local z = { error_categories cs1 = {}; -- for categorizing citations that contain errors error_ids = {}; message_tail = {}; maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance}
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation
local cfg = {}; dates, year_date_check, reformat_dates, date_hyphen_to_dash -- table of configuration tables that are defined functions in Module:Citation/CS1/Configurationlocal whitelist = {}; -- talbe of tables listing valid template parameter names; defined in Module:Citation/CS1/WhitelistDate_validation
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, remove_wiki_link;
Returns true if argument is setlocal z ={}; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. -- tables in Module:Citation/CS1/UtilitiesThis function is global because it is called 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 brought in from both this module other modules; thatare created hereand from Date validationused here
]]
function is_set( var ) return not (var local added_deprecated_cat; -- boolean flag so that the category is added only oncelocal added_prop_cats == nil or var == ''){}; -- list of property categories that have been added to z.properties_catslocal added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category local Frame; -- holds the module's frame tableend
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
First Locates and returns the first set variable value in a table of values where the order established in the table,left-to-right (or top-to-bottom), is the order in which the values are evaluated. Returns nil if noneare set. This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs. With the pairsversion the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminatethe for-loop before it reached the actual end of the list.
]]
local function first_set(...list, count) local list i = {...}1; for _, var while i <= count do -- loop through all items in pairs(list) do if is_set( var list[i] ) then return varlist[i]; -- return the first set list member
end
i = i + 1; -- point to next
end
end
--[[--------------------------< I N A D D _ A R P R O P _ C A Y T >-------------------------------------------------------------- Adds a category to z.properties_cats using names from the configuration file with additional text if any.
Whether needle added_prop_cats is a table declared in haystackpage scope variables above
]]
local function in_arrayadd_prop_cat ( needlekey, haystack arguments) if needle == nil not added_prop_cats [key] then return falseadded_prop_cats [key] = true; -- note that we've added this category table.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 A D D _ V A N C _ E R R O R >----------------------------------------------------------
Populates numbered arguments in Adds a single Vancouver system error message string using to the template's output regardless of how many error actually exist.To prevent duplication, added_vanc_errs is nil until an argument tableerror message is emitted. added_vanc_errs is a boolean declared in page scope variables above
]]
local function substituteadd_vanc_error ( msg, args source) return args and mwif not added_vanc_errs then added_vanc_errs = true; -- note that we've added this category table.messageinsert( z.newRawMessagemessage_tail, { set_error( msg'vancouver', args {source}, true ):plain(} ) or msg; end
end
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------
Wraps error messages with css markup according --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ does this thing that purports to the state be a uri scheme seem to be a valid scheme? The scheme is checked to see if itis in agreement with http://tools.ietf.org/html/std66#section-3.1 which says: Scheme names consist of hiddena sequence of characters beginning with a letter and followed by any combination of letters, digits, plus ("+"), period ("."), or hyphen ("-"). returns true if it does, else false
]]
local function error_commentis_scheme ( content, hidden scheme) return substitutescheme and scheme:match ( hidden and cfg'^%a[%a%d%+%.presentation['hidden%-error'] or cfg.presentation[*:'visible-error'], content ); -- true if scheme is set and matches the pattern
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 _ 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? 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 domain]]local function set_errorlist of tlds: https://www.iana.org/domains/root/db rfc952 ( error_idmodified 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, arguments, rawdigits, and the hyphen. Also 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. 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-- ASCII Compatible Encoding (ACE) prefixxn-- in the tld) see https://tools.ietf.org/html/rfc3490 single-letter/digit second-level domains in the .org TLD q, suffix 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) local error_state 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 ]= cfg.error_conditions[ error_id ] local function is_domain_name (domain) if not domain then return false; -- if not set, abandon end
prefix domain = prefix or ""domain:gsub ('^//', ''); suffix = suffix or "" -- strip '//' from domain name if present;done here so we only have to do it once
if error_state == nil then errornot domain:match ( cfg.messages'^[%a%d]'undefined_error'] ); elseif is_set( error_state.category ) then -- first character must be letter or digit table.insert( z.error_categories, error_state.category )return false;
end
-- Do most common case first
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
return true;
elseif domain:match ('%f[%a%d][%a%d]%.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$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
return true;
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
end
end
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
This function is the last step in the validation process. This function is separate because there are cases that
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.
]]
local function is_url (scheme, domain)
if is_set (scheme) then -- if scheme is set check it and domain
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when url is protocol relative
end
end
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
Split a url into a scheme, authority indicator, and domain.
First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#).
If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
Strip off any port and path;
]]
local function split_url (url_str)
local scheme, authority, domain;
local message url_str = substituteurl_str:gsub ( error_state'([%a%d])%.message?[/%?#].*$', arguments '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') message = message .. " if url_str:match ([[" .. cfg.messages['help page link^//%S*'] .. ) then -- if there is what appears to be a protocol relative url "#" .. error_state.anchor .. "|" .. cfg.messages[domain = url_str:match ('help page label^//(%S*)'] .. "]])"; elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name z.error_ids[ error_id ] scheme, authority, domain = trueurl_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions if in_array authority = authority:gsub ( error_id, { 'bare_url_missing_title//', 'trans_missing_title' } , 1); -- replace place 1 pair of '/' with nothing; and z.error_ids[ if is_set(authority) then -- if anything left (1 or 3+ 'citation_missing_title/'] 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+', false'%1'); -- strip port number if present
end
message = table.concat({ prefix, message, suffix }); if raw == true then return message, error_state.hidden; end return error_comment( messagescheme, error_state.hidden )domain;
end
--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
Adds a category --[[--------------------------< 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 z.maintenance_cats using names from hold the configuration file with additional text if 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 anyof these characters. When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).
]]
local function add_maint_cat link_param_ok (key, argumentsvalue) table.insert( z.maintenance_catslocal scheme, substitute domain; if value:find (cfg.maint_cats '[key<>%[%]|{}]') then -- if any prohibited characters return false; end scheme, argumentsdomain = split_url (value); -- get scheme or nil and domain or nil from url; return not is_url (scheme, domain); -- make name then add return true if value DOES NOT appear to tablebe a valid url
end
--[[--------------------------< A D D L I N K _ P R O P _ C A T I T L E _ O K >--------------------------------------------------------
Adds a category Use link_param_ok() to zvalidate |<param>-link= value and its matching |<title>= value.properties_cats using names from the configuration file with additional text if any |<title>= may be wikilinked but not when |<param>-link= has a value. This function emits an error message whenthat condition exists
]]
local function add_prop_cat link_title_ok (keylink, argumentslorig, title, torig)local orig; if is_set (link) then -- don't bother if <param>-link doesn't have a value if not link_param_ok (link) then -- check |<param>-link= markup orig = lorig; -- identify the failing link parameter elseif title:find ('%[%[') then -- check |title= for wikilink markup orig = torig; -- identify the failing |title= parameter end end if is_set (orig) then table.insert( z.properties_catsmessage_tail, substitute { set_error(cfg.prop_cats [key]'bad_paramlink', argumentsorig)}); -- make name then add to tableurl or wikilink in |title= with |title-link=; end
end
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
Determines whether a URL string is appears to be valid.
At present the only check is whether First we test for space characters. If any are found, return false. Then split the string appears to be prefixed with a URI url into schemeand domainportions, or for protocol relative (//example.com) urls, just the domain. It is not determined whether Use is_url() to validate the twoportions of the URI scheme is url. If both are valid , or whether the URL for protocol relative if domain is otherwise well formedvalid, return true, else false. Because it is different from a standard url, and because this module used external_link() to make external linksthat work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup nameis at https://tools.ietf.org/html/rfc5536#section-3.1.4
]]
local function check_url( url_str )
return if nil == url_str:submatch (1,2"^%S+$") then -- if there are any spaces in |url=value it can't be a proper url return false; end local scheme, domain; scheme, domain = "//" or split_url (url_str); -- get scheme or nil and domain or nil from url; if 'news:' == scheme then -- special case for newsgroups return domain:match( "'^[^/%a%d%+%-_]+%.[%a%d%+%-_%.]*:" [%a%d%+%-_]$') ~= nil; end return is_url (scheme, domain); -- Protocol-relative or URL schemereturn true if value appears to be a valid url
end
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
Protects a string that will be wrapped in wiki italic markup '' ... ''--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
Note: We cannot use <i> for italics, as Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the expected behavior for italics specified by ''...'' in firstnon-space characters following the title is thatthey will opening bracket appear to be inverted (i.e. unitalicized) in the resulting referencesa url. In addition, <i> and '' tend to interactThe test will also find external wikilinkspoorly under Mediawiki's HTML tidythat use protocol relative urls. Also finds bare urls.
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests thatfind bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]is possible as might be [[en://Hus]].
]=] local function safe_for_italicsis_parameter_ext_wikilink ( str value)local scheme, domain; if not is_setvalue:match (str'%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz] return strscheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]')); elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text scheme, domain = split_url (value:match ('(%a%S*:%S+)')); elseif value:match ('//%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
else
if str:sub(1,1) == "'" then str = "<span />" .. strreturn false; end if str:sub( -1,-1) == "didn'" then str = str .. "<span />"; end -- Remove newlines as they break italics. return str:gsub( '\n', ' ' );t find anything that is obviously a url
end
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
]]
local function check_for_url (parameter_list)
local error_message = '';
for k, v in pairs (parameter_list) do -- for each parameter in the list
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
if is_set(error_message) then -- once we've added the first portion of the error message ...
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "|" .. k .. "="; -- add the failed parameter
end
end
if is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
end
end
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
[']'] = ']',
['\n'] = ' ' } );
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
]]
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;
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
return domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path if path then -- if there is a path portion path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values URL=domain..path; -- and reassemble end if is_set (access) then -- access level (subscription, registration, limited) local label_head = ''; local label_tail; local markup = ''; -- can't start a span inside italic markup and end it outside the italic markup label = safe_for_url (label); -- replace square brackets and newlines (is this necessary? already done above?) if label:match ("(.*)%s+(.+)('''?)$") then -- for italicized titles (cite book, etc) label_head, label_tail, markup = label:match ("(.*)%s+(.+)('''?)$"); -- split the label at the right-most space; separate the markup elseif label:match ("(.*)%s+(.+)$") then -- for upright titles (journal, news, magazine, etc) label_head, label_tail = label:match ("(.*)%s+(.+)$"); -- split the label at the right-most space; no markup elseif label:match ("(.+)('''?)$") then -- single word label with markup label_tail, markup = label:match ("(.+)('''?)$"); -- save label text as label tail; separate the markup else label_tail = label; end base_url = table.concat ( { '<span class="plainlinks">[', -- opening css URL, -- the url ' ', -- the required space label_head, -- all but the last word of the label ' <span class="nowrap">', -- nowrap css for the last word and the signal icon label_tail, -- last (or only) word of the label inside the span '<span style="padding-left:0.15em">', -- signal spacing css cfg.presentation[access], -- the appropriate icon '</span></span>', -- close signal spacing and nowrap spans markup, -- insert italic markup if any ']</span>' -- close the plain links span }); else base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]"}); -- no signal markup end return table.concat({ base_url, error_str });
end
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
Formats a wiki style external link--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
]]Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes theoffending parameter name to the error message. Only one error message is emitted regardless of the number of deprecatedparameters in the citation.
local function external_link_id(options) local url_string = options.id; if options.encode == true or options.encode == nil then url_string = mw.uri.encode( url_string ); end return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]', options.link, options.label, options.separator or " ", options.prefix, url_string, options.suffix or "", mw.text.nowiki(options.id) );endadded_deprecated_cat is a boolean declared in page scope variables above
--[[
Categorize and emit an error message when the citation contains one or more deprecated parameters. Because deprecated parameters (currently |month=,
|coauthor=, and |coauthors=) aren't related to each other and because these parameters may be concatenated into the variables used by |date= and |author#= (and aliases)
details of which parameter caused the error message are not provided. Only one error message is emitted regardless of the number of deprecated parameters in the citation.
]]
local function deprecated_parameter(name)
if true ~= Page_in_deprecated_cat then -- if we haven't been here before not added_deprecated_cat then set a Page_in_deprecated_catadded_deprecated_cat =true; -- sticky flag so note that if there are more than one deprecated parameter the we've added this category is added only once
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
" '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 with typewriter quote marks regardless of the need for kerning.
Call this function for chapter titles, for website titles, etc; not for book titles.
local cap='';
local cap2='';
-- TODO: move this elswhere so that all title-holding elements get these quote marks replaced?
str= mw.ustring.gsub (str, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
str= mw.ustring.gsub (str, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
is not added. At this time there is no error message for this condition.
At this writing, only Supports |script-title= is supported. It is anticipated that additional parameters will be created to use this function.and |script-chapter=
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
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', 'hy', 'ja', 'ka', 'ko', 'ku', 'he', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}cfg.script_lang_codes) then
add_prop_cat ('script_with_name', {name, lang})
else
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
str = return substitute( msg, {str} ); -- including template text return str;
else
return substitute( cfg.messages[key], {str} );
end
end
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
Chooses one matching parameter from a list of --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >-------------------------------------- Format the four chapter parameters to consider: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-Generates an parameter (chapter_url_source used for error if more than one match is presentmessages).
]]
local function select_oneformat_chapter_title ( argsscriptchapter, possiblechapter, error_conditiontranschapter, index chapterurl, chapter_url_source, no_quotes) local value = nil; local selected chapter_error = ''; local error_list = {};
if index ~= nil then index = tostringnot is_set (indexchapter); endthen -- Handle special case of "#" replaced by empty string if index = chapter = '1' then ; -- to be safe for _, v in ipairs( possible ) doconcatenation v = v:gsub( "#", "" ); if is_set(args[v]) then if value ~= nil and selected ~= v then table.insert( error_list, v ); else value = args[v]; selected = v; end end end end for _, v in ipairs( possible ) do if index ~false == nil no_quotes then v chapter = v:gsubkern_quotes ( "#", index chapter); end -- if is_set(args[v]) thennecessary, separate chapter title's leading and trailing quote marks from Module provided quote marks if value ~chapter = nil and selected ~= v then table.insertwrap_style ( error_list'quoted-title', v chapter); else value = args[v]; selected = v; end
end
end
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped if #error_list > 0 is_set (transchapter) then local error_str transchapter = ""wrap_style ('trans-quoted-title', transchapter); for _, k in ipairsif is_set ( error_list chapter) dothen if error_str ~chapter = "" then error_str = error_str .chapter . cfg.messages[ 'parameter-separator'] end.. transchapter; else -- here when transchapter without chapter or script-chapter error_str chapter = error_str transchapter; -- chapter_error = ' ' .. wrap_style set_error ('parametertrans_missing_title', k{'chapter'});
end
if #error_list > 1 then
error_str = error_str .. cfg.messages['parameter-final-separator'];
else
error_str = error_str .. cfg.messages['parameter-pair-separator'];
end
error_str = error_str .. wrap_style ('parameter', selected);
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
end
if is_set (chapterurl) then chapter = external_link (chapterurl, chapter, chapter_url_source, nil); -- adds bare_url_missing_title error if appropriate end return value, selectedchapter .. chapter_error;
end
--[[--------------------------< F O R M A T _ C H A P T E R S _ T I T N V I S I B L E _ C H A R S >----------------------------------------
Format This function searches a parameter's value for nonprintable or invisible characters. The search stops at the three chapter parameters: |chapter=first match. This function will detect the visible replacement character when it is part of the wikisource. Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, |trans-chapter=math, pre, ref)and |chapter-url= into identifies them with a single Chapter meta-slightly different error message. See also coins_cleanup().parameter Detects but ignores the character pattern that results from the transclusion of {{'}} templates. Output of this function is an error message that identifies the character or the Unicode group, or the stripmarkerthat was detected along with its position (chapter_url_source used or, for error messagesmulti-byte characters, the position of its first byte)in theparameter value.
]]
local function format_chapter_title has_invisible_chars (chapterparam, transchapter, chapterurl, chapter_url_sourcev) local chapter_error position = ''; -- position of invisible char or starting position of stripmarker local dummy; -- end of matching string; not used but required to hold end position when a capture is returned local capture; -- used by stripmarker detection to hold name of the stripmarker local i=1; local stripmarker, apostrophe;
if not is_set capture = string.match (chapter) then chapter = v, '[%w%p ]*'); -- just to be safe Test for concatenationvalues that are simple ASCII text and bypass other tests if true if is_set (transchapter) capture == v then -- if same there are no unicode characters chapter return; end while cfg.invisible_chars[i] do local char= wrap_style ('transcfg.invisible_chars[i][1] -quoted-title', transchapter);the character or group name chapter_error local pattern= " " cfg.invisible_chars[i][2] -- the pattern used to find it position, dummy, capture = mw. set_error ustring.find ('trans_missing_chapter'v, pattern); -- see if the parameter value contains characters that match the pattern end if is_set (chapterurl) position then chapter if 'nowiki' = external_link (chapterurl, chapter, chapter_url_source); = capture or 'math' == capture then -- adds bare_url_missing_title nowiki, math stripmarker (not an error if appropriatecondition) end return chapter .. chapter_error stripmarker = true; else -- here when chapter is seta flag chapter elseif true = kern_quotes (chapter); = stripmarker and 'delete' == char then -- if necessarybecause stripmakers begin and end with the delete char, separate chapter titleassume that we's leading and trailing quote marks from Module provided quote marksve found one end of a stripmarker chapter position = wrap_style ('quotednil; -title', chapter)- unset else local err_msg; if is_set (transchapter) capture then transchapter err_msg = wrap_style (capture .. 'trans-quoted-title', transchapter).. char; chapter else err_msg = chapter char .. ' ' .. transchapter'character'; end if is_set (chapterurl) then chapter = external_link table.insert(chapterurlz.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', chapterparam), position}, true ) } ); -- adds bare_url_missing_title add error if appropriatemessage return; -- and done with this parameter end
end
i=i+1; -- bump our index
end
return chapter;
end
--[[--------------------------< A R G U M E N T _ W R A P P E R >---------------------------------------------- Argument wrapper. This function provides support for argument mapping defined in the configuration file so that multiple namescan be transparently aliased to single internal variable.
]]
end
--[[--------------------------< V A L I D A T E >-------------------------------------------------------------- Looks for a parameter's name in the whitelistone of several whitelists.
Parameters in the whitelist can have three values:
false - deprecated, supported parameters
nil - unsupported parameters
]]
--local function validate( name )local function validate( name, cite_class )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- Normal argumentslimited 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 if 'arxiv' == cite_class then -- basic parameters unique to these templates state = whitelist.arxiv_basic_arguments[name]; end if 'biorxiv' == cite_class then state = whitelist.biorxiv_basic_arguments[name]; end if 'citeseerx' == cite_class then state = whitelist.citeseerx_basic_arguments[name]; end if true == 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 return false; -- not supported because not found or name is set to nil end -- end limited parameter-set templates state = whitelist.basic_arguments[ name ]; -- all other templates; all normal parameters allowed if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in themall enumerated parameters allowed name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- Not not supported because not found or name is set to nilend -- Formats a wiki style internal linklocal function internal_link_id(options) return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]', options.link, options.label, options.separator or " ", options.prefix, options.id, options.suffix or "", mw.text.nowiki(options.id) );
end
date = substitute (cfg.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$") then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
return date;
end
--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
If the 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)
local temp = 0;
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58
len = len+1; -- adjust to be a loop counter
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
temp = temp + 10*( len - i ); -- it represents 10 decimal
else
temp = temp + tonumber( string.char(v) )*(len-i);
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
end
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
Determines whether an ISBN string is valid
]]
local function check_isbn( isbn_str )
if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
local len = isbn_str:len();
if len ~= 10 and len ~= 13 then
return false;
end
if len == 10 then
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
return is_valid_isxn(isbn_str, 10);
else
local temp = 0;
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979
isbn_str = { isbn_str:byte(1, len) };
for i, v in ipairs( isbn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) );
end
return temp % 10 == 0;
end
end
--[[--------------------------< I S S N >----------------------------------------------------------------------
Validate and format an issn. This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
digits with a space. When that condition occurred, the resulting link looked like this:
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
This code now prevents that by inserting a hyphen at the issn midpoint. It also validates the issn for length and makes sure that the checkdigit agrees
with the calculated value. Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn
error message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
]]
local function issn(id)
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local handler = cfg.id_handlers['ISSN'];
local text;
local valid_issn = true;
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
valid_issn=false; -- wrong length or improper character
else
valid_issn=is_valid_isxn(id, 8); -- validate issn
end
if true == valid_issn then
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if false == valid_issn then
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
end
return text
end
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
]]
local function amazon(id, domain)
local err_cat = ""
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
if check_isbn( id ) then -- see if asin value is isbn10
add_maint_cat ('ASIN');
elseif not is_set (err_cat) then
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10
end
elseif not id:match("^%u[%d%u]+$") 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'}) 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="//www.amazon."..domain.."/dp/",id=id,
encode=handler.encode, separator = handler.separator}) .. err_cat;
end
--[[--------------------------< A R X I V >--------------------------------------------------------------------
See: http://arxiv.org/help/arxiv_identifier
format and error check arXiv identifier. There are three valid forms of the identifier:
the first form, valid only between date codes 9108 and 0703 is:
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 and MM is the month number January = 01
first digit of YY for this form can only 9 and 0
<number> is a three-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented)
the second form, valid from April 2007 through December 2014 is:
arXiv:<date code>.<number><version>
where:
<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 number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces
the third form, valid from January 2015 is:
arXiv:<date code>.<number><version>
where:
<date code> and <version> are as defined for 0704-1412
<number> is a five-digit number
]]
local function arxiv (id, class)
local handler = cfg.id_handlers['ARXIV'];
local year, month, version;
local err_cat = '';
local text;
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") 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 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
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
--[[
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
1. Remove all blanks.
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
3. If there is a hyphen in the string:
a. Remove it.
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
1. All these characters should be digits, and there should be six or less. (not done in this function)
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
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 (lccn)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
if nil ~= string.find (lccn,'/') then
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end
local prefix
local suffix
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
if nil ~= suffix then -- if there was a hyphen
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
lccn=prefix..suffix; -- reassemble the lccn
end
return lccn;
end
--[[
Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
length = 8 then all digits
length = 9 then lccn[1] is lower case alpha
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
length = 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 == 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 -- LCCN should be aadddddddddd
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
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 id:match("[^%d]") then -- if PMID has anything but digits
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
else -- PMID is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
end
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
|embargo= was not set in this cite.
]]
local function is_embargoed (embargo)
if is_set (embargo) then
local lang = mw.getContentLanguage();
local good1, embargo_date, good2, todays_date;
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
good2, todays_date = 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 embargoed
else
add_maint_cat ('embargo')
return ''; -- unset because embargo has expired
end
end
end
return ''; -- |embargo= not set return empty string
end
--[[--------------------------< P M C >------------------------------------------------------------------------
Format a PMC, do simple error checking, and check for embargoed articles.
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
be linked to the article. If the embargo date is today or in the past, or if it is empty or omitted, then the
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
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 less
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
]]
local function pmc(id, embargo)
local test_limit = 5000000; -- update this value as PMCs approach
local handler = cfg.id_handlers['PMC'];
local err_cat = ''; -- presume that PMC is valid
local text;
if id:match("[^%d]") then -- if PMC has anything but digits
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
else -- PMC is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
end
end
if is_set (embargo) then -- is PMC is still embargoed?
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
return text;
end
-- Formats a DOI and checks for DOI errors.
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
-- Prefix: directory indicator '10.' followed by a registrant code
-- Suffix: character string of any length chosen by the registrant
-- This function checks a DOI name for: prefix/suffix. If the doi name contains spaces or endashes,
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
-- 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 rarely if ever used in doi names.
local function doi(id, inactive)
local cat = ""
local handler = cfg.id_handlers['DOI'];
local text;
if is_set(inactive) then
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
if is_set(inactive_year) then
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
else
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
else
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
inactive = ""
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 .. inactive .. cat
end
-- Formats an OpenLibrary link, and checks for associated errors.
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];
if ( code == "A" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/authors/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "M" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/books/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "W" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/works/OL",id=id, separator=handler.separator,
encode = handler.encode})
else
return external_link_id({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator,
encode = handler.encode}) ..
' ' .. set_error( 'bad_ol' );
end
end
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
'<' and/or '>' angle brackets.
]]
local function message_id (id)
local handler = cfg.id_handlers['USENETID'];
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
end
return text
end
end
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
Removes irrelevant text and dashes from ISBN numberSimilar to that used for Special:BookSources ]] local function clean_isbn( isbn_str ) return isbn_str:gsub( "--[^[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------0-9X]", "" );end
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------Converts a hyphen to a dash
Returns a string where all of lua's magic characters have been escaped. This is important because functions like
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
]]
local function escape_lua_magic_chars (argument)
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
return argument;
end
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
This function strips common patterns of apostrophe markup. We presume that editors who have taken the time to
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.
]]
local function strip_apostrophe_markup (argument)
if not is_set (argument) then return argument; end
while true do
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
argument=argument:gsub("%'%'%'%'", "");
elseif argument:match ("%'%'%'") then -- bold (3)
argument=argument:gsub("%'%'%'", "");
elseif argument:match ("%'%'") then -- italic (2)
argument=argument:gsub("%'%'", "");
else
break;
end
end
return argument; -- done
end
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
of %27%27...
]]
local function make_coins_title (title, script)
if is_set (title) then
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
else
title=''; -- if not set, make sure title is an empty string
end
if is_set (script) then
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
else
script=''; -- if not set, make sure script is an empty string
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
return title .. script; -- return the concatenation
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 for use in COinS.
]]
local function get_coins_pages (pages)
local pattern;
if not is_set (pages) then return pages; end -- if no page numbers then we're done
while true do
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, 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 a literal string; escape lua's magic pattern characters
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like?
return pages;
end
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
local function remove_wiki_link( str )
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end));
end
-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str:gsub( '-', '–' );
end
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
return str;
end
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
]]
local function is_suffix (suffix)
if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
return false;
end
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
At the time of this writing, I had to write the 'This original test: if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring..find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%' test %.]+[2-6%a]*$") thenwas written ouside of the code editor and past it pasted herebecause the code editor gets confused between character insertion point and cursor position.The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessaryto use an external editor to maintain this code. \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls) \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B) \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
]]
local function is_good_vanc_name (last, first)
if nil local first, suffix == mwfirst:match ('(.ustring.find (last-), "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-?%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-dJS][%s%'drndth]+)%.]*?$"') then if true ~= Page_in_vanc_error_cat then or first; -- if we haven't been here before then set first has something that looks like a sticky flaggenerational suffix, get it Page_in_vanc_error_cat=true; -- so that if there are more than one error the category is added only onceis_set (suffix) then if not is_suffix (suffix) then table.insert( z.message_tail, { set_erroradd_vanc_error ( 'vancouversuffix', {}, true ) } ); return false; -- not a name with an appropriate suffix
end
end if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then add_vanc_error ('non-Latin character'); return false; -- not a string of latin characters; Vancouver required requires Romanization
end;
return true;
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is notcurrently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
local function reduce_to_initials(first)
if local name, suffix = mw.ustring.match(first, "^(%u+) ([%udJS][%drndth]+)$") then return first end; -- when first contains just two upper-case letters, nothing to do local initials = {} local i = 0; if not name then -- counter for number of if not initialsand a suffix for word in name = mw.ustring.gmatchmatch(first, "[^(%s%.%-]u+)$") do -- names separated by spaces, hyphens, or periods table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops. i = i + 1; -- bump the counter if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quitis it just intials?
end
if name then -- if first is initials with or without suffix
if 3 > mw.ustring.len (name) then -- if one or two initials
if suffix then -- if there is a suffix
if is_suffix (suffix) then -- is it legitimate?
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
else
return first; -- one or two initials without suffix; nothing to do
end
end
end -- if here then name has 3 or more uppercase letters so treat them as a word
local initials, names = {}, {}; -- tables to hold name parts and initials
local i = 1; -- counter for number of initials
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
while names[i] do -- loop through the table
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
if is_suffix (names[i]) then -- if a legitimate suffix
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
break; -- and done because suffix must fall at the end of a name
end -- no error message if not a suffix; possibly because of Romanization
end
if 3 > i then
table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table
end
i = i+1; -- bump the counter
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
sep = ','; -- name-list separator between authors is a comma
namesep = ' '; -- last/first separator is a space
elseif 'mla' == control.mode then
sep = ','; -- name-list separator between authors is a comma
namesep = ', ' -- last/first separator is <comma><space>
else
sep = ';' -- name-list separator between authors is a semicolon
one = person.last
local first = person.first
if is_set(first) then if 'mla' == control.mode then if i == 1 then -- for mla one = one .. namesep .. first; -- first name last, first else -- all other names one = first .. ' ' .. one; -- first last end else if ( "vanc" == format ) then -- if vancouver format one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person.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
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
if is_set(person.link) and ((nil ~= person.link:find("//")) or (nil ~= person.link:find("[%[%]]"))) then
one = one .. " " .. set_error( 'bad_authorlink' ) end -- url or wikilink in author link;
end
table.insert( text, one )
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
if 'mla' == control.mode then text[#text-2] = ", and "; -- replace last separator with ', and ' text else text[#text-2] = " & "; -- replace last separator with ampersand text end
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 local etal_text result = result .. sep .. ' ' .. cfg.messages['et al']; result = result . -- we've go a last-first list and etal so add et al. " " .. etal_text;
end
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
]]namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
]]local function anchor_id( options namelist, year) local names={}; -- a table for the one to four names and year for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names names[i] = v.last if i == 4 then break end -- if four then done end table.insert (names, year); -- add the year at the end local id = table.concat( options names); -- concatenate names and year for CITEREF id
if is_set (id) then -- if concatenation is not an empty string
return "CITEREF" .. id; -- add the CITEREF portion
end
end
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
]]
local function name_has_etal (name, etal, nocat)
if is_set (name) then -- name can be nil in which case just return
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
if name:match (etal_pattern) then -- variants on et al.
name = name:gsub (etal_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
return name, etal; --
end
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
]]
local function name_has_ed_markup (name, list_name)
local _, pattern;
local patterns = { -- these patterns match annotations at end of name
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (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
}
if is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name: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
end
return name; -- and done
end
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are
indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name
(author or editor) maintenance category.
]]
local function name_has_mult_names (name, list_name)
local count, _;
if is_set (name) then
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
end
end
return name; -- and done
end
--[[--------------------------< 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-holding
parameters.
]]
local function name_checks (last, first, list_name)
if is_set (last) then
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
last = last:match ('^%(%((.*)%)%)$'); -- strip parens
else
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
end
end
if is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
else
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
end
end
return last, first; -- done
end
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
local pattern = ",? *'*[Ee][Tt] *[Aa][Ll][%.']*$" -- variations on the 'et al' theme
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
local name last, etal = tostringname_has_etal (last, etal, false); if name:match (pattern) then -- varients find and remove variations on et al. last = name:gsub (pattern first, ''); -- if found, remove etal = true; end name = tostringname_has_etal (first, etal, false); if name:match (pattern) then -- varients find and remove variations on et al. last, first = name:gsub name_checks (patternlast, first, ''list_name); -- if foundmultiple names, remove etal = true;extraneous annotation, etc checks end
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
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 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
end
if true == etal then
add_maint_cat ('etal');
end
return names, etal; -- all done, return our list of names
end
-- Populates ID table from arguments using configuration settings
local function extract_ids( args )
local id_list = {};
for k, v in pairs( cfg.id_handlers ) do
v = select_one( args, v.parameters, 'redundant_parameters' );
if is_set(v) then id_list[k] = v; end
end
return id_list;
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
Takes a table of IDs and turns it into a table of formatted ID outputs.
]]
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 k, v in pairs( id_list ) do
-- fallback to read-only cfg
handler = setmetatable( { ['id'] = v }, fallback(k) );
if handler.mode == 'external' then
table.insert( new_list, {handler.label, external_link_id( handler ) } );
elseif handler.mode == 'internal' then
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
elseif handler.mode ~= 'manual' then
error( cfg.messages['unknown_ID_mode'] );
elseif k == 'DOI' then
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
elseif k == 'ARXIV' then
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
elseif k == 'ASIN' then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
error( cfg.messages['unknown_manual_ID'] );
end
end
function comp( a, b ) -- used in following table.sort()
return a[1] < b[1];
end
table.sort( new_list, comp );
for k, v in ipairs( new_list ) do
new_list[k] = v[2];
end
return new_list;
end
-- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse
-- the citation information.
local function COinS(data, class)
if 'table' ~= type(data) or nil == next(data) then
return '';
end
local ctx_ver = "Z39.88-2004";
-- treat table strictly as an array with only set values.
local OCinSoutput = setmetatable( {}, {
__newindex = function(self, key, value)
if is_set(value) then
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
end
end
});
if is_set(data.Chapter) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter;
OCinSoutput["rft.btitle"] = data.Title;
elseif is_set(data.Periodical) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
if 'arxiv' == class then
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
else
OCinSoutput["rft.genre"] = "article";
end
OCinSoutput["rft.jtitle"] = data.Periodical;
OCinSoutput["rft.atitle"] = data.Title;
else
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
OCinSoutput["rft.genre"] = "book"
OCinSoutput["rft.btitle"] = data.Title;
end
OCinSoutput["rft.place"] = data.PublicationPlace;
OCinSoutput["rft.date"] = data.Date;
OCinSoutput["rft.series"] = data.Series;
OCinSoutput["rft.volume"] = data.Volume;
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages;
OCinSoutput["rft.edition"] = data.Edition;
OCinSoutput["rft.pub"] = data.PublisherName;
for k, v in pairs( data.ID_list ) do
local id, value = cfg.id_handlers[k].COinS;
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
OCinSoutput[ id ] = value;
end
end
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = v.last, v.first;
if k == 1 then
if is_set(last) then
OCinSoutput["rft.aulast"] = last;
end
if is_set(first) then
OCinSoutput["rft.aufirst"] = first;
end
end
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
elseif is_set(last) then
OCinSoutput["rft.au"] = last;
end
end
OCinSoutput.rft_id = data.URL;
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian whereISO639or 639-1 2 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
Returns the language name and associated ISO639two-1 or three-character code. Because case of the source may be incorrect or different from the case that WikimediaWikiMedia uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned alongwith the code. When there is no match, we return the original language name string.
mw.language.fetchLanguageNames(<local wiki language>, 'all') will return a list of languages that arenin some cases may includeextensions. For example, code 't part of ISO639cbk-1zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not supportcode 'cbk' or name 'Chavacano'. Names that aren't ISO639-1 but that are includedin the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan AramaicChavacano de Zamboanga, that name will befound with the associated code 'sam', not an ISO639cbk-1 codezam'. When names are found and the associated code is not two or three characters, this functionreturns only the Wikimedia language name.
Adapted from code taken from Module:Check ISO 639-1.
]]
local function get_iso639_code (lang, this_wiki_code) if 'norwegianbangla' == lang:lower() then -- special case related to Wikimedia remap of code 'nobn' at mw:Extension:CLDR return 'NorwegianBengali', 'nobn'; -- Make make sure rendered version is properly capitalized
end
local languages = mw.language.fetchLanguageNames('en'this_wiki_code, 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() and 3 ~= code:len() then -- ISO639two-1 or three-character codes only; extensions not supported
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 the code
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 the code
end
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Get language name from ISO639-1 code value provided. If a code is valid use the returned name; if not, then use the value that was provided with the language parameter. There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') andNorwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639[[--------------------------< L A N G U A G E _ P A R A M E T E R >----------------------------------------1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appearsthat on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.
Because Norwegian Bokmål is the most common Gets language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639name from a provided two-1 or three-character ISO 639 code 'no'. Here we undo that and If a code is recognized by MediaWiki,return 'Norwegian' when editors use |language=no. We presume the returned name; if not, then use the value that editors don't know about was provided with the variants or can't descriminate between themlanguage parameter.
See Help talkWhen |language= contains a recognized language (either code or name), the page is assigned to the category forthat code:Citation Style_1#An Category:Norwegian-language sources (no). For valid three-character code languages, the page is assignedto the single category for '639-2' codes: Category:CS1 ISO 639-1 2 language name testsources.
When |language= contains a valid ISO639-1 code, Languages that are the page is assigned to same as the category for that code: Category:Norwegianlocal wiki are not categorized. MediaWiki does not recognize three-language sources (no) ifcharacterthe page is a mainspace page and the ISO639equivalents of two-1 character codes: code 'ar' is not recognized bit code 'enara'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same waynot.
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas.
]]
local function language_parameter (lang, namespace) local code; -- the ISO639-1 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 unrec_cat this_wiki = false mw.getContentLanguage(); -- flag so that we only add unrecognized category onceget 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
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 0 == namespace and (('en' == lang:lower()) or match ('english^%a%a%-' == lang:lower())) then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? add_maint_cat lang = lang:match ('english(%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 -- ISO639if two-or three-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)code name = mw.language.fetchLanguageName( lang:lower(), "en" this_wiki_code); -- get ISO 639-1 language name if Language |language= is a proper code
end
if is_set (name) then -- if Language |language= specified a valid ISO639-1 code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if is_set (code) then -- only 2- or 3-character codes if 'nobn' == code then name = 'NorwegianBengali' end; -- override wikimedia when code is 'nobn' if 0 == namespace and 'en' this_wiki_code ~= code then -- when the language is this page main / article space and English 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', {name, code}) -- categorize it else -- or is a recognized language (but has a three-character code) add_prop_cat ('foreign_lang_source_2', {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template end
end
elseif false == unrec_cat thenelse unrec_cat = trueadd_maint_cat ('unknown_lang'); -- only add this maint category once add_maint_cat (unknown_lang);if not already added
end
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
if this_wiki_name == name then return ''; -- if one language and that language is this wiki's return an empty string (no annotation) end return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' --[[ TODO: should only return blank or name rather than full list so we can clean up the bunched parenthetical elements Language, Type, Format ]]
end
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);
elseif 'mla' == mode then -- if this template is to be rendered in mla style use cs1 for bot cs1 & cs2 templates
sep, ps = set_cs1_style (ps);
else -- anything but cs1 or cs2
if is_set (mode) then
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'mode', mode}, true ) } ); -- add error message
end
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
applying the pdf icon to external links.
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format:upper()); -- force upper case, add leading space, parenthases, resize
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
Returns a number that may or may not limit defines the length number of the names displayed for author or and editor name listsand a boolean flagto indicate when et al. should be appended to the name list.
When the value assigned to |display-authorsxxxxors= is a number greater than or equal to zero, return the number and
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
some variant of the text 'et al.').
When the value assigned to |display-authorsxxxxors= is the keyword 'etal', return a number that is one greater than the
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
the names in the name list followed by 'et al.'
In all other cases, returns nil and the previous state of the 'etal' flag.
inputs:
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
count: #a or #e
list_name: 'authors' or 'editors'
etal: author_etal or editor_etal
]]
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed', cfg.special_case_translation [list_name]);
end
else -- not a valid keyword or number
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
return max, etal;
end
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
abbreviation in the first characters of the parameter content.
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
]]
local function extra_text_in_page_check (page)
-- local good_pattern = '^P[^%.P%l]';
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]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
add_maint_cat ('extra_text');
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
end
--[[--------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
split apart a |vautthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the
rendered citation and in the metadata.
|vauthors=Jones AB, White EB, ((Black, Brown, and Co.))
This code is experimental and may not be retained.
]]
local function get_v_name_table (vparam, output_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local i = 1;
while name_table[i] do
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens
local name = name_table[i];
i=i+1; -- bump indexer to next segment
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens
break; -- and done reassembling so
end
i=i+1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
else
table.insert (output_table, name_table[i]); -- add this name
end
i = i+1;
end
return output_table;
end
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
]]
local function parse_vauthors_veditors (args, vparam, list_name)
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, 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)
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ('wikilink');
end
v_name_table = get_v_name_table (vparam, v_name_table); -- names are separated by commas
for i, v_name in ipairs(v_name_table) do
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
corporate = true; -- flag used in list_people()
elseif string.find(v_name, "%s") then
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
add_vanc_error ('punctuation');
end
local lastfirstTable = {}
lastfirstTable = mw.text.split(v_name, "%s")
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
if is_suffix (first) then -- if a valid suffix
suffix = first -- save it as a suffix and
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end -- no suffix error message here because letter combination may be result of Romanization; check for digits?
last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error ('name'); -- matches a space between two intiials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
if is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit
if is_set (suffix) then
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
suffix = ''; -- unset so we don't add this suffix to all subsequent names
end
else
if not corporate then
is_good_vanc_name (last, '');
end
end
-- 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
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
similarly, |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 second
test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better
way to do this, I just haven't discovered what that way is.
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
]]
local function select_author_editor_source (vxxxxors, xxxxors, args, 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 (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 error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if is_set (vxxxxors) then return 2 end;
if is_set (xxxxors) then return 3 end;
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
end
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.
]]
local function is_valid_parameter_value (value, name, possible, cite_class)
-- begin hack to limit |mode=mla to a specific set of templates
if ('mode' == name) and ('mla' == value) and not in_array (cite_class, {'book', 'journal', 'news'}) then
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
end
-- end hack
if not is_set (value) then
return true; -- an empty parameter is ok
elseif in_array(value:lower(), possible) then
return true;
else
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
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 space
when the last character is not a sepc character or when the last three characters are not sepc followed by two
closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
single space character.
]]
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list,-3,-1) == sepc .. '. ') then -- if already properly terminated
return name_list; -- just return the name list
elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
return name_list .. sepc .. ' '; -- otherwise terninate the name list
end
end
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
or formatted issue, or an empty string if neither are set.
]]
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower, mode)
if not is_set (volume) and not is_set (issue) then
return '';
end
if ('mla' == mode) and ('journal' == cite_class) then -- same as cs1 for magazines
lower = true; -- mla 8th edition; force these to lower case
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return '';
end
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
local vol = '';
if is_set (volume) then
if (4 < mw.ustring.len(volume)) then
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
else
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)});
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
not currently used
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
returns list unchanged if there are no commas else strips whitespace and then reformats the list
]]
--[[
local function normalize_page_list (list)
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
list = table.concat (list, ', '); -- and now make a normalized list
return list;
end
]]
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
The return order is:
page, pages, sheet, sheets
Singular has priority over plural when both are provided.
]]
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower, mode)
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
else
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
if is_journal and 'mla' == mode then
is_journal = false; -- mla always uses p & pp
end
if is_set (page) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif is_set(pages) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
return '', '', '', ''; -- return empty strings
end
--[=[-------------------------< A R C H I V E _ U R L _ C 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 allow
unwitting readers to do.
When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
|archive-date= and an error message when:
|archive-url= holds an archive.org save command url
|archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
correct place
otherwise returns |archive-url= and |archive-date=
There are two mostly compatible archive.org urls:
//web.archive.org/<timestamp>... -- the old form
//web.archive.org/web/<timestamp>... -- the new form
The old form does not support or map to the new form when it contains a display flag. There are four identified flags
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
we don't check for these specific flags but we do check the form.
This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modified
archive url:
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 archive_url_check (url, date)
local err_msg = ''; -- start with the error message empty
local path, timestamp, flag; -- portions of the archive.or url
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
end
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page
err_msg = 'save command';
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
elseif url:match('//liveweb%.archive%.org/') then
err_msg = 'liveweb';
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = 'timestamp';
if '*' ~= flag then
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
err_msg = 'path';
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
err_msg = 'flag';
elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = 'flag';
else
return url, date; -- return archiveURL and ArchiveDate
end
end
-- if here, something not right so
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
if is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for archiveURL and ArchiveDate
else
return url, date; -- preview mode so return archiveURL and ArchiveDate
end
end
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a
parameter that is missing its pipe:
{{cite ... |title=Title access-date=2016-03-17}}
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html
tags are removed before the search.
If a missing pipe is detected, this function adds the missing pipe maintenance category.
]]
local function missing_pipe_check (value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
add_maint_cat ('missing_pipe');
end
end
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
This is the main function doing the majority of the citationformatting.
]]
--[[
Load Input Parameters
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
]]
local A = argument_wrapper( args );
local i
local PPrefix = A['PPrefix'] local PPPrefix = A['PPPrefix'] if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end
-- Pick out the relevant fields from the arguments. Different citation templates
-- define different field names for the same underlying things.
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values local Authors Mode = A['AuthorsMode']; if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode'], config.CitationClass) then Mode = ''; end
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authors; local NameListFormat = A['NameListFormat']; local Collaboration = A['Collaboration']; do -- to limit scope of selected local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList'); if 1 == selected then a, author_etal = extract_names( args, 'AuthorList' ); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might be a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= elseif 3 == selected then Authors = A['Authors']; -- use content of |authors= if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors= add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO: end end if is_set (Collaboration) then author_etal = true; -- so that |display-authors=etal not required end end
local Coauthors = A['Coauthors'];
local Others = A['Others'];
local Editors = A['Editors'];
local editor_etal;
local e, editor_etal = extract_names( args, 'EditorList' ){}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= local Editors;
do -- to limit scope of selected local NameListFormat selected = select_author_editor_source (A['NameListFormatVeditors'], A['Editors'], args, 'EditorList'); if 1 == selected then e, editor_etal = extract_names (args, 'EditorList'); -- replaces fetch editor list from |authoreditorn= / |editor-formatlastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format=might be if is_set e, editor_etal = parse_vauthors_veditors (NameListFormatargs, args.veditors, 'EditorList') ; -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= elseif 3 == selected then Editors = A['Editors']; -- use content of |editors= add_maint_cat ('vanceditors' ~); -- but add a maint cat because use of this parameter is discouraged end end local t = NameListFormat{}; -- 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= local interviewers_list = {}; local Interviewers = A['Interviewers'] if is_set (Interviewers) then -- add a maint cat if the |interviewers= is used add_maint_cat ('interviewers'); -- only accepted value for because use of this parameter is discouraged else interviewers_list = extract_names (args, 'vancInterviewerList'); -- else, process preferred interviewers parameters end local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs local Contributors; -- assembled contributors name list local Contribution = A['Contribution']; 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 < #c then if not is_set (Contribution) then -- |contributor= requires |contribution= table.insert( z.message_tail, { set_error( 'invalid_param_valcontributor_missing_required_param', 'contribution')}); -- add missing contribution error message c = {}; -- blank the contributors'nametable; it is used as a flag later end if 0 == #a then -list-format|contributor= requires |author= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', NameListFormat'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', true 1 ) then -- are there contributor name list parameters? table.insert( z.message_tail, { set_error( 'contributor_ignored') } ); -- not vanc so add contributor ignored error message end Contribution = nil; -- unset end if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc' NameListFormat = ''; -- anything else, set to empty string
end
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
local Chapter = A['Chapter'];
local ScriptChapter = A['ScriptChapter']; local ChapterLink -- = A['ChapterLink']; -- deprecatedas a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
local ArchiveDate; local ArchiveURL ; ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) local DeadURL = A['DeadURL'] if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string end
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
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; -- previously conference books did not support volume-- if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then if in_array (config.CitationClass, cfg.templates_using_volume) then Volume = A['Volume']; local end -- conference & map books do not support issue if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then Issue = A['Issue']; end
local Position = '';
local if not in_array (config.CitationClass, cfg.templates_not_using_page) then Page = A['Page']; local Pages = hyphen_to_dash( A['Pages'] ); local At = A['At']; end
local Edition = A['Edition'];
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, '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
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription=
end
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message
RegistrationRequired = nil; -- unset; prefer |access= over |registration=
end
local Via = A['Via'];
local AccessDate = A['AccessDate'];
local ArchiveDate = A['ArchiveDate'];
local Agency = A['Agency'];
local DeadURL = A['DeadURL']
local Language = A['Language'];
local Format = A['Format'];
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
IgnoreISBN = nil; -- anything else, set to empty string
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
local ID_list = extract_ids( args );
local ID_access_levels = extract_id_access_levels( args, ID_list );
local Quote = A['Quote'];
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
end
if 'mla' == Mode then
LastAuthorAmp = 'yes'; -- replaces last author/editor separator with ' and ' text
end
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no--these are used by cite interview local Callsign = Atracking', cfg.keywords ['Callsignyes_true_y'];) then local City no_tracking_cats = A['City']nil; -- set to empty string local Program = A['Program']; 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= {}; -- used in holds date info extracted from |date= for the COinS metadataby Module:Date verification local DF = A['DF']; -- date format set in cs1|2 template if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword DF = ''; -- not valid, set to empty string end
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (A['Mode']:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
end
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category local 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
if is_set(Page) then
if is_set(Pages) or is_set(At) then
Page = Page .. " " .. set_error('extra_pages'); -- add error message Pages = ''; -- unset the others
At = '';
end
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
elseif is_set(Pages) then
if is_set(At) then
Pages = Pages .. " " .. set_error('extra_pages'); -- add error messages 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
All other combinations of |encyclopedia, |title, and |article are not modified
TODO: script-title to script-chapter if and when we support script-chapter
]]
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then
if not is_set(Chapter) then
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle;
TransChapter = TransTitle;
ChapterURL = URL;
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
end
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset TransTitle = ''; -- redundant so unset URL = ''; -- redundant so unset Format = ''; -- redundant so unset TitleLink = ''; 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
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport if is_set(IssueA['Number']) then -- cite techreport uses 'number', which other citations aliase alias to 'issue' if not is_set(ID) then -- can we use ID for the "number"? ID = IssueA['Number']; -- yes, use it Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata else -- can't use ID has a value so emit error message ID = ID .. " " table.insert( z. message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', '<code>|id=</code> ') .. ' and <code>|' .. wrap_style ('parameter', 'number=</code>')}, true )});
end
end
end
-- special case for cite interview
if (config.CitationClass == "interview") then
if is_set(Program) then
ID = ' ' .. Program;
end
if is_set(Callsign) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. Callsign;
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
else
Others = '(Interview)';
end
end
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local Began = A['Began']; -- these two are deprecated because the module understands date ranges
local Ended = A['Ended'];
local SeriesLink = A['SeriesLink'];
link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate or Began/Ended to date if is_set (AirDate) then Date = AirDate; elseif is_set (Began) then -- deprecated if Began:match('%s') or Ended:match('%s') then -- so we don't create errors: if either has spaces then Date = Began .. ' – ' .. Ended; -- use spaced ndash as separator else Date = Began .. '–' .. Ended; -- elsewise no spaces end end
end
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
end
URL = ''; -- unset
TransTitle = ''; -- unset 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
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. do if in_array (config.CitationClass, {'arxiv' == config.CitationClass , 'biorxiv', 'citeseerx'}) then if not is_set (ID_list['ARXIV'config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates table.insert( z.message_tail, { set_error( config.CitationClass .. 'arxiv_missing_missing', {}, true ) } ); -- add error message end if first_set (AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'], ID_list[if 'JFMarxiv'], 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']) == config.CitationClass then table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message AccessDatePeriodical = 'arXiv'; -- set these to arXiv for COinS; after that, must be set to empty string; not supported in cite arXiv end if 'biorxiv' == config.CitationClass then PublisherName Periodical = 'bioRxiv'; -- (if the article has been published, use cite journalset to bioRxiv for COinS; after that, or other)must be set to empty string Chapter = ''; end URL = if 'citeseerx'; Format = '';= config.CitationClass then Page Periodical = 'CiteSeerX'; Pages = ''; At = '' -- set to CiteSeerX for COinS;after that, must be set to empty string end
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notesinterview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " ' ' .. cfg.title_types ['thesis"']:lower();
end
end
if is_set(TitleType) then -- if type parameter is specified
TitleType = " substitute(" .cfg. messages['type'], TitleType .. ")"; -- display it in parentheses -- TODO: Hack on TitleType to fix bunched parentheses problem
end
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
if not is_set (Date) then
Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not is_set(Date) then local Month = A['Month']; if and is_set(MonthPublicationDate) then Date = Month .. " " .. Date; end elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set Date = PublicationDate; -- promote PublicationDate to Date PublicationDate = ''; -- unset, no longer needed
end
end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
--[[
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message and , date_parameters_list, mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
anchor_year, COinS_date, error_message local date_parameters_list = dates({['accessdateaccess-date']=AccessDate, ['archivedatearchive-date']=ArchiveDate, ['date']=Date, ['doi_brokendatedoi-broken-date']=DoiBroken, ['embargo']=Embargo, ['laydatelay-date']=LayDate, ['publicationdatepublication-date']=PublicationDate, ['year']=Year}; anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
end
end
if not is_set(error_message) then -- error free dates only
local modified = false; -- flag
if is_set (DF) then -- if we need to reformat dates
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
end
if is_settrue == date_hyphen_to_dash (error_messagedate_parameters_list) then -- convert hyphens to dashes where appropriate modified = true; add_maint_cat ('date_format'); -- hyphens were converted so add maint category end if modified then -- if the date_parameters_list values were modified AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list['archive-date']; Date = date_parameters_list['date']; DoiBroken = date_parameters_list['doi-broken-date']; LayDate = date_parameters_list['lay-date']; PublicationDate = date_parameters_list['publication-date']; end else
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
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
end
end
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); else table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); end
end
if 'none' == Title and is_set(Periodical) and not (in_array ( config.CitationClass == "encyclopaedia" , {'journal', 'citation'}) or and is_set ( config.CitationClass Periodical) and 'journal' == "citation" and is_set A:ORIGIN(Encyclopedia))'Periodical') then -- special casefor journal cites
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
check_for_url ({ -- add error message when any of these parameters contains a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[A:ORIGIN('PublisherName')] = PublisherName
});
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
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 COinS()
local OCinSoutput = COinS({
['Periodical'] = Periodical,
['Encyclopedia'] = Encyclopedia, ['Chapter'] = strip_apostrophe_markup 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'] = first_set(COinS_date.rftdate, Date), -- COinS_date has correctly formatted date if Date is valid; any reason to keep Date here? ['Season'] = COinS_date.rftssn, ['Chron'] = Should we be including COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid dates in metadatadate format use Date; keep this last bit?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = get_coins_pages (first_set({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['URL'] = first_set( {ChapterURL, URL}, ChapterURL 2), ['Authors'] = acoins_author,
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
-- if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed Periodical = ''; -- periodical not allowed in cite arxivthese templates; if article has been published, use cite journal
end
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName = '[substitute (cfg.messages[Newsgroup]]: ' .. newsgroup'], external_link( 'news:' .. PublisherName, PublisherName , A:ORIGIN('PublisherName'), nil ));
end
end
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
do local EditorCount; -- doused only for choosing {ed.) or (eds.) annotation at end of editor name-block to limit scope of LastFirstAuthorslist local LastFirstAuthors; do local Maximum = A['DisplayAuthors']last_first_list; Maximum , author_etal = get_display_authors_editors (Maximum, #a, 'authors', author_etal);
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = Maximumnil, -- 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 authorlinkneditorlinkn mode = Mode
};
-- If the coauthor field is also used, prevent ampersand and et al. formatting.
if is_set(Coauthors) then
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
LastFirstAuthors = list_people(control, a, author_etal);
if is_set (Authors) then if is_set (LastFirstAuthors) then do -- if both author do editor name styles list first because the now unsupported coauthors used to modify control table control.insert( z.message_tailmaximum , { set_erroreditor_etal = get_display_authors_editors ( A['redundant_parametersDisplayEditors'], {wrap_style ('parameter'#e, 'authorseditors', editor_etal) ; last_first_list, EditorCount = list_people(control, e, editor_etal); if is_set (Editors) then if editor_etal then Editors = Editors .. ' and ' .. wrap_style (cfg.messages['parameteret al', 'last')}, true ) } )]; -- add error messageet al. to editors parameter beause |display-editors=etal Authors EditorCount = LastFirstAuthors2; -- TODO: with et al., |editors= is this correct or should multiple names; spoof to display (eds.) annotation else EditorCount = 2; -- we use don't know but assume |authorseditors= instead?is multiple names; spoof to display (eds.) annotation end else Editors = last_first_list; -- either an author name list or an empty string
end
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then EditorCount = 2; -- spoof to display (eds.) annotation end elseend do -- now do interviewers Authors control.maximum = LastFirstAuthors#interviewers_list; -- either an author name list or an empty stringnumber of interviewerss Interviewers = list_people(control, interviewers_list, false); -- et al not currently supported end do -- now do translators control.maximum = #t; -- number of translators Translators = list_people(control, t, false); -- et al not currently supported
end
end do -- end now do contributors control.maximum = #c; -- number of contributors Contributors = list_people(control, c, false); -- et al not currently supported end do -- now doauthors control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors last_first_list =, authorn=, or lastn= isn't specified table.insertlist_people( z.message_tailcontrol, { set_error('coauthors_missing_author'a, {}, true) } author_etal); -- emit error message end
local EditorCount; -- used only for choosing {ed. if is_set (Authors) or then Authors, author_etal = name_has_etal (eds.Authors, author_etal, false) annotation at end of editor name; -list- find and remove variations on et al. if not is_set(Editors) author_etal then local Maximum Authors = AAuthors .. ' ' .. cfg.messages['DisplayEditorset al']; -- add et al. to authors parameter end Maximum , editor_etal else Authors = get_display_authors_editors (Maximum, #e, 'editors', editor_etal)last_first_list; -- either an author name list or an empty string end end -- Preserve old-style implicit et al.end of do if not is_set(MaximumAuthors) and #e == 4 is_set (Collaboration) then Maximum Authors = 3; tableAuthors .insert( z.message_tail, { set_error' ('implict_etal_editor.. Collaboration .. ', {}, true) } )'; -- add collaboration after et al.
end
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = Maximum,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
};
Editors, EditorCount = list_people(control, e, editor_etal);
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
EditorCount = 2; -- spoof to display (eds.) annotation
end
else
EditorCount = 1;
end
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', 'url');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
-- special case for chapter format so no error message or cat when chapter not supported if not is_set(URLin_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) then --andor-- not ('citation' == config.CitationClass and is_set(ArchiveURLPeriodical) then --and -- prevents format_missing_url error from registering-- not is_set(ConferenceURLEncyclopedia) and -- TODO: keep this here? conference as part of cite web or cite podcast?)) then ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter- url'); end if not is_set(TranscriptURLURL) then -- TODO: remove? |transcript-url= and |transcript= has separate test -- Test if cite web or cite podcast |url= is missing or empty if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- |url= required for cite web, cite podcast, and cite mailinglist
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
-- Test if do we have |accessdate is given = without giving a URLeither |url= or |chapter-url=? if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are URL is not set; TODO: move this to a separate test?
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
DeadURL = DeadURL:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages OriginalFormat = ChapterFormat; -- and original |format= if 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages ChapterFormat = ArchiveFormat or ''; -- swap in archive's format end elseif is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages OriginalFormat = Format; -- and original |format= OriginalAccess = UrlAccess;
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived urls
end
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 OriginalFormat = ChapterFormat; -- and original |format= if 'no' ~= DeadURL then ChapterURL = ArchiveURL -- swap-in the archive's url URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages ChapterFormat = ArchiveFormat or ''; -- swap in archive's format 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 chap_param; if is_set (Chapter) or then -- get a parameter name from one of these chapter related meta-parameters chap_param = A:ORIGIN ('Chapter') elseif is_set (TransChapter) or then chap_param = A:ORIGIN ('TransChapter') elseif is_set (ChapterURL)then chap_param = A:ORIGIN ('ChapterURL') elseif is_set (ScriptChapter) then chap_param = A:ORIGIN ('ScriptChapter') else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat') end if is_set (chap_param) then -- chapter parameters not supported for these citation typesif we found one table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
ScriptChapter = '';
ChapterFormat = '';
end
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title no_quotes = true; -- then render it unquoted end end Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
if is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
if 'map' == config.CitationClass and is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
end
Chapter = Chapter .. sepc .. ' '; elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
end
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 );
end
local TransError = "";
if is_set(TransTitle) then
if is_set(Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. set_error( 'trans_missing_title' , {'title'} );
end
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title , URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format;-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available-- local err_msg-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this-- Title = Title .. (err_msg or '');-- end-- else-- Title = temp_title;-- end URL = ""''; -- unset these because no longer needed
Format = "";
else
Title = Title .. TransTitle .. TransError;
end
end
if is_set (Conference) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference , ConferenceURLorigin, nil );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin , nil );
end
if not is_set(Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
if is_set(Minutes) then
if is_set (Time) then
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
local Time = A['Time'];
if is_set(Time) then
local TimeCaption = A['TimeCaption']
Position = " " .. Position;
At = '';
end
if not is_set(Page) then
if is_set(Pages) then
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
Pages = ": " .. Pages;
elseif tonumber(Pages) ~= nil then
Pages = sepc .." " .. PPrefix .. Pages;
else
Pages = sepc .." " .. PPPrefix .. Pages;
end
end
else
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
Page = ": " .. Page;
else
Page = sepc .." " .. PPrefix .. Page;
end
end
if 'map' == config.CitationClass then -- cite map oddity done after COinS call (and with other in-source locators) if is_set (Page, Pages, Sheet) or is_set (, Sheets) then local err_msg1 = 'sheet=, |sheets'; -- default error message in case any of page pages or at are set local err_msg2; if is_set format_pages_sheets (Page) or is_set (, Pages) or is_set (At) then -- are any set? err_msg2 = 'page=, |pages=Sheet, |at'; -- a generic error message Page = ''; Pages = ''; At = ''; elseif is_set (Sheet) and is_set (Sheets) then -- if both are set make error message err_msg1 = 'sheet'; err_msg2 = 'sheets'; end if is_set (err_msg2) then table, config.insert( z.message_tailCitationClass, { set_error( 'redundant_parameters'Periodical_origin, {wrap_style ('parameter'sepc, err_msg1) .. ' and ' .. wrap_style ('parameter'NoPP, err_msg2)}use_lowercase, true Mode) } ); -- add error message end if not is_set (Sheet) then -- do sheet static text and formatting; Sheet has priority over Sheets if both provided if is_set (Sheets) then if is_set (Periodical) then Sheet = ": Sheets " .. Sheets; -- because Sheet has priority, no need to support both later on else Sheet = sepc .. " Sheets " .. Sheets; end end else if is_set (Periodical) then Sheet = ": Sheet " .. Sheet; else Sheet = sepc .. " Sheet " .. Sheet; end end end end
At = is_set(At) and (sepc .. " " .. At) or "";
if is_set (Language) then
Language = language_parameter (Language, this_page.namespace); -- format, categories (article namespace only), name from ISO639-1, etc
else
Language=""; -- language not specified so make sure this is an empty string;
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then if 'mla' == Mode then Others = sepc .. ' Trans. ' .. Translators .. Others; else Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others; end end if is_set (Interviewers) then Others = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others; end
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
Edition = if is_set(Edition) and then if Edition:match (" " '%f[%a][Ee]d%.. wrap_msg ?$') or Edition:match ('edition%f[%a][Ee]dition$') then add_maint_cat ('extra_text', Edition'edition')) or ""; Issue end if 'mla' = is_set(Issue) and (" (" = Mode then Edition = '.' . Issue .Edition . . ' ed.'; else Edition = ")".. wrap_msg ('edition', Edition) or ""; end else Edition = ''; end
Series = is_set(Series) and (sepc .. " " .. Series) or "";
if 'mla' == Mode then -- not in brackets for mla OrigYear = is_set(OrigYear) and (". " .. OrigYear) or ""; else OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; end
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
if is_setVolume = format_volume_issue (Volume) then if ( mw, Issue, config.ustring.len(Volume) > 4 ) then Volume = CitationClass, Periodical_origin, sepc .." " .. Volume; else Volume = " <b>" .. hyphen_to_dash(Volume, use_lowercase, Mode) .. "</b>"; end end
------------------------------------ totally unrelated data
]]
if in_arrayis_set (SubscriptionRequired:lower(), {'yes', 'true', 'y'}) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif in_arrayis_set (RegistrationRequired:lower(), {'yes', 'true', 'y'}) then
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if 'mla' == Mode then -- retrieved text not used in mla AccessDate = ' ' .. AccessDate; else if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation'mode is cs2, 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 end
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
end
ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin , UrlAccess );
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 cs1|2 does not supply terminal punctuation when |quote= is set
end
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'), nil ) .. 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', 'bot: unknown'}) then Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled if 'bot: unknown' == DeadURL then add_maint_cat ('bot:_unknown'); -- and add a category if not already added else add_maint_cat ('unfit'); -- and add a category if not already added end else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " .. substitute( arch_text, { external_link( OriginalURL, cfg.messages['original'] , OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled end
else
local arch_text = cfg.messages['archived-missing'];
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=
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript , TranscriptURLorigin, nil );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin , nil );
end
local Publisher;
if is_set(Periodical) and not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}PublicationDate) 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(PublicationDate) then if is_set(Publisher) then Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate); else Publisher = PublicationDate; end end if is_set(Publisher) then Publisher = " (" .. Publisher .. ")"; end else if is_set(PublicationDatePublisherName) then PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")"; end if is_set(PublisherNamePublicationPlace) then if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; else Publisher = sepc .. " " .. PublisherName .. PublicationDate; end elseif is_set(PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; else Publisher = PublicationDate; end
end
-- 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
if 'mla' == Mode then tcommon = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); else tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); end 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 if 'mla' == Mode then tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Edition, Publisher, Agency}, sepc ); else tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, IssueOthers, Edition, Publisher, Agency}, sepc ); end elseif 'mla' == Mode then tcommon = safe_join( {TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Publisher, Agency}, sepc ); else tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, 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, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume, Issue}, sepc );
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
elseif ('news' == config.CitationClass) and ('mla' == Mode) then -- special case for cite news in MLA mode
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, Edition, Agency}, sepc );
elseif ('web' == config.CitationClass) and ('mla' == Mode) then -- special case for cite web in MLA mode
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language,
Edition, Publisher, Agency}, sepc );
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume, Issue, Others, Edition, Publisher, Agency}, sepc );
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; if is_set(AuthorsDate) then if is_set(Coauthors'mla' == Mode) then local sep if in_array (config.CitationClass, {'book', 'news', 'web'}) then Date = '; , '.. Date; -- origyear follows title in mla if elseif 'vancjournal' == NameListFormat config.CitationClass then sep Date = ', ('.. Date .. ')'; end elseif is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses else -- neither of authors and editors set if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc Date = " " .. Date .. OrigYear; -- Date does not begin with sepc else Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
end
Authors = Authors .. sep .. Coauthors;
end
end if is_set(DateAuthors) then Date = " if (not is_set ("..Date..")" .. OrigYear .. sepc .. " " elseif string.sub) or (Authors,-1,-1) 'mla' == sepc Mode) then -- when date is set it's in parentheses; no Authors = Authors .. " " elsetermination Authors = terminate_name_list (Authors .. , sepc); -- when no date, terminate with 0 or 1 sepc .. " "and a space
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) and 0 == #c and 'mla' ~= Mode then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
elseif is_set(Chapter) and 'mla' == Mode then
if EditorCount <= 1 then
in_text = '. Ed. ';
else
in_text = '. Eds. ';
end
else
if EditorCount <= 1 then
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 in_text by_text = in_textby_text:lower() end -- lowercase for cs2 Editors Authors = in_text by_text .. Editors .. post_textAuthors; -- author follows title so tweak it here if is_set (string.subEditors) and is_set (Date) and ('mla' ~= Mode) then -- when Editorsmake sure that Authors gets terminated Authors = terminate_name_list (Authors,sepc); -1,-terminate with 0 or 1) == sepcand a space end if (not is_set (Date)) or (string.sub(Editors,'mla' == Mode) then -3,-1) =when date is set it's in parentheses; no Contributors termination Contributors = terminate_name_list (Contributors, sepc .. ']]') then ; -- if last editor name ends terminate with 0 or 1 sepc charand a space end if 'mla' == Mode then Editors text = safe_join( {Contributors, Chapter, tcommon, OrigYear, Authors, Place, Others, Editors .. " ", tcommon2, Date, pgtext, idcommon }, sepc ); -- don't add another
else
Editors text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors .. , tcommon2, pgtext, idcommon }, sepc .. " " -- otherwise terninate the editor list);
end
elseif 'mla' == Mode then
tcommon = tcommon .. Date; -- hack to avoid duplicate separators
text = safe_join( {Authors, Chapter, Title, OrigYear, Others, Editors, Edition, Place, tcommon, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
elseif is_set(Editors) then
if is_set(Date) then
Editors = Editors .. ", " .. cfg.messages['editors'];
end
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
else
if EditorCount <= 1 then
end
end
if 'mla' == Mode then if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then text = safe_join( {Editors, Date, ChapterTitle, Place, tcommon, pgtext, Date, idcommon}, sepc ); else text = safe_join( {textEditors, Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc ); else if is_set(Date) then if ( string.sub(tcommon,-1,-1) ~= sepc ) then Date = sepc .." " .. Date .. OrigYear else Date = " " .. Date .. OrigYear
end
else
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
end
elseif 'mla' == Mode then if in_array(config.CitationClass==", {'journal" ', 'news', 'web'}) and is_set(Periodical) then text = safe_join( {ChapterTitle, Place, tcommon, pgtext, Date, idcommon}, sepc ); else text = safe_join( {Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc ); end else if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then text= safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Place, tcommon, Date}, sepc ); text = safe_join( {text, pgtext, idcommon}, sepc );
end
end
text = safe_join( {text, PostScript}, sepc );
-- Now enclose the whole thing in a <spancite/> 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 names namelist = {} ; --table of last names & holds selected contributor, author, editor name list local year= first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation if #a c > 0 then for i,v in ipairs( -- if there is a) do contributor list names[i] namelist = v.last c; -- select it if i == 4 elseif #a > 0 then break end -- or an author list endnamelist = a; elseif #e > 0 then -- or an editor list for i,v in ipairs(namelist = e) do ; names[i] = v.last end if i == 4 #namelist > 0 then break end -- if there are names in namelist id = anchor_id (namelist, year); -- go make the CITEREF anchor else endid = ''; -- unset
end
names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
id = anchor_id(names)
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');
end
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags text = substitute (cfg.presentation['<span cite-id="' .. ], {mw.uri.anchorEncode(options.id) ..'" class="' .. , mw.text.nowiki(options.class) .. '">' .. , text .. "</span>"});-- when |ref= is set
else
text = substitute (cfg.presentation['<span class="cite' .. ], {mw.text.nowiki(options.class) .. '">' .. , text .. "</span>"});-- all other cases
end
local empty_span text = '<span style="display:none;"> </span>'; -- Note: Using display: none on then COinS span breaks some clientstext . local OCinS = '<span title="' .. OCinSoutput .substitute (cfg. presentation['" class="Z3988">' .. empty_span .. '</span>ocins'], {OCinSoutput}); text = text .. OCinS;-- append metadata to the citation
if #z.message_tail ~= 0 then
if #z.maintenance_cats ~= 0 then
text = text .. ' <span class="citation-comment" style="display:none; color:#33aa33; margin-left:0.3em">';
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
end
-- [[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------ This is used by templates such as {{cite book}} to create the actual citation text. ]] function zcs1.citation(frame) Frame = frame; -- save a copy incase we need to display an error message in preview mode
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ...support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
utilities = require ('Module:Citation/CS1/Utilities/sandbox'); validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... identifiers = require ('Module:Citation/CS1/Identifiers/sandbox version of date validation code'); metadata = require ('Module:Citation/CS1/COinS/sandbox');
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
utilities = require ('Module:Citation/CS1/Utilities'); validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation codeidentifiers = require ('Module:Citation/CS1/Identifiers'); metadata = require ('Module:Citation/CS1/COinS');
end
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module validation.set_selected_modules (utilities); -- so that functions in Date validataion can see the selected Utilities module metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module dates = validation.dates; -- imported functionsfrom Module:Citation/CS1/Date validation
year_date_check = validation.year_date_check;
reformat_dates = validation.reformat_dates;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
in_array = utilities.in_array;
substitute = utilities.substitute;
error_comment = utilities.error_comment;
set_error = utilities.set_error;
select_one = utilities.select_one;
add_maint_cat = utilities.add_maint_cat;
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
remove_wiki_link = utilities.remove_wiki_link;
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
extract_id_access_levels = identifiers.extract_id_access_levels;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
get_coins_pages = metadata.get_coins_pages;
COinS = metadata.COinS;
local args = {}; -- table where we store all of the template's arguments local suggestions = {}; -- table where we store suggestions if we need to loadData them
local error_text, error_state;
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
config[k] = v;
-- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}}
end
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 , config.CitationClass ) then
error_text = "";
if type( k ) ~= 'string' then
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
elseif validate( k:lower() , config.CitationClass ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
else
if #suggestions nil == 0 suggestions.suggestions then -- if this table is nil thenwe 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 suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version end
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match if capture then -- if the pattern matches param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator) error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message end end if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion? if suggestions.suggestions[ k:lower() ] ~= nil then error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); 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
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
end
for k, v in pairs( args ) do if 'string' == type (k) then -- don't evaluate positional parameters has_invisible_chars (k, v); end end
return citation0( config, args)
end
return zcs1;