography', Cartography, use_lowercase); end Scale = A['Scale']; if "thesis" == config.CitationClass and is_set(DocketScale ) then ID Scale = sepc .." Docket ".. Docket .. IDScale; end if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. ID_list if 'episode' == config.CitationClass or 'serial' == config.CitationClass then local AirDate = A['AirDate']; local SeriesLink = A['SeriesLink']; if is_set (SeriesLink) and false == build_id_listlink_param_ok (SeriesLink) then table.insert( ID_listz.message_tail, {IdAccessLevelsset_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))}); end local Network =ID_access_levelsA['Network']; local Station = A['Station']; local s, DoiBroken n = DoiBroken{}, ASINTLD = ASINTLD{}; -- do common parameters first if is_set(Network) then table.insert(n, IgnoreISBN = IgnoreISBNNetwork); end if is_set(Station) then table.insert(n, EmbargoStation); end ID =Embargotable.concat(n, Class sepc .. ' '); if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = Class} )AirDate; end
if is_set(URL) 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} URL local Season = " " .. external_link( URL, nil, URLorigin, UrlAccess )A['Season']; end local SeriesNumber = A['SeriesNumber'];
if is_set(QuoteSeason) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set if Quote:sub table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style (1'parameter',1'season') == .. '"and ' and Quote:sub.. wrap_style ('parameter', 'seriesno')}, true ) } ); -1,-1) =add error message SeriesNumber = '"' then ; -- unset; prefer |season= over |seriesno= end -- if first and last characters assemble a table of quote are quote marksparts concatenated later into Series Quote = Quote:subif is_set(Season) then table.insert(2s,-2wrap_msg ('season', Season, use_lowercase)); -- strip them offend if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end Quote = sepc if is_set(Issue) then table.." " .. wrap_style insert(s, wrap_msg ('quoted-textepisode', Quote Issue, use_lowercase)); -- wrap in <q>...</q> tagsend PostScript Issue = ""''; -- cs1|2 does unset because this is not supply terminal punctuation when |quote= is set enda unique parameter
local Archived Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink if is_set(ArchiveURL) then TransChapter = TransTitle; if not is_set(ArchiveDate) then ChapterURL = URL; ArchiveDate ChapterURLorigin = set_errorA:ORIGIN('archive_missing_dateURL'); end if "no" Title =Series; -- promote series to title TitleLink = DeadURL thenSeriesLink; local arch_text Series = cfgtable.concat(s, sepc ..messages['archived']); -- this is concatenation of season, seriesno, episode number if sepc ~= "." then arch_text = arch_text:loweris_set (ChapterLink) and not is_set (ChapterURL) endthen -- link but not URL Archived Chapter = sepc '[[' .. ChapterLink ..'|' . " " .Chapter . substitute( cfg.messages['archived]]'; -- ok to wikilink elseif is_set (ChapterLink) and is_set (ChapterURL) then -not-dead']if both are set,URL links episode; { external_link( ArchiveURL, arch_text, A:ORIGIN(Series = '[[' .. ChapterLink .. 'ArchiveURL|'), nil ) .. ArchiveFormat, ArchiveDate } Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink)ugly end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; else -- now oddities that are cite serial Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? if not is_set(OriginalURLSeries) and is_set (SeriesLink) then Archived Series = Archived '[[' .. " " SeriesLink .. '|' .. Series .. set_error('archive_missing_url]]');
end
elseif is_set Series = wrap_style (OriginalURL'italic-title', Series) then ; -- DeadURL series is empty, 'yes', 'true', 'y', 'unfit', 'usurped'italicized local arch_text = cfg.messages['archived-dead']; end if sepc ~= "." then arch_text = arch_text:lower() end if in_array (DeadURL, -- end of {{'unfit', 'usurped', 'bot: unknown'cite episode}}) thenstuff Archived = sepc .. " " .. 'Archived from -- Account for the original on ' oddities that are {{cite arxiv}}, before generation of COinS data.. ArchiveDate; -- format already styled if 'bot: unknownarxiv' == DeadURL config.CitationClass then add_maint_cat ('bot:_unknown'); -- and add a category if not already added else add_maint_cat is_set (ID_list['unfitARXIV']); then -- and add a category if not already added end|arxiv= or |eprint= required for cite arxiv else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc table.insert( z. " " .. substitute( arch_textmessage_tail, { external_linkset_error( OriginalURL, cfg.messages['originalarxiv_missing'], OriginalURLorigin{}, OriginalAccess true ) .. OriginalFormat, ArchiveDate } ); -- format already styled end add error message elseelseif is_set (Series) then -- series is an alias of version local arch_text ID_list['ARXIV'] = cfg.messagesID_list['archived-missingARXIV'].. Series; -- concatenate version onto the end of the arxiv identifier if sepc ~Series = "." then arch_text = arch_text:lower() end''; -- unset Archived = sepc .. " " .. substitute( arch_text, { set_errordeprecated_parameter ('archive_missing_urlversion'), ArchiveDate } ); -- deprecated parameter but only for cite arxiv
end
elseif is_set if first_set (ArchiveFormat{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 Archived = ArchiveFormat table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- if set and ArchiveURL not set ArchiveFormat has add error message else Archived AccessDate= "" end ''; -- set these to empty string; not supported in cite arXiv local Lay PublisherName = ''; -- (if is_set(LayURLthe article has been published, use cite journal, or other) then if is_set(LayDate) then LayDate Chapter = " (" .. LayDate .. ")" end''; if is_set(LaySource) then URL = ''; LaySource Format = " &ndash''; Page = ''" .. safe_for_italics(LaySource) .. "; Pages = ''"; else LaySource At = ""'';
end
if sepc Periodical == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURLarXiv'), nil ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; -- if set and LayURL not to arXiv for COinS; after that, must be set, then LayFormat has error messageto empty string
end
-- handle type parameter for those CS1 citations that have default values if is_setin_array(Transcriptconfig.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then TitleType = set_titletype (config.CitationClass, TitleType); if is_set(TranscriptURLDegree) and "Thesis" == TitleType then -- special case for cite thesis Transcript TitleType = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil )Degree .. "论文";
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
end
local Publisher; if is_set(PublicationDateTitleType) then -- if type parameter is specified PublicationDate TitleType = wrap_msg substitute(cfg.messages['publishedtype'], PublicationDateTitleType); -- display it in parentheses
end
if is_set(PublisherName) then -- legacy: promote concatenation of |month=, and |year= to Date if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. Date not set; or, promote PublicationDate; else Publisher = sepc .. " " .. PublisherName to Date if neither Date nor Year are set.. PublicationDate; end elseif if not is_set(PublicationPlaceDate) then PublisherDate = sepc .. " " .. PublicationPlace .. PublicationDateYear; else -- promote Year to Date Publisher Year = PublicationDatenil; end -- Several of the above rely upon detecting this as make nil, so do it last. if is_set(Periodical) thenYear as empty string isn't used for CITEREF if not is_set(TitleDate) or and is_set(TitleNotePublicationDate) then -- use PublicationDate when |date= and |year= are not set Periodical Date = sepc .. " " .. wrap_style ('italicPublicationDate; --title', Periodical) else promote PublicationDate to Date Periodical PublicationDate = wrap_style ('italic'; -title'- unset, Periodical)no longer needed
end
end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation --[[ Handle Go test all of the oddity date-holding parameters for valid MOS:DATE format and make sure that is cite speechdates are real dates. This code overrides whatever may must be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so thatdone before we do COinS because here is where the annotation directly follows we get the |title= parameter value date used in the citation rather than the |event= parameter value (if provided)metadata. Date validation supporting code is in Module:Citation/CS1/Date_validation]] if "speech" do -- create defined block to contain local variables error_message and mismatch local error_message == config.CitationClass then ''; -- cite speech onlyAirDate has been promoted to Date so not necessary to check it TitleNote anchor_year, error_message = " dates(Speech{['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date)"; -- annotate the citation if is_set (PeriodicalYear) and is_set (Date) then -- both |date= and |year= not normally needed; local mismatch = year_date_check (Year, Date) if Periodical, perhaps because of an included 0 == mismatch then -- |websiteyear= or does not match a year-value in |journaldate= parameter if is_set (Conferenceerror_message) then -- and if |event= there is setalready an error message Conference error_message = Conference error_message .. sepc ', '; -- tack on this additional message end error_message = error_message .. " "'|year= / |date= mismatch'; elseif 1 == mismatch then -- then add appropriate punctuation to the end of the Conference variable before rendering|year= matches year-value in |date= add_maint_cat ('date_year');
end
end
end
-- Piece all bits together at last if is_set(error_message) then table.insert( z. Heremessage_tail, all should be non-nil. { set_error( 'bad_date', {error_message}, true ) } ); -- We build things add this way because it is more efficient in LUAerror message end end -- not to keep reassigning to the same string variable over and over.end of do
local tcommon; local tcommon2; -- used Account for book the oddity that is {{cite when journal}} with |contributorpmc= is set if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then if is_set(Others) then Others |url= Others not set. Do this after date check but before COInS. sepc .. " " end tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites Here we unset Embargo if is_set PMC not embargoed (Contributors|embargo= not set in the citation) then -- when we are citing foreword, prefaceor if the embargo time has expired. Otherwise, introduction, etcholds embargo date tcommon Embargo = safe_joinis_embargoed ( {Title, TitleNote}, sepc Embargo); -- author and other stuff will come after this and before tcommon2 tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); else tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); end
elseif 'map' == if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then -- special cases for cite map if not is_set (ChapterEmbargo) then -- map in a book; TitleType is part of Chapterif not embargoed or embargo has expired tcommon URL= safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc )cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; elseif is_set (Periodical) then -- map in a periodicalset url to be the same as the PMC external link if not embargoed tcommon URLorigin = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc )cfg.id_handlers['PMC'].parameters[1]; else -- set URLorigin to parameter name for use in error message if citation is missing a sheet or stand-alone map tcommon |title= safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
end
elseif 'episode' == config.CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. else -- all other CS1 templatesTest if citation has no title if not is_set(Title) and tcommon = safe_joinnot is_set(TransTitle) and not is_set( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, ScriptTitle) then Volumeif 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? table.insert( z.message_tail, Others{ set_error( 'citation_missing_title', Edition{'series'}, Publisher, Agencytrue ) }, sepc ); end else if #ID_list > 0 then ID_list = safe_join table.insert( { sepc z.. " "message_tail, table.concat{ set_error( ID_list'citation_missing_title', sepc .. " " {'title'}, true ), ID }, sepc ); else ID_list = ID; end
end
local idcommon if 'none' = safe_join= Title and in_array ( config.CitationClass, { ID_list, URL, Archived, AccessDate'journal', Via, SubscriptionRequired, Lay, Quote 'citation'}, sepc ) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites Title = ''; -- set title to empty string add_maint_cat ('untitled'); local text;end local pgtext check_for_url ({ -- add error message when any of these parameters contains a URL ['title']=Title, [A:ORIGIN('Chapter')]= Position .. Sheet .. Sheets .. Page .. Pages .. AtChapter, [A:ORIGIN('Periodical')]=Periodical, [A:ORIGIN('PublisherName')] = PublisherName, });
if is_set-- COinS metadata (Datesee <http://ocoins.info/>) thenfor automated parsing of citation information. -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not Periodical, Title, and Chapter are all set Date = " , then Periodical is the book (" .. Date .."encyclopedia)" title, Title -- is the article title, and Chapter is a section within the article.. OrigYear .. sepc .. " " So, we remap local coins_chapter = Chapter; -- in paranethesesdefault assuming that remapping not required else local coins_title = Title; -- neither of authors et tu if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and editors setis_set (Encyclopedia)) then if is_set (string.subChapter) and is_set (tcommon,-1,-1Title) == sepcand is_set (Periodical) then -- if the last character of tcommon is sepcall are used then Date coins_chapter = " " .. Date .. OrigYearTitle; -- Date does not begin with sepcremap else Date coins_title = sepc .. " " .. Date .. OrigYearPeriodical; -- Date begins with sepc end
end
end local coins_author = a; -- default for coins rft.au if 0 < #c then -- but if is_setcontributor list coins_author = c; -- use that instead end -- this is the function call to COinS() local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Map'] = Map, ['Degree'] = Degree; -- cite thesis only ['Title'] = make_coins_title (Authorscoins_title, ScriptTitle) then, -- Title and ScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; ['Season'] = COinS_date.rftssn, ['Chron'] = COinS_date.rftchron or (not is_set COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit? ['Series'] = Series, ['Volume'] = Volume, ['Issue'] = Issue, ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links ['Edition'] = Edition, ['PublisherName'] = PublisherName, ['URL'] = first_set (Date{ChapterURL, URL}, 2), ['Authors'] = coins_author, ['ID_list'] = ID_list, ['RawPage'] = this_page.prefixedText, }, config.CitationClass) ; -- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data. if 'arxiv' == config.CitationClass then -- when date is we have set rft.jtitle in COinS to arXiv, now unset so itisn't displayed Periodical = 's '; -- periodical not allowed in parenthesescite arxiv; no Authors terminationif 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 text if 'newsgroup' == config.CitationClass then if is_set (PublisherName) then Authors PublisherName = terminate_name_list substitute (cfg.messages['newsgroup'], external_link(Authors'news:' .. PublisherName, PublisherName, sepcA:ORIGIN('PublisherName') )); -- when no date, terminate with 0 or 1 sepc and a space
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; local control = { format = NameListFormat, -- empty string or 'vanc' maximum = nil, -- as if is_set(Editors) thendisplay-authors or display-editors not set lastauthoramp = LastAuthorAmp, local in_text page_name = " "this_page.text -- 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 local post_text maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', 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 --2017.6.23 shizhao if not is_set(Chaptermaximum) and 0 #e == #c 4 then in_text maximum = in_text 3; table.insert( z. cfg.messages[message_tail, { set_error('inimplict_etal_editor', {}, true) } ); end ]] control.. " "maximum = maximum; if last_first_list, EditorCount = list_people(sepc ~= control, e, editor_etal, '.editor') then; in_text = in_text:lower if is_set (Editors) -- lowercase for cs2 end elsethen if EditorCount <= 1 editor_etal then post_text Editors = ", " Editors .. ' ' .. cfg.messages['editoret al']; -- add et al. to editors parameter beause |display-editors=etal EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
post_text EditorCount = ", " .. cfg.messages[2; -- we don't know but assume |editors']= is multiple names;spoof to display (eds.) annotation
end
end else Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space end if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 Authors = by_text .. Authorslast_first_list; -- either an 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 name list or 1 sepc and a spacean empty string
end
if 1 == EditorCount and (not is_set (Date)true == editor_etal or 1 < #e) then -- when date is set it's in parentheses; no Contributors terminationonly one editor displayed but includes etal then Contributors EditorCount = terminate_name_list (Contributors, sepc)2; -- terminate with 0 or 1 sepc and a spacespoof to display (eds.) annotation
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 do -- now do translators control.maximum = #t; -- number of translators Translators = list_people(Editorscontrol, t, false, 'translator') then; -- et al not currently supported end if is_set(Date) thendo -- now do contributors if EditorCount <control.maximum = 1 then#c; -- number of contributors Editors Contributors = Editors list_people(control, c, false, 'contributor'); -- et al not currently supported end do -- now do authors control.. "maximum , " .. cfg.messagesauthor_etal = get_display_authors_editors (A['editorDisplayAuthors'], #a, 'authors', author_etal); elseif is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting. Editors control.lastauthoramp = Editors nil; control.. ", " .. cfg.messages['editors']maximum = #a + 1;
end
else last_first_list = list_people(control, a, author_etal, 'author'); if EditorCount <is_set (Authors) then Authors, author_etal = 1 name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. if author_etal then Editors Authors = Editors Authors .. " (" ' ' .. cfg.messages['editoret al'] ; -- add et al.. ")" .. sepc .. " "to authors parameter end
else
Editors Authors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "last_first_list; -- either an author name list or an empty string
end
end -- end of do
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
text 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 = safe_joinstyle_format ( {EditorsArchiveFormat, ArchiveURL, 'archive-format', Date'archive-url'); ConferenceFormat = style_format (ConferenceFormat, ChapterConferenceURL, Place'conference-format', tcommon'conference-url'); Format = style_format (Format, pgtextURL, idcommon}'format', sepc 'url'); elseLayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); TranscriptFormat = 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',"citation"'arxiv'}) or ('citation' == config.CitationClass and is_set(Periodical) and not is_set (Encyclopedia))) then text ChapterFormat = safe_joinstyle_format ( ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); end if not is_set(URL) then --and if in_array(config.CitationClass, {Chapter"web", Place"podcast", tcommon"mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty table.insert( z.message_tail, pgtext{ set_error( 'cite_web_url', Date{}, idcommontrue ) }, sepc ); elseend -- Test if accessdate is given without giving a URL if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test? text = safe_jointable.insert( z.message_tail, {Chapterset_error( 'accessdate_missing_url', Place{}, tcommon, Date, pgtext, idcommontrue ) }, sepc ); AccessDate = '';
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 );
local OriginalURL, OriginalURLorigin, OriginalFormat; -- Now enclose the whole thing in a <cite/> elementTODO: swap chapter and title here so that archive applies to most specific if both are set? local options DeadURL = {}; if is_setDeadURL:lower(config.CitationClass) and config.CitationClass ~= "citation" then options.class = config.CitationClass; options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight used later when used with |ref= else options.class = "citation"; end assembling archived text if is_set(Ref) and Ref:lower(ArchiveURL ) ~= "none" then -- set reference anchor if appropriate local id = Ref if is_set ('harv' == Ref URL) then local namelist OriginalURL = URL; -- save copy of original source URL OriginalURLorigin = {}URLorigin; -- holds selected contributor, author, editor name listof url parameter for error messages local year OriginalFormat = first_set ({Year, anchor_year}, 2)Format; -- Year first for legacy citations and for YMD dates that require disambiguationoriginal |format= if #c > 0 'no' ~= DeadURL then -- if there is a contributor listURL set then archive-url applies to it namelist URL = c; ArchiveURL -- select it elseif #a > 0 then swap-- or an author listin the archive's url namelist URLorigin = a; elseif #e > 0 then A:ORIGIN('ArchiveURL') -- or an editor listname of archive url parameter for error messages namelist Format = eArchiveFormat or ''; -- swap in archive's format
end
elseif 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 #namelist > 0 'no' ~= DeadURL then ChapterURL = ArchiveURL -- if there are names swap-in namelistthe archive's url id ChapterURLorigin = anchor_id A:ORIGIN(namelist, year'ArchiveURL'); --name of archive- go make the CITEREF anchor elseurl parameter for error messages id ChapterFormat = ArchiveFormat or ''; -- unsetswap in archive's format
end
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>","")) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains
z.error_categories = {};
text = set_error('empty_citation');
z.message_tail = {};
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if is_setin_array(optionsconfig.idCitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) then or -- here we wrap if any of the rendered citation in <cite ...>...</cite> tags'periodical' cites except encyclopedia table.insert (render, substitute (cfg.presentation['cite-idcitation'], {mw== config.uri.anchorEncodeCitationClass and is_set (options.idPeriodical), mw.text.nowikiand not is_set (options.classEncyclopedia), text})then local chap_param; if is_set (Chapter); then --get a parameter name from one of these chapter related meta- when |refparameters chap_param = is setA:ORIGIN ('Chapter') elseif is_set (TransChapter) then else chap_param = A:ORIGIN ('TransChapter') table.insert elseif is_set (render, substitute ChapterURL) then chap_param = A:ORIGIN (cfg.presentation['citeChapterURL'], {mw.text.nowiki) elseif is_set (ScriptChapter) then chap_param = A:ORIGIN (options.class'ScriptChapter'), text} else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat'); -- all other cases end
if is_set (chap_param) then -- if we found one table.insert (renderz.message_tail, substitute { set_error(cfg.presentation['ocinschapter_ignored'], {OCinSoutputchap_param}, true )} ); -- append metadata add error message Chapter = ''; -- and set them to empty string to be safe with concatenation TransChapter = ''; ChapterURL = ''; ScriptChapter = ''; ChapterFormat = ''; end else -- otherwise, format chapter / article title local no_quotes = false; -- default assume that we will be quoting the citationchapter parameter value if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title no_quotes = true; -- then render it unquoted end end
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter if is_set (Chapter) then if #z'map' == config.CitationClass and is_set (TitleType) then Chapter = Chapter .. ' ' ..message_tail ~TitleType; end Chapter = 0 Chapter .. ChapterFormat .. sepc .. ' '; elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it end end -- Format main title. if is_set(TitleLink) and is_set(Title) then Title = "[[" .. TitleLink .. "|" .. Title .. "]]" end if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or table('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or ('map' == config.insert CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style (render'trans-quoted-title', TransTitle ); elseif ' report'== config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for itrans-title else Title = wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags,v in ipairslang 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( z'trans_missing_title', {'title'} ); end end Title = Title ..message_tail TransTitle; if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title, URLorigin ) do.. TransError .. Format; URL = ""; Format = ""; else Title = Title .. TransError; end end if is_set(Place) then Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; end if is_set(v[1]Conference) then if i is_set (ConferenceURL) then Conference =external_link( ConferenceURL, Conference, ConferenceURLorigin ); end Conference = #zsepc .. " " .. Conference ..message_tail ConferenceFormat; elseif is_set(ConferenceURL) then table Conference = sepc .. " " ..insert external_link(renderConferenceURL, error_commentnil, ConferenceURLorigin ); end if not is_set( vPosition) then local Minutes = A[1'Minutes'], v; local Time = A[2'Time'] ; if is_set(Minutes)then if is_set (Time);then else table.insert (renderz.message_tail, { set_error( 'redundant_parameters', error_comment{wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ( v[1] 'parameter', 'time')}, true ) } ); end Position = " " .. Minutes .. "" .. cfg.messages['minutes']; ", v else if is_set(Time) then local TimeCaption = A[2'TimeCaption'] if not is_set(TimeCaption)then TimeCaption = cfg.messages['event']; if sepc ~= '.' then TimeCaption = TimeCaption:lower(); end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end else Position = " " .. Position; At = ''; end Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); At = is_set(At) and (sepc .. " " .. At) or ""; Position = is_set(Position) and (sepc .. " " .. Position) or ""; if config.CitationClass == 'map' then local Section = A['Section']; local Sections = A['Sections']; local Inset = A['Inset']; if is_set( Inset ) then Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end if is_set( Sections ) then Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); elseif is_set( Section ) then Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end if #zis_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this is an empty string; end Others = is_set(Others) and (sepc .. " " .. Others) or ""; if is_set (Translators) then Others = sepc .. ' 由' .. Translators .. '翻译 ' .. Others; end TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; if is_set (Edition) then if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then add_maint_cat ('extra_text', 'edition'); end Edition = " " .. wrap_msg ('edition', Edition); else Edition = ''; end Series = is_set(Series) and (sepc .. " " .. Series) or ""; OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); ------------------------------------ totally unrelated data if is_set(Via) then Via = " " .. wrap_msg ('via', Via); end --[[Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required linknote is displayed. There are no error messages for this condition. ]] if is_set (SubscriptionRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message elseif is_set (RegistrationRequired) then SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message else SubscriptionRequired = ''; -- either or both might be set to something other than yes true y end if is_set(AccessDate) then local retrv_text = " " .. cfg.maintenance_cats messages['retrieved'] AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format if (sepc ~= 0 ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text -- neither of these work; don't know why; it seems that substitute() isn't being called AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates end if is_set(ID) then ID = sepc .." ".. ID; end if "thesis" == config.CitationClass and is_set(Docket) then ID = sepc .." Docket ".. Docket .. ID; end if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set end ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); if is_set(URL) then tableURL = " " ..insert external_link( URL, nil, URLorigin ); end if is_set(Quote) then if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks Quote = Quote:sub(render2, -2); -- strip them off end Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <span classq>...</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(ArchiveDate) then ArchiveDate = set_error('archive_missing_date'); end if "no" == DeadURL then local arch_text = cfg.messages['archived']; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } ); if not is_set(OriginalURL) then Archived = Archived .. " " .. set_error('archive_missing_url'); end elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' local arch_text = cfg.messages['archived-dead']; if sepc ~= "." then arch_text = arch_text:lower() end if in_array (DeadURL, {'unfit', 'usurped'}) then Archived =sepc .. "citation" .. 'Archived from the original on ' .. ArchiveDate; -- format already styled else --commentDeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " style.. substitute( arch_text, { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled end else local arch_text = cfg.messages['archived-missing']; if sepc ~="display." then arch_text = arch_text:nonelower() end Archived = sepc .. " " .. substitute( arch_text, { set_error('archive_missing_url'), ArchiveDate } ); end elseif is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = "" end local Lay = ''; if is_set(LayURL) then if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; color end if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:#33aa33ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; margin --leftif set and LayURL not set, then LayFormat has error message end if is_set(Transcript) then if is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin ); end Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; elseif is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin ); end local Publisher; if is_set(Periodical) and not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = PublicationPlace .. ": " .. PublisherName; else Publisher = PublisherName; end elseif is_set(PublicationPlace) then Publisher= PublicationPlace; else Publisher = ""; end if is_set(Publisher) then Publisher = " (" .. Publisher .. ")"; end else if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ":0" .. PublisherName; else Publisher = sepc .. " " .. PublisherName; end elseif is_set(PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace; else Publisher = ''; end end -- Several of the above rely upon detecting this as nil, so do it last. if is_set(Periodical) then if is_set(Title) or is_set(TitleNote) then Periodical = sepc ..3em">" .. wrap_style ('italic-title', Periodical) else Periodical = wrap_style ('italic-title', Periodical) end end --[[Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so thatthe annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).]] if "speech" == config.CitationClass then -- cite speech only TitleNote = " (Speech)"; -- annotate the citation if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter if is_set (Conference) then -- and if |event= is set Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering end end end -- Piece all bits together at last. Here, all should be non-nil. -- We build things this way because it is more efficient in LUA -- not to keep reassigning to the same string variable over and over. local tcommon; local tcommon2; -- used for book cite when |contributor= is set if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then if is_set(Others) then Others = Others .. sepc .. " " end tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Edition, Publisher, Agency}, sepc ); elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for _book cites if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2 tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); else tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); end elseif 'map' == config.CitationClass then -- special cases for cite map if is_set (Chapter) then -- map in a book; TitleType is part of Chapter tcommon = safe_join( {Title, Format, Edition, Scale, Series, Cartography, Others, Publisher, Volume}, v sepc ); elseif is_set (Periodical) then -- map in ipairsa periodical tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Cartography, Others, Publisher, Volume}, sepc ); else -- a sheet or stand-alone map tcommon = safe_join( z{Title, TitleType, Format, Edition, Scale, Series, Cartography, Others, Publisher}, sepc ); end elseif 'episode' == config.maintenance_cats CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Edition, Publisher}, sepc ) do ; else -- append maintenance categoriesall other CS1 templates tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); end if #ID_list > 0 then ID_list = safe_join( { sepc .. " ", table.insert concat( ID_list, sepc .. " " ), ID }, sepc ); else ID_list = ID; end -- LOCAL local xDate = Date local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; if ( is_set(Periodical) and Date ~= '' and not in_array(config.CitationClass, {"encyclopaedia","web"}) ) or ( in_array(config.CitationClass, {"book","news"}) ) then if in_array(config.CitationClass, {"journal","citation"}) and ( Volume ~= '' or Issue ~= '' ) then xDate = xDate .. ',' .. Volume end xDate = xDate .. pgtext pgtext = '' end if PublicationDate and PublicationDate ~= '' then xDate = xDate .. ' (' .. PublicationDate .. ')' end if OrigYear ~= '' then xDate = xDate .. OrigYear end if AccessDate ~= '' then xDate = xDate .. ' ' .. AccessDate end if xDate ~= '' then xDate = sepc .. ' ' .. xDate end -- END LOCAL local idcommon = safe_join(render{ URL, vxDate, ID_list, Archived, Via, SubscriptionRequired, Lay, Language, Quote }, sepc ); local text; if is_set(Authors) then if is_set(Coauthors) then tableif 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator Authors = Authors .. ', ' .. Coauthors; else 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; elseif #e > 0 then -- or an editor list namelist = e; end tableid = 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