local z = { error_categories = {}; -- for categorizing citations that contain errors error_ids cs1 = {}; 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 cfg = {}; dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- table of configuration tables that are defined functions in Module:Citation/CS1/ConfigurationDate_validationlocal whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist date_name_xlate
local is_set, in_array, substitute, error_comment, set_error, select_one, --[[--------------------------< I S _ S E T >------------------------------------------------------------------functions in Module:Citation/CS1/Utilities add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink;
Returns true if argument is setlocal z ={}; false otherwise. Argument is 'set' when it exists ( -- 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/Whitelist --[[--------------------------< 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 nil) or when it is not an empty string.brought in from other modules; thatare created hereThis function is global because it is called from both this module and from Date validationused here
]]
function is_set( var ) return not (var == nil or var =local added_deprecated_cat; -- boolean flag so that the category is added only oncelocal added_prop_cats = {}; -- 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 >--------------------------------------------------------------
Whether needle --[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- Adds a category to z.properties_cats using names from the configuration file with additional text if any. 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. added_prop_cats is a table declared in haystackpage scope variables above
]]
local function in_arrayadd_prop_cat ( needlekey, haystack arguments) if needle not added_prop_cats [key] then added_prop_cats [key] =true; -- note that we've added this category key = nil thenkey:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname return falsetable.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
for n,v in ipairs( haystack ) do
if v == needle then
return n;
end
end
return false;
end
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
Populates numbered arguments in a message string using an argument table.--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
]]Adds 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.
local function substitute( msg, args ) return args and mw.message.newRawMessage( msg, args ):plain() or msg;endadded_vanc_errs is a boolean declared in page scope variables above
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------]]
Wraps error messages with css markup according to the state of hidden. ]]local function error_commentadd_vanc_error ( content, hidden source) return substitute( hidden and cfg.presentation['hiddenif not added_vanc_errs then added_vanc_errs = true; --errornote that we'] or cfgve added this category table.presentation[insert( z.message_tail, { set_error( 'visible-errorvancouver'], content {source}, true ) } ); end
end
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
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.--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
]]local function set_error( error_id, arguments, raw, prefix, suffix ) local error_state = cfg.error_conditions[ error_id ]; prefix = prefix or ""; suffix = suffix or ""; does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if error_state == nil thenit error( cfgis in agreement with http://tools.messages['undefined_error'] ); elseif is_set( error_stateietf.category ) then table.insert( z.error_categories, error_stateorg/html/std66#section-3.category );1 which says: endScheme names consist of a sequence of characters beginning with a local message = substitute( error_state.message letter and followed by any combination of letters, digits, arguments ); plus message = message .. " ([[" .. cfg.messages['help page link'] .. +"#" .. error_state.anchor .. "|), period (" .. cfg.messages['help page label'] .. "]])"; 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 '', false; end message = table.concator hyphen ({ 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 >------------------------------------------------------ Adds a category to z.maintenance_cats using names from the configuration file with additional text returns true if any.To prevent duplicationit does, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.else false
]]
local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_catslocal function add_maint_cat is_scheme (key, argumentsscheme) if not added_maint_cats return scheme and scheme:match ('^%a[key] then added_maint_cats [key%a%d%+%.%-] = true; -- note that we*:'ve added this category table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table endtrue if scheme is set and matches the pattern
end
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
Adds a category to z.properties_cats using names from the configuration file with additional text if any.--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
]]Does this thing that purports to be a domain name seem to be a valid domain name?
local added_prop_cats = {} Syntax defined here: http://tools.ietf.org/html/rfc1034#section-- list of property categories that have been added to z3.5BNF defined here: https://tools.ietf.properties_catsorg/html/rfc4234local function add_prop_cat (key, arguments)Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; if not added_prop_cats see also [key] then added_prop_cats [key] = true; Single-letter second- note that we've added this categorylevel domain]] table.insert( zlist of tlds: https://www.properties_cats, substitute (cfgiana.prop_cats [key], arguments)); -- make name then add to table endendorg/domains/root/db
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------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.
Adds 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 emittedAlso allowed are IPv4 addresses.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.
local added_vanc_errs; 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 .xn-- flag so we only emit one Vancouver error / categorylocal function add_vanc_error ASCII Compatible Encoding (ACE) prefix xn-- in the tld)see https://tools.ietf.org/html/rfc3490 if not added_vanc_errs then added_vanc_errs = true; single-letter/digit second- note that we've added this categorylevel domains in the .org and .cash TLDs table q, x, and z SL domains in the .insert( zcom TLD i and q SL domains in the .message_tail, { set_errornet TLD single-letter SL domains in the ccTLDs ( 'vancouver', {}, true where the ccTLD is two letters) } two-character SL domains in gTLDs (where the gTLD is two or more letters); endthree-plus-character SL domains in gTLDs (where the gTLD is two or more letters)end IPv4 dot-decimal address format; TLD not allowed
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 >------------------------------------------------------------]=]
does this thing that purports 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 to do it once if not domain:match ('^[%a%d]') then -- first character must be letter or digit return false; end -- Do most common case first if domain:match ('%f[%a%d][%a%d][%a uri scheme seem to be %d%-]+[%a%d]%.%a%a valid scheme? The scheme is checked to see if it+$') then -- three or more character hostname.hostname or hostname.tld return true;is in agreement elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with httpACE prefix return true; elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character//toolsdigit .ietfcash hostname return true; elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/html/std66#sectiondigit .org hostname return true; elseif domain:match ('%f[%a][qxz]%.com$') then --3assigned one character .com hostname (x.1 which sayscom times out 2015-12-10) return true; elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) return true; Scheme names consist of elseif domain:match ('%f[%a%d][%a%d]%.%a sequence of characters beginning with %a$') then -- one character hostname and cctld (2 chars) letter and followed by any combination of letters, digits, plus return true; elseif domain:match ("'%f[%a%d][%a%d][%a%d]%.%a%a+"$'), period then -- two character hostname and tld return true; elseif domain:match ("'^%d%d?%d?%."%d%d?%d?%.%d%d?%d?%.%d%d?%d?'), or hyphen ("then --").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_scheme is_url (scheme, domain) if is_set (scheme) then -- if scheme is set check it and domain return is_scheme (scheme ) and scheme:match is_domain_name (domain); else return is_domain_name ('^%a[%a%d%+%.%-]*:'domain); -- true if scheme not set when url is set and matches the patternprotocol relative end
end
--[=[--------------------------< I S _ D O M A P L I N T _ N A M E U R L >------------------------------------------------------------ Split a url into a scheme, authority indicator, and domain.
Does this thing that purports to be First remove Fully Qualified Domain Name terminator (a domain name seem to be a valid domain namedot following tld) (if any) and any path(/), query(?) or fragment(#).
Syntax defined here: http://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 If protocol relative url, return nil scheme and domain else return nil for both scheme and domain]]list of tlds: https://www.iana.org/domains/root/db
rfc952 (modified by rfc 1123) requires the first When not protocol relative, get scheme, authority indicator, and last character of a hostname to be a letter or a digitdomain. BetweenIf there is an authority indicator (onethe first and last or more '/' characters immediately following the name may use lettersscheme's colon), digits, and the hyphenmake sure that there are only 2.
Also allowed are IPv4 addresses. IPv6 not supportedStrip off any port and path;
]] local function split_url (url_str) local scheme, authority, domain is expected to be stripped of any ; url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path so that the last character in (/), query(?), fragment (#) (the last character capture prevents false replacement of the tld. tld'//') if url_str:match ('^//%S*') then -- if there is two or more alpha characters. Any preceding what appears to be a protocol relative url domain = url_str:match ('^//(%S*)' ) elseif url_str:match (from splitting '%S-:/*%S+') then -- if there is what appears to be a url scheme, optional authority indicator, and domain name scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return scheme; -- return scheme only making domain nil which will cause an error message end domain = domain:gsub ('(%a ):%d+', '%1'); -- strip port number if present end return scheme) will be stripped, domain;here. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.end
There are several tests:
the first character of the whole domain name including subdomains must be a letter or a digit
single-letter/digit second-level domains in the .org TLD
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
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)
IPv4 dot-decimal address format; TLD not allowed
returns true if domain appears to be a proper name and tld or IPv4 address, else false--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
]checks the content of |title-link=], |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
local function is_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 Link parameters are to do it once if not domain:match ('^[%hold the title of a%d]') then -- first character must be letter or digit return false; end if domainwikipedia article so none of the WP: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]+$') then -- internationalized domain name with ACE prefix return true; elseif domainTITLESPECIALCHARACTERS are allowed:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname return true; elseif domain:match ('%f# < > [%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) return true;| { } _ elseif domain:match ('%f[%a%d][%a%d][%except the underscore which is used as a%d]%.%a%a+$') then -- two character hostname space in wiki urls 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 -- IPv4 address return true; else return false; endend# 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 |< I S _ U R L param>------------------------------------------------------------------link= parameter is NOT ok).
returns true if the scheme and domain parts of a url appear to be a valid url; else false.]]
This local function is the last step in the validation process. This function is separate because there are cases thatare not covered by split_urllink_param_ok (value) local scheme, for example is_parameter_ext_wikilinkdomain; if value:find ('[<>%[%]|{}]') which is looking for bracketted externalthen -- if any prohibited characters return false;wikilinks. end
]] local function is_url ( scheme, domain) if is_set = split_url (schemevalue) then ; -- if get scheme is set check it or nil and domain return is_scheme (scheme) and is_domain_name (domain)or nil from url; else return is_domain_name not is_url (scheme, domain); -- scheme not set when return true if value DOES NOT appear to be a valid url is protocol relative end
end
--[[--------------------------< S P L I N K _ T I T L E _ U R L O K >------------------------------------------------------------
Split a url into a scheme, authority indicator, Use link_param_ok() to validate |<param>-link= value and domain.If protocol relative url, return nil scheme and domain else return nil for both scheme and domainits matching |<title>= value.
When |<title>= may be wikilinked but not protocol relative, get scheme, authority indicator, and domainwhen |<param>-link= has a value. If there is This function emits an authority indicator (oneerror message whenor more '/' characters following the scheme's colon), make sure that there are only 2.condition exists
]]
local function split_url link_title_ok (url_str) local schemelink, authoritylorig, domain; url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$'title, '%1'torig)local orig; -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
if url_str:match is_set ('^//%S*'link) then -- don't bother if there is what appears to be <param>-link doesn't have a protocol relative urlvalue domain = url_str:match ('^//(%S*)') elseif url_str:match if not link_param_ok ('%S-:/*%S+'link) then -- if there is what appears to be a scheme, optional authority indicator, and domain namecheck |<param>-link= markup scheme, authority, domain orig = url_str:match ('(%S-:)(/*)(%S+)')lorig; -- extract identify the scheme, authority indicator, and domain portionsfailing link parameter authority = authorityelseif title:gsub find ('//', '', 1); -- replace place 1 pair of %[%['/' with nothing; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) thencheck |title= for wikilink markup return schemeorig = torig; -- return scheme only making domain nil which will cause an error messageidentify the failing |title= parameter
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
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 is_set (theorig) then|<param>-link= parameter is ok); else false when value appears to be a valid url table.insert(the |<param>-link= parameter is NOT ok)z. ]] local function link_param_ok (value) local schememessage_tail, domain; if value:find { set_error('[<>%[%]|{bad_paramlink', orig)}]') then ; --url or wikilink in |title= with |title- if any prohibited characters return falselink=;
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
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 _ I T A U R L I C S >------------------------------------------------------
Protects a string Escape sequences for content that will be wrapped in wiki italic markup '' ... '' Note: We cannot use <i> used for italics, as the expected behavior for italics specified by ''...'' in the title is thatthey will be inverted (i.e. unitalicized) in the resulting references. In addition, <i> and '' tend to interactpoorly under Mediawiki's HTML tidy.URL descriptions
]]
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
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
return table domain, path = URL:match ('^([/%.concat%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path if path then -- if there is a path portion path = path:gsub ('[%[%]]', { "["'[']='%5b', [']']='%5d'}); -- replace '[' and ']' with their percent encoded values URL=domain..path; -- and reassemble end if is_set (access) then -- access level (subscription, " "registration, limited) label = safe_for_url( label ), "]", error_str });end -- replace square brackets and newlines
base_url = table.concat ( --assemble external link with access signal { '<span class="plainlinks">[[-------------', --opening css and url markup URL, --the url ' ', --the required space label, '<span style="padding-left:0.15em">', --signal spacing css cfg.presentation[access], --the appropriate icon '</span>', --close signal spacing span ']< E X T E R N A L _ L I N K _ I D /span>' ----------------------------------------------close url markup and plain links span Formats a wiki style external link ]] local function external_link_id(options }) local url_string = options.id; if options.encode == true or options.encode == nil thenelse url_string base_url = mwtable.uri.encodeconcat({ "[", URL, " ", safe_for_url( url_string label ), "]" });-- no signal markup
end
return mw.ustringtable.formatconcat( '[%s%s%s \<span title\=\"%s\"\>%s%s%s\<\/span\>]', options.prefix, url_string, options.suffix or ""{ base_url, options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) error_str });
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 page_in_deprecated_cat added_deprecated_cat then page_in_deprecated_cat added_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 quote mark contained in a |title= or |chapter= parameter's value.
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.
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]]
cap, cap2 if 1 == str:wl_type then -- [[D]] simple wikilink with or without quote marks if mw.ustring.match (str, '%[%[[\"^(“”\'‘’].+[\"“”\'‘’]%]%]')then -- leading and trailing quote marks str = substitute (cfg.presentation['kern-wl-both'], str); elseif mw.ustring.match (str, '%[%[[^\"“”\'‘’].+%]%]')"); then -- match leading double or single quote but not double single quotesmarks str = substitute (cfg.presentation['kern-wl-left'], str); if is_set elseif mw.ustring.match (capstr, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks str = substitute (cfg.presentation['kern-leftwl-right'], {capstr); end else -- plain text or [[L|D]]; text in label variable label= mw.ustring.gsub (label, cap2}'[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) end 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 = str:mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) if is_set (cap) then str label = 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, mw.getContentLanguage():getCode() "en" ); -- 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, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}cfg.script_lang_codes) 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
--[[--------------------------< I S F O R M A T _ C H A P T E R _ T I T L I A S _ U S E D >-----------------------------------------------------
This function is used by select_one() to determine if one of a list of alias Format the four chapter 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|script-chapter=, |chapter=, |trans-chapter=, identifies which oneand |chapter-url= into a single Chapter meta- enumerated – true/false flag parameter (chapter_url_source used choose how enumerated aliases are examined value – value associated with an alias that has previously been selected; nil if not yet selected selected – the alias that has previously been selected; nil if not yet selected error_list – list of aliases that are duplicates of the alias already selected Returns: value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selectedfor error messages).
]]
local function is_alias_used format_chapter_title (argsscriptchapter, aliaschapter, indextranschapter, enumeratedchapterurl, valuechapter_url_source, selectedno_quotes, error_listaccess) local chapter_error = ''; if enumerated not is_set (chapter) then -- is this a test for an enumerated parameters? alias chapter = alias:gsub ('#', index); -- replace '#' with the value in indexto be safe for concatenation
else
alias if false = alias:gsub = no_quotes then chapter = kern_quotes ('#', ''chapter); -- remove if necessary, separate chapter title'#s leading and trailing quote marks from Module provided quote marks chapter = wrap_style (' if it existsquoted-title', chapter); end
end
if is_setchapter = script_concatenate (args[alias]chapter, scriptchapter) then -- alias <bdi> tags, lang atribute, categorization, etc; must be done after title is in the template's argument listwrapped if value ~= nil and selected ~= alias is_set (transchapter) then -- if we have already selected one of the aliases local skip; for _, v in ipairs transchapter = wrap_style (error_list) do 'trans-quoted- spin through the error list to see if wetitle've added this alias, transchapter); if v == alias is_set (chapter) then skip chapter = truechapter .. ' ' .. transchapter; break; else -- has been added so stop looking end end if not skip then -- has not been added so table.insert( error_list, alias ); -here when transchapter without chapter or script- add error alias to the error listchapter end else value chapter = args[alias]transchapter; -- not yet selected an alias, so select this one selected chapter_error = alias' ' .. set_error ('trans_missing_title', {'chapter'});
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
--[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- return chapter .. chapter_error;end
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 |--[[--------------------------<paramH A S _ I N V I S I B L E _ C H A R S >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.
Generates an error if more than one match This function will detect the visible replacement character when it is presentpart of the wikisource.
]]Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)and identifies them with a slightly different error message. See also coins_cleanup().
local function select_one( args, aliases_list, error_condition, index ) local value = nil; -- Detects but ignores the value assigned to character pattern that results from the selected parameter local selected = ''; -- the name transclusion of the parameter we have chosen local error_list = {{'}};templates.
if index ~= nil then index = tostringOutput of this function is an error message that identifies the character or the Unicode group, or the stripmarkerthat was detected along with its position (indexor, for multi-byte characters, the position of its first byte); endin theparameter value.
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) if #error_list > 0 and local position = 'none' ~= error_condition then ; -- position of invisible char or starting position of stripmarker local dummy; -- for cases where this code end of matching string; not used but required to hold end position when a capture is returned local capture; -- used outside by stripmarker detection to hold name of extract_names()the stripmarker local error_str i= ""1; for _ local stripmarker, k in ipairsapostrophe; capture = string.match ( error_list v, '[%w%p ]*') do; -- Test for values that are simple ASCII text and bypass other tests if true if error_str ~capture == "" v then error_str -- if same there are no unicode characters return; end while cfg.invisible_chars[i] do local char= error_str .cfg. invisible_chars[i][1] -- the character or group name local pattern=cfg.messagesinvisible_chars[i]['parameter2] --separator'] endthe pattern used to find it error_str position, dummy, capture = error_str mw.ustring. wrap_style find (v, pattern) -- see if the parameter value contains characters that match the pattern if position and (char == 'parameterzero width joiner') then -- if we found a zero width joiner character if mw.ustring.find (v, kcfg.indic_script)then -- its ok if one of the indic scripts position = nil; -- unset position end end if #error_list > 1 position then if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition) 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 error_str else local err_msg; if capture then err_msg = error_str .capture . cfg.messages['parameter-final-separator'].. char; else error_str err_msg = error_str char .. cfg' ' .. 'character'; end table.insert( z.messages[message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -pair-separator']add error message return; -- and done with this parameter end
end
error_str i= error_str .. wrap_style ('parameter', selected); table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } )i+1; -- bump our index
end
return value, selected;
end
--[[--------------------------< F O A R G U M A E N T _ C H W R A P T P E R _ T I T L E >----------------------------------------------
Format Argument wrapper. This function provides support for argument mapping defined in the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a configuration file so thatmultiple names can be transparently aliased to single Chapter meta-parameter (chapter_url_source used for error messages)internal variable.
]]
local function format_chapter_title argument_wrapper(scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotesargs ) local chapter_error origin = ''{};
if not is_set return setmetatable(chapter) then{ chapter ORIGIN = ''; -- to be safe for concatenation else if false == no_quotes thenfunction( self, k ) chapter local dummy = kern_quotes (chapter)self[k]; -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marksforce the variable to be loaded. chapter = wrap_style ('quoted-title', chapter)return origin[k];
end
end}, { chapter __index = script_concatenate function (chaptertbl, scriptchapterk ) -- <bdi> tags if origin[k] ~= nil then return nil; end local args, lang atributelist, categorizationv = args, etccfg.aliases[k]; must be done after title is wrapped if is_set type(transchapterlist ) == 'table' then transchapter v, origin[k] = wrap_style select_one(args, list, 'trans-quoted-titleredundant_parameters', transchapter); if is_set (chapter) origin[k] == nil then chapter origin[k] = chapter .. ' ' .. transchapter; else -- here when transchapter without chapter or script-chapterEmpty string, not nil end chapter elseif list ~= transchapternil then v, origin[k] = args[list], list; else -- maybe let through instead of raising an error? chapter_error -- v, origin[k] = ' ' args[k], k; error( cfg.. set_error (messages['trans_missing_titleunknown_argument_map', {'chapter'}] ); end end -- Empty strings, not nil; if is_set (chapterurl) v == nil then chapter v = cfg.defaults[k] or ''; origin[k] = ''; end tbl = external_link rawset(chapterurltbl, chapterk, chapter_url_sourcev ); -- adds bare_url_missing_title error if appropriate return v; end, return chapter .. chapter_error});
end
--[[--------------------------< 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 thefirst match.--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
This function will detect the visible replacement character when it is part Looks for a parameter's name in one of the wikisourceseveral whitelists.
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (galleryParameters in the whitelist can have three values: true - active, mathsupported parameters false - deprecated, pre, ref)supported parameters nil - unsupported parameters and identifies them with a slightly different error message. See also coins_cleanup().]]
Detects but ignores the character pattern that results from the transclusion of {local function validate( name, cite_class ) local name = tostring( name ); local state; if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}} ) then -- limited parameter sets allowed for these templates state = whitelist.limited_basic_arguments[ name ]; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker if 'arxiv' == cite_class then -- basic parameters unique to these templates state = whitelist.arxiv_basic_arguments[name];that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the end if 'biorxiv' == cite_class then state = whitelist.biorxiv_basic_arguments[name]; end if 'citeseerx' == cite_class thenparameter value state = whitelist.citeseerx_basic_arguments[name]; end
if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end -- limited enumerated parameters list name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) state = whitelist.limited_numbered_arguments[ name ]]; if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return true; end
local function has_invisible_chars (param, v) return false; -- not supported because not found or name is set to nil end -- end limited parameter-set templates local position state = ''whitelist.basic_arguments[ name ]; -- position of invisible char or starting position of stripmarkerall other templates; all normal parameters allowed local dummyif true == state then return true; end -- end of matching stringvalid actively supported parameter if false == state then deprecated_parameter (name); not used -- parameter is deprecated but required to hold still supported return true; end position when a capture is returned local capture; -- used by stripmarker detection to hold name of the stripmarkerall enumerated parameters allowed local iname =1name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last# local stripmarker, apostrophestate = whitelist.numbered_arguments[ name ];
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 position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern if position then-- if 'nowiki' == capture or 'math' =true = capture or ('ref' == capture and 'quote' == param) state then -- nowiki, math, or quote param and ref stripmarker (not an error condition) if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition) stripmarker = return 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; -- unsetvalid actively supported parameter elseif 'apostrophe' if false == char state then -- apostrophe template uses ‍, hair space and zero-width space apostrophe = true; elseif true == apostrophe and in_array deprecated_parameter (char, {'zero width joiner', 'zero width space', 'hair space'}) then position = nil; -- unset else local err_msg; if capture then err_msg = capture .. ' ' .. cfg.invisible_chars[i][3] or char; else err_msg = cfg.invisible_chars[i][3] or (char .. ' character'); end table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } name); -- add error message return; -- and done with this parameter endis deprecated but still supported end i=i+1return 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 T _ O W R A P P _ D A T E R >-------------------------------------------------------- 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
Argument wrapper. This function provides DOES NOT yet support for argument mapping defined in MMMM YYYY or any of the configuration file so thatmultiple names can be transparently aliased to single internal variabledate ranges.
]]
local function argument_wrappernowrap_date ( args date) local origin cap= {}''; local cap2=''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date);
return setmetatableelseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ({"^%d%d?%s*%a+%s+%d%d%d%d$") then ORIGIN cap, cap2 = functionstring.match ( selfdate, k "^(.*)%s+(%d%d%d%d)$"); local dummy date = selfsubstitute (cfg.presentation[k'nowrap2'], {cap, cap2}); end return date; end --force [[--------------------------< 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 the variable special case where it is desirable to be loadedomit the title type from the rendered citation (|type=none). ]] local function set_titletype (cite_class, title_type) if is_set(title_type) then if "none" == title_type then return origin[k]title_type = ""; -- if |type=none then type parameter not displayed
end
}, { __index = function ( tbl, k ) return title_type; -- if origin[k] ~|type= nil thenhas been set to any other value use that value return nil; end local args, list, v = args, return cfg.aliasestitle_types [kcite_class]; if type( list ) == 'table' then v, origin[k] = select_one( args, list, or 'redundant_parameters' ); if origin[k] == nil then origin[k] = ' -- set template's default title type; -- Empty else empty string, not nilfor concatenation end elseif list ~= nil then v, origin--[k] = args[list], list; else -- maybe let through instead of raising an error? -- v, origin[k] = args[k], k; error( cfg.messages['unknown_argument_map'] ); end -- Empty strings, not nil; if v == nil then v = cfg.defaults[k] or ''; origin[k] = ''; end tbl = rawset( tbl, k, v ); return v; end, });end--------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------Looks for Converts a parameter's name in the whitelist.hyphen to a dash
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
local function validatehyphen_to_dash( name str ) local name = tostring( name ); local state = whitelist.basic_arguments[ name ]; -- Normal arguments if true == state then return true; end -- valid actively supported parameter if false == state then deprecated_parameter not is_set(namestr); -- parameter is deprecated but still supported return true; end -- Arguments with numbers in them name = nameor str:gsubmatch( "[%[%d+", "#]{}<>]" ); -- replace digit(s) with # (last25 becomes last# state ~= whitelist.numbered_arguments[ name ]; if true == state nil then return true; end -- valid actively supported parameter if false == state then deprecated_parameter (name); -- parameter is deprecated but still supported return truestr; end return falsestr:gsub( '-', '–' ); -- Not supported because not found or name is set to nil
end
-- Formats a wiki style internal linklocal function internal_link_id(options) return mw.ustring.format( '[[%s%s%s|\--------------------------<span title\=\"%s\"\S A F E _ J O I N >%s\<\/span\>%s%s]]', options.prefix, options.id, options.suffix or "", options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) );end------------------------------------------------------------
--[[--------------------------< N O W R A P _ D A T E >-------------------------------------------------------- When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or isMMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY DOES NOT yet support MMMM YYYY or any Joins a sequence of the date rangesstrings together while checking for duplicate separation characters.
]]
local function nowrap_date safe_join(datetbl, duplicate_char ) local cap='';--[[ local cap2=''; if dateNote:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfgwe use string functions here, rather than ustring functions.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") thenThis has considerably faster performance and should work correctly as cap, cap2 = string.match (date, "^( long as the duplicate_char is strict ASCII.*)%s+(%d%d%d%d)$"); The strings date = substitute (cfg in tbl may be ASCII or UTF8.presentation['nowrap2'], {cap, cap2}); end]]
return datelocal str = '';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 number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes,spaces and other non-isxn characters. ]] local function is_valid_isxn (isxn_str, len)output string local temp comp = 0; isxn_str = { isxn_str:byte(1, len) }''; -- make a table of byte values what does '0comp' → 0x30 .. mean? local end_chr = '9' → 0x39, 'X' → 0x58; len = len+1local trim; -- adjust to be a loop counter for i_, v value in ipairs( isxn_str tbl ) do -- loop through all of the bytes and calculate the checksum if v value == nil then value = ''; end if str == string.byte( "X" ) '' then -- if checkdigit output string is X empty str = value; -- assign value to it (compares first time through the byte loop) elseif value of ~= 'X' which is 0x58)then temp = temp + 10*if value:sub( len - i 1,1); == '<' then -- it represents 10 decimalSpecial case of values enclosed in spans and other markup. else temp comp = temp + tonumbervalue:gsub( string.char(v"%b<>", "" ) )*; -- remove html markup (len<span>string</span> -i> string) else comp = value; end end -- typically duplicate_char is sepc return temp % 11 if comp:sub(1,1) == 0; duplicate_char then -- returns true if calculation result is zeroend 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.. ")" --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,-< IS _ V A L I D _ I S X N _ 1 3 >---------) == 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; end elseif end_chr == " " then --if last char of output string is a space if str:sub(-2,-1) == duplicate_char .. " " then --if last two chars of str are <sepc><space> str = str:sub(1,-3); --remove them both end end
ISBN if trim then if value ~= comp then --13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digitvalue does not equal comp when value contains html markup local dup2 = duplicate_char; if dup2:match( "%A" ) then dup2 = "%" ..dup2; end -- if duplicate_char not a letter then escape itIf the number is valid value = value:gsub( "(%b<>)" .. dup2, the result will be 0. Before calling this function"%1", isbn1 ) -13/ismn must be checked for length- remove duplicate_char if it follows html markup elseand stripped of dashes value = value:sub( 2, spaces and other non-isxn1 ); --13 charactersremove duplicate_char when it is first character end end end str = str ..value; --add it to the output string end end return str;]]end
local function is_valid_isxn_13 (isxn_str)
local temp=0;
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39
for i, v in ipairs( isxn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
end
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
end
--[[--------------------------< C H E C K I S _ S U F F I S B N X >------------------------------------------------------------
Determines whether an ISBN string returns true is validsuffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
]]
local function check_isbnis_suffix ( isbn_str suffix) if nil ~= isbn_str:matchin_array ("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digitssuffix, hyphens{'Jr', or the uppercase X isbn_str = isbn_str:gsub( "-"'Sr', "" ):gsub( " "'2nd', "" '3rd'}); -- remove hyphens and spaces local len = isbn_str:len(); if len ~= 10 and len ~= 13 then return false; end if len == 10 then if isbn_str:match( "^%d*X?$" ) == nil then return false; end return is_valid_isxn(isbn_str, 10); else local temp = 0; if isbn_stror suffix:match( "'^97[89]%d*dth$" ') == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979 return is_valid_isxn_13 (isbn_str)true;
end
return false;
end
--[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0[[--------------------------< I S _ G O O D _ V A N C _ N A M E >------------------------------------------... and uses thesame check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdfsection 2, pages 9–12.
]]For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a nameuses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.These things are not currently possible in this module so are left to the editor to do.
local function ismn (id)This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets local handler = cfg[http://www.unicode.org/charts/PDF/U0000.id_handlers['ISMN'pdf C0 Controls and Basic Latin];0041–005A, 0061–007A local text;[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF local valid_ismn = true;[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F id=id[http:gsub( "[%s//www.unicode.org/charts/PDF/U0180.pdf Latin Extended- –B]"0180–01BF, "" ); -- strip spaces, hyphens, and endashes from the ismn01C4–024F
if 13 ~|lastn= id:lenalso allowed to contain hyphens, spaces, and apostrophes. () or idhttp:match( "^9790%d*$" //www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |firstn== nil then -- ismn must be 13 digits also allowed to contain hyphens, spaces, apostrophes, and begin 9790 valid_ismn = false; else valid_ismn=is_valid_isxn_13 (id); -- validate ismn endperiods
-- text This original test: if nil = internal_link_id({link = handlermw.link, label = handlerustring.labelfind (last, "^[A-Za-zÀ-ÖØ-öø- use this (or external version) when there is some place to link toƿDŽ-ɏ%- prefix%s%']*$") or nil ==handlermw.prefix,id=id,separator=handlerustring.separatorfind (first, encode=handler.encode}) text="^[[" A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.. handler.link .. "|" .. handler.label .. "]+[2-6%a]*$" ) thenwas written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.. handler.separator .. id; -- because no place The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessaryto link use an external editor to yetmaintain this code.
if false == valid_ismn then text = text .. ' ' .. set_error\195\128-\195\150 – À-Ö ( 'bad_ismn' U+00C0–U+00D6 – C0 controls) \195\152-\195\182 – Ø- add an error message if the issn is invalidö (U+00D8-U+00F6 – C0 controls) end \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B) return text;end\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
--[[--------------------------< I S S N >----------------------------------------------------------------------]]
Validate and format an issnlocal function is_good_vanc_name (last, first) local first, suffix = first:match ('(. This code fixes the case where an editor -),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has included an ISSN in the citation but has separated the two groups of fourdigits with something that looks like a space. When that condition occurredgenerational suffix, the resulting link looked like this:get it
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] if is_set (suffix) then if not is_suffix (suffix) then add_vanc_error ('suffix'); return false; -- can't have spaces in not a name with an external linkappropriate suffix end endThis code now prevents that by inserting a hyphen at the issn midpoint if nil == mw. It also validates the issn for length and makes sure that the checkdigit agreeswith the calculated valueustring. Incorrect length find (8 digits)last, characters other than 0"^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-9 and X, %s%']*$") or checkdigit / calculated value mismatch will all cause a check issnerror message nil == mw. The issn is always displayed with a hyphenustring.find (first, even if the issn was given as "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then add_vanc_error ('non-Latin character'); return false; -- not a single group string of 8 digits.latin characters; Vancouver requires Romanization end; return true;end
]]
local function issn(id, e) local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate local handler; local text; local valid_issn = true; if e then handler = cfg.id_handlers['EISSN']; else handler = cfg.id_handlers['ISSN']; end--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
id=id:gsub( "[%sAttempts to convert names to initials in support of |name- –]", "" ); list-- strip spaces, hyphens, and endashes from the issnformat=vanc.
if 8 ~Names in |firstn= id:len() may be separated by spaces or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits longhyphens, containing only 0-9 or X in the last position valid_issn=false; -- wrong length or improper character else valid_issn=is_valid_isxn(idfor initials, 8); -- validate issn enda period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
if true == valid_issn then id = string.subVancouver style requires family rank designations ( idJr, 1II, 4 ) .. "-" .. string.sub( idIII, 5 etc); -- if validto be rendered as Jr, display correctly formatted version else id = issn_copy; -- if not valid2nd, use the show the invalid issn with error message end text = external_link_id({link = handler.link3rd, label = handleretc.label, prefix=handler See http://www.prefix,id=id,separator=handlerncbi.separator, encode=handlernlm.encode}) if false == valid_issn then text = text 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.. set_error( 'bad_issn' ) -- add an error message if the issn is invalid end return textend
--[[--------------------------< A M A Z O N >------------------------------------------------------------------ Formats a link to Amazon. Do simple error checking: asin must This function uses ustring functions because firstname initials may be mix any of 10 numeric or uppercase alphathe unicode Latin characters. 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 digitaccepted by is_good_vanc_name ().
]]
local function amazonreduce_to_initials(id, domainfirst) local err_cat name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
if not id:name then -- if not initials and a suffix name = mw.ustring.match(first, "^[%d(%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]+)$") then err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric charactersit just intials? end elseif name then -- if first is initials with or without suffix if id:match3 > mw.ustring.len ("^%d%d%d%d%d%d%d%d%d[%dX]$"name) then -- if 10-digit numeric (one or 9 digits with terminal X)two initials if check_isbnsuffix then -- if there is a suffix if is_suffix ( id suffix) then -- is it legitimate? return first; -- see if asin value is isbn10one or two initials and a valid suffix so nothing to do add_maint_cat else add_vanc_error ('ASINsuffix'); -- one or two initials with invalid suffix so error message return first; -- and return first unmolested end elseif not is_set (err_cat) thenelse err_cat = ' ' .. set_error ('bad_asin')return first; -- asin is not isbn10one or two initials without suffix; nothing to do
end
elseif not id:match("^%u[%d%u]+$") then
err_cat = ' ' .. set_error ('bad_asin'); -- 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'}) if here 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 --[[--------------------------< A R X I V >--------------------------------------------------------------------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 local initials, names = {}, valid only between date codes 9108 and 0703 is: 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-digit year tables to hold name parts and MM is the month number January = 01 first digit of YY for this form can only 9 and 0initials <number> is a three-digit number <version> is a local i = 1 or more digit number preceded with a lowercase v; no spaces (undocumented) the second form, valid from April 2007 through December 2014 is: arXiv:<date code>.<number><version>where: <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-digit counter for number <version> is a 1 or more digit number preceded with a lowercase v; no spacesof initials
the third form, valid from January 2015 is: arXiv:<date code>names = mw.text.<number><version>where: <date code> and <version> are as defined for 0704split (first, '[%s,]+'); --1412 <number> is split into a five-digit number]]table of names and possible suffix
local function arxiv (id, class) local handler = cfg.id_handlerswhile names['ARXIV'i];do -- loop through the table local year, month, version; local err_cat = ''; local text; if id:match("^%a[%a%.%-]+/[90]%d1 < i and names[01i]%d%d%d%d$") or id:match("^%a'[%a%.%-dJS]+/[90]%d[01drndth]+%d%d%d%dv%d+.?$"') then -- test for if not the 9108-0703 format w/ & w/o version yearfirst name, month = id:match("^%a[%and looks like a%.%-]+/suffix ([90]%dmay have trailing dot)( names[01i]%d)%d%d%d= names[v%di]*$"); year = tonumber:gsub (year); month = tonumber(month'%.', ''); if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- remove terminal dot if invalid year or invalid monthpresent if is_suffix ((91 == year and 7 > month) or (7 == year and 3 < month)names[i]) then -- if years ok, are starting and ending months ok?a legitimate suffix err_cat = table.insert (initials, ' ' .. set_error( 'bad_arxiv' names[i]); -- set add a separator space, insert at end of initials table break; -- and done because suffix must fall at the end of a name end -- no error messageif not a suffix; possibly because of Romanization
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") 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 ((7 3 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)i then table.insert ((7 == year) and (4 > month)) then --or -- when year is 07initials, is month invalid (before April)? err_cat = ' ' mw.ustring. set_errorsub( 'bad_arxiv' names[i],1,1)); -- set error messageinsert the intial at end of initials table
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 i = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); year = tonumber(year); month = tonumber(month); if ((15 > year) or (i+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' ); -- arXiv id doesn't match any formatbump the counter
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
if is_set (class) then class = ' --[[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink else class = ''; -- empty string for concatenation end return text .. class;end----------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[[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 Formats a hyphen in the string: a. Remove it. b. Inspect the substring following (to the right list of) the people (removed) hyphene. Then (and assuming that steps 1 and 2 have been carried out): 1g. All these characters should be digits, and there should be six or less. (not done in this functionauthors / editors) 2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function.
]]
local function normalize_lccn list_people(lccncontrol, people, etal) lccn local sep; local namesep; local format = control.format local maximum = control.maximum local lastauthoramp = lccn:gsub ("%s", "")control.lastauthoramp; -- 1. strip whitespace local text = {}
if nil ~= string.find (lccn,'/vanc') then lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it end local prefix local suffix prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix if nil ~= suffix format then -- if there was a hyphen suffix=string.rep("0", 6 -string.len (suffix)) .. suffix; -Vancouver- 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:like author//info-uri.info/registry/OAIHandlereditor name styling?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['LCCN']; local err_cat = ''; -- presume that LCCN is valid local id = 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 -- LCCN should be adddddddd if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern? err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message end elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... if nil =sep = 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' ); -- no match, set an error message end elseif 12 == len then name-- LCCN should be aaddddddddddlist separator between authors is a comma 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 namesep = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message endlast/first separator is a space
else
err_cat sep = ' ;' .. set_error( -- name-list separator between authors is a semicolon namesep = 'bad_lccn, ' ); -- wrong length, set an error messagelast/first separator is <comma><space>
end
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
err_cat = ' ' .. set_error( 'bad_lccn' ); -- 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 idsep:matchsub(-1,-1) ~= "[^%d]") then -- if PMID has anything but digits err_cat sep = ' ' sep .. set_error( 'bad_pmid' ); -- set an error message" " end else -- PMID is only digits local id_num = tonumberif is_set (idmaximum)and maximum < 1 then return "", 0; end -- convert id to a number returned 0 is for range testing if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries err_cat = ' ' .. set_error( 'bad_pmid' )EditorCount; -- set an error message end endnot used for authors
return external_link_idfor i,person in ipairs(people) do if is_set({link = handlerperson.link, label last) then local mask = handlerperson.label,mask local one prefix=handler.prefix,idlocal sep_one =id,separator=handler.separator, encode=handler.encode}) .. err_catsep;end --[[--------------------------< I S _ E M B A R G O E D if is_set (maximum) and i >------------------------------------------------------maximum then Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo etal = against today's date. If embargo date istrue;in the future, returns the content of |embargo= break; otherwise, returns and empty string because the embargo has expired or because|embargo elseif (mask ~= was not set in this cite. ]]nil) then local function is_embargoed n = tonumber(embargomask) if is_set (embargon ~= nil) then local lang one = mwstring.getContentLanguagerep("—",n); local good1, embargo_date, good2, todays_date; else good1, embargo_date one = pcall( lang.formatDate, lang, 'U', embargo )mask; good2, todays_date sep_one = pcall( lang.formatDate, lang, 'U' )" "; if good1 and good2 then -- if embargo date and today's date are good dates if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future? return embargo; -- still embargoedend
else
add_maint_cat one = person.last local first = person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub ('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; return ''end if is_set(person.link) and person.link ~= control.page_name then one = make_wikilink (person.link, one); -- unset because embargo has expiredlink author/editor if this page is not the author's/editor's page end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
return ''; -- |embargo= not set return empty string
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[[--------------------------< P M C >-------------------------------------------------------------#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 Format a PMC, do simple error checking, and check for embargoed articles result = result .. sep .. The embargo parameter takes a date for a value' ' . If the embargo date is in the future the PMC identifier will notbe linked to the article. If the embargo date is today or in the past, or if it is empty or omitted, then thePMC identifier is linked to the article through the link at cfg.id_handlersmessages['PMCet al']; -- we've go a last-first list and etal so add et al.prefix. end return result, countend
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.
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.--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
]]Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
local function pmc(idnamelist is one of the contributor-, embargo) local test_limit = 6000000; author-, or editor- update this value as PMCs approach local handler = cfgname lists chosen in that order.id_handlers['PMC']; local err_cat = ''; -- presume that PMC year is valid local text;Year or anchor_year.
if id:match("[^%d]") then -- if PMC has anything but digits] err_cat = ' ' .. set_errorlocal function anchor_id ( 'bad_pmc' namelist, year); -- set an error message else -- PMC is only digits local id_num names= tonumber(id){}; -- convert id to a number table for range testingthe one to four names and year if 1 > id_num or test_limit < id_num then for i,v in ipairs (namelist) do -- if PMC is outside test limit boundariesloop through the list and take up to the first four last names err_cat names[i] = ' ' v.. set_error( 'bad_pmc' ); -- set an error messagelast 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 (embargoid) then -- if concatenation is PMC is still embargoed?not an empty string text=return "[[CITEREF" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external linkadd the CITEREF portion
else
text = external_link_id({link = handler.link, label = handler.label, return ''; -- return an empty string; no embargo date or embargo has expired, ok reason to link to article prefix=handler.prefix,include CITEREF id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;in this citation
end
return text;
end
--[[--------------------------< D O I >------------------------------------------------------------------------
Formats a DOI and checks for DOI errors.--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
DOI names contain two parts: prefix Evaluates the content of author and suffix separated by a forward slasheditor name parameters for variations on the theme of et al. If found, Prefix: directory indicator '10the et al.' followed by is removed, a registrant code Suffix: character string of any length chosen by flag is set to true and the function returns the modified name and the registrantflag.
This function checks a DOI name for: prefix/suffix. If never sets the doi name contains spaces or endashes, or, if flag to false but returns it's previous state because it endsmay have been set bywith a period or a comma, previous passes through this function will emit a bad_doi error message.or by the parameters |display-authors=etal or |display-editors=etal
DOI names are case-insensitive and can incorporate any printable Unicode characters so the test 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 (name, etal, nocat)
local function doi if is_set (id, inactivename)then -- name can be nil in which case just return local cat etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme local handler others_pattern = cfg.id_handlers"[;,]? *%f[%a]and ['DOI'Oo]thers"; -- and alternate to et al. local text; if is_setname:match (inactiveetal_pattern) then -- variants on et al. local inactive_year name = inactivename:matchgsub ("%d%d%d%d"etal_pattern, '') ; -- if found, remove etal = true; -- set flag (may have been set previously here or by |display-authors=etal) if not nocat then -- no categorization for |vauthors= add_maint_cat ('etal'); -- try to get the year portion from the inactive dateand add a category if not already added end if is_setelseif name:match (inactive_yearothers_pattern) then -- if not 'et al.', then 'and others'? table.insertname = name:gsub ( z.error_categoriesothers_pattern, "自" .. inactive_year .. "年含有不活躍DOI的頁面" ''); -- if found, remove else etal = true; -- set flag (may have been set previously here or by |display-authors=etal) table.insertif not nocat then -- no categorization for |vauthors= add_maint_cat ( z.error_categories, "含有不活躍DOI的頁面" 'etal'); -- when inactive doesn't contain and add a recognizable yearcategory if not already added end
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
end
text = external_link_id({link = handler.link, label = handler.label, q = handler.qreturn name,etal; -- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. (inactive or '')end
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
cat = ' ' .. set_error( 'bad_doi' );
end
return text .. cat end--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
--[[--------------------------< H D L >------------------------------------------------------------------------]]
Formats an HDL with minor error checkinglocal function name_has_ed_markup (name, list_name) local _, pattern; local patterns = { -- these patterns match annotations at end of name '%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (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 if is_set (name) then for _, pattern in ipairs (patterns) do -- spin through patterns table and suffix separated by a forward slash. Prefix if name: character string using any character in the UCS-2 character set except match (pattern) then add_maint_cat ('/extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template break; end end Suffix: character string of any length using any character in the UCSend return name; --2 character set chosen by the registrantand doneend
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-insensitive -[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >---------------------------------------- Evaluates the content of author and can incorporate any printable Unicode characters so the test editor (surnames only) parameters for endashes multiple names. Multiple names areindicated if there is more than one comma andterminal punctuation may not be technically correct but it appearsor semicolon. If found, that in practice these characters are rarelythe function adds the multiple nameif ever used in HDLs(author or editor) maintenance category.
]]
local function hdlname_has_mult_names (idname, list_name) local handler = cfg.id_handlers['HDL']count, _; local text = external_link_idif is_set ({link = handler.link, label = handler.label, q = handler.q,name) then prefix=handler.prefix _,idcount =idname:gsub ('[;,separator=handler.separator]', encode=handler.encode}''); -- count the number of separator-like characters if nil 1 < count then -- param could be |author=or |editor= id:matchso one separator character is acceptable add_maint_cat ("^[^%s–]-/'mult_names', cfg.special_case_translation [^%s–list_name]-[^%.,]$") then ; -- hdl must contain more than one separator indicates multiple names so add a fwd slash, must not contain spaces, endashes, and must not end with period or commamaint cat for this template text = text .. ' ' .. set_error( 'bad_hdl' );end
end
return textname; -- and done
end
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
Formats an OpenLibrary link, and checks for associated errors--[[--------------------------< 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-holdingparameters.
]]
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];
local function name_checks (last, first, list_name) if is_set ( code == "A" last) then return external_link_idif last:match ('^%(%({link=handler.link, label=handler.label*%)%)$') then -- if wrapped in doubled parentheses,accept as written prefixlast =handler.prefix .last:match ('^%(%((. *)%)%)$'authors/OL',); -- strip parens else idlast =idname_has_mult_names (last, separator=handler.separator, encode = handler.encode}list_name) elseif ; -- check for multiple names in the parameter ( code == "M" last only) then return external_link_id last = name_has_ed_markup ({link=handler.linklast, label=handler.label, prefix=handler.prefix .. list_name); -- check for extraneous 'books/OLeditor',annotation end id=id, separator=handler.separator, encode = handler.encode}) end elseif if is_set ( code == "W" first) then return external_link_idif first:match ('^%(%({link=handler.link, label=handler.label*%)%)$') then -- if wrapped in doubled parentheses,accept as written prefixfirst =handler.prefix .first:match ('^%(%((. *)%)%)$'works/OL',); -- strip parens else idfirst =id, separator=handler.separatorname_has_ed_markup (first, encode = handler.encode}list_name); -- check for extraneous 'editor' annotation end elseend return external_link_id({link=handler.linklast, label=handler.label, prefix=handler.prefix .. 'OL', id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' )first; -- done
end
end
--[[--------------------------< E X T R A C T _ N A M E S S A G E _ I D >----------------------------------------------------------Gets name list from the input arguments
Validate Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and format a usenet message idmask parameters. Simple error checkingStops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, looks for |last2=, and |last3= but doesn'id-left@id-right' not enclosed int'<' find |last4= and/or '>' angle brackets|last5= then the search is done.
]]This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
local function message_id (id) local handler = cfgWhen an author or editor parameter contains some form of 'et al.id_handlers['USENETID, the 'et al.']; text = external_link_idis stripped from the parameter and a flag ({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}etal)returned if not id:matchthat will cause list_people('^.+@.+$') or not id:match(to add the static '^[^<]et al.*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>' text = text from Module:Citation/CS1/Configuration.. ' This keeps ' et al.. set_error( 'bad_message_id' ) -- add an error message if out of the message id is invalid end return textend --[[--------------------------< 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 defaultstemplate's metadata.Also handles When this occurs, the special case where it page is desirable added to omit the title type from the rendered citation (|type=none)a maintenance category.
]]
local function set_titletype extract_names(cite_classargs, title_typelist_name) if is_set(title_type) thenlocal names = {}; -- table of names local last; -- individual name components local first; local link; local mask; if "none" local i =1; -- loop counter/indexer local n = title_type then1; -- output table indexer title_type local count = ""0; -- if used to count the number of times we haven't found a |typelast=none then type parameter not displayed end(or alias for authors, |editor-last or alias for editors) local etal=false; return title_type; -- if |type= has been return value set to any other value use that value endtrue when we find some form of et al. in an author parameter
return 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.title_types aliases[cite_classlist_name .. '-Last'] or , 'redundant_parameters', i ); -- set templatesearch through args for name components beginning at 1 first = select_one( args, cfg.aliases[list_name .. '-First's default title type], 'redundant_parameters', i ); link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); else empty string for concatenationend mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
last, etal = name_has_etal (last, etal, false); --[[--------------find and remove variations on et al. first, etal = name_has_etal (first, etal, false); --find and remove variations on et al. 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; --number of times we haven't found last and first if 2 < C L E A N _ I S B N >-----------------------------------------------= count then --two missing names and we give up break; --normal exit or there is a two-name hole in the list; can't tell which end else --we have last with or without a first link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); --check for improper wikimarkup
Removes irrelevant text and dashes from ISBN number names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)Similar n = n + 1; -- point to that used 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 Special:BookSourcestwo consecutive missing names end i = i + 1; -- point to next args location end]] return names, etal; -- all done, return our list of namesend
local function clean_isbn( isbn_str )
return isbn_str:gsub( "[^-0-9X]", "" );
end
--[[--------------------------< G E S C A P E T _ L U A _ M A G I C S O 6 3 9 _ C H A R S O D E >------------------------------------------------ Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. Returns the language name and associated two- or three-character code. Because case of the source may be incorrector different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match isfound, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, wereturn the original language name string.
Returns mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a string where all list of lua's magic characters have been escaped. This is important because functions likelanguages that in some cases may includestringextensions.gsubFor example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' () treat their pattern and replace strings as patterns, MediaWiki does not literal stringssupportcode 'cbk' or name 'Chavacano'.]]local function escape_lua_magic_chars Most (argumentall?)of these languages are not used a 'language' codes per se, rather they argument = argumentare used as sub-domain names:gsubcbk-zam.wikipedia.org. These names can be found ("%%", "%%%%"for the time being); -- replace % with %%at argument = argumenthttps:gsub("([%^%$%(%)%//phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEn.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters return argument;endphp
Names but that are included in the list will be found if that name is provided in the |language= parameter. For example,if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------zam'. When names are foundand the associated code is not two or three characters, this function returns only the Wikimedia language name.
Strip wiki italic and bold markup Adapted from argument so that it doesn't contaminate COinS metadata.This function strips common patterns of apostrophe markup. We presume that editors who have code taken the time tomarkup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behindfrom Module:Check ISO 639-1.
]]
local function strip_apostrophe_markup get_iso639_code (argumentlang, this_wiki_code) 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 not is_set remap[lang:lower(argument) ] then return argumentremap[lang:lower()][1], remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code end
while true do if argument:match local languages = mw.language.fetchLanguageNames("%this_wiki_code, '%all'%'%'%'") then -- bold italic (5)get a list of language names known to Wikimedia argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it elseif argument:match ("%'%all'%'%'") then -- italic start is required for North Ndebele, South Ndebele, and end without content (4Ojibwa) argument local langlc =argument:gsubmw.ustring.lower("%'%'%'%'", ""lang); -- lower case version for comparisons elseif argument:match for code, name in pairs("%'%'%'"languages) then do -- bold scan the list to see if we can find our language if langlc == mw.ustring.lower(3name)then argumentif 2 ~=argumentcode:gsublen("%'%'%'", ""); elseif argumentand 3 ~= code:match len("%'%'") then -- two-or three- italic (2)character codes only; extensions not supported argument=argument:gsub("%'%'", "") return name; -- so return the name but not the code else end breakreturn name, code; -- found it, return name to ensure proper capitalization and the the code
end
end
return argumentlang; -- donenot valid language; return language in original case and nil for the code
end
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
Makes --[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------ Gets language name from a title for COinS from Title and / provided two- or ScriptTitle 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 (either code or any other name), the page is assigned to the category forthat code: Category:Norwegian-script pairslanguage sources (no). For valid three-character code languages, the page is assignedto the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-characterequivalents of two-character codes: code 'ar' is recognized bit code 'ara' is not. This function supports multiple languages in the form |language=nb, 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 make_coins_title language_parameter (titlelang) local code; -- the two- or three-character language code local name; -- the language name local language_list = {}; -- table of language names to be rendered local names_table = {}; -- table made from the value assigned to |language= local this_wiki = mw.getContentLanguage(); -- get a language object for this wiki local this_wiki_code = this_wiki:getCode() -- get this wiki's language code local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name local remap = { ['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org ['bn'] = 'Bengali', -- MediaWiki returns Bangla } names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list for _, lang in ipairs (names_table) do -- reuse lang if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? end if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code name = mw.language.fetchLanguageName( lang:lower(), scriptthis_wiki_code); -- get language name if |language= is a proper code end if is_set (titlename) then -- if |language= specified a valid code code = lang:lower(); -- save it title else name, code = strip_apostrophe_markup get_iso639_code (titlelang, this_wiki_code); -- strip any apostrophe markupattempt 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 == 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 title=else add_maint_cat ('unknown_lang'); -- add maint category if not setalready added end table.insert (language_list, make sure title is an empty stringname); name = ''; -- so we can reuse it
end
code = #language_list -- reuse code as number of languages in the list if is_set (script) 2 >= code then script name = script:gsub table.concat ('^%l%l%s*:%s*'language_list, 'and '); -- remove insert '<space>and<space>' between two language prefix if present (script value may now be empty string)names elseif 2 < code then script language_list[code] = strip_apostrophe_markup (script)'and ' .. language_list[code]; -- strip any apostrophe markup elseprepend last name with 'and<space>' scriptname =table.concat (language_list, ', '; ) -- if not set, make sure script is an empty stringand concatenate with '<comma><space>' separators
end
if is_set (title) and is_set (script) this_wiki_name == name then script = return ' ' .. script; -- add a space before we concatenateif one language and that language is this wiki's return an empty string (no annotation)
end
return title (" " .. scriptwrap_msg ('language', name)); -- otherwise wrap with '(in ...)' --[[ TODO: should only return blank or name rather than full list so we can clean up the concatenationbunched parenthetical elements Language, Type, Format ]]
end
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters --[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- Set style settings for use in COinSCS1 citation templates.Returns separator and postscript settings
]]
local function get_coins_pages set_cs1_style (pagesps) local pattern; if not is_set (pagesps) then return pages; end -- if no page numbers then we're done while true dounless explicitely set to something pattern ps = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d]'.*%]")'; -- pattern is the opening bracket, terminate the url and following space(s): "[url " if nil == pattern then break; end -- no more urls pattern = escape_lua_magic_chars (pattern); -- pattern is not rendered citation with a literal string; escape lua's magic pattern characters pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possibleperiod
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets pages = pages:gsub("–"return '.', "-" )ps; -- replace endashes with hyphens pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like? return pages;separator is a full stop
end
-- Gets the display text for a wikilink like [[A|B--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- Set style settings for CS2 citation templates. Returns separator, postscript, ref settings ]] or [[B]] gives B local function remove_wiki_linkset_cs2_style ( str ps, ref) return (str:gsubif not is_set ( "%[%[([^%[%]]*ps)%]%]"then -- if |postscript= has not been set, function(l)set cs2 default return l:gsub( "^[^|]*|ps = ''; -- make sure it isn't nil end if not is_set (.*ref)$", "%1" ):gsub("^%s*(.then --)%s*$", if |ref= is not set ref = "%1harv"); -- set default |ref=harv end)) return ',', ps, ref; -- separator is a comma
end
-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end
--[[--------------------------< G E T _ S A F E T T I N G S _ J F R O M _ C I N T E _ C L A S S >------------------------------------------------------------
Joins a sequence of strings together while checking for duplicate separation charactersWhen |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establishrendered style.
]]
local function safe_joinget_settings_from_cite_class ( tblps, duplicate_char 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 (ps); 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); Noteelse -- 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' == ps: we use lower() then -- if assigned value is 'none' then ps = ''; -- set to empty string functions here, rather than ustring functions. end
This has considerably faster performance and should work correctly as return sep, ps, ref long as the duplicate_char is strict ASCII. The stringsend in tbl may be ASCII or UTF8. ]] local str --[= ''; [-------------------------< I S _ P D F >---------------------------------------------------------------- the output string local comp = ''; -- what does 'comp' mean? local end_chr = ''; local trim;Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] whenapplying the pdf icon to external links. for _, value in ipairs( tbl ) do returns true if value == nil then value = ''; endfile extension is one of the recognized extensions, else false if str ]== '' then -- if output string is empty] str = value; -- assign value to it local function is_pdf (first time through the loopurl) elseif value ~= return url:match ('%.pdf$' then if value) or url:submatch (1,1'%.PDF$') == or url:match ('<%.pdf[%?#]' then -- Special case of values enclosed in spans and other markup. comp = value) or url:gsubmatch ( "'%b<>", "" .PDF[%?#]'); -- remove html markup (<span>string</span> -> string) elseend 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 .. "<HERE(enchr=" .. end_chr.. ")" S T Y L E _ F O R M A T >-------------- 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 -- normal case when Applies css style to |urlformat=something & , |titlechapter-format=Title, etc. Also emits an error message if the format parameter does trim = true; endnot have a matching url parameter. If the format parameter is not set and the url contains a file extension that elseif end_chr == " " then -- if last char of output string is recognized as a space if str:sub(-2pdf document by MediaWiki's commons.css,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> str = str:subthis code will set the format parameter to (1,-3PDF); -- remove them bothwith end endthe appropriate styling.
if trim then]] if value ~= comp then -- value does not equal comp when value contains html markup local dup2 = duplicate_char;function style_format (format, url, fmt_param, url_param) if dup2:matchis_set ( "%A" format) then dup2 format = "%" .. dup2wrap_style ('format', format); end -- if duplicate_char not a letter then escape it value = value:gsub( "(%b<>)" .. dup2add leading space, "%1"parentheses, 1 ) resize -- remove duplicate_char if it follows html markup else value = value:subnot is_set ( 2, -1 url); -- remove duplicate_char when it is first character end end endthen str format = str format .. valueset_error( 'format_missing_url', {fmt_param, url_param} ); --add it to the output stringan error message
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
return strformat;end
--[[--------------------------< G E T _ D I S P L A Y _ G A U T H O O D _ V A N C R S _ N A M E D I T O R S >--------------------------------------------
For Vancouver Style, Returns a number that defines the number of names displayed for author/and editor names are supposed to be rendered in Latin (read ASCII) characters. When name lists and a nameboolean flaguses characters that contain diacritical marks, those characters are to converted to the corresponding Latin characterindicate when et al.When a name is written using a non-Latin alphabet or logogram, that name is to should be transliterated into Latin characters.These things are not currently possible in this module so are left appended to the editor to doname list.
This test allows When the value assigned to |firstdisplay-xxxxors= is a number greater than or equal to zero, return the number and |last= names to contain any the previous state of the letters defined in 'etal' flag (false by default but may have been set to true if the four Unicode Latin character setsname list contains [http://wwwsome variant of the text 'et al.unicode').org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and LatinWhen the value assigned to |display-1 Supplement] 00C0–00D6xxxxors= is the keyword 'etal', 00D8–00F6, 00F8–00FFreturn a number that is one greater than the [http://wwwnumber of authors in the list and set the 'etal' flag true.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F This will cause the list_people() to display all of [http://www.unicode.org/charts/PDF/U0180the names in the name list followed by 'et al.pdf Latin Extended-B] 0180–01BF, 01C4–024F'
|lastn= also allowed to contain hyphens, spacesIn all other cases, returns nil and apostrophesthe previous state of the 'etal' flag. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
At the time inputs: max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of this writing, I had to write the etal count: #a or #e list_name: 'if nil == mw.ustring.find ...authors' or 'editors' test ouside of the code editor and paste it herebecause the code editor gets confused between character insertion point and cursor position. etal: author_etal or editor_etal
]]
local function is_good_vanc_name get_display_authors_editors (lastmax, firstcount, list_name, etal) if nil is_set (max) then if 'etal' == mw.ustring.find max:lower():gsub(last, "^[A'%.]", '') then -Za-zÀthe :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; - ÖØ- öønumber of authors + 1 so display all author name plus et al. etal = true; - ƿDŽ- ɏ%-%soverrides value set by extract_names() elseif max:match ('^%d+$']*$") or nil then -- if is a string of numbers max == mw.ustring.find tonumber (first, "^[Amax); -Za-zÀmake it a number if max >= count then - ÖØ- öøif |display- ƿDŽ-ɏ%-%s%xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed'%, cfg.special_case_translation [list_name]*$") then; end add_vanc_error else -- not a valid keyword or number table.insert( z.message_tail, { set_error('invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message return false max = nil; -- unset; as if |display-xxxxors= had not a string of latin characters; Vancouver required Romanizationbeen set end end; return truemax, etal;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-format=vanc. [[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Names in Adds page to Category:CS1 maint: extra text if |page= or |firstnpages= may has what appears to be separated by spaces or hyphens, some form of p. or for initials, a periodpp. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/abbreviation in the first characters of the parameter content.
Vancouver style requires family rank designations (Jrcheck Page and Pages for extraneous p, IIp., IIIpp, etcand pp. at start of parameter value: good pattern: '^P[^%.P%l]' matches when |page(s) to be rendered as Jr, 2nd, 3rd, etc. This form = begins PX or P# but not Px where x and X are letters and # is nota dgiitcurrently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http bad pattern://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.'^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().]]
local function extra_text_in_page_check (page) local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg? local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
local function reduce_to_initials if not page:match (firstgood_pattern) if mw.ustring.and (page:match(first, "^%u%u$"bad_pattern) then return first end; -- when first contains just two upper-case letters, nothing to do local initials = {} local i = 0; -- counter for number of initials for word in mw.ustring.gmatchor page:match (first, "'^[^%s%.%-Pp]+"ages?') do -- names separated by spaces, hyphens, or periods) then table.insert(initials, mw.ustring.subadd_maint_cat (word,1,1)'extra_text') -- Vancouver format does not include full stops. i = i + 1; -- bump the counter 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 >-------------------------------------------------------
Formats --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- split apart a list |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubledparentheses to also have commas; in the old version of people (e.gthe code, the doubled parnetheses were included in therendered citation and in the metadata. authors / editors) Individual author names may be wikilinked
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function local sep; local namesep; local format ]= control.format local maximum = control.maximum local lastauthoramp = control.lastauthoramp; local text = {}]
local function get_v_name_table (vparam, output_table, output_link_table) if 'vanc' local name_table == format then -- Vancouver-like author/editor name styling? sep = 'mw.text.split(vparam, "%s*,'%s*"); - - name-list separator between authors is a commanames are separated by commas namesep = ' ' local wl_type, label, link; -- last/first separator is a space else sep = 'wl_type not used here;' -- name-list separator between authors is just a semicolon namesep = ', ' -- last/first separator is <comma><space> endplace holder
if sep:sub(-1,-1) ~= " " then sep local i = sep .. " " end if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for while name_table[i,person in ipairs(people) ] do if is_setname_table[i]:match ('^%(%(person.last*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens local mask name = person.maskname_table[i]; local onei=i+1; -- bump indexer to next segment local sep_one while name_table[i] do name = sepname .. ', ' .. name_table[i]; -- concatenate with previous segments if is_set name_table[i]:match (maximum'^.*%)%)$') then -- if this table member has the closing doubled parens break; -- and i > maximum thendone reassembling so end etal i= truei+1; -- bump indexer break end table.insert (output_table, name); -- and add corporate name to the output table elseif table.insert (mask ~= niloutput_link_table, '') then; -- no wikilink else local n wl_type, label, link = tonumberis_wikilink (maskname_table[i]); if -- wl_type is: 0, no wl (n ~= niltext in label variable) then; 1, [[D]]; 2, [[L|D]] one = string table.repinsert ("—"output_table,nlabel); -- add this name else one if 1 = mask; sep_one = " ";wl_type then endtable.insert (output_link_table, label); -- simple wikilink [[D]]
else
one = persontable.last local first = person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub insert ('%.'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) -- 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 = "no wikilink or [[" .. person.link .. "L|" .. one .. "D]]" -- ; add this link author/editor if this page there is not the author's/editor's page endone, else empty string
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 [[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S > 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 This function extracts author / editor names from |vauthors= or |veditors= table.concat(text) -- construct list if etal and is_set (result) then -- etal may be set by finds matching |displayxxxxor-authorsmaskn=etal but we might not have a lastand|xxxxor-first list result linkn= result in args.. sep .. ' ' .. cfg.messages['et al']; -- we've go It then returns a last-first list and etal so add et altable of assembled names just as extract_names() does. end return result, countend
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional namesmay sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliancetests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty stringSupports generational suffixes Jr, 2nd, 3rd, 4th–6th.
namelist This function sets the vancouver error when a reqired comma is missing and when there is one of the contributor-, a space between an author-, or editor-name lists chosen in that order. year is Year or anchor_year's initials.
]]
local function anchor_id parse_vauthors_veditors (namelistargs, yearvparam, list_name) local names={}; -- a table for the one of names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = {}; local v_link_table = {}; -- when name is wikilinked, targets go in this table local etal = false; -- return value set to four 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 and yearare separated by commas for i,v v_name in ipairs (namelistv_name_table) do if v_name:match ('^%(%(.+%)%)$') then -- loop through the list corporate authors are wrapped in doubled parentheses to supress vanc formatting and take up error detection first = ''; -- set to the first four empty string for concatenation and because it may have been set for previous author/editor last names= v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses corporate = true; -- flag used in list_people() nameselseif string.find(v_name, "%s") then if v_name:find('[i;%.] ') then -- look for commonly occurring punctuation characters; add_vanc_error ('punctuation'); end local lastfirstTable = {} lastfirstTable = vmw.text.split(v_name, "%s") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials if i == 4 is_suffix (first) then break end -- if four then donea valid suffix end suffix = first -- save it as a suffix and first = table.insert remove(names, yearlastfirstTable); -- add get what should be the year at initials from the table end -- no suffix error message here because letter combination may be result of Romanization; check for digits? local id last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other namesthat are not initials if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then add_vanc_error ('missing comma'); -- concatenate names and year for CITEREF idmatches last II last; the case when a comma is missing end if is_set mw.ustring.match (idv_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test add_vanc_error ('name'); -- matches a space between two intiials end else first = ''; -- if concatenation is not an set to empty stringfor concatenation and because it may have been set for previous author/editor last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end return if is_set (first) then if not mw.ustring.match (first, "CITEREF^%u?%u$" ) then -- first shall contain one or two upper-case letters, nothing else add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials end is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit if is_set (suffix) then first = first .. id' ' .. suffix; -- if there was a suffix concatenate with the initials suffix = ''; -- unset so we don't add the CITEREF portionthis suffix to all subsequent names end else if not corporate then is_good_vanc_name (last, ''); end end return link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[i]; mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- return an empty string; no reason add this assembled name to include CITEREF id in this citationour names list
end
return names, etal; -- all done, return our list of names
end
--[[--------------------------< N A M S E L E C T _ A U T H A S O R _ E D I T A L O R _ S O U R C E >----------------------------------------------------
Evaluates Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the content source of the author and name list orselect one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name parameters for variations on the theme list. Only one of et althese appropriate three will be used. If foundThe hierarchy is: |authorn= (and aliases) highest and |authors= lowest andsimilarly,|editorn= (and aliases) highest and |editors= lowest 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 et alauthor name list. is removed There may be a betterway to do this, a flag I just haven't discovered what that way is set to true and the function returns the modified . Emits an error message when more than one xxxxor name and the flagsource is provided.
This function never sets the flag to false but returns it's previous state because it may have been set byprevious passes through In this function , vxxxxors = vauthors or by the parameters |display-veditors; xxxxors = authors=etal or |display-editors=etalas appropriate.
]]
local function name_has_etal select_author_editor_source (namevxxxxors, etalxxxxors, nocatargs, list_name)local lastfirst = false; if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a |first1= without a |last1=; this ... select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors= select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 )then lastfirst=true; end
if (is_set (namevxxxxors) then -- name can be nil in which case just return local etal_pattern and true == "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" lastfirst) or -- variations on these are the 'et al' themethree error conditions local others_pattern = "[;,]? *%f[%a](is_set (vxxxxors) and [Oo]thers"; -- and alternate to et al.is_set (xxxxors)) or if name:match (etal_patterntrue == lastfirst and is_set (xxxxors)) then -- variants on et al. name = name:gsub (etal_pattern, local err_name; if 'AuthorList'); == list_name then -- if found, removefigure out which name should be used in error message etal err_name = true'author'; -- set flag (may have been set previously here or by |display-authors=etal) if not nocat then -- no categorization for |vauthors=else add_maint_cat (err_name = 'etaleditor'); -- and add a category if not already added
end
elseif name:match table.insert(others_pattern) then -- if not 'et alz.'message_tail, then { set_error( 'and othersredundant_parameters'?, name = name:gsub (others_pattern, {err_name .. ''); -name- if foundlist parameters'}, 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 end enderror message
end
if true == lastfirst then return 1 end; -- return a number indicating which author name, etalsource 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
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn'tfind |last4= and |last5= then the search is done.--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
This function emits an error message when there is used to validate a |firstn= without a matching |lastn=. When there are parameter'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 s assigned value for those parameters that have only a matching |firstn=.limited numberWhen an author or editor parameter contains some form of 'et al.'allowable values (yes, y, true, no, the 'et aletc).' is stripped from When the parameter and value has not been assigned a flag value (etal) returnedmissing or emptythat will cause list_people(in the source template) to add the static 'et al.' text from Module:Citation/CS1/Configurationfunction returns true. This keeps 'et al.' out If the parameter value is one of the list of allowed values returnstemplate's metadata. When this occurstrue; else, the page is added to a maintenance categoryemits an error message and returns false.
]]
local function extract_namesis_valid_parameter_value (argsvalue, name, list_namepossible) local names = {}; if not is_set (value) then -- table of names local lastreturn true; -- individual name componentsan empty parameter is ok local first;elseif in_array(value:lower(), possible) then local link return true; local mask;else local i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; -- used to count the number of times we haven.insert( z.message_tail, { set_error( 'invalid_param_val't found a |last= (or alias for authors, |editor-last or alias for editors{name, value}, true ) } ) local etal=false; -- not an allowed value so add error message return value set to true when we find some form of et al. in an author parameterfalse endend
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 .. '[--------------------------< T E R M I N A T E _ N A M E _ L I S T >-----------------------------------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 This function terminates a name list (lastauthor, etalcontributor, falseeditor) with a separator character (sepc); -- find and remove variations on et al.a spacewhen the last character is not a sepc character or when the last three characters are not sepc followed by two first, etal = name_has_etal closing square brackets (firstclose of a wikilink). When either of these is true, etal, false); -- find and remove variations on et althe name_list is terminated with asingle space character.
if first and not last then -- if there is a firstn without a matching lastn table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1; -- number of times we haven't found last and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there is a two-name hole in the list; can't tell which end else -- we have last with or without a first if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link; end names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message end count = 0; -- reset the counter, we're looking for two consecutive missing names end i = i + 1; -- point to next args location end return names, etal; -- all done, return our list of namesend]
local function terminate_name_list (name_list, sepc) if (string.sub (name_list,-3,-[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- Populates ID table from arguments using configuration settings. Loops through cfg1) == sepc .id_handlers and searches args forany of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value tothe identifier list. Emits redundant error message is more than one alias exists in args ]] local function extract_ids( args )then -- if already properly terminated local id_list = {} return name_list; -- just return the name list of identifiers found in args for kelseif (string.sub (name_list,-1, v in pairs-1) == sepc) or ( cfgstring.id_handlers ) do sub (name_list,-3,- k is uc identifier name as index to cfg.id_handlers; e1) == sepc .g. cfg.id_handlers['ISBN]]'], v is a table) then -- if last name in list ends with sepc char v = select_one( args, vreturn name_list ..parameters, 'redundant_parameters' )" "; -- v.parameters is a table of aliases for k; here we pick one from args if presentdon't add another else if is_set(v) then id_list[k] = vreturn name_list .. sepc .. ' '; end -- if found in args, add identifier to our otherwise terninate the name list
end
return id_list;
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
inputs: id_list – table returns the concatenation of identifiers built by extract_ids()the formatted volume and issue parameters as a single string; or formatted volume options – table of various template parameter values used to modify some manually handled identifiersor formatted issue, or an empty string if neither are set.
]]
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;
for klocal function format_volume_issue (volume, issue, cite_class, v in pairs( id_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN']origin, v is a table -- fallback to read-only cfg handler = setmetatable( { ['id'] = v }sepc, fallback(klower) ); if handler.mode == 'external' then table.insertnot is_set ( new_list, {handler.label, external_link_idvolume) and not is_set ( handler issue) } );then elseif handler.mode == return 'internal' then table.insert( new_list, {handler.label, internal_link_id( handler ) } ); elseif handler.mode ~= 'manual' then end error( cfg.messages['unknown_ID_mode'] ); elseif k == if 'DOImagazine' then table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } ); elseif k == 'HDL' then table.insertcite_class or ( new_list, {handler.label, hdlin_array ( v ) } ); elseif k == 'ARXIV' then table.insert( new_listcite_class, {handler.label, arxiv( v, options.Class ) } ); elseif k == 'ASINcitation' then table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } ); elseif k == 'LCCNmap' then table.insert( new_list, {handler.label, lccn( v ) } ); elseif k == and 'OLmagazine' or k == 'OLA' then table.insert( new_list, {handler.label, openlibrary( v origin) } ); elseif k == 'PMC' then table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } ); elseif k == 'PMID' then table.insertif is_set ( new_list, {handler.label, pmid( v volume) } ); elseif k == 'ISMN' then table.insert( new_list, {handler.label, ismnand is_set ( v ) } issue); elseif k == 'ISSN' then table.insertreturn wrap_msg ( new_list, {handler.label, issn( v ) } ); elseif k == 'EISSNvol-no' then table.insert( new_list, {handler.labelsepc, issn( vvolume, true ) issue} , lower); -- true distinguishes eissn from issn elseif k == 'ISBN' then local ISBN = internal_link_id( handler ); if not check_isbn( v ) and not is_set(options.IgnoreISBNvolume) then ISBN = ISBN .. set_error return wrap_msg ( 'bad_isbnvol', {sepc, volume}, false, " ", "" lower); end else table.insertreturn wrap_msg ( new_list, {handler.label, ISBN } ); elseif k == 'USENETIDissue' then table.insert( new_list, {handler.labelsepc, message_id( v ) issue} ); else error( cfg.messages['unknown_manual_ID'] , lower);
end
end
local vol = ''; function compif is_set ( a, b volume) -- used in following tablethen if (4 < mw.ustring.sortlen(volume)) then return a vol = substitute (cfg.messages[1'j-vol'] < b, {sepc, volume}); else vol = substitute (cfg.presentation[1'vol-bold'], {sepc, hyphen_to_dash(volume)}); end
end
table.sortif is_set ( new_list, comp issue);then for k, v in ipairs return vol .. substitute ( new_list ) do new_listcfg.messages[k] = v[2'j-issue'], issue);
end
return new_listvol;
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.--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
2015-12-10: there is a bug in mw.adds static text.unstripNoWiki to one of |page(s)= or |sheet(s). It replaced math stripmarkers = values and returns it with all of the appropriate contentothers set to empty strings.when it shouldn't. See httpsThe return order is://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 page, pages, sheet, sheets
TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisiblecharacters table?]] local function coins_cleanup (value) value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s value = value:gsub ('‍\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11) value = value:gsub (' ', ' '); -- replace entity with plain space value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space value = value:gsub ('‍', ''); -- remove ‍ entities value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space return value;end --[[--------------------------< C O I N S >-------------------------------------------------------------------- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation informationSingular has priority over plural when both are provided.
]]
local function COinSformat_pages_sheets (datapage, classpages, sheet, sheets, cite_class, origin, sepc, nopp, lower) if 'tablemap' ~= type(data) or nil == next(data) cite_class then return ''; end for k, v in pairs (data) do -- spin through all of the metadata parameter values if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables only cite map supports sheet(author nowiki stripmarker done when Author table processeds) data[k] = coins_cleanup (v); end end local ctx_ver = "Z39.88-2004"; -as in- treat table strictly as an array with only set values. local OCinSoutput = setmetatable( {}, {source locators __newindex = function(self, key, value) if is_set(valuesheet) then rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } ); end end }); if in_array (class, {'arxiv', 'journal', == origin then return 'news'}) or (in_array (class, {'conference', wrap_msg ('interviewj-sheet', 'map'sheet, 'press release'lower), 'web'}) and is_set(data.Periodical)) or ('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier if 'arxiv' == class then -- set genre according to the type of citation template we are rendering OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv elseif 'conference' == class then OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set) elseif 'web' == class then OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set)
else
OCinSoutput["rft.genre"] = "article"; -- journal and other return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), 'periodical' articles;
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only elseif is_set (sheets) then if is_set (data.Map) 'journal' == origin then OCinSoutput["rft.atitle"] = data.Mapreturn '', '', '', wrap_msg ('j-sheets', sheets, lower); -- for a map in a periodical
else
OCinSoutput["rft.atitle"] = data.Title; -- all other return '', '', '', wrap_msg ('periodicalsheets' article titles, {sepc, sheets}, lower);
end
-- these used onlu for periodicals
OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall
OCinSoutput["rft.chron"] = data.Chron; -- free-form date components
OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata
elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier
if 'report' == class or 'techreport' == class then -- cite report and cite techreport
OCinSoutput["rft.genre"] = "report";
elseif 'conference' == class then -- cite conference when Periodical not set
OCinSoutput["rft.genre"] = "conference";
elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then
if is_set (data.Chapter) then
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title
else
if 'map' == class or 'interview' == class then
OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview
else
OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia
end
end
else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
OCinSoutput["rft.genre"] = "unknown";
end
OCinSoutput["rft.btitle"] = data.Title; -- book only
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
OCinSoutput["rft.series"] = data.Series; -- book only
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
OCinSoutput["rft.edition"] = data.Edition; -- book only
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
end
-- and now common parameters (as much as possible) OCinSoutput["rft.date"] local is_journal = data.Date; -- book'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal, dissertation' == origin);
for k, v in pairsif is_set ( data.ID_list page) do -- what to do about these? For now assume that they are common to all?then if k == 'ISBN' is_journal then v = clean_isbn return substitute ( v ) end local id = cfg.id_handlersmessages[k'j-page(s)'].COinS; if string.sub( id or "", 1page), 4 ) == 'info' then -- for ids that are in the info:registry OCinSoutput["rft_id"] = table.concat{ id, "/"'', v }''; elseif stringnot nopp then return substitute (cfg.sub (id or ""messages['p-prefix'], 1{sepc, 3 page}) == , 'rft' then -- for isbn, issn'', eissn, etc that have defined COinS keywords OCinSoutput[ id ] = v''; elseif id then -- when cfg.id_handlers[k].COinS is not nilelse OCinSoutput["rft_id"] = table.concat{ return substitute (cfg.id_handlersmessages[k'nopp'].prefix, v {sepc, page}), '', '', ''; -- others; provide a url
end
endelseif is_set(pages) then if is_journal then return substitute (cfg.messages['j--[[ page(s)'], pages), '', '', ''; for k, v in pairs elseif tonumber( data.ID_list pages) do ~= nil and not nopp then -- what to do about these? For now if pages is only digits, assume that they are common to all?a single page number local id return '', value = substitute (cfg.id_handlersmessages[k].COinS; if k == 'ISBNp-prefix' then value = clean_isbn( v ], {sepc, pages}); else value = v; end if string.sub( id or "", 1'', 4 ) == 'info' ; elseif not nopp then OCinSoutputreturn '', substitute (cfg.messages["rft_id"'pp-prefix'] = table.concat, { idsepc, pages}), "/"'', v }'';
else
OCinSoutputreturn '', substitute (cfg.messages[ id 'nopp'] = value, {sepc, pages}), '', '';
end
end
]]
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers
if k == 1 then -- for the first author name only
if is_set(last) and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise 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{ last, ", ", first }; -- 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 );
-- sort with version string always firstreturn '', and combine. table.sort( OCinSoutput ); table.insert( OCinSoutput'', 1'', "ctx_ver=" .. ctx_ver )''; -- such as "Z39.88-2004" return table.concat(OCinSoutput, "&");empty strings
end
--[=[--------------------------< G A R C H I V E T _ I S O 6 3 9 U R L _ C O D H E C K >------------------------------------------------ Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...)archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allowunwitting readers to do. When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its ownalgorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
Validates language names provided in This function looks at the value assigned to |archive-url= and returns empty strings for |languagearchive-url= parameter if not and|archive-date= and an ISO639error message when: |archive-1 codeurl= holds an archive. Handles the special case that is Norwegian whereorg save command urlISO639 |archive-1 code 'no' url= is mapped to language name 'Norwegian Bokmål' by Extention:CLDRan archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the correct placeotherwise returns |archive-url= and |archive-date=
Returns the language name and associated ISO639-1 codeThere are two mostly compatible archive. Because case of the source may be incorrect or different from the case that Wikimediaorg urls:uses, the name comparisons are done in lower case and when a match is found, //web.archive.org/<timestamp>... -- the Wikimedia version (assumed to be correct) is returned alongold formwith the code //web.archive.org/web/<timestamp>... When there is no match, we return -- the original language name string.new form
mwThe old form does not support or map to the new form when it contains a display flag.language.fetchLanguageNames There are four identified flags() will return a list of languages that aren't part of ISO639-1. Names that arenid_'t ISO639-1 but that are includedin the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan Aramaic'js_', that name will befound with the associated code 'samcs_', not an ISO639-1 code'im_') but since archive. When names are found and org ignores others following the associated code is not same form (two characters, this functionletters and an underscore)returns only we don't check for these specific flags but we do check the Wikimedia language nameform.
Adapted from code taken from ModuleThis function supports a preview mode. When the article is rendered in preview mode, this funct may return a modifiedarchive url:Check ISO 639-1. for save command errors, return undated wildcard (/*/) for timestamp errors when the timestamp has a wildcard, return the url unmodified for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
]=]
local function get_iso639_code archive_url_check (langurl, date) local err_msg = ''; -- start with the error message empty local path, timestamp, flag; -- portions of the archive.or url if (not url:match('norwegian//web%.archive%.org/' == lang)) and (not url:lowermatch('//liveweb%.archive%.org/')) then -- special case related to Wikimedia remap of code 'no' at Extension:CLDRalso deprecated liveweb Wayback machine url return 'Norwegian'url, 'no'date; -- Make sure rendered version is properly capitalizednot an archive.org archive, return ArchiveURL and ArchiveDate
end
local languages = mw.language.fetchLanguageNames(mw.getContentLanguage()if url:getCodematch(), 'all//web%.archive%.org/save/') then -- get if a list save command url, we don't want to allow saving of language names known to Wikimediathe target page err_msg = 'save command'; -- url = url:gsub ('all(//web%.archive%.org)/save/' is required for North Ndebele, South Ndebele'%1/*/', and Ojibwa1); -- for preview mode: modify ArchiveURL local langlc = mwelseif url:match('//liveweb%.ustringarchive%.lower(langorg/')then err_msg = 'liveweb'; -- lower case version for comparisons else for code path, timestamp, name in pairsflag = url:match('//web%.archive%.org/(languages[^%d]*)(%d+)([^/]*)/') do ; -- scan split out some of the list to see if we can find our languageurl parts for evaluation if langlc == mw.ustring.lowernot is_set(nametimestamp) then if 2 or 14 ~= codetimestamp:len() then -- ISO639path and flag optional, must have 14-1 codes onlydigit timestamp here err_msg = 'timestamp'; if '*' ~= flag then return name; url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- so return the name but not the codefor preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element err_msg = 'path'; elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element) err_msg = 'flag'; elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element) err_msg = 'flag'; else return nameurl, codedate; -- found it, return name to ensure proper capitalization archiveURL and the ISO639-1 codeArchiveDate
end
end
-- if here, something not right so table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and if is_set (Frame:preprocess('{{REVISIONID}}')) then return lang'', ''; -- not valid languagereturn empty strings for archiveURL and ArchiveDate else return url, date; -- preview mode so return language in original case archiveURL and nil for ISO639-1 codeArchiveDate end
end
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Get language name from ISO639-1 code value provided-[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ Look at the contents of a parameter. If the content has a code is valid use string of characters and digits followed by an equalsign, compare the alphanumeric string to the returned name; if notlist of cs1|2 parameters. If found, then use the value string is possibly aparameter that was provided is missing its pipe: {{cite ... |title=Title access-date=2016-03-17}} cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/htmltags are removed before the search. If a missing pipe is detected, this function adds the language parametermissing pipe maintenance category. ]]
There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål local function missing_pipe_check (code 'nb'value) andNorwegian Nynorsk local capture; value = value:gsub (code 'nn%b<>'). The third, code 'no', is defined by ISO639); --1 as 'Norwegian' though in Norway this is pretty much meaningless. Howeverremove xml/html tags because attributes: class=, it appearsthat on enwikititle=, 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.etc
Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code capture = value:match ('no%s+(%a[%a%d]+)%s*='. Here we undo that andreturn ) or value:match ('Norwegian' when editors use |language^(%a[%a%d]+)%s*=no. We presume that editors don't know about ); -- find and categorize parameters with possible missing pipes if capture and validate (capture) then -- if the variants or cancapture is a valid parameter name add_maint_cat ('missing_pipe't descriminate between them.); endend
See Help talk:Citation Style_1#An ISO 639-1 language name test
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) ifthe page is a mainspace page and the ISO639[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------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 supports multiple languages in doing the form |language=nb, French, th where majority of the language names or codes are separated from each other by commascitation formatting.
]]
local function language_parameter citation0(langconfig, args) local code; -- [[ Load Input Parameters The argument_wrapper facilitates the ISO639-1 two character codemapping of multiple aliases to single internal variable. local name; -- the language name]] local language_list A = {}argument_wrapper( args ); -- table of language names to be rendered local names_table = {}; -- table made from the value assigned to |language=i
names_table = mw.text-- Pick out the relevant fields from the arguments.split (lang, '%s*,%s*'); Different citation templates -- define different field names should be a comma separated listfor the same underlying things.
-- set default parameter values defined by |mode= parameter. for _local Mode = A['Mode']; if not is_valid_parameter_value (Mode, lang in ipairs (names_table'mode', cfg.keywords['mode']) do -- reuse langthen Mode = ''; end
if lang:match ('^% local author_etal; local a%a%= {}; --') authors list from |lastn= / |firstn= pairs or 2 |vauthors= local Authors; local NameListFormat =A['NameListFormat']; local Collaboration = lang:len() then A['Collaboration']; do -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)to limit scope of selected if lang:match local selected = select_author_editor_source (A['Vauthors'], A['^zh-Authors'], args, 'AuthorList') ; if 1 == selected then name a, author_etal = mw.language.fetchLanguageName( lang:lowerextract_names ()args, lang:lower() 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then elseNameListFormat = 'vanc'; -- override whatever |name-list-format= might be name a, author_etal = mw.language.fetchLanguageName( lang:lowerparse_vauthors_veditors ()args, mwargs.getContentLanguage():getCode() vauthors, 'AuthorList'); -- get ISO 639fetch author list from |vauthors=, |author-1 language name if Language is a proper code endlinkn=, and |author-maskn= endelseif 3 == selected then if is_set (name) then Authors = A['Authors']; -- if Language specified a valid ISO639-1 codeuse content of |authors= code if 'authors' = lang= A:lowerORIGIN('Authors'); then -- save itbut add a maint cat if the parameter is |authors= else name, code = get_iso639_code add_maint_cat (lang'authors'); -- attempt because use of this parameter is discouraged; what to get code from name (assign name here so that we are sure of proper capitalization)do about the aliases is a TODO: end
end
if is_set (codeCollaboration) then if 'no' == code then name author_etal = '挪威语' endtrue; --so that |display- override wikimedia when code is 'no' if 'zh' ~authors= code and not code:match ('^zh-') then -- English not the language add_prop_cat ('foreign_lang_source', {name, code}) end else add_maint_cat ('unknown_lang'); -- add maint category if etal not already addedrequired
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
code = #language_list -- reuse code as number of languages in the list
if 2 >= code then
name = table.concat (language_list, '及') -- insert '<space>及<space>' between two language names
elseif 2 < code then
language_list[code] = '及' .. language_list[code]; -- prepend last name with '及<space>'
name = table.concat (language_list, '，') -- and concatenate with '<comma><space>' separators
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
-- local Others = A[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------'Others'];
Set style settings for CS1 citation templates. Returns separator and postscript settings local editor_etal; 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 (A['Veditors'], A['Editors'], args, 'EditorList'); if 1 == selected thenlocal function set_cs1_style e, editor_etal = extract_names (psargs, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= elseif 2 == selected then if not is_set NameListFormat = 'vanc'; -- override whatever |name-list-format= might be e, editor_etal = parse_vauthors_veditors (psargs, args.veditors, 'EditorList') then ; -- fetch editor list from |veditors=, |editor-linkn=, and |editor- unless explicitely set to somethingmaskn= ps elseif 3 = = selected then Editors = A['.Editors']; -- use content of |editors= add_maint_cat ('editors'); -- terminate the rendered citation with but add a periodmaint cat because use of this parameter is discouraged end
end
return '.', ps; -- separator is a full stop
end
local t = {}; --[[--------------------------< S E T _ C S 2 _ S T Y L E >------------------------------------------translators list from |translator-lastn= / translator-firstn= pairs local Translators; --assembled translators name list t = extract_names (args, 'TranslatorList'); --fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings local interviewers_list = {}; ] local Interviewers = A['Interviewers'] local function set_cs2_style (ps, ref) if not is_set (psInterviewers) then -- add a maint cat if the |postscriptinterviewers= has not been set, set cs2 defaultis used ps = add_maint_cat ('interviewers'); -- make sure it isn't nilbecause use of this parameter is discouraged endelse if not is_set interviewers_list = extract_names (refargs, 'InterviewerList') then -- if |ref= is not set; ref = "harv"; -- set default |ref=harvelse, process preferred interviewers parameters
end
return ',', ps, ref; -- separator is a comma
end
local c = {}; --[[--------------contributors list from |contributor-lastn= / contributor-firstn= pairs local Contributors; --assembled contributors name list local Contribution = A['Contribution']; if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then --|contributor= and |contribution= only supported in book cites c = extract_names (args, 'ContributorList'); --fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= if 0 < G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >-#c then if not is_set (Contribution) 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 = {}; --blank the contributors' table; it is used as a flag later end end else --if not a book cite if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then --are there contributor name list parameters? table.insert( z.message_tail, { set_error( 'contributor_ignored')}); --add contributor ignored error message end Contribution = nil; --unset end
When |mode= is if not set or when its is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is invalid'vanc' NameListFormat = ''; -- anything else, use config.CitationClass and parameter values set to establishempty stringrendered style. end
local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local function get_settings_from_cite_class (ps, ref, cite_class)Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- Get title data local Title = A['Title']; local ScriptTitle = A['ScriptTitle']; local sepBookTitle = A['BookTitle']; if (cite_class local Conference =A['Conference']; local TransTitle = "citation") then -- for citation templates (CS2)A['TransTitle']; sep, ps, ref local TitleNote = set_cs2_style (ps, ref)A['TitleNote']; else -- not a citation template so CS1local TitleLink = A['TitleLink']; sep link_title_ok (TitleLink, ps = set_cs1_style A:ORIGIN (ps'TitleLink'), Title, 'title'); end-- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
return sep, ps, ref local Chapter = A['Chapter']; local ScriptChapter = A['ScriptChapter']; local ChapterLink -- = A['ChapterLink']; -- return them alldeprecated 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'];end local ArchiveFormat = A['ArchiveFormat'];
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ local ArchiveDate; local ArchiveURL;
Establish basic style settings to be used when rendering the citation. Uses |mode 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 and valid or usesin config.CitationClass from the templatedefaults to 's #invoke: yes' DeadURL = ''; -- anything else, set to establish style.empty string end
local URL = A['URL'] local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter local Series = A['Series']; local Volume; local Issue; local Page; local Pages; local At;
local function set_style if in_array (modeconfig.CitationClass, ps, ref, cite_classcfg.templates_using_volume) local sep; if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style sep, ps, ref Volume = set_cs2_style (ps, ref); elseif A['cs1Volume' == 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
-- conference & map books do not support issue if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'nonemap' }) and not is_set (Periodical))then Issue =A['Issue']; end local Position = ps:lower''; if not in_array (config.CitationClass, cfg.templates_not_using_page) then -- if assigned value is Page = A['Page']; Pages = hyphen_to_dash( A['nonePages' then] ); ps At = A['At']; -- set to empty string
end
return sep, ps, ref
end
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Determines if a url has the file extension that is one of the pdf file extensions used by local Edition = A['Edition']; local PublicationPlace = A['PublicationPlace'] local Place = A['Place']; local PublisherName = A[MediaWiki:Common.css'PublisherName']; local RegistrationRequired = A['RegistrationRequired'] when;applying the pdf icon to external links if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then RegistrationRequired=nil; end
returns true local SubscriptionRequired = A['SubscriptionRequired']; if file extension is one of the recognized extensionnot is_valid_parameter_value (SubscriptionRequired, else false'subscription', cfg.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 if not is_set(URL) and is_set(UrlAccess) then UrlAccess =]nil; table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } ); end
local function is_pdf if is_set (urlUrlAccess) and is_set (SubscriptionRequired)then -- while not aliases, these are much the same so if both are set return table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url:match -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.pdf[%?#]?message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') or url:match .. ' and ' .. wrap_style ('%.PDF[%?#]?parameter', 'registration')}, true ) } ); -- add error message RegistrationRequired = nil; -- unset;prefer |access= over |registration= end
local ChapterUrlAccess = A['ChapterUrlAccess']; if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', cfg.keywords [[--------------------------< S T Y L E _ F O R M A T >-------------------------------------------------'url-access']) then --same as url-access ChapterUrlAccess = nil; end if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then ChapterUrlAccess = nil; table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'chapter-url'}, true ) } ); end
Applies css style to |format local Via =, |chapter-formatA['Via']; local AccessDate =, etc. Also emits an error message if the format parameter doesA['AccessDate'];not 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 local Agency = A['Agency's commons.css, this code will set the format parameter to (PDF) withthe appropriate styling.];
local Language = A['Language']; local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local function style_format (format, url, fmt_param, url_param)DoiBroken = A['DoiBroken']; local ID = A['ID']; if is_set (format) thenlocal ASINTLD = A['ASINTLD']; format local IgnoreISBN = wrap_style (A['formatIgnoreISBN', format)]; -- add leading space, parenthases, resize if not is_set is_valid_parameter_value (urlIgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then format IgnoreISBN = format .. set_error( 'format_missing_url', {fmt_param, url_param} )nil; -- add an error messageanything else, set to empty string
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then format local Embargo = wrap_style ('format', A['PDFEmbargo')]; -- set format to pdf else format local Class = A['Class']; -- empty string for concatenation end return format;endarxiv class identifier
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------ 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 = A['Quote'];
When the value assigned to |display-authors local LayFormat = is a number greater than or equal to zero, return the number andA['LayFormat'];the previous state of the local LayURL = A['etalLayURL' flag (false by default but may have been set to true if the name list contains];some variant of the text local LaySource = A['et al.LaySource').]; local Transcript = A['Transcript'];When the value assigned to |display-authors local TranscriptFormat = is the keyword A['etalTranscriptFormat', return a number that is one greater than the];number of authors in the list and set the local TranscriptURL = A['etalTranscriptURL' flag true. This will cause the list_people] local TranscriptURLorigin = A:ORIGIN('TranscriptURL') to display all ; -- get name ofparameter that holds TranscriptURLthe names in the name list followed by local LastAuthorAmp = A['LastAuthorAmp']; if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp'et al, cfg.keywords ['yes_true_y']) then LastAuthorAmp = nil; -- set to empty string end
In all other cases local no_tracking_cats = A['NoTracking']; if not is_valid_parameter_value (no_tracking_cats, returns nil and the previous state of the 'etalno-tracking' flag, cfg.keywords ['yes_true_y']) then no_tracking_cats = nil; -- set to empty string end
]] --local variables that are not cs1 parameters local use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.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 function get_display_authors_editors (max, count, list_name, etal) if is_set (max) then if 'etal' DF == max:lower():gsub("A[ '%.DF']", '') 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 date format set by extract_names() elseif max:match ('^%d+$') then -- if is a string of numbersin cs1|2 template max = tonumber (max); -- make it a number if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed', list_name); end else -- not a valid keyword or number table.insertis_valid_parameter_value ( z.message_tailDF, { set_error( 'invalid_param_valdf', {cfg.keywords['displaydate-format' .. list_name, max}, true ]) } ); then -- add error messagevalidate reformatting keyword max DF = nil; -- unset end elseif 'authors' == list_name then ; -- AUTHORS ONLY need not valid, set to clear implicit et al category max = count + 1; -- number of authors + 1empty string
end
return max, etal;
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 == ',' ); --------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------used to control capitalization for certain static text
Adds --check this page to Category:CS1 maint: extra text 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= or |pages= has what appears to be some form of p if in_array (this_page. or ppnsText, cfg. uncategorized_namespaces) thenabbreviation no_tracking_cats = "true"; -- set no_tracking_cats end for _,v in the first characters of the parameter contentipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end end
-- check Page for extra |page=, |pages= or |at= parameters. (also sheet and Pages for extraneous psheets while we're at it) select_one( args, {'page', 'p.', 'pp', and pp. 'pages', 'at start of parameter value: good pattern: '^P[^%.P%l], 'sheet', 'sheets'}, 'redundant_parameters' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # ; -- this is a dgiit bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PPdummy call simply to get the error message and category
local NoPP = A['NoPP'] if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then NoPP = true; else NoPP = nil; -- unset, used as a flag later end
local function extra_text_in_page_check if is_set(Page) then if is_set(Pages) or is_set(pageAt)then-- local good_pattern Pages = '^P[^%.P%l]'; -- unset the others local good_pattern At = '^P[^%.Pp]'; end extra_text_in_page_check (Page); -- ok add this page to begin maint cat if |page= value begins with uppercase P: P7 what looks like p. or pp. elseif is_set(pg 7 of section PPages) but not p123 then if is_set(page 123At) TODO: add Gg for PG or Pg?then-- local bad_pattern At = '^[Pp][Pp]'; -- unset local bad_pattern end extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= '^[Pp]?[Pp]%value begins with what looks like p. or pp.?[ %d]'; end -- both |publication-place= and |place= (|location=) allowed if different if not page:match is_set(good_patternPublicationPlace) and is_set(page:match (bad_pattern) or page:match ('^[Pp]ages?')Place) then add_maint_cat PublicationPlace = Place; -- promote |place= ('extra_text'|location=);to |publication-place
end
-- if Page:match (PublicationPlace == Place then Place = '^[Pp]?[Pp]%.?[ %d]') or Page:match (; end -- don'^[Pp]ages?[ %d]') ort need both if they are the same -- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages Parameter remapping for cite encyclopedia: When the citation has these parameters:match ('^[Pp]ages?[ %d]') |encyclopedia and |title then map |title to |article and |encyclopedia to |title |encyclopedia and |article then map |encyclopedia to |title |encyclopedia thenmap |encyclopedia to |title |trans-title maps to |trans- add_maint_cat ('extra_text');chapter when |title is re-mapped |url maps to |chapterurl when |title is remapped All other combinations of |encyclopedia, |title, and |article are not modified-- endend ]]
local Encyclopedia = A['Encyclopedia'];
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >----------------------------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;
This function extracts author / editor names from |vauthors if not is_set (ChapterURL) and is_set (TitleLink) then Chapter = make_wikilink (TitleLink, Chapter); end Title = Periodical; ChapterFormat = or |veditorsFormat; Periodical = and finds matching |xxxxor''; --masknredundant so unset TransTitle = ''; URL = ''; Format = ''; TitleLink = ''; ScriptTitle = and''; end else -- |xxxxortitle not set Title = Periodical; --linkn|encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical = in args. It then returns a table of assembled names just as extract_names() does.''; -- redundant so unset end end end
Author / editor names in |vauthors -- Special case for cite techreport. if (config.CitationClass = or |veditors= must be in Vancouver system style. Corporate or institutional names"techreport") then -- special case for cite techreportmay sometimes be required and because such names will often fail the is_good_vanc_name if is_set(A['Number']) and then -- cite techreport uses 'number', which other format compliancecitations alias to 'issue' if not is_set(ID) then -- can we use ID for the "number"?tests ID = A['Number']; -- yes, use it else -- ID has a value so emit error message table.insert( z.message_tail, are wrapped in doubled paranethese { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style (corporate name'parameter', 'number')}, true ) to suppress the format tests.}); end end end
This function sets the vancouver error when a reqired comma is missing and when there -- special case for cite mailing list if (config.CitationClass == "mailinglist") then Periodical = A ['MailingList']; elseif 'mailinglist' == A:ORIGIN('Periodical') then Periodical = ''; -- unset because mailing list is a space between an author's initials.only used for cite mailing list end
]] -- Account for the oddity that is {{cite conference}}, before generation of COinS data. if 'conference' == config.CitationClass thenlocal function parse_vauthors_veditors if is_set(args, vparam, list_nameBookTitle)then local names Chapter = Title;-- ChapterLink = {}TitleLink; -- table of names assembled from |vauthorschapterlink=, |author-masknis deprecated ChapterURL =, |author-linknURL; ChapterUrlAccess =UrlAccess; local v_name_table ChapterURLorigin = {}URLorigin; local etal URLorigin = false''; -- return value set to true when we find some form of et al. vauthors parameter local last, first, link, mask ChapterFormat = Format; local corporate TransChapter = falseTransTitle; Title = BookTitle; vparam, etal Format = 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) TitleLink = ''; TransTitle = ''; if vparam:find ( URL = '%[%[') or vparam:find (; end elseif '%]%]speech') ~= config.CitationClass then -- no wikilinking vauthors names add_vanc_error ()Conference = ''; -- not cite conference or cite speech so make sure this is empty string
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 detectioncite map oddities local Cartography = ""; first local Scale = ""; local Sheet = A['Sheet'] or ''; -- set to empty string for concatenation and because it may have been set for previous author/editor last local Sheets = v_name:match (A['Sheets'] or '^%(%((.+)%)%)$') corporate = true; elseif string if config.find(v_name, CitationClass == "%smap") then lastfirstTable Chapter = {}A['Map']; lastfirstTable ChapterURL = mw.text.split(v_name, "%s")A['MapURL']; first ChapterUrlAccess = table.remove(lastfirstTable)UrlAccess; -- removes and returns value of last element in table which should be author intials last TransChapter = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initialsA['TransMap']; if mw.ustring.match ChapterURLorigin = A:ORIGIN(last, '%a+%s+%u+%s+%a+MapURL') or mw.ustring.match (v_name, ; ChapterFormat = A[' %u %u$MapFormat') then add_vanc_error ()]; -- matches last II last; the case when a comma is missing or a space between two intiials end else first Cartography = A['Cartography']; -- set to empty string for concatenation and because it may have been set for previous author/editor if is_set( Cartography ) then last Cartography = v_namesepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end Scale = A['Scale']; if is_set (firstScale ) and not mwthen Scale = sepc .ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else add_vanc_error ().. Scale;
end
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
return names, etal; -- all done, return our list of names
end
--Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. if 'episode' == config.CitationClass or 'serial' == config.CitationClass then local AirDate = A['AirDate']; local SeriesLink = A[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------'SeriesLink'];
Select one of |authors= link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), |authorn= / |lastn / firstn=Series, or 'series'); -- check for wikimarkup in |vauthorsseries-link= as the source of the author name list orselect one of wikimarkup in |editorsseries=, when |editorn= / editorseries-lastn= / |editor-firstn= or |veditorslink= as the source of the editor name list.is set
Only one of these appropriate three will be used. The hierarchy is: |authorn local Network = (and aliases) highest and |authorsA['Network']; local Station = lowest andA['Station'];similarly local s, |editornn = {}, {}; -- do common parameters first if is_set(Network) then table.insert(and aliasesn, Network) highest and |editors= lowest; end if is_set(Station) then table.insert(n, Station); endWhen looking for |authorn ID = / |editorn= parameterstable.concat(n, test |xxxxor1= and |xxxxor2= (and all of their aliasessepc .. ' '); stops after the secondtest which mimicks the test used in extract_names if not is_set (Date) and is_set (AirDate) when looking for a hole in the author name list. There may be a betterthen -- promote airdate to date Date = AirDate;way to do this, I just haven't discovered what that way is. end
Emits an error message when more than one xxxxor name source is provided if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Season = A['Season']; local SeriesNumber = A['SeriesNumber'];
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate. ]] local function select_author_editor_source if is_set (Season) and is_set (vxxxxors, xxxxors, args, list_nameSeriesNumber)then -- these are mutually exclusive so if both are setlocal lastfirst = false; if select_one table.insert( argsz.message_tail, cfg.aliases[list_name .. { set_error( '-Lastredundant_parameters'], {wrap_style ('noneparameter', 1 'season') or -- do this twice incase we have a first 1 without a last1 select_one( args, cfg.aliases[list_name . ' and ' .. wrap_style ('-Lastparameter'], 'noneseriesno')}, 2 ) then lastfirst=true; end if (is_set (vxxxxors) and true == lastfirst} ) or -- these are the three error conditions (is_set (vxxxxors) and is_set (xxxxors)) or (true == lastfirst and is_set (xxxxors)) then local err_name; if 'AuthorList' == list_name then -- figure out which name should be used in add error message err_name SeriesNumber = 'author'; else err_name -- unset; prefer |season= over |seriesno= 'editor';
end
-- assemble a table of parts concatenated later into Series if is_set(Season) then table.insert( zs, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table.message_tailinsert(s, { set_errorwrap_msg ( 'redundant_parametersseries',SeriesNumber, use_lowercase)); end {err_name . if is_set(Issue) then table. insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ''; -name-list unset because this is not a unique parameter Chapter = Title; -- promote title parametersto chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURLorigin = A:ORIGIN('URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '}); -- this is concatenation of season, seriesno, episode number if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = make_wikilink (ChapterLink, true Chapter); elseif is_set (ChapterLink) and is_set (ChapterURL) } then -- if both are set, URL links episode; Series = make_wikilink (ChapterLink, Series); end URL = ''; -- add error messageunset TransTitle = ''; ScriptTitle = ''; else -- now oddities that are cite serial Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? if is_set (Series) and is_set (SeriesLink) then Series = make_wikilink (SeriesLink, Series); end Series = wrap_style ('italic-title', Series); -- series is italicized end
end
-- end of {{cite episode}} stuff
if true == lastfirst then return 1 end; -- return a number indicating which author name source to useAccount for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. do if is_set in_array (vxxxxorsconfig.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then return 2 end; if not is_set (xxxxorsID_list[config.CitationClass:upper()]) then return 3 end -- |arxiv= or |eprint= required for cite arxiv;|biorxiv= & |citeseerx= required for their templates table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); return 1-- add error message end if 'arxiv' == config.CitationClass then Periodical = 'arXiv'; -- no authors so return 1set to arXiv for COinS; this allows missing author name test after that, must be set to run in case there is a first without last empty string end
if 'biorxiv' == config.CitationClass then
Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string
end
if 'citeseerx' == config.CitationClass then Periodical = 'CiteSeerX'; --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------set to CiteSeerX for COinS; after that, must be set to empty string end end end
This function is used to validate a -- handle type parameter's assigned value for those parameters CS1 citations that have only a limited numberdefault valuesof allowable values if in_array(yesconfig.CitationClass, {"AV-media-notes", "interview", y"mailinglist", true"map", no"podcast", etc"pressrelease", "report", "techreport", "thesis"})then TitleType = set_titletype (config. When the parameter value has not been assigned a value CitationClass, TitleType); if is_set(missing or emptyDegree) and "Thesis" == TitleType then -- special case for cite thesisin the source template TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower() the function refurns true. If the parameter value is one of the list of allowed values returns; endtrue; else, emits an error message and returns false. end
]] local function is_valid_parameter_value (value, name, possible) if not is_set (valueTitleType) then return true; -- an empty if type parameter is ok elseif in_array(value:lower(), possible) then return true; elsespecified table.insertTitleType = substitute( zcfg.message_tail, { set_error( messages['invalid_param_valtype'], {name, value}, true ) } TitleType); -- not an allowed value so add error messagedisplay it in parentheses return false -- TODO: Hack on TitleType to fix bunched parentheses problem
end
end
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a spacewhen the last character is not a sepc character or when the last three characters legacy: promote PublicationDate to Date if neither Date nor Year are not sepc followed by twoclosing square brackets (close of a wikilink)set. When either of these is true, the name_list is terminated with asingle space character. ]] local function terminate_name_list if not is_set (name_list, sepcDate)then if (string.sub (name_list, Date = Year; -1,-1) promote Year to Date Year == sepc) or (nil; -- make nil so Year as empty string.sub isn't used for CITEREF if not is_set (name_list,-3,-1Date) == sepc .. ']]'and is_set(PublicationDate) then -- if last name in list ends with sepc charuse PublicationDate when |date= and |year= are not set return name_list .. " " Date = PublicationDate; -- don't add anotherpromote PublicationDate to Date else return name_list .. sepc .. PublicationDate = ' '; -- otherwise terninate the name listunset, no longer needed end
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_message, date_parameters_list, mismatch local error_message = ''; --AirDate has been promoted to Date so not necessary to check it local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, ['embargo']=Embargo, ['lay-date']=LayDate, ['publication---------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------date']=PublicationDate, ['year']=Year};
returns the concatenation of the formatted volume and issue parameters as a single string anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date); or formatted volumeor formatted issue, or an empty string -- start temporary Julian / Gregorian calendar uncertainty categorization if neither are setCOinS_date.inter_cal_cat then add_prop_cat ('jul_greg_uncertainty'); end-- end temporary Julian / Gregorian calendar uncertainty categorization
]] local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) if not is_set (volumeYear) and not is_set (issueDate) then return '' -- both |date= and |year= not normally needed; end if 'magazine' local mismatch == cite_class or (in_array year_date_check (cite_class, {'citation'Year, 'map'}Date) and 'magazine' if 0 == origin) mismatch then -- |year= does not match a year-value in |date= if is_set (volume) and is_set (issueerror_message) then -- if there is already an error message return wrap_msg ( error_message = error_message .. ', 'vol; -no- tack on this additional message end error_message = error_message .. '|year= / |date= mismatch', {sepc, volume, issue}, lower); elseif is_set (volume) 1 == mismatch then -- |year= matches year-value in |date= return wrap_msg add_maint_cat ('voldate_year', {sepc, volume}, lower); else return wrap_msg ('issue', {sepc, issue}, lower);end
end
end
local vol = '';
if not is_set(error_message) then -- error free dates only local modified = false; -- flag if is_set (volumeDF) 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 if -- convert hyphens to dashes where appropriate modified = true; add_maint_cat (6 < mw'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 lines.ustring Not supported by en.lenwiki (volumefor obvious reasons)-- if date_name_xlate (date_parameters_list) then-- modified = true;-- end if modified then -- if the date_parameters_list values were modified AccessDate = date_parameters_list['access-date']; vol -- overwrite date holding parameters with modified values ArchiveDate = substitute (cfg.messagesdate_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['jpublication-voldate'], {sepc, volume}); end
else
vol = wrap_style table.insert( z.message_tail, { set_error('vol-boldbad_date', hyphen_to_dash(volume{error_message}, true )} );-- add this error message
end
end-- end of do -- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS. -- Here we unset Embargo if is_set PMC not embargoed (issue|embargo= not set in the citation) then return vol or if the embargo time has expired.. substitute (cfg.messages['j-issue']Otherwise, issue);holds embargo date end return volEmbargo = is_embargoed (Embargo);end
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if not is_set (Embargo) then -- if not embargoed or embargo has expired
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = ''; -- unset
end
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- end end
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of -- At this point fields may be nil if they weren't specified in the others set to empty stringstemplate use. We can use that fact.The return order is: page, pages, sheet, sheets Singular -- Test if citation has priority over plural when both are provided.no title ]] local function format_pages_sheets if not is_set(page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lowerTitle)and if 'map' == cite_class then -- only cite map supports sheet not is_set(sTransTitle) as in-source locatorsand if not is_set (sheetScriptTitle) then if 'journalepisode' == origin config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? return ''table.insert( z.message_tail, { set_error( 'citation_missing_title', wrap_msg ({'j-sheetseries'}, sheet, lowertrue ) } ), '';
else
return ''table.insert( z.message_tail, { set_error( 'citation_missing_title', wrap_msg ({'sheettitle'}, {sepc, sheettrue ) }, lower), '';
end
elseif is_set (sheets) then end if 'journalnone' == origin then return Title and in_array (config.CitationClass, {'journal', 'citation', }) and is_set (Periodical) and 'journal', wrap_msg == A:ORIGIN('j-sheetsPeriodical', sheets, lower);then -- special case for journal cites else return Title = '', '', '', wrap_msg ; -- set title to empty string add_maint_cat ('sheetsuntitled', {sepc, sheets}, lower); end end
end
local is_journal = check_for_url ({ -- add error message when any of these parameters contains a URL ['journaltitle' ]== cite_class or Title, [A:ORIGIN(in_array (cite_class, {'citationChapter')]=Chapter, [A:ORIGIN('mapPeriodical'}) and ]=Periodical, [A:ORIGIN('journalPublisherName' )] == originPublisherName });
if is_set -- COinS metadata (pagesee <http://ocoins.info/>) thenfor automated parsing of citation information. if is_journal then -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that return substitute (cfg.messages['j --page(s)']when Periodical, page)Title, '', ''and Chapter are all set, ''; elseif not nopp then return substitute Periodical is the book (cfg.messages['p-prefix'], {sepc, page}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 else local coins_title = Title; -- et tu return substitute (cfg.messages[ if 'noppencyclopaedia'], {sepc, page}), == config.CitationClass or ('citation', '', ''; end elseif == config.CitationClass and is_set(pagesEncyclopedia)) then if is_journal then return substitute is_set (cfg.messages['j-pageChapter) and is_set (sTitle)'], pages), '', '', ''; elseif tonumberand is_set (pagesPeriodical) ~= nil and not nopp then -- if pages is only digits, assume a single page numberall are used then return '', substitute (cfg.messages['pcoins_chapter = Title; -prefix'], {sepc, pages}), '', ''; elseif not nopp then return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; elseremap return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''coins_title = Periodical;
end
end
local coins_author = a; -- default for coins rft.au return '', '', '', ''if 0 < #c then -- but if contributor list coins_author = c; -- return empty stringsuse 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 ['Degree'] = Degree; --cite thesis only ['Title'] = make_coins_title (coins_title, ScriptTitle), --Title and ScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, --------------------< C I T A T I O N 0 >------------------------------------------------------------COinS_date has correctly formatted date if Date is valid; ['Season'] = COinS_date.rftssn,This is the main function doing the majority of the citation formatting ['Chron'] = COinS_date.rftchron or (not 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, local function citation0 ['Pages'] = get_coins_pages (first_set ( config{Sheet, Sheets, Page, Pages, At}, args5)) , --pages stripped of external links ['Edition'] = Edition, [ 'PublisherName'] = PublisherName, Load Input Parameters ['URL'] = first_set ({ChapterURL, URL}, 2), The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. ['Authors'] = coins_author, ['ID_list']= ID_list, ['RawPage']= this_page.prefixedText, local A = argument_wrapper( args }, config.CitationClass); local i
-- Pick out Account for the relevant fields from the argumentsoddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite citeseerx}} AFTER generation of COinS data. Different citation templates if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then -- define different field names for the same underlying thingswe have set rft. jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed local author_etal; local a Periodical = {}''; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authorsperiodical not allowed in these templates;if article has been published, use cite journal local NameListFormat = A['NameListFormat'];end
do -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to limit scope of selectedinclude some static text local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, if 'AuthorListnewsgroup'); if 1 == selected config.CitationClass then a, author_etal = extract_names if is_set (args, 'AuthorList'PublisherName); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then NameListFormat PublisherName = substitute (cfg.messages['vancnewsgroup'; -- override whatever |name-list-format= might be a], author_etal = parse_vauthors_veditors external_link(args, args.vauthors, 'AuthorListnews:'); -- fetch author list from |vauthors=.. PublisherName, |author-linkn=PublisherName, and |author-maskn= elseif 3 == selected then Authors = A[:ORIGIN('AuthorsPublisherName']), nil )); -- use content 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 -- Now perform various field substitutions. -- We also add leading spaces and surrounding markup and punctuation to limit scope the -- various parts of selectedthe citation, but only when they are non-nil. local selected = select_author_editor_source EditorCount; -- used only for choosing {ed.) or (A['Veditors'], A['Editors'], args, 'EditorList'eds.)annotation at end of editor name-list do local last_first_list; if 1 local control == selected then{ e, editor_etal format = extract_names (argsNameListFormat, -- empty string or 'EditorListvanc'); maximum = nil, -- fetch editor list from |editorn= / |editoras if display-lastn= / |editorauthors or display-firstneditors not set lastauthoramp =LastAuthorAmp, |editor-linkn page_name =this_page.text, and |editor --masknget current page name so that we don't wikilink to it via editorlinkn mode =Mode elseif 2 == selected then}; NameListFormat = 'vanc'; do -- override whatever |do editor name-list-format= might befirst because the now unsupported coauthors used to modify control table econtrol.maximum , editor_etal = parse_vauthors_veditors get_display_authors_editors (argsA['DisplayEditors'], args.veditors#e, 'EditorListeditors', editor_etal); -- fetch editor list from |veditors last_first_list, EditorCount =list_people(control, |editor-linkn=e, and |editor-maskn= elseif 3 == selected then Editors = A['Editors']editor_etal); -- use content of |editors= end end
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs if is_set (Editors) then local Translators; -- assembled translators name list if editor_etal then t Editors = extract_names (args, Editors .. ' ' .. cfg.messages['TranslatorListet al')]; -- fetch translator list from add et al. to editors parameter beause |translatorn= / |translator-lastn=, -firstn=, display-linkn=, -maskneditors=etal local c EditorCount = {}2; -- contributors list from with et al., |contributor-lastneditors= / contributor-firstn= pairs local Contributorsis multiple names; -- assembled contributors name list local Contribution = A['Contribution']; if in_arrayspoof to display (configeds.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book citesannotation else c EditorCount = extract_names (args, 'ContributorList')2; -- fetch contributor list from we don't know but assume |contributorneditors= / |contributor-lastn=, -firstn=, -linkn=, -maskn= if 0 < #c then if not is_set is multiple names; spoof to display (Contributioneds.) then -- |contributor= requires |contribution=annotation table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error messageend else c Editors = {}last_first_list; -- blank the contributors' table; it is used as a flag latereither an author name list or an empty string
end
if 0 1 == #a then -- |contributorEditorCount and (true = requires |author= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author'editor_etal or 1 < #e)}); then -- add missing author error messageonly one editor displayed but includes etal then c EditorCount = {}2; -- blank the contributors' table; it is used as a flag laterspoof to display (eds.) annotation
end
end
else do -- if now do interviewers control.maximum = #interviewers_list; -- number of interviewerss Interviewers = list_people(control, interviewers_list, false); -- et al not a book citecurrently supported end if select_one (args, cfgdo -- now do translators control.aliases['ContributorListmaximum = #t; -Last']- number of translators Translators = list_people(control, 'redundant_parameters't, 1 false) then ; -- et al not currently supported end do -- are there contributor name list parameters?now do contributors tablecontrol.insertmaximum = #c; -- number of contributors Contributors = list_people( z.message_tailcontrol, c, { set_error( 'contributor_ignored')}false); -- add contributor ignored error messageet al not currently supported
end
Contribution = nil; do -- unsetnow do authors end control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
if not is_valid_parameter_value last_first_list = list_people(NameListFormatcontrol, 'name-list-format'a, cfg.keywords['name-list-format']author_etal) then -- only accepted value for this parameter is 'vanc' NameListFormat = ''; -- anything else, set to empty string end
local Year = A['Year']; if is_set (Authors) then local PublicationDate Authors, author_etal = A['PublicationDate']name_has_etal (Authors, author_etal, false);-- find and remove variations on et al. local OrigYear = A['OrigYear']; if author_etal then local Date Authors = A[Authors .. 'Date']; local LayDate = A.. cfg.messages['LayDateet al']; ------------------------------------------------- Get title dataadd et al. to authors parameter local Title = A['Title']; end local ScriptTitle = A['ScriptTitle']; else local BookTitle Authors = A['BookTitle']last_first_list; -- either an author name list or an empty string local Conference = A['Conference']; end local TransTitle = A['TransTitle']; local TitleNote = A['TitleNote']; end -- end of do local TitleLink = A['TitleLink']; if is_set (TitleLinkAuthors) and false == link_param_ok is_set (TitleLinkCollaboration) then tableAuthors = Authors .insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink.. Collaboration .. '))})'; -- url or wikilink in |title-link=;add collaboration after et al.
end
local Chapter = A['Chapter'];end local ScriptChapter = A['ScriptChapter']; local ChapterLink -- = Aapply |['ChapterLink']; xx-- deprecated as a parameter but still used internally by cite episode local TransChapter = A['TransChapter']; local TitleType format= A['TitleType']styling;at the end, these parameters hold correctly styled format annotation, local Degree = A['Degree'];-- an error message if the associated url is not set, or an empty string for concatenation local Docket ArchiveFormat = A['Docket']; local style_format (ArchiveFormat = A[, ArchiveURL, 'ArchiveFormatarchive-format']; local ArchiveURL = A[, 'ArchiveURLarchive-url']); local URL ConferenceFormat = A[style_format (ConferenceFormat, ConferenceURL, 'URLconference-format'] local URLorigin = A:ORIGIN(, 'URLconference-url'); -- get name of parameter that holds URL local ChapterURL Format = A[style_format (Format, URL, 'ChapterURLformat']; local ChapterURLorigin = A:ORIGIN(, 'ChapterURLurl'); -- get name of parameter that holds ChapterURL local ConferenceFormat LayFormat = A[style_format (LayFormat, LayURL, 'ConferenceFormatlay-format']; local ConferenceURL = A[, 'ConferenceURLlay-url']); local ConferenceURLorigin TranscriptFormat = A:ORIGINstyle_format (TranscriptFormat, TranscriptURL, 'ConferenceURL'); transcript-- get name of parameter that holds ConferenceURL local Periodical = A['Periodicalformat']; local Periodical_origin = A:ORIGIN(, 'Periodicaltranscripturl'); -- get the name of the periodical parameter
local Series = A[-- 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', 'Seriesciteseerx'];}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then local Volume ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); local Issue; local Page; local Pages; local At;end
if not is_set(URL) then if in_array (config.CitationClass, cfg.templates_using_volume{"web","podcast", "mailinglist"}) then -- |url= required for cite web, cite podcast, and not cite mailinglist table.insert( z.message_tail, { set_error('conferencecite_web_url' , {}, true ) } ); end -- do we have |accessdate= without either |url=or |chapter-url= config.CitationClass ? if is_set(AccessDate) and not is_set (PeriodicalChapterURL)then -- ChapterURL may be set when URL is not set; table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ) then; Volume AccessDate = A['Volume']; end
end
if in_array (config.CitationClasslocal OriginalURL, cfg.templates_using_issue) and not (in_array (config.CitationClassOriginalURLorigin, {'conference'OriginalFormat, 'map'}OriginalAccess; DeadURL = DeadURL:lower() and not ; -- used later when assembling archived text if is_set (PeriodicalArchiveURL )then if is_set (ChapterURL)then -- URL not set so if chapter-url is set apply archive url to it OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages Issue OriginalFormat = ChapterFormat; -- and original |format= if 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url ChapterURLorigin = A[:ORIGIN('IssueArchiveURL'];) -- name of archive-url parameter for error messages end local Position ChapterFormat = ArchiveFormat or ''; -- swap in archive's format end if not in_array elseif is_set (config.CitationClass, cfg.templates_not_using_pageURL) then Page OriginalURL = URL; -- save copy of original source URL OriginalURLorigin = URLorigin; -- name of url parameter for error messages OriginalFormat = Format; -- and original |format= OriginalAccess = A[UrlAccess; if 'no'Page~= DeadURL then -- if URL set then archive-url applies to it URL = ArchiveURL -- swap-in the archive'];s url Pages URLorigin = hyphen_to_dashA:ORIGIN( A['PagesArchiveURL'] ); -- name of archive url parameter for error messages At Format = A[ArchiveFormat or 'At']; -- swap in archive's format UrlAccess = nil; -- restricted access levels do not make sense for archived urls end end
end
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or -- if any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then local Edition chap_param; if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters chap_param = A[:ORIGIN ('EditionChapter'];) elseif is_set (TransChapter) then local PublicationPlace chap_param = A[:ORIGIN ('PublicationPlaceTransChapter']) elseif is_set (ChapterURL) then local Place chap_param = A[:ORIGIN ('PlaceChapterURL'];) elseif is_set (ScriptChapter) then local PublisherName chap_param = A[:ORIGIN ('PublisherNameScriptChapter'];) else is_set (ChapterFormat) local RegistrationRequired chap_param = A[:ORIGIN ('RegistrationRequiredChapterFormat'];) end if is_set (chap_param) then -- if not is_valid_parameter_value we found one table.insert(RegistrationRequiredz.message_tail, { set_error( 'registrationchapter_ignored', cfg.keywords [{chap_param}, true ) } ); -- add error message Chapter = ''; -- and set them to empty string to be safe with concatenation TransChapter = ''; ChapterURL = 'yes_true_y']) then; RegistrationRequired ScriptChapter =nil''; ChapterFormat = ''; end else -- otherwise, format chapter / article title local SubscriptionRequired no_quotes = A['SubscriptionRequired']false; -- default assume that we will be quoting the chapter parameter value if not is_valid_parameter_value is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(SubscriptionRequired, 'subscription'), cfg.keywords ['yes_true_y'].contribution) then-- and a generic contribution title SubscriptionRequired no_quotes =niltrue; -- then render it unquoted end
end
local Via Chapter = A['Via']format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter if is_set (Chapter) then local AccessDate Chapter = A['AccessDate']Chapter .. ChapterFormat ; local ArchiveDate = A[ if 'ArchiveDatemap'];== config.CitationClass and is_set (TitleType) then local Agency Chapter = A[Chapter .. 'Agency'].. TitleType; -- map annotation here;not after title local DeadURL end Chapter = A[Chapter.. sepc .. 'DeadURL']; if not is_valid_parameter_value elseif is_set (DeadURL, 'dead-url', cfg.keywords ['deadurl']ChapterFormat) then -- |chapter= not set in configbut |chapter-format= is so ...defaults to 'yes' DeadURL Chapter = ChapterFormat .. sepc .. ''; -- anything else... ChapterFormat has error message, set we want to empty stringsee it
end
end
local Language = A['Language'];-- Format main title. local Format = A[if 'Format...']; local ChapterFormat = A['ChapterFormat'];= Title:sub (-3) then -- if elipsis is the last three characters of |title= local DoiBroken Title = A[mw.ustring.gsub (Title, 'DoiBroken(%.%.%.)%.+$']; local ID = A[, 'ID%1']); -- limit the number of dots to three local ASINTLD = A[elseif not mw.ustring.find (Title, 'ASINTLD%.%s*%a%.']; local IgnoreISBN = A[) then -- end of title is not a 'IgnoreISBNdot-(optional space-)letter-dot'];initialism if not is_valid_parameter_value Title = mw.ustring.gsub(IgnoreISBNTitle, 'ignore-isbn-error%'..sepc..'$', cfg.keywords ['yes_true_y']) then IgnoreISBN = nil; -- anything else, set to empty stringremove any trailing separator character end local Embargo if is_set(TitleLink) and is_set(Title) then Title = A['Embargo']make_wikilink (TitleLink, Title); local Class = A['Class']; -- arxiv class identifierend
local ID_list if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); elseif 'report' == config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle = extract_idswrap_style ( args 'trans-italic-title', TransTitle); end
local Quote TransError = A['Quote']""; local LayFormat = A['LayFormat'];if is_set(TransTitle) then local LayURL = A['LayURL']; local LaySource = A['LaySource']; local Transcript = A['Transcript']; local TranscriptFormat = A['TranscriptFormat']; local TranscriptURL = A['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN if is_set('TranscriptURL'Title); -- get name of parameter that holds TranscriptURLthen local LastAuthorAmp TransTitle = A['LastAuthorAmp']" " .. TransTitle; if not is_valid_parameter_value else TransError = " " .. set_error(LastAuthorAmp, 'last-author-amptrans_missing_title', cfg.keywords [{'yes_true_ytitle']} ) then LastAuthorAmp = nil; -- set to empty string
end
local no_tracking_cats = A['NoTracking'];end if is_set(Title) then if not is_valid_parameter_value is_set(no_tracking_catsTitleLink) and is_set(URL) then Title = external_link( URL, 'no-tracking'Title, URLorigin, cfgUrlAccess ) .keywords [. TransTitle .. TransError .. Format; URL = 'yes_true_y']) then; -- unset these because no longer needed Format = ""; else no_tracking_cats Title = nilTitle .. TransTitle .. TransError; -- set to empty string
end
else
Title = TransTitle .. TransError;
end
--these are used by cite interview local Callsign = A['Callsign'];if is_set(Place) then local City Place = A[" " .. wrap_msg ('Citywritten'], Place, use_lowercase) .. sepc .. " "; local Program = A['Program'];end
--local variables that are not cs1 parameters if is_set (Conference) then if is_set (ConferenceURL) then Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil ); end local use_lowercase Conference = sepc .. " " .. Conference .. ConferenceFormat; -- controls capitalization of certain static text local this_page elseif is_set(ConferenceURL) then Conference = mwsepc .title.getCurrentTitle" " .. external_link(ConferenceURL, nil, ConferenceURLorigin, nil ); -- 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 verificationend
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values local Mode = A['Mode']; if not is_valid_parameter_value is_set(Mode, 'mode', cfg.keywords['mode']Position) then Mode local Minutes = A['Minutes']; end local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma local PostScript; local Ref; sepc, PostScript, Ref Time = set_style (Mode:lower(), A['PostScript'], A['RefTime'], 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 categoriesis_set(Minutes) then if not is_set (no_tracking_catsTime) then -- ignore if we are already not going to categorize this page if in_array table.insert(this_pagez.nsTextmessage_tail, cfg.uncategorized_namespaces) then no_tracking_cats = "true"; -- set no_tracking_cats end for _{ set_error( 'redundant_parameters',v in ipairs {wrap_style (cfg'parameter', 'minutes') .. ' and ' .uncategorized_subpages) do -- cycle through page name patterns if this_page.text:match wrap_style (v'parameter', 'time') then -- test page name against each pattern no_tracking_cats = "}, true") } ); -- set no_tracking_cats break; -- bail out if one is found
end
end end -- check for extra |page Position =, |pages= or |at= parameters" " .. Minutes .. " " .. cfg. (also sheet and sheets while wemessages['minutes're at it)]; else select_one if is_set( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' Time); -- this is a dummy call simply to get the error message and categorythen local NoPP TimeCaption = A['NoPPTimeCaption'] if not is_set (NoPPTimeCaption) and is_valid_parameter_value (NoPP, 'nopp', then TimeCaption = cfg.keywords messages['yes_true_yevent']; if sepc ~= '.' then TimeCaption = TimeCaption:lower() then; end end NoPP Position = true" " .. TimeCaption .. " " .. Time; end end
else
NoPP Position = nil" " .. Position; At = ''; -- unset, used as a flag later
end
if is_set(Page) then if is_set(Pages) or is_set(At) then , Pages , Sheet, Sheets = ''; -- unset the others At = ''; end extra_text_in_page_check format_pages_sheets (Page); -- add this page to maint cat if |page= value begins with what looks like p, Pages, Sheet, Sheets, config. or pp. elseif is_set(PagesCitationClass, Periodical_origin, sepc, NoPP, use_lowercase) 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-place At = is_set(At) and |place= (|location=sepc .. " " .. At) allowed if differentor ""; if not Position = is_set(PublicationPlacePosition) and is_set(Placesepc .. " " .. Position) then PublicationPlace = Placeor ""; -- promote |place= (|location=) to |publication-place end if PublicationPlace config.CitationClass == Place 'map' then Place local Section = A['Section']; end -- don local Sections = A['Sections't need both if they are the same]; --[ local Inset = A['Inset'];Parameter remapping for cite encyclopedia: When the citation has these parameters: |encyclopedia and |title if is_set( Inset ) then map |title to |article and |encyclopedia to |title |encyclopedia and |article then map |encyclopedia to |title Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); |encyclopedia then map |encyclopedia to |title 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; |trans_title maps to |trans_chapter when |title is re-mapped |url maps to |chapterurl when |title is remappedend
All other combinations of |encyclopedia if is_set (Language) then Language = language_parameter (Language); -- format, |titlecategories, and |article are name from ISO639-1, etc else Language=""; -- language not modifiedspecified 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 Others = A['Encyclopedia']; if is_set(Others) and ( configsepc ..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(Title) or is_set (ScriptTitleTranslators) then if not is_set Others = sepc .. ' ' .. wrap_msg (Chapter'translated', Translators, use_lowercase) then Chapter = Title.. Others; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; end TransChapter = TransTitle; ChapterURL = URL; if not is_set (ChapterURL) and is_set (TitleLinkInterviewers) then Chapter Others = sepc .. '[[' .. TitleLink .. wrap_msg ('|interview' , Interviewers, use_lowercase) .. Chapter .. ']]'Others; end Title = Periodical; ChapterFormat TitleNote = Formatis_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; Periodical = ''; -- redundant so unset if is_set (Edition) then TransTitle = if Edition:match ('%f[%a][Ee]d%.?$'; URL = ) or Edition:match ('%f[%a][Ee]dition$';) then Format = add_maint_cat ('extra_text'; TitleLink = , 'edition'); ScriptTitle = ''; end else -- |title not set Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title Periodical = ''; -- redundant so unset end
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
-- Special case for cite techreport. if Series = is_set(Series) and (configsepc ..CitationClass == "techreport".. Series) then -- special case for cite techreportor ""; if OrigYear = is_set(A['Number']OrigYear) then -- cite techreport uses 'number', which other citations alias to 'issue' if not is_setand (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 end-- TODO: presentation
-- special case for cite interview if (config.CitationClass == "interview") then if is_set(Program) then ID Agency = ' ' .. Program; end if is_set(CallsignAgency) then if is_setand (ID) then ID = ID .. sepc .. ' ' " " .. CallsignAgency) or ""; else ID Volume = ' ' .. Callsign; end end if is_setformat_volume_issue (City) then if is_set(ID) then ID = ID .Volume, Issue, config. CitationClass, Periodical_origin, sepc .. ' ' .. City, use_lowercase); else ID = ' ' .. City; end end
if is_set(Others) then ------------------------------------ totally unrelated data if is_set(TitleTypeVia) then Others Via = ' ' " " .. TitleType .. ' with ' .. Others; TitleType = ''; else Others = wrap_msg (' via' .. 'Interview with ' .. Others; end else Others = '(Interview, Via)'; end
end
-- special case [[ Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link note is displayed. There are no error messages for cite mailing listthis condition. ]] if is_set (config.CitationClass == "mailinglist"SubscriptionRequired) then Periodical SubscriptionRequired = A sepc .. " " .. cfg.messages['MailingListsubscription']; -- subscription required message elseif 'mailinglist' is_set (RegistrationRequired) then SubscriptionRequired == A:ORIGIN(sepc .. " " .. cfg.messages['Periodicalregistration') then]; -- registration required message else Periodical SubscriptionRequired = ''; -- unset because mailing list is only used for cite mailing listeither or both might be set to something other than yes true y
end
-- Account for the oddity that is {{cite conference}}, before generation of COinS data. if is_set(AccessDate) then local retrv_text = " " .. cfg.messages['conferenceretrieved' ] AccessDate == config.CitationClass thennowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format if is_set(BookTitlesepc ~= ".") thenretrv_text = retrv_text:lower() end Chapter = Title;-- if mode is cs2, lower case ChapterLink AccessDate = TitleLinksubstitute (retrv_text, AccessDate); -- |chapterlink= is deprecatedadd retrieved text ChapterURL = URL; ChapterURLorigin = URLorigin; URLorigin AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate});-- allow editors to hide accessdates end ChapterFormat if is_set(ID) then ID = Formatsepc .." ".. ID;end TransChapter if "thesis" == TransTitle;config.CitationClass and is_set(Docket) then Title ID = BookTitlesepc .." Docket ".. Docket .. ID; Format end if "report" == '';config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set TitleLink ID = sepc .. ''.. Docket; -- overwrite ID even if |id= is set TransTitle end ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo= ''; URL Embargo, Class = ''Class} ); end elseif 'speech' ~= config.CitationClass if is_set(URL) then Conference URL = ''" " .. external_link( URL, nil, URLorigin, UrlAccess ); -- not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities local Cartography = ""; local Scale = ""; local Sheet = A['Sheet'] or ''; local Sheets = A['Sheets'] or ''; if config.CitationClass == "map" is_set(Quote) then Chapter if Quote:sub(1,1) = A['Map']; ChapterURL = A['MapURL']; TransChapter = A['TransMap"']; ChapterURLorigin = Aand Quote:ORIGINsub('MapURL'-1,-1); ChapterFormat = A['MapFormat']; Cartography = A['Cartography"']; then -- if is_set( Cartography ) thenfirst and last characters of quote are quote marks Cartography Quote = sepc .. " " .. wrap_msg Quote:sub('cartography'2, Cartography, use_lowercase-2); end Scale = A['Scale']; if is_set( Scale ) then Scale = sepc .. " " .. Scale; -- strip them off
end
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. local Archived if 'episode' == config.CitationClass or 'serial' == config.CitationClass is_set(ArchiveURL) then local AirDate if not is_set(ArchiveDate) then ArchiveDate = A[set_error('AirDatearchive_missing_date']); end if "no" == DeadURL then local SeriesLink arch_text = Acfg.messages['SeriesLinkarchived']; if is_set (SeriesLink) and false sepc ~="." then arch_text = link_param_ok arch_text:lower(SeriesLink) thenend table Archived = sepc .. " " ..insertsubstitute( zcfg.message_tailmessages['archived-not-dead'], { set_errorexternal_link( 'bad_paramlink'ArchiveURL, arch_text, A:ORIGIN('SeriesLinkArchiveURL'), nil ).. ArchiveFormat, ArchiveDate }); if not is_set(OriginalURL) then Archived = Archived .. " " .. set_error('archive_missing_url');
end
local Network = A[elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'Networkusurped']; local Station arch_text = Acfg.messages['Stationarchived-dead']; local s if sepc ~= "." then arch_text = arch_text:lower() end if in_array (DeadURL, n = {}'unfit', 'usurped', {'bot: unknown'}) then Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- do common parameters firstformat already styled if is_set'bot: unknown' == DeadURL then add_maint_cat (Network'bot:_unknown') then table.insert; -- and add a category if not already added else add_maint_cat (n, Network'unfit'); -- and add a category if not already added end if is_set else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " .. substitute( arch_text, { external_link(StationOriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) then table.insert(n. OriginalFormat, StationArchiveDate } ); -- format already styled end ID else local arch_text = table.concat(n, sepc .cfg. messages[' archived-missing')]; if not is_set sepc ~= "." then arch_text = arch_text:lower(Date) and is_set (AirDate) then -- promote airdate to dateend Date Archived = AirDatesepc .. " " .. 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 = "";
end
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
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(SeasonTranscript) 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; ChapterURLorigin = A:ORIGIN('URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; Series = '[[' .. ChapterLink .. '|' .. 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 is_set (Series) and is_set (SeriesLinkTranscriptURL) then Series = '[[' .. SeriesLink .. '|' .. Series .. ']]'; end Series Transcript = wrap_style external_link('italic-title'TranscriptURL, Series); -- series is italicized end end-- end of {{cite episode}} stuff -- Account for the oddities that are {{cite arxiv}}Transcript, before generation of COinS data. if 'arxiv' == config.CitationClass then if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv table.insert( z.message_tail, { set_error( 'arxiv_missing', {}TranscriptURLorigin, true ) } ); -- add error message elseif is_set (Series) then -- series is an alias of version ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier Series = ''; -- unset deprecated_parameter ('version'nil ); -- deprecated parameter but only for cite arxiv
end
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv ID_list[Transcript = sepc .. '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 table.insert( z.message_tail, { set_errorTranscript .. TranscriptFormat; elseif is_set( 'arxiv_params_not_supported', {}, true TranscriptURL) } ); -- add error messagethen AccessDate Transcript = ''; -- set these to empty string; not supported in cite arXiv PublisherName = ''; -- external_link(if the article has been publishedTranscriptURL, nil, use cite journalTranscriptURLorigin, or othernil ) Chapter = ''; URL = ''; Format = ''; Page = ''; Pages = ''; At = ''; end Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
-- handle type parameter for those CS1 citations that have default values local Publisher; if in_arrayis_set(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}PublicationDate) then TitleType PublicationDate = set_titletype wrap_msg (config.CitationClass'published', TitleType); if is_set(DegreePublicationDate) and "Thesis" == TitleType then -- special case for cite thesis TitleType = Degree .. "论文"; end
end
if is_set(TitleTypePublisherName) then -- if type parameter is specifiedis_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; else Publisher = sepc .. " " .. PublisherName .. PublicationDate; end TitleType elseif is_set(PublicationPlace) then Publisher= substitute( cfgsepc .. " " .. PublicationPlace ..messages['type'], TitleType)PublicationDate; else Publisher = PublicationDate; -- display it in parentheses
end
-- legacy: promote concatenation Several of |month=the above rely upon detecting this as nil, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are setso do it last. if not is_set (DatePeriodical) then Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not is_set (DateTitle) and or is_set(PublicationDateTitleNote) then -- use PublicationDate when |date= and |year= are not set Date Periodical = PublicationDate; sepc .. " " .. wrap_style ('italic-- promote PublicationDate to Datetitle', Periodical) else PublicationDate Periodical = wrap_style ('italic-title'; -- unset, no longer neededPeriodical)
end
end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation --[[Go test all of Handle the date-holding parameters for valid MOS:DATE format and make sure oddity that dates are real datesis cite speech. This must code overrides whatever may be done before we do COinS because here is wherethe value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so thatwe get the annotation directly follows the date used |title= parameter value in the metadatacitation rather than the |event= parameter value (if provided). Date validation supporting code is in Module:Citation/CS1/Date_validation ]] do -- create defined block to contain local variables error_message and mismatch local error_message if "speech" == ''; config.CitationClass then -- AirDate has been promoted to Date so not necessary to check itcite speech only anchor_year, error_message TitleNote = dates" ({['accessSpeech)"; -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 (Year) and is_set (DatePeriodical) then -- both if Periodical, perhaps because of an included |datewebsite= and or |yearjournal= not normally needed; local mismatch = year_date_check (Year, Date)parameter if 0 == mismatch then -- |year= does not match a year-value in |date= if is_set (error_messageConference) then -- and if there |event= is already an error messageset error_message Conference = error_message Conference .. ', '; -- tack on this additional message end error_message = error_message sepc .. '|" ";year= / |date= mismatch'; elseif 1 == mismatch then -- |year= matches year-value in |date= add_maint_cat ('date_year');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(error_messageOthers) thenOthers = Others .. sepc .. " " end tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); table.insert elseif in_array( zconfig.message_tailCitationClass, { set_error"book","citation"}) and not is_set(Periodical) then -- special cases for book cites if is_set ( 'bad_date'Contributors) then -- when we are citing foreword, preface, introduction, etc tcommon = safe_join( {error_messageTitle, TitleNote}, true ) } sepc ); -- add author and other stuff will come after this error messageand 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
end -- end of do
elseif 'map' == config.CitationClass then -- Account special cases for the oddity that cite map if is_set (Chapter) then -- map in a book; TitleType is part of Chapter tcommon = safe_join( {{cite journalTitle, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}} with |pmc= set and |url= not set. Do this after date check but before COInS., sepc ); elseif is_set (Periodical) then -- Here we unset Embargo if PMC not embargoed map in a periodical tcommon = safe_join(|embargo= not set in the citation{Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ) ; else -- a sheet or if the embargo time has expired. Otherwisestand-alone map tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, holds embargo datesepc ); end Embargo elseif 'episode' = is_embargoed = config.CitationClass then -- special case for cite episode tcommon = safe_join(Embargo{Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc ); --
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then if not is_set (Embargo) then else -- if not embargoed or embargo has expiredall other CS1 templates URL tcommon =cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoedsafe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, URLorigin = cfg.id_handlers['PMC'].parameters[1]Volume, Others, Edition, Publisher, Agency}, sepc ); -- set URLorigin to parameter name for use in error message if citation is missing a |title= end
end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not is_set(Title) and#ID_list > 0 then not is_setID_list = safe_join(TransTitle) and not is_set(ScriptTitle) then if 'episode' == config{ sepc ..CitationClass then -- special case for cite episode; TODO: is there a better way to do this? " ", table.insertconcat( zID_list, sepc ..message_tail" " ), { set_error( 'citation_missing_title', {'series'ID }, true ) } sepc ); else table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ) ID_list = ID; end
end
if 'none' local idcommon == Title and in_array safe_join(config.CitationClass{ ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, {'journal'Lay, 'citation'Quote }, 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; endlocal pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
check_for_url ({ -- add error message when any of these parameters contains a URL ['title']=Title, [A:ORIGINif is_set('Chapter'Date)]=Chapter,then [A:ORIGINif is_set ('Periodical'Authors)]=Periodical, [A:ORIGINor is_set ('PublisherName'Editors)] = PublisherName, }); then -- COinS metadata date follows authors or editors when authors not set Date = " (see <http://ocoins" .info/>. Date ..") for automated parsing of citation information" .. OrigYear .. sepc .. " "; -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume thatin paranetheses else -- when Periodical, Title, neither of authors and Chapter are all editors set if (string.sub(tcommon,-1, -1) == sepc) then Periodical is the book (encyclopedia) title, Title -- is if the article title, and Chapter last character of tcommon is a section within the article. So, we remap sepc local coins_chapter Date = Chapter" " .. Date .. OrigYear; -- default assuming that remapping Date does not requiredbegin with sepc local coins_title = Title; -- et tu else if 'encyclopaedia' Date == configsepc .. " " .. Date .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 = TitleOrigYear; -- remapDate begins with sepc coins_title = Periodical;end
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 -- this is the function call to COinSis_set(Authors) local OCinSoutput = COinS({ ['Periodical'] = Periodical,then ['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 (coins_title, ScriptTitle), -- 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 COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use is_set (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 ({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 -- we have when date is set rft.jtitle in COinS to arXiv, now unset so it isn't displayed Periodical = ''; -- periodical not allowed s in cite arxivparentheses; if article has been published, use cite journal end -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text if 'newsgroup' == config.CitationClass then if is_set (PublisherName) thenno Authors termination PublisherName Authors = substitute terminate_name_list (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherNameAuthors, PublisherName, A:ORIGIN('PublisherName') )sepc); -- 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 if is_set(eds.Editors) annotation at end of editor name-listthen do local last_first_list; local maximum; local control in_text = { format = NameListFormat, -- empty string or 'vanc' maximum = nil, -- as if display-authors or display-editors not set lastauthoramp = LastAuthorAmp, page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn }" "; do -- do editor name list first because coauthors can modify control table maximum , editor_etal local post_text = 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(maximumChapter) and #e 0 == 4 #c then maximum in_text = 3; tablein_text ..insert( zcfg.message_tail, { set_error(messages['implict_etal_editorin', {}, true) } ); end ]].. " " control if (sepc ~= '.maximum = maximum;') then last_first_list, EditorCount in_text = list_peoplein_text:lower(control, e, editor_etal, 'editor'); -- lowercase for cs2 end if is_set (Editors) thenelse if editor_etal EditorCount <= 1 then Editors post_text = Editors .. ' ' ", " .. cfg.messages['et aleditor']; -- 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
EditorCount post_text = 2; -- we don", " .. cfg.messages['t know but assume |editors= is multiple names']; spoof to display (eds.) annotation
end
elseend 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 Editors -- lowercase for cs2 Authors = last_first_listby_text .. Authors; -- either an author name list follows title so tweak it here if is_set (Editors) and is_set (Date) then -- when Editors make sure that Authors gets terminated Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or an empty string1 sepc and a space
end
if 1 == EditorCount and (true == editor_etal or 1 < #enot is_set (Date)) then -- only one editor displayed but includes etal then when date is set it's in parentheses; no Contributors termination EditorCount Contributors = 2terminate_name_list (Contributors, sepc); -- spoof to display (eds.) annotationterminate with 0 or 1 sepc and a space
end
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
do -- now do translators control.maximum = #t; -- number of translators Translators = list_people elseif is_set(control, t, false, 'translator'Editors); -- et al not currently supportedthen end do -- now do contributorsif is_set(Date) then control.maximum if EditorCount <= #c; -- number of contributors1 then Contributors Editors = list_people(controlEditors .. ", c, false, 'contributor'); -- et al not currently supported end do -- now do authors control" .. cfg.maximum , author_etal = get_display_authors_editors (Amessages['DisplayAuthorseditor'], #a, 'authors', author_etal); else if is_set(Coauthors) then -- if the coauthor field is also used Editors = Editors .. ", prevent ampersand and et al" . formatting. controlcfg.lastauthoramp = nil; control.maximum = #a + 1messages['editors'];
end
else last_first_list if EditorCount <= list_people(control, a, author_etal, 'author'); if is_set (Authors) 1 then Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. if author_etal then Authors Editors = Authors Editors .. ' ' " (" .. cfg.messages['et aleditor']; -- add et al. to authors parameter end. ")" .. sepc .. " "
else
Authors Editors = last_first_list; -- either an author name list or an empty stringEditors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
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
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 text = style_format safe_join(ArchiveFormat, ArchiveURL, 'archive-format'{Editors, 'archive-url'); ConferenceFormat = style_format (ConferenceFormatDate, ConferenceURLChapter, 'conference-format'Place, 'conference-url'); Format = style_format (Formattcommon, URLpgtext, 'format'idcommon}, 'url'sepc ); LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');else 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', 'arxiv'"citation"}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then ChapterFormat text = style_format safe_join(ChapterFormat{Chapter, ChapterURLPlace, 'chapter-format'tcommon, 'chapter-url'); end if not is_set(URL) then --and if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty table.insert( z.message_tailpgtext, { set_error( 'cite_web_url'Date, {idcommon}, true ) } sepc ); end -- 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?else table.inserttext = safe_join( z.message_tail{Chapter, Place, tcommon, Date, { set_error( 'accessdate_missing_url'pgtext, {idcommon}, true 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; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?Now enclose the whole thing in a <cite/> element DeadURL local options = DeadURL:lower{}; 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 later when assembling archived textwith |ref= else options.class = "citation"; end if is_set( ArchiveURL Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate local id = Ref if is_set (URL'harv' == Ref ) then OriginalURL local namelist = URL{}; -- save copy of original source URLholds selected contributor, author, editor name list OriginalURLorigin local year = URLoriginfirst_set ({Year, anchor_year}, 2); -- name of url parameter Year first for legacy citations and for error messagesYMD dates that require disambiguation OriginalFormat = Format; -- and original |format= if 'no' ~= DeadURL #c > 0 then -- if URL set then archive-url applies to itthere is a contributor list URL namelist = ArchiveURL c; -- swapselect it elseif #a > 0 then -in the archive's url- or an author list URLorigin namelist = A:ORIGIN('ArchiveURL') a; elseif #e > 0 then -- name of archive url parameter for error messagesor an editor list Format namelist = ArchiveFormat or ''e; -- 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 'no' ~= DeadURL #namelist > 0 then ChapterURL = ArchiveURL -- swap-if there are names in the archive's urlnamelist ChapterURLorigin id = A:ORIGINanchor_id ('ArchiveURL'namelist, year) ; -- name of archive-url parameter for error messagesgo make the CITEREF anchor else ChapterFormat id = ArchiveFormat or ''; -- swap in archive's formatunset
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 in_arrayis_set(configoptions.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}id) or then -- if any of here we wrap the 'periodical' cites except encyclopediarendered citation in <cite ...>...</cite> tags table.insert (render, substitute (cfg.presentation['citationcite-id' == config], {mw.uri.CitationClass and is_set anchorEncode(Periodicaloptions.id) and not is_set , mw.text.nowiki(Encyclopediaoptions.class), text})) then local chap_param; if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameterswhen |ref= is set chap_param = A:ORIGIN ('Chapter') else elseif is_set table.insert (TransChapter) then chap_param = A:ORIGIN render, substitute (cfg.presentation['TransChaptercite'], {mw.text.nowiki(options.class) elseif is_set (ChapterURL, text}) then chap_param = A:ORIGIN ('ChapterURL'); -- all other cases elseif is_set (ScriptChapter) then end chap_param = A:ORIGIN ('ScriptChapter') else is_set table.insert (ChapterFormat) chap_param = A:ORIGIN render, substitute (cfg.presentation['ChapterFormatocins'], {OCinSoutput})) end; -- append metadata to the citation
if is_set (chap_param) #z.message_tail ~= 0 then -- if we found one table.insert( z.message_tailrender, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message Chapter = ''; -- and set them to empty string to be safe with concatenation for i,v in ipairs( z.message_tail ) do TransChapter = ''; if is_set(v[1]) then ChapterURL if i = ''; ScriptChapter = '';#z.message_tail then ChapterFormat = ''; end else -- otherwise table.insert (render, format chapter / article title local no_quotes = false; -- default assume that we will be quoting the chapter parameter value if is_set error_comment(Contributionv[1], v[2] ) and 0 < #c then -- if this is a contribution with contributor(s); else if in_array table.insert (Contribution:lowerrender, error_comment(), cfgv[1] .keywords.contribution"; ", v[2] )) then -- and a generic contribution title; no_quotes = true; -- then render it unquotedend
end
end
end
if #z.maintenance_cats ~= 0 then Chapter = format_chapter_title table.insert (ScriptChapterrender, Chapter'<span class="citation-comment" style="display:none; color:#33aa33; margin-left:0.3em">'); for _, TransChapter, ChapterURL, ChapterURLorigin, no_quotesv in ipairs( z.maintenance_cats ); do -- Contribution is also in Chapterappend maintenance categories if is_set table.insert (Chapterrender, v) then; if table.insert (render, 'map(' == config); table.CitationClass and is_set insert (TitleTyperender, make_wikilink (':Category:' .. v, 'link') then); Chapter = Chapter table.insert (render, ') '); end table. insert (render, ' </span>' .. TitleType); end Chapter no_tracking_cats = Chapter no_tracking_cats:lower(); if in_array(no_tracking_cats, {"", "no", "false", "n"}) then for _, v in ipairs( z.error_categories ) do table. ChapterFormat insert (render, make_wikilink ('Category:' .. sepc .. ' 'v)); elseif is_set end for _, v in ipairs(ChapterFormatz.maintenance_cats ) then -do - |chapter= not set but |chapter-format= is so ...append maintenance categories Chapter = ChapterFormat table.insert (render, make_wikilink ('Category:' . sepc .v)); end for _, v in ipairs( z. ' '; properties_cats ) do -- append properties categories table.insert (render, make_wikilink ('Category:' .. ChapterFormat has error message, we want to see itv));
end
end
-- Format main titlereturn table. if is_setconcat (TitleLinkrender) and is_set(Title) then; end Title = "--[[" --------------------------< 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. TitleLink .. "|" .. Title .. " ]]" end
if in_array(configfunction cs1.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or ('citation' == config.CitationClass and is_set (Periodicalframe) and not is_set (Encyclopedia)) or ('map' Frame == config.CitationClass and is_set (Periodical)) then frame; -- special case for cite map when the map is in save a periodical treat as copy incase we need to display an articleerror message in preview mode Title local pframe = kern_quotes frame:getParent(Title); -- if necessary local validation, utilities, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title'identifiers, Title)metadata;
Title if nil ~= script_concatenate string.find (Titleframe:getTitle(), ScriptTitle'sandbox', 1, true); then -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrappeddid the {{#invoke:}} use sandbox version? TransTitle cfg = wrap_style mw.loadData ('transModule:Citation/CS1/Configuration/sandbox'); -quoted-titleload sandbox versions of support modules whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox', TransTitle ); elseif utilities = require ('reportModule:Citation/CS1/Utilities/sandbox' ); validation =require ('Module:Citation/CS1/Date_validation/sandbox'); identifiers = config.CitationClass then -- no styling for cite reportrequire ('Module:Citation/CS1/Identifiers/sandbox'); Title metadata = script_concatenate require (Title, ScriptTitle'Module:Citation/CS1/COinS/sandbox'); else -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrappedotherwise TransTitlecfg = wrap_style mw.loadData ('trans-quoted-titleModule:Citation/CS1/Configuration', TransTitle ); -- for cite report, use this form for trans-titleload live versions of support modules else whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); Title utilities = wrap_style require ('italic-titleModule:Citation/CS1/Utilities', Title); Title validation = script_concatenate require (Title, ScriptTitle'Module:Citation/CS1/Date_validation'); -- <bdi> tags, lang atribute, categorization, etc identifiers = require ('Module:Citation/CS1/Identifiers'); must be done after title is wrapped TransTitle metadata = wrap_style require ('trans-italic-titleModule:Citation/CS1/COinS', TransTitle);
end
TransError = ""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 if is_setvalidation.set_selected_modules (TransTitlecfg, utilities) then; -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module if is_set metadata.set_selected_modules (Titlecfg, utilities) then; -- so that functions in COinS can see the selected cfg tables and selected Utilities module TransTitle dates = " " validation.dates; -- imported functions from Module:Citation/CS1/Date validation year_date_check = validation. TransTitleyear_date_check; else reformat_dates = validation.reformat_dates; TransError 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( 'trans_missing_title', {'title'} )= 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 end build_id_list = identifiers.build_id_list; endis_embargoed = identifiers.is_embargoed; extract_id_access_levels = identifiers.extract_id_access_levels;
Title make_coins_title = Title metadata.. TransTitlemake_coins_title; -- imported functions from Module:Citation/CS1/COinS if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title get_coins_pages = external_link( URL, Title, URLorigin ) .metadata. TransError .. Formatget_coins_pages; URL = ""; Format = ""; else Title COinS = Title metadata.. TransErrorCOinS; end end
if is_set(Place) thenlocal args = {}; -- table where we store all of the template's arguments Place local suggestions = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "{}; -- table where we store suggestions if we need to loadData them endlocal error_text, error_state;
if is_set (Conference) thenlocal config = {}; -- table to store parameters from the module {{#invoke:}} if is_set for k, v in pairs(ConferenceURL) then Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin frame.args ); enddo Conference config[k] = sepc .. " " .. Conference .. ConferenceFormatv;-- elseif is_set(ConferenceURL) then Conference args[k] = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin )v; -- debug tool that allows us to render a citation from module {{#invoke:}} end
if not is_setlocal capture; -- the single supported capture when matching unknown parameters using patterns for k, v in pairs(Positionpframe.args ) thendo local Minutes = A['Minutes']; local Time if v ~= A['Time']; if is_set(Minutes) then if is_set not validate(Timek, config.CitationClass ) then table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } ); end Position error_text = " " .. Minutes .. " " .. cfg.messages['minutes']; else if is_settype(Timek ) then local TimeCaption ~= A['TimeCaptionstring'] if not is_set(TimeCaption) then TimeCaption = cfg.messages['event'];-- Exclude empty numbered parameters if sepc v:match("%S+") ~= '.' nil then TimeCaption error_text, error_state = TimeCaption:lowerset_error('text_ignored', {v}, true );
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_setvalidate( Section ) then Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end if is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this is an empty string; end Others = is_set(Others) and (sepc .. " " .. Others) or ""; if is_set (Translators) then Others = sepc .. ' 由' .. Translators .. '翻译 ' .. Others; end TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; if is_set (Edition) then if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then add_maint_cat ('extra_text', 'edition'); end Edition = " " .. wrap_msg ('edition', Edition); else Edition = ''; end Series = is_set(Series) and (sepc .. " " .. Series) or ""; OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); ------------------------------------ totally unrelated data if is_set(Via) then 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.messages['retrieved'] AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text -- neither of these work; don't know why; it seems that substitute() isn't being called AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates end if is_set(ID) then ID = sepc .." ".. ID; end if "thesis" == config.CitationClass and is_set(Docket) then ID = sepc .." Docket ".. Docket .. ID; end if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set end ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); if is_set(URL) then URL = " " .. external_link( URL, nil, URLorigin ); end if is_set(Quote) then if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks Quote = Quote:sub(2,-2); -- strip them off end Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags PostScript = ""; -- 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 .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " .. substitute( arch_text, { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled end else local arch_text = cfg.messages['archived-missing']; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. " " .. substitute( arch_text, { set_error('archive_missing_url'), ArchiveDate } ); end elseif is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = "" end local Lay = ''; if is_set(LayURL) then if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; end if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message end if is_set(Transcript) then if is_set(TranscriptURL) then Transcript = external_link( 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 .. ": " .. 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 .. " " .. 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}, sepc ); elseif is_set (Periodical) then -- map in a 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( {Title, TitleType, Format, Edition, Scale, Series, Cartography, Others, Publisher}, sepc ); end elseif 'episode' == config.CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Edition, Publisher}, sepc ); else -- all 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.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( { URL, xDate, ID_list, Archived, Via, SubscriptionRequired, Lay, Language, Quote }, sepc ); local text; if is_set(Authors) then if is_set(Coauthors) then if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator Authors = Authors .. ', ' .. Coauthors; else Authors = Authors .. '; ' .. Coauthors; end end Authors = terminate_name_list (Authors, 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_textk:lower() end -- lowercase for cs2 else if EditorCount <= 1 then post_text = ", " .. cfg.messages['editor']; else post_text = ", " .. cfg.messages['editors']; end end Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space end if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 Authors = by_text .. Authors; -- author follows title so tweak it here if is_set (Editors) 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. 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 ('harv' == 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 id = anchor_id (namelist, year); -- go make the CITEREF anchor end options.id = id; end if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%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 text = 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 .. error_comment( v[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 text = text .. '[[Category:' .. v ..']]'; end for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories text = text .. '[[Category:' .. v ..']]'; end for _, v in ipairs( z.properties_cats ) do -- append maintenance categories text = text .. '[[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.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('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 else -- otherwise cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ... whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code end dates = validation.dates; -- imported functions year_date_check = validation.year_date_check; local args = {}; local suggestions = {}; local error_text, error_state; local config = {}; for k, v in pairs( frame.args ) do config[k] = v; args[k] = v; end local capture; -- the single supported capture when matching unknown parameters using patterns for k, v in pairs( pframe.args ) do if v ~= '' then if not validate( k ) then error_text = ""; if type( k ) ~= 'string' then -- Exclude empty numbered parameters if v:match("%S+") ~= nil then error_text, error_state = set_error( 'text_ignored', {v}, true ); end elseif validate( k:lower() ) then error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); else if nil == suggestions.suggestions then -- if this table is nil then we need to load it
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
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 zcs1;