ዊኪፒድያ tigwiki https://tig.wikipedia.org/wiki/%E1%8A%A0%E1%8C%8D%E1%8B%B3_%E1%8C%88%E1%8C%BD MediaWiki 1.47.0-wmf.2 first-letter ሜድያ ፍንቱይ ህድግ መትነፈዓይ ህድግ መትነፈዓይ ዊኪፒድያ ህድግ ዊኪፒድያ ፋይል ህድግ ፋይል ሜድያዊኪ ህድግ ሜድያዊኪ ሞደል ህድግ ሞደል ሰዳየት ህድግ ሰዳየት ከረርም ህድግ ከረርም TimedText TimedText talk Module Module talk Event Event talk 10 652 9072 2026-05-15T07:09:23Z WikiBayer 737 Created page with "<includeonly>{{#invoke:citation/CS1|citation |CitationClass=web }}</includeonly><noinclude> {{documentation}} </noinclude>" 9072 wikitext text/x-wiki <includeonly>{{#invoke:citation/CS1|citation |CitationClass=web }}</includeonly><noinclude> {{documentation}} </noinclude> rcgmbcxu7hvs583g1f3rzz4c4dkizda 828 653 9073 2026-05-15T07:11:54Z WikiBayer 737 [[:w:Special:PermanentLink/1340931214|Module:Citation/CS1]] 9073 Scribunto text/plain require ('strict'); --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- each of these counts against the Lua upvalue limit ]] local validation; -- functions in Module:Citation/CS1/Date_validation local utilities; -- functions in Module:Citation/CS1/Utilities local z = {}; -- table of tables in Module:Citation/CS1/Utilities local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers local metadata; -- functions in Module:Citation/CS1/COinS local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration local 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 >--------------- declare variables here that have page-wide scope that are not brought in from other modules; that are created here and used here ]] local added_deprecated_cat; -- boolean flag so that the category is added only once local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category local added_generic_name_errs; -- boolean flag so we only emit one generic name error / category and stop testing names once an error is encountered local added_numeric_name_errs; -- boolean flag so we only emit one numeric name error / category and stop testing names once an error is encountered local added_numeric_name_maint; -- boolean flag so we only emit one numeric name maint category and stop testing names once a category has been emitted local is_preview_mode; -- true when article is in preview mode; false when using 'Preview page with this template' (previewing the module) local is_sandbox; -- true when using sandbox modules to render citation local url_was_archive_today; -- boolean flag set to true when has_archive_today_url() has unset |url= because it held a deprecated archive.today url --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ Locates and returns the first set 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 none are set. This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs. With the pairs version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate the for-loop before it reached the actual end of the list. ]] local function first_set (list, count) local i = 1; while i <= count do -- loop through all items in list if utilities.is_set( list[i] ) then return list[i]; -- return the first set list member end i = i + 1; -- point to next end end --[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- Adds a single Vancouver system error message to the template's output regardless of how many error actually exist. To prevent duplication, added_vanc_errs is nil until an error message is emitted. added_vanc_errs is a Boolean declared in page scope variables above ]] local function add_vanc_error (source, position) if added_vanc_errs then return end added_vanc_errs = true; -- note that we've added this category utilities.set_message ('err_vancouver', {source, position}); end --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ does this thing that purports to be a URI scheme seem to be a valid scheme? The scheme is checked to see if it is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says: Scheme names consist of a 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 is_scheme (scheme) return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern end --[=[-------------------------< 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-3.5 BNF defined here: https://tools.ietf.org/html/rfc4234 Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; see also [[Single-letter second-level domain]] list of TLDs: https://www.iana.org/domains/root/db RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit. Between the first and last characters the name may use letters, digits, and the hyphen. 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. tld is two or more alpha characters. Any preceding '//' (from splitting a URL with a scheme) will be stripped here. Perhaps not necessary but retained in case 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) prefix xn-- in the TLD) see https://tools.ietf.org/html/rfc3490 single-letter/digit second-level domains in the .org, .cash, and .today TLDs q, x, and z SL domains in the .com TLD i and q SL domains in the .net TLD single-letter SL domains in the ccTLDs (where the ccTLD is two letters) two-character SL domains in gTLDs (where the gTLD is two or more letters) three-plus-character SL domains in gTLDs (where the gTLD is two or more letters) IPv4 dot-decimal address format; TLD not allowed returns true if domain appears to be a proper name and TLD or IPv4 address, else false ]=] local function is_domain_name (domain) if not domain then return false; -- if not set, abandon end domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once if not domain:match ('^[%w]') then -- first character must be letter or digit return false; end if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource return false; end local patterns = { -- patterns that look like URLs '%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld '%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix '%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10) '%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10) '%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars) '%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD '^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address '[%a%d]+%:?' -- IPv6 address } for _, pattern in ipairs (patterns) do -- loop through the patterns list if domain:match (pattern) then return true; -- if a match then we think that this thing that purports to be a URL is a URL end end for _, d in ipairs (cfg.single_letter_2nd_lvl_domains_t) do -- look for single letter second level domain names for these top level domains if domain:match ('%f[%w][%w]%.' .. d) then return true end end return false; -- no matches, we don't know what this thing is 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 utilities.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. Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes like news: that don't use authority indicator? Strip off any port and path; ]] local function split_url (url_str) local scheme, authority, domain; url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL domain = url_str:match ('^//(%S*)') elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions if utilities.is_set (authority) then authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return scheme; -- return scheme only making domain nil which will cause an error message end else if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test? return scheme; -- return scheme only making domain nil which will cause an error message end end domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present end return scheme, domain; end --[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed: # < > [ ] | { } _ except the underscore which is used as a space in wiki URLs and # which is used for section links returns false when the value contains any of these characters. When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid URL (the |<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok). ]] local function link_param_ok (value) local scheme, domain; if value:find ('[<>%[%]|{}]') then -- if any prohibited characters return false; end scheme, domain = split_url (value); -- get scheme or nil and domain or nil from URL; return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL end --[[--------------------------< L I N K _ T I T L E _ O K >--------------------------------------------------- Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value. |<title>= may be wiki-linked but not when |<param>-link= has a value. This function emits an error message when that condition exists check <link> for inter-language interwiki-link prefix. prefix must be a MediaWiki-recognized language code and must begin with a colon. ]] local function link_title_ok (link, lorig, title, torig) local orig; if utilities.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 elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon orig = lorig; -- flag as error end end end if utilities.is_set (orig) then link = ''; -- unset utilities.set_message ('err_bad_paramlink', orig); -- URL or wikilink in |title= with |title-link=; end return link; -- link if ok, empty string else end --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------ Determines whether a URL string appears to be valid. First we test for space characters. If any are found, return false. Then split the URL into scheme and domain portions, or for protocol-relative (//example.com) URLs, just the domain. Use is_url() to validate the two portions of the URL. If both are valid, or for protocol-relative if domain is valid, return true, else false. Because it is different from a standard URL, and because this module used external_link() to make external links that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name is at https://tools.ietf.org/html/rfc5536#section-3.1.4 ]] local function check_url( url_str ) if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL return false; end local scheme, domain; scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL; if 'news:' == scheme then -- special case for newsgroups return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$'); end return is_url (scheme, domain); -- return true if value appears to be a valid URL end --[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >---------------------------- Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first non-space characters following the opening bracket appear to be a URL. The test will also find external wikilinks that use protocol-relative URLs. Also finds bare URLs. The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs. The tests that find 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 is_parameter_ext_wikilink (value) local scheme, domain; if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz] scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); elseif value:match ('%f[%[]%[//%S+.*%]') 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+') or value:match ('%s//%S+') then -- if protocol-relative bare URL: //yyyyy.zzz; authority indicator (//) must be be preceded nothing or by whitespace scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain else return false; -- didn't find anything that is obviously a URL end return is_url (scheme, domain); -- return true if value appears to be a valid URL end --[[--------------------------< I S _ A R C H I V E _ T O D A Y _ U R L >-------------------------------------- archive.today (and .ph, .is, .md, .li, .fo, .vn) are deprecated. See Wikipedia:Requests_for_comment/Archive.is_RFC_5 (Special:Permalink/1339352976) <val> is a string that may or may not be a url ]] local function is_archive_today_url (val) if is_parameter_ext_wikilink (val) then -- is <val> a url? local tld = val:match ('archive%.(%l+)'); -- get the tld return tld and cfg.archive_today_tlds_t[tld]; -- return true if <tld> is one of the archive.today tlds; nil else end end --[[--------------------------< H A S _ A R C H I V E _ T O D A Y _ U R L >------------------------------------ blank any parameter that holds one of the archive.today tlds (.today, .ph, .is, .md, .li, .fo, .vn) and also blank parameters that are dependent on the offending parameter. input <cite_args_t> is a table of all of this template's parameters This function modifies <cite_args_t> when |url= or its alias |URL= hold an archive.today url, this function sets the flag <url_was_archive_today> which is used later to suppress the missing url error message from {{citation}} when it has |website=<summat> or from the templates {{cite web}}, {{cite podcast}}, {{cite mailing list}} which all require a url. returns nothing ]] local function has_archive_today_url (cite_args_t) local unset_params_t = {}; -- to hold a sequence of parameters to unset from cite_args_t for p, v in pairs (cite_args_t) do -- look at each parameter in the template if is_archive_today_url (v:lower()) then -- if it has a parameter with an archive.today url table.insert (unset_params_t, p); -- add the url-holding parameter name to our list of parameters to unset (may or may not be a legitimate url parameter) if 'url' == p:lower() then -- if this parameter is |url= or |URL= url_was_archive_today = true; -- set a flag so that cite web / podcast / mailinglist don't emit a missing url error message end if cfg.dependencies_t[p] then -- if this url-holding parameter (<p>) has dependencies for _, dependent in ipairs (cfg.dependencies_t[p]) do -- loop through the url-holding parameter's dependency sequence table.insert (unset_params_t, dependent); -- add dependent parameter to the list to be unset end end end end if 0 < #unset_params_t then -- when there are parameters to unset if not is_preview_mode then -- when in preview mode do not suppress any parameters for _, unset_param in ipairs (unset_params_t) do -- loop through the sequence cite_args_t[unset_param] = nil; -- and unset the url-holding parameter and its dependent parameters to avoid parameter-requires-other-parameter errors end end utilities.set_message ('maint_deprecated_archive'); -- add a maintenance message end 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, error_list) 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 table.insert (error_list, utilities.wrap_style ('parameter', k)); end end end --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------ Escape sequences for content that will be used for URL descriptions ]] local function safe_for_url( str ) if str:match( "%[%[.-%]%]" ) ~= nil then utilities.set_message ('err_wikilink_in_url', {}); end return str:gsub( '[%[%]\n]', { ['['] = '&#91;', [']'] = '&#93;', ['\n'] = ' ' } ); end --[[--------------------------< E X T E R N A L _ L I N K >---------------------------------------------------- Format an external link with error checking ]] local function external_link (URL, label, source, access) local err_msg = ''; local domain; local path; local base_url; if not utilities.is_set (label) then label = URL; if utilities.is_set (source) then utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)}); else error (cfg.messages["bare_url_no_origin"]); -- programmer error; valid parameter name does not have matching meta-parameter end end if not check_url (URL) then utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); end domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path if path then -- if there is a path portion path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values URL = table.concat ({domain, path}); -- and reassemble end base_url = table.concat ({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL if utilities.is_set (access) then -- access level (subscription, registration, limited) base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon end return base_url; end --[[--------------------------< 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 the offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated parameters in the citation. added_deprecated_cat is a Boolean declared in page scope variables above ]] local function deprecated_parameter(name) if not added_deprecated_cat then added_deprecated_cat = true; -- note that we've added this category utilities.set_message ('err_deprecated_params', {name}); -- add error message end end --[=[-------------------------< K E R N _ Q U O T E S >-------------------------------------------------------- Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value. This function will positive kern either single or double quotes: "'Unkerned title with leading and trailing single quote marks'" " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example) Double single quotes (italic or bold wiki-markup) are not kerned. Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks. Call this function for chapter titles, for website titles, etc.; not for book titles. ]=] local function kern_quotes (str) local cap = ''; local wl_type, label, link; wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks str = utilities.substitute (cfg.presentation['kern-left'], str); str = utilities.substitute (cfg.presentation['kern-right'], str); elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks str = utilities.substitute (cfg.presentation['kern-left'], str); elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks str = utilities.substitute (cfg.presentation['kern-right'], str); end else -- plain text or [[L|D]]; text in label variable label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark) cap = mw.ustring.match (label, "^([\"\'][^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) if utilities.is_set (cap) then label = utilities.substitute (cfg.presentation['kern-left'], cap); end cap = mw.ustring.match (label, "^(.+[^\'][\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) if utilities.is_set (cap) then label = utilities.substitute (cfg.presentation['kern-right'], cap); end if 2 == wl_type then str = utilities.make_wikilink (link, label); -- reassemble the wikilink else str = label; end end return str; end --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- |script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped in italic markup. Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate RTL languages from the English left to right. |script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO 639-1 language code and a colon: |script-title=ja:*** *** (where * represents a Japanese character) Spaces between the two-character code and the colon and the colon and the first script character are allowed: |script-title=ja : *** *** |script-title=ja: *** *** |script-title=ja :*** *** Spaces preceding the prefix are allowed: |script-title = ja:*** *** The prefix is checked for validity. If it is a valid ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute is not added. At this time there is no error message for this condition. Supports |script-title=, |script-chapter=, |script-<periodical>= ]] local function format_script_value (script_value, script_param) local lang=''; -- initialize to empty string local name; if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script if not utilities.is_set (lang) then utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing title part']}); -- prefix without 'title'; add error message return ''; -- script_value was just the prefix so return empty string end -- if we get this far we have prefix and script name = cfg.lang_tag_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code? script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script -- is prefix one of these language codes? if utilities.in_array (lang, cfg.script_lang_codes) then utilities.add_prop_cat ('script', {name, lang}) else utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['unknown language code']}); -- unknown script-language; add error message end lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute else utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['invalid language code']}); -- invalid language code; add error message lang = ''; -- invalid so set lang to empty string end else utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing prefix']}); -- no language code prefix; add error message end script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL return script_value; end --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been wrapped in <bdi> tags. ]] local function script_concatenate (title, script, script_param) if utilities.is_set (script) then script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error if utilities.is_set (script) then title = title .. ' ' .. script; -- concatenate title and script title end end return title; end --[[--------------------------< W R A P _ M S G >-------------------------------------------------------------- Applies additional message text to various parameter values. Supplied string is wrapped using a message_list configuration taking one argument. Supports lower case text for {{citation}} templates. Additional text taken from citation_config.messages - the reason this function is similar to but separate from wrap_style(). ]] local function wrap_msg (key, str, lower) if not utilities.is_set ( str ) then return ""; end if true == lower then local msg; msg = cfg.messages[key]:lower(); -- set the message to lower case before return utilities.substitute ( msg, str ); -- including template text else return utilities.substitute ( cfg.messages[key], str ); end end --[[----------------< W I K I S O U R C E _ U R L _ M A K E >------------------- Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate label; nil else. str is the value assigned to |chapter= (or aliases) or |title= or |title-link= ]] local function wikisource_url_make (str) local wl_type, D, L; local ws_url, ws_label; local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'}); wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink) if 0 == wl_type then -- not a wikilink; might be from |title-link= str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace if utilities.is_set (str) then ws_url = table.concat ({ -- build a Wikisource URL wikisource_prefix, -- prefix str, -- article title }); ws_label = str; -- label for the URL end elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]] str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace if utilities.is_set (str) then ws_url = table.concat ({ -- build a Wikisource URL wikisource_prefix, -- prefix str, -- article title }); ws_label = str; -- label for the URL end elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]]) str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace if utilities.is_set (str) then ws_label = D; -- get ws article name from display portion of interwiki link ws_url = table.concat ({ -- build a Wikisource URL wikisource_prefix, -- prefix str, -- article title without namespace from link portion of wikilink }); end end if ws_url then ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker end return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil end --[[----------------< F O R M A T _ P E R I O D I C A L >----------------------- Format the three periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta-parameter. ]] local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) if not utilities.is_set (periodical) then periodical = ''; -- to be safe for concatenation else periodical = utilities.wrap_style ('italic-title', periodical); -- style end periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped if utilities.is_set (trans_periodical) then trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical); if utilities.is_set (periodical) then periodical = periodical .. ' ' .. trans_periodical; else -- here when trans-periodical without periodical or script-periodical periodical = trans_periodical; utilities.set_message ('err_trans_missing_title', {'periodical'}); end end return periodical; end --[[------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------- Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single chapter meta- parameter (chapter_url_source used for error messages). ]] local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access) local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link if ws_url then ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters chapter = ws_label; end if not utilities.is_set (chapter) then chapter = ''; -- to be safe for concatenation else if false == no_quotes then chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks chapter = utilities.wrap_style ('quoted-title', chapter); end end chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped if utilities.is_set (chapter_url) then chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate elseif ws_url then chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this? chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter}); end if utilities.is_set (trans_chapter) then trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter); if utilities.is_set (chapter) then chapter = chapter .. ' ' .. trans_chapter; else -- here when trans_chapter without chapter or script-chapter chapter = trans_chapter; chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param> utilities.set_message ('err_trans_missing_title', {chapter_source}); end end return chapter; end --[[----------------< H A S _ I N V I S I B L E _ C H A R S >------------------- This function searches a parameter's value for non-printable or invisible characters. The search stops at the 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, math, pre, ref) and identifies them with a slightly different error message. See also coins_cleanup(). Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the parameter value. ]] local function has_invisible_chars (param, v) local position = ''; -- position of invisible char or starting position of stripmarker local capture; -- used by stripmarker detection to hold name of the stripmarker local stripmarker; -- boolean set true when a stripmarker is found capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true if capture == v then -- if same there are no Unicode characters return; end for _, invisible_char in ipairs (cfg.invisible_chars) do local char_name = invisible_char[1]; -- the character or group name local pattern = invisible_char[2]; -- the pattern used to find it position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts position = nil; -- unset position elseif cfg.emoji_t[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}? position = nil; -- unset position end end if position then if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) ('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters stripmarker = true; -- set a flag elseif true == stripmarker and cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset else local err_msg; if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then err_msg = utilities.substitute (cfg.messages.invisible_1, {capture, char_name}); -- <capture> here is stripmarker name else err_msg = utilities.substitute (cfg.messages.invisible_2, char_name); end utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}); -- add error message return; -- and done with this parameter end end end 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 names can be transparently aliased to single internal variable. ]] local function argument_wrapper ( args ) local origin = {}; return setmetatable({ ORIGIN = function ( self, k ) local dummy = self[k]; -- force the variable to be loaded. return origin[k]; end }, { __index = function ( tbl, k ) if origin[k] ~= nil then return nil; end local args, list, v = args, cfg.aliases[k]; if type( list ) == 'table' then v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' ); if origin[k] == nil then origin[k] = ''; -- Empty string, not nil end elseif list ~= nil then v, origin[k] = args[list], list; else -- maybe let through instead of raising an error? -- v, origin[k] = args[k], k; error( cfg.messages['unknown_argument_map'] .. ': ' .. k); end -- Empty strings, not nil; if v == nil then v = ''; origin[k] = ''; end tbl = rawset( tbl, k, v ); return v; end, }); end --[[--------------------------< N O W R A P _ D A T E >------------------------- When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY DOES NOT yet support MMMM YYYY or any of the date ranges. ]] local function nowrap_date (date) local cap = ''; local cap2 = ''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = utilities.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 = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2}); end return date; end --[[--------------------------< S E T _ T I T L E T Y P E >--------------------- This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults. Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none). ]] local function set_titletype (cite_class, title_type) if utilities.is_set (title_type) then if 'none' == cfg.keywords_xlate[title_type] then title_type = ''; -- if |type=none then type parameter not displayed end return title_type; -- if |type= has been set to any other value use that value end return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation end --[[--------------------------< S A F E _ J O I N >----------------------------- Joins a sequence of strings together while checking for duplicate separation characters. ]] local function safe_join( tbl, duplicate_char ) local f = {}; -- create a function table appropriate to type of 'duplicate character' if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions f.gsub = string.gsub f.match = string.match f.sub = string.sub else -- for multi-byte characters use the ustring library functions f.gsub = mw.ustring.gsub f.match = mw.ustring.match f.sub = mw.ustring.sub end local str = ''; -- the output string local comp = ''; -- what does 'comp' mean? local end_chr = ''; local trim; for _, value in ipairs( tbl ) do if value == nil then value = ''; end if str == '' then -- if output string is empty str = value; -- assign value to it (first time through the loop) elseif value ~= '' then if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup. comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string) else comp = value; end -- typically duplicate_char is sepc if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character? -- Because individual string segments often (always?) begin with terminal punct for the -- preceding segment: 'First element' .. 'sepc next element' .. etc.? trim = false; end_chr = f.sub(str, -1, -1); -- get the last character of the output string -- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff? if end_chr == duplicate_char then -- if same as separator str = f.sub(str, 1, -2); -- remove it elseif end_chr == "'" then -- if it might be wiki-markup if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' trim = true; -- why? why do this and next differently from previous? elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' trim = true; -- same question end elseif end_chr == "]" then -- if it might be wiki-markup if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink trim = true; elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link trim = true; elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link trim = true; elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. trim = true; end elseif end_chr == " " then -- if last char of output string is a space if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> str = f.sub(str, 1, -3); -- remove them both end end if trim then if value ~= comp then -- value does not equal comp when value contains HTML markup local dup2 = duplicate_char; if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup else value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character end end end str = str .. value; -- add it to the output string end end return str; end --[[--------------------------< I S _ S U F F I X >----------------------------- returns true if suffix is properly formed Jr, Sr, or ordinal in the range 1–9. Puncutation not allowed. ]] local function is_suffix (suffix) if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '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 >------------------- For Vancouver style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name uses characters that contain diacritical marks, those characters are to be converted to the corresponding Latin character. When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters. The module doesn't do this so editors may/must. This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F |lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods This original test: if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then was written outside of the code editor and pasted here because 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 necessary to 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, suffix, position) if not suffix then if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix first = first:match ('(.-)[,%s]+'); -- get name/initials suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix end end if utilities.is_set (suffix) then if not is_suffix (suffix) then add_vanc_error (cfg.err_msg_supl.suffix, position); return false; -- not a name with an appropriate suffix end end if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191%-%s%']*$") 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\225\184\128-\225\187\191%-%s%'%.]*$") then add_vanc_error (cfg.err_msg_supl['non-Latin char'], position); return false; -- not a string of Latin characters; Vancouver requires Romanization end; return true; end --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ Attempts to convert names to initials in support of |name-list-style=vanc. Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. This function uses ustring functions because firstname initials may be any of the Unicode Latin characters accepted by is_good_vanc_name (). ]] local function reduce_to_initials (first, position) if first:find (',', 1, true) then return first; -- commas not allowed; abandon end local name, suffix = mw.ustring.match (first, "^(%u+) ([%dJS][%drndth]+)$"); if not name then -- if not initials and a suffix name = mw.ustring.match (first, "^(%u+)$"); -- is it just initials? end if name then -- if first is initials with or without suffix if 3 > mw.ustring.len (name) then -- if one or two initials if suffix then -- if there is a suffix if is_suffix (suffix) then -- is it legitimate? return first; -- one or two initials and a valid suffix so nothing to do else add_vanc_error (cfg.err_msg_supl.suffix, position); -- one or two initials with invalid suffix so error message return first; -- and return first unmolested end else return first; -- one or two initials without suffix; nothing to do end end end -- if here then name has 3 or more uppercase letters so treat them as a word local initials_t, names_t = {}, {}; -- tables to hold name parts and initials local i = 1; -- counter for number of initials names_t = mw.text.split (first, '[%s%-]+'); -- split into a sequence of names and possible suffix while names_t[i] do -- loop through the sequence if 1 < i and names_t[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot) names_t[i] = names_t[i]:gsub ('%.', ''); -- remove terminal dot if present if is_suffix (names_t[i]) then -- if a legitimate suffix table.insert (initials_t, ' ' .. names_t[i]); -- add a separator space, insert at end of initials sequence 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_t, mw.ustring.sub (names_t[i], 1, 1)); -- insert the initial at end of initials sequence end i = i + 1; -- bump the counter end return table.concat (initials_t); -- Vancouver format does not include spaces. end --[[--------------------------< I N T E R W I K I _ P R E F I X E N _ G E T >---------------------------------- extract interwiki prefixen from <value>. Returns two one or two values: false – no prefixen nil – prefix exists but not recognized project prefix, language prefix – when value has either of: :<project>:<language>:<article> :<language>:<project>:<article> project prefix, nil – when <value> has only a known single-letter prefix nil, language prefix – when <value> has only a known language prefix accepts single-letter project prefixen: 'd' (wikidata), 's' (wikisource), and 'w' (wikipedia) prefixes; at this writing, the other single-letter prefixen (b (wikibook), c (commons), m (meta), n (wikinews), q (wikiquote), and v (wikiversity)) are not supported. ]] local function interwiki_prefixen_get (value, is_link) if not value:find (':%l+:') then -- if no prefix return false; -- abandon; boolean here to distinguish from nil fail returns later end local prefix_patterns_linked_t = { -- sequence of valid interwiki and inter project prefixen '^%[%[:([dsw]):(%l%l+):', -- wikilinked; project and language prefixes '^%[%[:(%l%l+):([dsw]):', -- wikilinked; language and project prefixes '^%[%[:([dsw]):', -- wikilinked; project prefix '^%[%[:(%l%l+):', -- wikilinked; language prefix } local prefix_patterns_unlinked_t = { -- sequence of valid interwiki and inter project prefixen '^:([dsw]):(%l%l+):', -- project and language prefixes '^:(%l%l+):([dsw]):', -- language and project prefixes '^:([dsw]):', -- project prefix '^:(%l%l+):', -- language prefix } local cap1, cap2; for _, pattern in ipairs ((is_link and prefix_patterns_linked_t) or prefix_patterns_unlinked_t) do cap1, cap2 = value:match (pattern); if cap1 then break; -- found a match so stop looking end end if cap1 and cap2 then -- when both then :project:language: or :language:project: (both forms allowed) if 1 == #cap1 then -- length == 1 then :project:language: if cfg.inter_wiki_map[cap2] then -- is language prefix in the interwiki map? return cap1, cap2; -- return interwiki project and interwiki language end else -- here when :language:project: if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map? return cap2, cap1; -- return interwiki project and interwiki language end end return nil; -- unknown interwiki language elseif not (cap1 or cap2) then -- both are nil? return nil; -- we got something that looks like a project prefix but isn't; return fail elseif 1 == #cap1 then -- here when one capture return cap1, nil; -- length is 1 so return project, nil language else -- here when one capture and its length it more than 1 if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map? return nil, cap1; -- return nil project, language end end end --[[--------------------------< L I S T _ P E O P L E >-------------------------- Formats a list of people (authors, contributors, editors, interviewers, translators) names in the list will be linked when |<name>-link= has a value |<name>-mask- does NOT have a value; masked names are presumed to have been rendered previously so should have been linked there when |<name>-mask=0, the associated name is not rendered ]] local function list_people (control, people, etal) local sep; local namesep; local format = control.format; local maximum = control.maximum; local name_list = {}; if 'vanc' == format then -- Vancouver-like name styling? sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space else sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space> end if sep:sub (-1, -1) ~= " " then sep = sep .. " " end if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names for i, person in ipairs (people) do if utilities.is_set (person.last) then local mask = person.mask; local one; local sep_one = sep; if utilities.is_set (maximum) and i > maximum then etal = true; break; end if mask then local n = tonumber (mask); -- convert to a number if it can be converted; nil else if n then one = 0 ~= n and string.rep("&mdash;", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil else one = mask; -- replace name with mask text (must include name-list separator) sep_one = " "; -- modify name-list separator end else one = person.last; -- get surname local first = person.first -- get given name if utilities.is_set (first) then if ("vanc" == format) then -- if Vancouver format one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person.corporate and is_good_vanc_name (one, first, nil, i) then -- and name is all Latin characters; corporate authors not tested first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials end end one = one .. namesep .. first; end end if utilities.is_set (person.link) then one = utilities.make_wikilink (person.link, one); -- link author/editor end if one then -- if <one> has a value (name, mdash replacement, or mask text replacement) local proj, tag = interwiki_prefixen_get (one, true); -- get the interwiki prefixen if present if 'w' == proj and ('Wikipedia' == mw.site.namespaces.Project['name']) then proj = nil; -- for stuff like :w:de:<article>, :w is unnecessary TODO: maint cat? end if proj then local proj_name = ({['d'] = cfg.messages.wikidata, ['s'] = cfg.messages.wikisource, ['w'] = cfg.messages.wikipedia})[proj]; -- :w (wikipedia) for linking from a non-wikipedia project if proj_name then one = one .. utilities.wrap_style ('interproj', proj_name); -- add resized leading space, brackets, static text, language name utilities.add_prop_cat ('interproj-linked-name', proj); -- categorize it; <proj> is sort key tag = nil; -- unset; don't do both project and language end end if tag == cfg.this_wiki_code then tag = nil; -- stuff like :en:<article> at en.wiki is pointless TODO: maint cat? end if tag then local lang = cfg.lang_tag_remap[tag] or cfg.mw_languages_by_tag_t[tag]; if lang then -- error messaging done in extract_names() where we know parameter names one = one .. utilities.wrap_style ('interwiki', lang); -- add resized leading space, brackets, static text, language name utilities.add_prop_cat ('interwiki-linked-name', tag); -- categorize it; <tag> is sort key end end table.insert (name_list, one); -- add it to the list of names table.insert (name_list, sep_one); -- add the proper name-list separator end end end local count = #name_list / 2; -- (number of names + number of separators) divided by 2 if 0 < count then if 1 < count and not etal then if 'amp' == format then name_list[#name_list-2] = " & "; -- replace last separator with ampersand text elseif 'and' == format then if 2 == count then name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text else name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text end end end name_list[#name_list] = nil; -- erase the last separator end local result = table.concat (name_list); -- construct list if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list result = result .. sep .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al. end return result, count; -- return name-list string and count of number of names (count used for editor names only) end --[[--------------------< M A K E _ C I T E R E F _ I D >----------------------- Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string. namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year. ]] local function make_citeref_id (namelist, year) local names={}; -- a table for the one to four names and year for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names names[i] = v.last if i == 4 then break end -- if four then done end table.insert (names, year); -- add the year at the end local id = table.concat(names); -- concatenate names and year for CITEREF id if utilities.is_set (id) then -- if concatenation is not an empty string return "CITEREF" .. id; -- add the CITEREF portion else return ''; -- return an empty string; no reason to include CITEREF id in this citation end end --[[--------------------------< C I T E _ C L A S S _A T T R I B U T E _M A K E >------------------------------ construct <cite> tag class attribute for this citation. <cite_class> – config.CitationClass from calling template <mode> – value from |mode= parameter ]] local function cite_class_attribute_make (cite_class, mode) local class_t = {}; table.insert (class_t, 'citation'); -- required for blue highlight if 'citation' ~= cite_class then table.insert (class_t, cite_class); -- identify this template for user css table.insert (class_t, utilities.is_set (mode) and mode or 'cs1'); -- identify the citation style for user css or javascript else table.insert (class_t, utilities.is_set (mode) and mode or 'cs2'); -- identify the citation style for user css or javascript end for _, prop_key in ipairs (z.prop_keys_t) do table.insert (class_t, prop_key); -- identify various properties for user css or javascript end return table.concat (class_t, ' '); -- make a big string and done end --[[---------------------< N A M E _ H A S _ E T A L >-------------------------- Evaluates the content of name parameters (author, editor, etc.) 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 its previous state because it may have been set by previous passes through this function or by the associated |display-<names>=etal parameter ]] local function name_has_etal (name, etal, nocat, param) if utilities.is_set (name) then -- name can be nil in which case just return local patterns = cfg.et_al_patterns; -- get patterns from configuration for _, pattern in ipairs (patterns) do -- loop through all of the patterns if name:match (pattern) then -- if this 'et al' pattern is found in name name = name:gsub (pattern, ''); -- remove the offending text etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) if not nocat then -- no categorization for |vauthors= utilities.set_message ('err_etal', {param}); -- and set an error if not added end end end end return name, etal; end --[[---------------------< N A M E _ I S _ N U M E R I C >---------------------- Add an error message and category when <name> parameter value does not contain letters. Add a maintenance category when <name> parameter value has numeric characters mixed with characters that are not numeric characters; could be letters and/or punctuation characters. This function will only emit one error and one maint message for the current template. Does not emit both error and maint messages/categories for the same parameter value. returns nothing ]] local function name_is_numeric (name, name_alias, list_name) local patterns = { '^%D+%d', -- <name> must have digits preceded by other characters '^%D*%d+%D+', -- <name> must have digits followed by other characters } if not added_numeric_name_errs and mw.ustring.match (name, '^[%A]+$') then -- if we have not already set an error message and <name> does not have any alpha characters utilities.set_message ('err_numeric_names', name_alias); -- add an error message added_numeric_name_errs = true; -- set the flag so we emit only one error message return; -- when here no point in further testing; abandon end if not added_numeric_name_maint then -- if we have already set a maint message for _, pattern in ipairs (patterns) do -- spin through list of patterns if mw.ustring.match (name, pattern) then -- digits preceded or followed by anything but digits; %D+ includes punctuation utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template added_numeric_name_maint = true; -- set the flag so we emit only one maint message return; -- when here no point in further testing; abandon end end end end --[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------ Evaluates the content of last/surname (authors etc.) parameters for multiple names. Multiple names are indicated if there is more than one comma or any "unescaped" semicolons. Escaped semicolons are ones used as part of selected HTML entities. If the condition is met, the function adds the multiple name maintenance category. Same test for first except that commas should not appear in given names (MOS:JR says that the generational suffix does not take a separator character). Titles, degrees, postnominals, affiliations, all normally comma separated don't belong in a citation. <name> – name parameter value <list_name> – AuthorList, EditorList, etc <limit> – number of allowed commas; 1 (default) for surnames; 0 for given names returns nothing ]] local function name_has_mult_names (name, list_name, limit) local _, commas, semicolons, nbsps; limit = limit and limit or 1; if utilities.is_set (name) then _, commas = name:gsub (',', ''); -- count the number of commas _, semicolons = name:gsub (';', ''); -- count the number of semicolons -- nbsps probably should be its own separate count rather than merged in -- some way with semicolons because Lua patterns do not support the -- grouping operator that regex does, which means there is no way to add -- more entities to escape except by adding more counts with the new -- entities _, nbsps = name:gsub ('&nbsp;',''); -- count nbsps -- There is exactly 1 semicolon per &nbsp; entity, so subtract nbsps -- from semicolons to 'escape' them. If additional entities are added, -- they also can be subtracted. if limit < commas or 0 < (semicolons - nbsps) then utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message end end end --[=[-------------------------< I S _ G E N E R I C >---------------------------------------------------------- Compares values assigned to various parameters according to the string provided as <item> in the function call. <item> can have on of two values: 'generic_names' – for name-holding parameters: |last=, |first=, |editor-last=, etc 'generic_titles' – for |title= There are two types of generic tests. The 'accept' tests look for a pattern that should not be rejected by the 'reject' test. For example, |author=[[John Smith (author)|Smith, John]] would be rejected by the 'author' reject test. But piped wikilinks with 'author' disambiguation should not be rejected so the 'accept' test prevents that from happening. Accept tests are always performed before reject tests. Each of the 'accept' and 'reject' sequence tables hold tables for en.wiki (['en']) and local.wiki (['local']) that each can hold a test sequence table The sequence table holds, at index [1], a test pattern, and, at index [2], a boolean control value. The control value tells string.find() or mw.ustring.find() to do plain-text search (true) or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so that we don't run out of processing time on very large articles. Returns true when a reject test finds the pattern or string false when an accept test finds the pattern or string nil else ]=] local function is_generic (item, value, wiki) local test_val; local str_lower = { -- use string.lower() for en.wiki (['en']) and use mw.ustring.lower() or local.wiki (['local']) ['en'] = string.lower, ['local'] = mw.ustring.lower, } local str_find = { -- use string.find() for en.wiki (['en']) and use mw.ustring.find() or local.wiki (['local']) ['en'] = string.find, ['local'] = mw.ustring.find, } local function test (val, test_t, wiki) -- local function to do the testing; <wiki> selects lower() and find() functions val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched end local test_types_t = {'accept', 'reject'}; -- test accept patterns first, then reject patterns local wikis_t = {'en', 'local'}; -- do tests for each of these keys; en.wiki first, local.wiki second for _, test_type in ipairs (test_types_t) do -- for each test type for _, generic_value in pairs (cfg.special_case_translation[item][test_type]) do -- spin through the list of generic value fragments to accept or reject for _, wiki in ipairs (wikis_t) do if generic_value[wiki] then if test (value, generic_value[wiki], wiki) then -- go do the test return ('reject' == test_type); -- param value rejected, return true; false else end end end end end end --[[--------------------------< N A M E _ I S _ G E N E R I C >------------------------------------------------ calls is_generic() to determine if <name> is a 'generic name' listed in cfg.generic_names; <name_alias> is the parameter name used in error messaging ]] local function name_is_generic (name, name_alias) if not added_generic_name_errs and is_generic ('generic_names', name) then utilities.set_message ('err_generic_name', name_alias); -- set an error message added_generic_name_errs = true; end 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, last_alias, first_alias) local accept_name; if utilities.is_set (last) then last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last> if not accept_name then -- <last> not wrapped in accept-as-written markup name_has_mult_names (last, list_name); -- check for multiple names in the parameter name_is_numeric (last, last_alias, list_name); -- check for names that have no letters or are a mix of digits and other characters name_is_generic (last, last_alias); -- check for names found in the generic names list end end if utilities.is_set (first) then first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> if not accept_name then -- <first> not wrapped in accept-as-written markup name_has_mult_names (first, list_name, 0); -- check for multiple names in the parameter; 0 is number of allowed commas in a given name name_is_numeric (first, first_alias, list_name); -- check for names that have no letters or are a mix of digits and other characters name_is_generic (first, first_alias); -- check for names found in the generic names list end local wl_type, D = utilities.is_wikilink (first); if 0 ~= wl_type then first = D; utilities.set_message ('err_bad_paramlink', first_alias); end end return last, first; -- done end --[[----------------------< E X T R A C T _ N A M E S >------------------------- Gets name list from the input arguments Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the search is done. This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3= are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the template's metadata. When this occurs, an error is emitted. ]] local function extract_names(args, list_name) local names = {}; -- table of names local last; -- individual name components local first; local link; local mask; local i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; -- 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 last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging while true do last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1 first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i ); link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ); mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i ); if last then -- error check |lastn= alias for unknown interwiki link prefix; done here because this is where we have the parameter name local project, language = interwiki_prefixen_get (last, true); -- true because we expect interwiki links in |lastn= to be wikilinked if nil == project and nil == language then -- when both are nil utilities.set_message ('err_bad_paramlink', last_alias); -- not known, emit an error message -- TODO: err_bad_interwiki? last = utilities.remove_wiki_link (last); -- remove wikilink markup; show display value only end end if link then -- error check |linkn= alias for unknown interwiki link prefix local project, language = interwiki_prefixen_get (link, false); -- false because wiki links in |author-linkn= is an error if nil == project and nil == language then -- when both are nil utilities.set_message ('err_bad_paramlink', link_alias); -- not known, emit an error message -- TODO: err_bad_interwiki? link = nil; -- unset so we don't link link_alias = nil; end end last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al. first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al. last, first = name_checks (last, first, list_name, last_alias, first_alias); -- multiple names, extraneous annotation, etc. checks if first and not last then -- if there is a firstn without a matching lastn local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias utilities.set_message ('err_first_missing_last', { first_alias, -- param name of alias missing its mate first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form }); -- 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 local result; link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup if first then link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup end names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing utilities.set_message ('err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}); -- add this error message end count = 0; -- reset the counter, we're looking for two consecutive missing names end i = i + 1; -- point to next args location end return names, etal; -- all done, return our list of names and the etal flag end --[[--------------------------< N A M E _ T A G _ G E T >------------------------------------------------------ attempt to decode |language=<lang_param> and return language name and matching tag; nil else. This function looks for: <lang_param> as a tag in cfg.lang_tag_remap{} <lang_param> as a name in cfg.lang_name_remap{} <lang_param> as a name in cfg.mw_languages_by_name_t <lang_param> as a tag in cfg.mw_languages_by_tag_t when those fail, presume that <lang_param> is an IETF-like tag that MediaWiki does not recognize. Strip all script, region, variant, whatever subtags from <lang_param> to leave just a two or three character language tag and look for the new <lang_param> in cfg.mw_languages_by_tag_t{} on success, returns name (in properly capitalized form) and matching tag (in lowercase); on failure returns nil ]] local function name_tag_get (lang_param) local lang_param_lc = mw.ustring.lower (lang_param); -- use lowercase as an index into the various tables local name; local tag; name = cfg.lang_tag_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name if name then -- when <name>, <lang_param> is a tag for a remapped language name if cfg.lang_name_remap[name:lower()][2] ~= lang_param_lc then utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added return name, cfg.lang_name_remap[name:lower()][2]; -- so return name and tag from lang_name_remap[name]; special case to xlate sr-ec and sr-el to sr-cyrl and sr-latn end return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc> end tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags name = cfg.lang_tag_remap[tag]; -- attempt to get remapped language name with language subtag only if name then -- when <name>, <tag> is a tag for a remapped language name return name, tag; -- so return <name> from remap and <tag> end if cfg.lang_name_remap[lang_param_lc] then -- not a remapped tag, assume <lang_param_lc> is a name; attempt to get remapped language tag return cfg.lang_name_remap[lang_param_lc][1], cfg.lang_name_remap[lang_param_lc][2]; -- for this <lang_param_lc>, return a (possibly) new name and appropriate tag end name = cfg.mw_languages_by_tag_t[lang_param_lc]; -- assume that <lang_param_lc> is a tag; attempt to get its matching language name if name then return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name> end tag = cfg.mw_languages_by_name_t[lang_param_lc]; -- assume that <lang_param_lc> is a language name; attempt to get its matching tag if tag then return cfg.mw_languages_by_tag_t[tag], tag; -- <lang_param_lc> is a name so return the name from the table and <tag> end tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- is <lang_param_lc> an IETF-like tag that MediaWiki doesn't recognize? <tag> gets the language subtag; nil else if tag then name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag> if name then return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag end end end --[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------ Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki, use the returned name; if not, then use the value that was provided with the language parameter. When |language= contains a recognized language (either code or name), the page is assigned to the category for that code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assigned to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character equivalents of two-character codes: code 'ar' is recognized but code 'ara' is not. 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 with optional space characters. ]] local function language_parameter (lang) local tag; -- some form of IETF-like language tag; language subtag with optional region, sript, vatiant, etc subtags local lang_subtag; -- ve populates |language= with mostly unecessary region subtags the MediaWiki does not recognize; this is the base language subtag local name; -- the language name local language_list = {}; -- table of language names to be rendered local names_t = {}; -- table made from the value assigned to |language= local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name names_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list for _, lang in ipairs (names_t) do -- reuse lang here because we don't yet know if lang is a language name or a language tag name, tag = name_tag_get (lang); -- attempt to get name/tag pair for <lang>; <name> has proper capitalization; <tag> is lowercase if utilities.is_set (tag) then lang_subtag = tag:gsub ('^(%a%a%a?)%-.*', '%1'); -- for categorization, strip any IETF-like tags from language tag if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language if 2 == lang_subtag:len() then -- and is a two-character tag utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization else -- or is a recognized language (but has a three-character tag) utilities.add_prop_cat ('foreign-lang-source-2', {lang_subtag}, lang_subtag); -- categorize it differently TODO: support multiple three-character tag categories per cs1|2 template? end elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled utilities.add_prop_cat ('local-lang-source', {name, lang_subtag}); -- categorize it end else name = lang; -- return whatever <lang> has so that we show something utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added end table.insert (language_list, name); name = ''; -- so we can reuse it end name = utilities.make_sep_list (#language_list, language_list); if (1 == #language_list) and (lang_subtag == cfg.this_wiki_code) then -- when only one language, find lang name in this wiki lang name; for |language=en-us, 'English' in 'American English' 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 --[[-----------------------< S E T _ C S _ S T Y L E >-------------------------- Gets the default CS style configuration for the given mode. Returns default separator and either postscript as passed in or the default. In CS1, the default postscript and separator are '.'. In CS2, the default postscript is the empty string and the default separator is ','. ]] local function set_cs_style (postscript, mode) if utilities.is_set(postscript) then -- emit a maintenance message if user postscript is the default cs1 postscript -- we catch the opposite case for cs2 in set_style if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then utilities.set_message ('maint_postscript'); end else postscript = cfg.presentation['ps_' .. mode]; end return cfg.presentation['sep_' .. mode], postscript; end --[[--------------------------< S E T _ S T Y L E >----------------------------- Sets the separator and postscript styles. Checks the |mode= first and the #invoke CitationClass second. Removes the postscript if postscript == none. ]] local function set_style (mode, postscript, cite_class) local sep; if 'cs2' == mode then sep, postscript = set_cs_style (postscript, 'cs2'); elseif 'cs1' == mode then sep, postscript = set_cs_style (postscript, 'cs1'); elseif 'citation' == cite_class then sep, postscript = set_cs_style (postscript, 'cs2'); else sep, postscript = set_cs_style (postscript, 'cs1'); end if cfg.keywords_xlate[postscript:lower()] == 'none' then -- emit a maintenance message if user postscript is the default cs2 postscript -- we catch the opposite case for cs1 in set_cs_style if 'cs2' == mode or ('cs1' ~= mode and 'citation' == cite_class) then -- {{citation |title=Title |mode=cs1 |postscript=none}} should not emit maint message utilities.set_message ('maint_postscript'); end postscript = ''; end return sep, postscript 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. returns true if file extension is one of the recognized extensions, else false ]=] local function is_pdf (url) return url:match ('%.pdf$') or url:match ('%.PDF$') or url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or url:match ('%.PDF&#035') or url:match ('%.pdf&#035'); end --[[--------------------------< S T Y L E _ F O R M A T >----------------------- Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does not have a matching URL parameter. If the format parameter is not set and the URL contains a file extension that is recognized as a PDF document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with the appropriate styling. ]] local function style_format (format, url, fmt_param, url_param) if utilities.is_set (format) then format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize if not utilities.is_set (url) then utilities.set_message ('err_format_missing_url', {fmt_param, url_param}); -- add an error message end elseif is_pdf (url) then -- format is not set so if URL is a PDF file then format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF else format = ''; -- empty string for concatenation end return format; end --[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------ Returns a number that defines the number of names displayed for author and editor name lists and a Boolean flag to indicate when et al. should be appended to the name list. When the value assigned to |display-xxxxors= 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-xxxxors= 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'], etc; a number or some flavor of etal count: #a or #e list_name: 'authors' or 'editors' etal: author_etal or editor_etal This function sets an error message when |display-xxxxors= value greater than or equal to number of names but not when <max> comes from {{cs1 config}} global settings. When using global settings, <param> is set to the keyword 'cs1 config' which is used to supress the normal error. Error is suppressed because it is to be expected that some citations in an article will have the same or fewer names that the limit specified in {{cs1 config}}. ]] local function get_display_names (max, count, list_name, etal, param) if utilities.is_set (max) then if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; -- number of authors + 1 so display all author name plus et al. etal = true; -- overrides value set by extract_names() elseif max:match ('^%d+$') then -- if is a string of numbers max = tonumber (max); -- make it a number if (max >= count) and ('cs1 config' ~= param) then -- error when local |display-xxxxors= value greater than or equal to number of names; not an error when using global setting utilities.set_message ('err_disp_name', {param, max}); -- add error message max = nil; end else -- not a valid keyword or number utilities.set_message ('err_disp_name', {param, max}); -- add error message max = nil; -- unset; as if |display-xxxxors= had not been set end 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 error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be some form of p. or pp. abbreviation in the first characters of the parameter content. check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value: good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px where x and X are letters and # is a digit bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG ]] local function extra_text_in_page_check (val, name) if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns if val:match (pattern) then -- when a match, error so utilities.set_message ('err_extra_text_pages', name); -- add error message return; -- and done end end end end --[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------ Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator. Applies to both; this function looks for issue text in both |issue= and |volume= and looks for volume-like text in |voluem= and |issue=. For |volume=: 'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so are allowed. For |issue=: 'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the parameter content (all case insensitive); numero styling: 'n°' with degree sign U+00B0, and № precomposed numero sign U+2116. Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module. <val> is |volume= or |issue= parameter value <name> is |volume= or |issue= parameter name for error message <selector> is 'v' for |volume=, 'i' for |issue= sets error message on failure; returns nothing ]] local function extra_text_in_vol_iss_check (val, name, selector) if not utilities.is_set (val) then return; end local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue'; local accept_val; val, accept_val = utilities.has_accept_as_written (val); --if accept_val then -- if uncomment this, |volume=((vol. 1)) suppresses error -- return; --end --val = mw.text.unstripNoWiki (val); -- if uncomment this, |volume=<nowiki>vol. 1</nowiki> shows error val = val:lower(); -- force parameter value to lower case for _, pattern in ipairs (cfg.vol_iss_pg_patterns.vi_patterns_t) do -- spin through the sequence table of patterns if val:match (pattern) then -- when a match, error so utilities.set_message (handler, name); -- add error message return; -- and done end end end --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- split apart a |vauthors= 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 parentheses were included in the rendered citation and in the metadata. Individual author names may be wikilinked |vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.)) ]=] local function get_v_name_table (vparam, output_table, output_link_table) local _, accept = utilities.has_accept_as_written (vparam); if accept then utilities.add_prop_cat ('vanc-accept'); -- add properties category end local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas local wl_type, label, link; -- wl_type not used here; just a placeholder local i = 1; while name_table[i] do if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses local name = name_table[i]; i = i + 1; -- bump indexer to next segment while name_table[i] do name = name .. ', ' .. name_table[i]; -- concatenate with previous segments if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses 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 table.insert (output_link_table, ''); -- no wikilink else wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] table.insert (output_table, label); -- add this name if 1 == wl_type then table.insert (output_link_table, label); -- simple wikilink [[D]] else table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string end 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 parentheses ((corporate name)) to suppress the format tests. Supports generational suffixes Jr, 2nd, 3rd, 4th–6th. This function sets the Vancouver error when a required 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 v_link_table = {}; -- when name is wikilinked, targets go in this table local etal = false; -- return value set to true when we find some form of et al. vauthors parameter local last, first, link, mask, suffix; local corporate = false; vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas for i, v_name in ipairs(v_name_table) do first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor local accept_name; v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name> if accept_name then last = v_name; 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 (cfg.err_msg_supl.punctuation, i); 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 initials or generational suffix if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters suffix = first; -- not initials so assume that whatever we got is a generational suffix first = table.remove(lastfirstTable); -- get what should be the initials from the table end last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix if not utilities.is_set (last) then first = ''; -- unset last = v_name; -- last empty because something wrong with first add_vanc_error (cfg.err_msg_supl.name, i); end if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing end if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test add_vanc_error (cfg.err_msg_supl.initials, i); -- matches a space between two initials end else last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end if utilities.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 (cfg.err_msg_supl.initials, i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials end is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit if utilities.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, '', nil, i); end end link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i]; mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_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 |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; |editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn) 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 as appropriate. ]] local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) local lastfirst = false; if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ... utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors= utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then lastfirst = true; end if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions (utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or (true == lastfirst and utilities.is_set (xxxxors)) then utilities.set_message ('err_redundant_parameters', utilities.substitute (cfg.special_case_translation.name_list_params, ('AuthorList' == list_name) and cfg.special_case_translation.author or cfg.special_case_translation.editor)); -- add error message end if true == lastfirst then return 1 end; -- return a number indicating which author name source to use if utilities.is_set (vxxxxors) then return 2 end; if utilities.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, live, dead, etc.). When the parameter value has not been assigned a value (missing or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one of the list of allowed values returns the translated value; else, emits an error message and returns the value specified by ret_val. TODO: explain <invert> ]] local function is_valid_parameter_value (value, name, possible, ret_val, invert) if not utilities.is_set (value) then return ret_val; -- an empty parameter is ok end if (not invert and utilities.in_array (value, possible)) then -- normal; <value> is in <possible> table return cfg.keywords_xlate[value]; -- return translation of parameter keyword elseif invert and not utilities.in_array (value, possible) then -- invert; <value> is not in <possible> table return value; -- return <value> as it is else utilities.set_message ('err_invalid_param_val', {name, value}); -- not an allowed value so add error message return ret_val; 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 terminate 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 (or journal article number) 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, article, cite_class, origin, sepc, lower) if not utilities.is_set (volume) and not utilities.is_set (issue) and not utilities.is_set (article) then return ''; end -- same condition as in format_pages_sheets() local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); local is_numeric_vol = volume and (volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')); -- is only uppercase roman numerals or only digits? local is_long_vol = volume and (4 < mw.ustring.len(volume)); -- is |volume= value longer than 4 characters? if volume and (not is_numeric_vol and is_long_vol) then -- when not all digits or Roman numerals, is |volume= longer than 4 characters? utilities.add_prop_cat ('long-vol'); -- yes, add properties cat end if is_journal then -- journal-style formatting local vol = ''; if utilities.is_set (volume) then if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals? vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters? vol = utilities.substitute (cfg.messages['j-vol'], {sepc, utilities.hyphen_to_dash (volume)}); -- not bold else -- four or fewer characters vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, utilities.hyphen_to_dash (volume)}); -- bold end end vol = vol .. (utilities.is_set (issue) and utilities.substitute (cfg.messages['j-issue'], issue) or '') vol = vol .. (utilities.is_set (article) and utilities.substitute (cfg.messages['j-article-num'], article) or '') return vol; end if 'podcast' == cite_class and utilities.is_set (issue) then return wrap_msg ('issue', {sepc, issue}, lower); end if 'conference' == cite_class and utilities.is_set (article) then -- |article-number= supported only in journal and conference cites if utilities.is_set (volume) and utilities.is_set (article) then -- both volume and article number return wrap_msg ('vol-art', {sepc, utilities.hyphen_to_dash (volume), article}, lower); elseif utilities.is_set (article) then -- article number alone; when volume alone, handled below return wrap_msg ('art', {sepc, article}, lower); end end -- all other types of citation if utilities.is_set (volume) and utilities.is_set (issue) then return wrap_msg ('vol-no', {sepc, utilities.hyphen_to_dash (volume), issue}, lower); elseif utilities.is_set (volume) then return wrap_msg ('vol', {sepc, utilities.hyphen_to_dash (volume)}, lower); else return wrap_msg ('issue', {sepc, issue}, lower); end end --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of 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) if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators if utilities.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 utilities.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 (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); if utilities.is_set (page) then if is_journal then return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', ''; elseif not nopp then return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; else return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; end elseif utilities.is_set (pages) then if is_journal then return utilities.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 '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; elseif not nopp then return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; else return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; end end return '', '', '', ''; -- return empty strings end --[[--------------------------< I N S O U R C E _ L O C _ G E T >---------------------------------------------- returns one of the in-source locators: page, pages, or at. If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text for use in COinS. This COinS thing is done because here we convert an interwiki-link to an external link and add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? TODO: add support for sheet and sheets?; streamline; TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned to a new name)? ]] local function insource_loc_get (page, page_orig, pages, pages_orig, at) local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?) if utilities.is_set (page) then if utilities.is_set (pages) or utilities.is_set (at) then pages = ''; -- unset the others at = ''; end extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc. ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label if ws_url then page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page}); coins_pages = ws_label; end elseif utilities.is_set (pages) then if utilities.is_set (at) then at = ''; -- unset end extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc. ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label if ws_url then pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages}); coins_pages = ws_label; end elseif utilities.is_set (at) then ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label if ws_url then at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at}); coins_pages = ws_label; end end return page, pages, at, coins_pages; end --[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------ add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value ]] local function is_unique_archive_url (archive, url, c_url, source, date) if utilities.is_set (archive) then if archive == url or archive == c_url then utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); -- add error message return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url= end end return archive, date; 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 function 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*/) A secondary function is to return an archive-url timestamp from those archive urls that have them. The timestamp is used by validation.archive_date_check() to see if the value in |archive-date= matches the timestamp in the archive url. ]=] local function archive_url_check (url, date) local err_msg = ''; -- start with the error message empty local path, timestamp, flag; -- portions of the archive.org URL local function is_ts_date_valid (timestamp, origin_date) -- local function to validate archive url taimestamp date; time ignored local y, m, d = timestamp:match ('(%d%d%d%d)(%d%d)(%d%d)'); -- split into parts if y and validation.is_valid_date (y, m, d) and (tonumber (y) >= 1996) then return true, tonumber (y) >= origin_date; -- <origin_date> is 1996 for archive.org end end if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate end if url:match('//web%.archive%.org/save/') then -- if a save command URL, we don't want to allow saving of the target page err_msg = cfg.err_msg_supl.save; url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL elseif url:match('//liveweb%.archive%.org/') then err_msg = cfg.err_msg_supl.liveweb; else path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation if not path then -- malformed in some way; pattern did not match err_msg = cfg.err_msg_supl.timestamp; elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here err_msg = cfg.err_msg_supl.timestamp; if '*' ~= flag then local replacement = timestamp:match ('^%d%d%d%d%d%d') or timestamp:match ('^%d%d%d%d'); -- get the first 6 (YYYYMM) or first 4 digits (YYYY) if replacement then -- nil if there aren't at least 4 digits (year) replacement = replacement .. string.rep ('0', 14 - replacement:len()); -- year or yearmo (4 or 6 digits) zero-fill to make 14-digit timestamp url=url:gsub ('(//web%.archive%.org/[^%d]*)%d[^/]*', '%1' .. replacement .. '*', 1) -- for preview, modify ts to 14 digits plus splat for calendar display end end elseif not is_ts_date_valid (timestamp, 1996) then -- is ymd portion of timestamp a valid date? err_msg = cfg.err_msg_supl.timestamp; timestamp = nil; -- unset because invalid elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element err_msg = cfg.err_msg_supl.path; elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element) err_msg = cfg.err_msg_supl.flag; elseif utilities.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 = cfg.err_msg_supl.flag; else return url, date, timestamp; -- return ArchiveURL, ArchiveDate, and timestamp from |archive-url= end end -- if here, something not right so utilities.set_message ('err_archive_url', {err_msg}); -- add error message and if is_preview_mode then return url, date, timestamp; -- preview mode so return ArchiveURL, ArchiveDate, and timestamp from |archive-url= else return '', ''; -- return empty strings for ArchiveURL and ArchiveDate end end --[[--------------------------< P L A C E _ C H E C K >-------------------------------------------------------- check |place=, |publication-place=, |location= to see if these params include digits. This function added because many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that) returns the original parameter value without modification; added maint cat when parameter value contains digits ]] local function place_check (param_val) if not utilities.is_set (param_val) then -- parameter empty or omitted return param_val; -- return that empty state end if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value utilities.set_message ('maint_location'); -- yep, add maint cat end return param_val; -- and done end --[[--------------------------< I S _ A R C H I V E D _ C O P Y >---------------------------------------------- compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else ]] local function is_archived_copy (title) title = mw.ustring.lower(title); -- switch title to lower case if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy' return true; elseif cfg.special_case_translation.archived_copy['local'] then if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script return true; end end end --[[--------------------------< D I S P L A Y _ N A M E S _ S E L E C T >-------------------------------------- for any of the |display-authors=, |display-editors=, etc parameters, select either the local or global setting. When both are present, look at <local_display_names> value. When the value is some sort of 'et al.'string, special handling is required. When {{cs1 config}} has |display-<namelist>= AND this template has |display-<namelist>=etal AND: the number of names specified by <number_of_names> is: greater than the number specified in the global |display-<namelist>= parameter (<global_display_names>) use global |display-<namelist>= parameter value set overridden maint category less than or equal to the number specified in the global |display-<namelist>= parameter use local |display-<namelist>= parameter value The purpose of this function is to prevent categorizing a template that has fewer names than the global setting to keep the etal annotation specified by <local_display_names>. ]] local function display_names_select (global_display_names, local_display_names, param_name, number_of_names, test) if global_display_names and utilities.is_set (local_display_names) then -- when both if 'etal' == local_display_names:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings number_of_names = tonumber (number_of_names); -- convert these to numbers for comparison local global_display_names_num = tonumber (global_display_names); -- <global_display_names> not set when parameter value is not digits if number_of_names > global_display_names_num then -- template has more names than global config allows to be displayed? utilities.set_message ('maint_overridden_setting'); -- set a maint message because global is overriding local |display-<namelist>=etal return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names()) else return local_display_names, param_name; -- return local because fewer names so let <local_display_names> control end end -- here when <global_display_names> and <local_display_names> both numbers; <global_display_names> controls utilities.set_message ('maint_overridden_setting'); -- set a maint message return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names()) end -- here when only one of <global_display_names> or <local_display_names> set if global_display_names then return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names()) else return local_display_names, param_name; -- return local end end --[[--------------------------< M O D E _ S E T >-------------------------------------------------------------- fetch global mode setting from {{cs1 config}} (if present) or from |mode= (if present); global setting overrides local |mode= parameter value. When both are present, emit maintenance message ]] local function mode_set (Mode, Mode_origin) local mode; if cfg.global_cs1_config_t['Mode'] then -- global setting in {{cs1 config}}; nil when empty or assigned value invalid mode = is_valid_parameter_value (cfg.global_cs1_config_t['Mode'], 'cs1 config: mode', cfg.keywords_lists['mode'], ''); -- error messaging 'param' here is a hoax else mode = is_valid_parameter_value (Mode, Mode_origin, cfg.keywords_lists['mode'], ''); end if cfg.global_cs1_config_t['Mode'] and utilities.is_set (Mode) then -- when template has |mode=<something> which global setting has overridden utilities.set_message ('maint_overridden_setting'); -- set a maint message end return mode; end --[[--------------------------< Q U O T E _ M A K E >---------------------------------------------------------- create quotation from |quote=, |trans-quote=, and/or script-quote= with or without |quote-page= or |quote-pages= when any of those three quote parameters are set, this function unsets <PostScript>. When none of those parameters are set, |quote-page= and |quote-pages= are unset to nil so that they are not included in the template's metadata ]] local function quote_make (quote, trans_quote, script_quote, quote_page, quote_pages, nopp, sepc, postscript) if utilities.is_set (quote) or utilities.is_set (trans_quote) or utilities.is_set (script_quote) then if utilities.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 end quote = kern_quotes (quote); -- kern if needed quote = utilities.wrap_style ('quoted-text', quote ); -- wrap in <q>...</q> tags if utilities.is_set (script_quote) then quote = script_concatenate (quote, script_quote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped end if utilities.is_set (trans_quote) then if trans_quote:sub(1, 1) == '"' and trans_quote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks trans_quote = trans_quote:sub(2, -2); -- strip them off end quote = quote .. " " .. utilities.wrap_style ('trans-quoted-title', trans_quote ); end if utilities.is_set (quote_page) or utilities.is_set (quote_pages) then -- add page prefix local quote_prefix = ''; if utilities.is_set (quote_page) then extra_text_in_page_check (quote_page, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc. if not nopp then quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, quote_page}), '', '', ''; else quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, quote_page}), '', '', ''; end elseif utilities.is_set (quote_pages) then extra_text_in_page_check (quote_pages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc. if tonumber(quote_pages) ~= nil and not nopp then -- if only digits, assume single page quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, quote_pages}), '', ''; elseif not nopp then quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, quote_pages}), '', ''; else quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, quote_pages}), '', ''; end end quote = quote_prefix .. ": " .. quote; else quote = sepc .. " " .. quote; end postscript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set elseif utilities.is_set (quote_page) or utilities.is_set (quote_pages) then quote_page = nil; -- unset; these require |quote=; TODO: error message? quote_pages = nil; end return quote, quote_page, quote_pages, postscript; end --[[--------------------------< C H E C K _ P U B L I S H E R _ N A M E >-------------------------------------- look for variations of '<text>: <text>' that might be '<location>: <publisher>' in |publisher= parameter value. when found, emit a maintenance message; return nil else <publisher> is the value assigned to |publisher= or |institution= ]] local function check_publisher_name (publisher) local patterns_t = { '^[%w%s]+%s*:%s*[%w%s]+$', -- plain text <location>: <publisher> '^%[+[%w%s:|]+%]+%s*:%s*[%w%s]+$', -- partially wikilinked [[<location>]]: <publisher> '^[%w%s]+%s*:%s*%[+[%w%s:|]+%]+$', -- partially wikilinked <location>: [[<publisher>]] '^%[+[%w%s:|]+%]+%s*:%s*%[+[%w%s:|]+%]+$', -- wikilinked [[<location>]]: [[<publisher>]] } for _, pattern in ipairs (patterns_t) do -- spin through the patterns_t sequence if mw.ustring.match (publisher, pattern) then -- does this pattern match? utilities.set_message ('maint_publisher_location'); -- set a maint message return; -- and done end end end --[[--------------------------< I S _ P A G E _ A R T _ N U M >------------------------------------------------ compare the trailing (rightmost) characters of the |doi= value against the whole value assigned to |page(s)=. return boolean true when: |page(s)= has exactly 8 digits and a dot between the fourth and fifth digits matches the trailing 9 characters of the |doi= value: |page=12345678 → |page=1234.5678 matches |doi=10.xxxx/yyyy1234.5678 |page(s)= is 5 or more characters and matches |doi= values's trailing characters |page(s)= begins with a lowercase 'e' and |page(s)= without the 'e' matches |doi= values's trailing characters: |page=e12345 → |page=12345 matches |doi=10.xxxx/yyyy12345 |page(s)= begins with a uppercase 'CD' followed by (typically) six digits matches |doi= values that ends with 'CDxxxxxx.pubx' (where 'x' is any single digit) return nil when |page(s)= values: are ranges separated by underscore, hyphen, emdash, endash, figure dash, or minus character are comma- or semicolon-separated lists of pages have external urls (has text 'http') are digit-only values less than 10000 do not match |doi= values's trailing characters ]] local function is_page_art_num (page, doi) if not (utilities.is_set (page) and utilities.is_set (doi)) then -- both required return; -- abandon; nothing to do end if page:match ('[,;_−–—‒%-]') then -- when |page(s)= might be a page range or a separated list of pages return; -- abandon end page = page:lower(); -- because doi names are case insensitive doi = doi:lower(); -- force these to lowercase for testing if page:match ('http') then -- when |page(s)= appears to hold a url return; -- abandon end if tonumber (page) then -- is |page(s)= digits only if 10000 > tonumber (page) then -- when |page(s)= less than 10000 return; -- abandon end if doi:match (page .. '$') then -- digits only page number match the last digits in |doi=? return true; end if 8 == page:len() then -- special case when |page(s)= is exactly 8 digits local dot_page = page:gsub ('(%d%d%d%d)(%d%d%d%d)', '%1.%2'); -- make a |page=xxxx.yyyy version commonly used in |doi= if doi:match (dot_page .. '$') then -- 8-digit dotted page number match the last characters in |doi=? return true; end end else -- here when |page(s)= is alpha-numeric if 4 < page:len() then -- when |page(s)= is five or more characters if doi:match (page .. '$') then -- alpha-numeric page match the last characters in |doi=? return true; end local epage = page:match ('^e([%w]+)$'); -- if first character of |page= is 'e', remove it if epage and doi:match (epage .. '$') then -- page number match the last characters in |doi=? return true; end local cdpage = page:match ('^cd%d+$'); -- if first characters of |page= are 'CD' and last characters are digits (typically 6 digits) if cdpage and doi:match (cdpage .. '%.pub%d$') then -- page number matches doi 'CDxxxxxx.pubx' where 'x' is a digit return true; end end end end --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ This is the main function doing the majority of the citation formatting. ]] local function citation0( config, args ) --[[ Load Input Parameters The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. ]] local A = argument_wrapper ( args ); local i -- Pick out the relevant fields from the arguments. Different citation templates -- define different field names for the same underlying things. local author_etal; local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authors; local NameListStyle; if cfg.global_cs1_config_t['NameListStyle'] then -- global setting in {{cs1 config}} overrides local |name-list-style= parameter value; nil when empty or assigned value invalid NameListStyle = is_valid_parameter_value (cfg.global_cs1_config_t['NameListStyle'], 'cs1 config: name-list-style', cfg.keywords_lists['name-list-style'], ''); -- error messaging 'param' here is a hoax else NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], ''); end if cfg.global_cs1_config_t['NameListStyle'] and utilities.is_set (A['NameListStyle']) then -- when template has |name-list-style=<something> which global setting has overridden utilities.set_message ('maint_overridden_setting'); -- set a maint message end 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 NameListStyle = 'vanc'; -- override whatever |name-list-style= might be a, author_etal = parse_vauthors_veditors (args, A['Vauthors'], 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= elseif 3 == selected then Authors = A['Authors']; -- use content of |people= or |credits=; |authors= is deprecated; TODO: constrain |people= and |credits= to cite av media, episode, serial? end if utilities.is_set (Collaboration) then author_etal = true; -- so that |display-authors=etal not required end end local editor_etal; local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= do -- to limit scope of selected local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn if 1 == selected then e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= elseif 2 == selected then NameListStyle = 'vanc'; -- override whatever |name-list-style= might be e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= end end local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= and |script-chapter= aliases local Chapter_origin = A:ORIGIN ('Chapter'); local ScriptChapter = A['ScriptChapter']; local ScriptChapter_origin = A:ORIGIN ('ScriptChapter'); local Contribution; -- because contribution is required for contributor(s) if 'contribution' == Chapter_origin then -- is there a |contribution= parameter? Contribution = Chapter; -- get the name of the contribution elseif 'script-contribution' == ScriptChapter_origin then -- no, so is there a |script-contribution= parameter? Contribution = ScriptChapter; -- get the name of the contribution end local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.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 utilities.is_set (Contribution) then -- |contributor= requires |contribution= utilities.set_message ('err_contributor_missing_required_param', 'contribution'); -- add missing contribution error message c = {}; -- blank the contributors' table; it is used as a flag later end if 0 == #a then -- |contributor= requires |author= utilities.set_message ('err_contributor_missing_required_param', 'author'); -- add missing author error message c = {}; -- blank the contributors' table; it is used as a flag later end end else -- if not a book cite if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters? utilities.set_message ('err_contributor_ignored'); -- add contributor ignored error message end Contribution = nil; -- unset end local Title = A['Title']; local TitleLink = A['TitleLink']; local auto_select = ''; -- default is auto local accept_link; TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords auto_select = TitleLink; -- remember selection for later TitleLink = ''; -- treat as if |title-link= would have been empty end TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used if 'map' == config.CitationClass and 'section' == Chapter_origin then Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}} Chapter = ''; -- unset for now; will be reset later from |map= if present end local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); local ScriptPeriodical = A['ScriptPeriodical']; local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); local TransPeriodical = A['TransPeriodical']; local TransPeriodical_origin = A:ORIGIN ('TransPeriodical'); if (utilities.in_array (config.CitationClass, {'book', 'encyclopaedia'}) and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical))) then local param; if utilities.is_set (Periodical) then -- get a parameter name from one of these periodical related meta-parameters Periodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters param = Periodical_origin -- get parameter name for error messaging elseif utilities.is_set (TransPeriodical) then TransPeriodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters param = TransPeriodical_origin; -- get parameter name for error messaging elseif utilities.is_set (ScriptPeriodical) then ScriptPeriodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters param = ScriptPeriodical_origin; -- get parameter name for error messaging end if utilities.is_set (param) then -- if we found one utilities.set_message ('err_periodical_ignored', {param}); -- emit an error message end end if utilities.is_set (Periodical) then local i; Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated if i then -- non-zero when markup was stripped so emit an error message utilities.set_message ('err_apostrophe_markup', {Periodical_origin}); end end if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error TODO: make a function for this and similar? utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'mailinglist')}); end Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}} Periodical_origin = A:ORIGIN('MailingList'); end -- web and news not tested for now because of -- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors? if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter -- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message if p[config.CitationClass] then utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}); end end local Volume; if 'citation' == config.CitationClass then if utilities.is_set (Periodical) then if not utilities.in_array (Periodical_origin, cfg.citation_no_volume_t) then -- {{citation}} does not render |volume= when these parameters are used Volume = A['Volume']; -- but does for all other 'periodicals' end elseif utilities.is_set (ScriptPeriodical) then if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website= Volume = A['Volume']; -- but does for all other 'periodicals' end else Volume = A['Volume']; -- and does for non-'periodical' cites end elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings Volume = A['Volume']; end extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v'); local Issue; if 'citation' == config.CitationClass then if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, cfg.citation_issue_t) then -- {{citation}} may render |issue= when these parameters are used Issue = A['Issue']; end elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then Issue = A['Issue']; end end local ArticleNumber; if utilities.in_array (config.CitationClass, {'journal', 'conference'}) or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then ArticleNumber = A['ArticleNumber']; end extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i'); Issue = utilities.hyphen_to_dash (Issue); local Page; local Pages; local At; local QuotePage; local QuotePages; if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then -- TODO: rewrite to emit ignored parameter error message? Page = A['Page']; Pages = utilities.hyphen_to_dash (A['Pages']); At = A['At']; QuotePage = A['QuotePage']; QuotePages = utilities.hyphen_to_dash (A['QuotePages']); end local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil); local Mode = mode_set (A['Mode'], A:ORIGIN('Mode')); -- separator character and postscript local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass); local Quote; Quote, QuotePage, QuotePages, PostScript = quote_make (A['Quote'], A['TransQuote'], A['ScriptQuote'], QuotePage, QuotePages, NoPP, sepc, PostScript); local Edition = A['Edition']; local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace')); local Place = place_check (A['Place'], A:ORIGIN('Place')); local PublisherName = A['PublisherName']; local PublisherName_origin = A:ORIGIN('PublisherName'); if utilities.is_set (PublisherName) and (cfg.keywords_xlate['none'] ~= PublisherName) then local i = 0; PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized if i and (0 < i) then -- non-zero when markup was stripped so emit an error message utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}); end end if ('document' == config.CitationClass) and not utilities.is_set (PublisherName) then utilities.set_message ('err_missing_publisher', {config.CitationClass, 'publisher'}); end local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup? local Newsgroup_origin = A:ORIGIN('Newsgroup'); if 'newsgroup' == config.CitationClass then if utilities.is_set (PublisherName) and (cfg.keywords_xlate['none'] ~= PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup utilities.set_message ('err_parameter_ignored', {PublisherName_origin}); end PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS end if 'book' == config.CitationClass or 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and not utilities.is_set (Periodical)) then local accept; PublisherName, accept = utilities.has_accept_as_written (PublisherName); -- check for and remove accept-as-written markup from |publisher= wrapped if not accept then -- when no accept-as-written markup check_publisher_name (PublisherName); -- emit maint message when |publisher= might be prefixed with publisher's location end end local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL? local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then UrlAccess = nil; utilities.set_message ('err_param_access_requires_param', 'url'); end local ChapterURL = A['ChapterURL']; local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then ChapterUrlAccess = nil; utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}); end local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil); if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then MapUrlAccess = nil; utilities.set_message ('err_param_access_requires_param', {'map-url'}); end local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil); -- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page if cfg.uncategorized_namespaces[this_page.namespace] then -- is this page's namespace id one of the uncategorized namespace ids? no_tracking_cats = "true"; -- set no_tracking_cats end for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end end -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category local coins_pages; Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At); if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together if PublicationPlace == Place then Place = ''; -- unset; don't need both if they are the same end elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ... PublicationPlace = Place; -- promote |place= (|location=) to |publication-place end if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL -- local ScriptChapter = A['ScriptChapter']; -- local ScriptChapter_origin = A:ORIGIN ('ScriptChapter'); local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local TransChapter = A['TransChapter']; local TransChapter_origin = A:ORIGIN ('TransChapter'); local TransTitle = A['TransTitle']; local ScriptTitle = A['ScriptTitle']; --[[ Parameter remapping for cite encyclopedia: When the citation has these parameters: |encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title= for rendering |encyclopedia= and |article= then map |encyclopedia= to |title= for rendering |trans-title= maps to |trans-chapter= when |title= is re-mapped |url= maps to |chapter-url= when |title= is remapped All other combinations of |encyclopedia=, |title=, and |article= are not modified ]] local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS local ScriptEncyclopedia = A['ScriptEncyclopedia']; local TransEncyclopedia = A['TransEncyclopedia']; if utilities.is_set (Encyclopedia) or utilities.is_set (ScriptEncyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}} if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then if utilities.is_set (Encyclopedia) then utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}); else utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('ScriptEncyclopedia')}); end Encyclopedia = nil; -- unset these because not supported by this template ScriptEncyclopedia = nil; TransEncyclopedia = nil; end elseif utilities.is_set (TransEncyclopedia) then utilities.set_message ('err_trans_missing_title', {'encyclopedia'}); end if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both parameters set emit an error message; {{citation}} only; Periodical not allowed in {{cite encyclopedia}} utilities.set_message ('err_periodical_ignored', {Periodical_origin}); end if utilities.is_set (Encyclopedia) or utilities.is_set (ScriptEncyclopedia) then Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia for rendering; {{citation}} could (not legitimately) have both; use Encyclopedia Periodical_origin = A:ORIGIN ('Encyclopedia'); ScriptPeriodical = ScriptEncyclopedia; ScriptPeriodical_origin = A:ORIGIN ('ScriptEncyclopedia'); if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then if not utilities.is_set (Chapter) then Chapter = Title; -- |encyclopedia= and |title= are set so map |title= params to |article= params for rendering ScriptChapter = ScriptTitle; ScriptChapter_origin = A:ORIGIN('ScriptTitle') TransChapter = TransTitle; ChapterURL = URL; ChapterURL_origin = URL_origin; ChapterUrlAccess = UrlAccess; ChapterFormat = Format; if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then Chapter = utilities.make_wikilink (TitleLink, Chapter); end Title = Periodical; -- now map |encyclopedia= params to |title= params for rendering ScriptTitle = ScriptPeriodical or ''; TransTitle = TransEncyclopedia or ''; Periodical = ''; -- redundant so unset ScriptPeriodical = ''; URL = ''; Format = ''; TitleLink = ''; end elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= for rendering ScriptTitle = ScriptPeriodical or ''; TransTitle = TransEncyclopedia or ''; Periodical = ''; -- redundant so unset ScriptPeriodical = ''; end end end -- special case for cite techreport. local ID = A['ID']; if (config.CitationClass == "techreport") then -- special case for cite techreport if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' if not utilities.is_set (ID) then -- can we use ID for the "number"? ID = A['Number']; -- yes, use it else -- ID has a value so emit error message utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'number')}); end end end -- Account for the oddity that is {{cite conference}}, before generation of COinS data. local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode local Conference = A['Conference']; local BookTitle = A['BookTitle']; local TransTitle_origin = A:ORIGIN ('TransTitle'); if 'conference' == config.CitationClass then if utilities.is_set (BookTitle) then Chapter = Title; Chapter_origin = 'title'; -- ChapterLink = TitleLink; -- |chapter-link= is deprecated ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURL_origin = URL_origin; URL_origin = ''; ChapterFormat = Format; TransChapter = TransTitle; TransChapter_origin = TransTitle_origin; Title = BookTitle; Format = ''; -- TitleLink = ''; TransTitle = ''; URL = ''; end elseif 'speech' ~= config.CitationClass then Conference = ''; -- not cite conference or cite speech so make sure this is empty string end local cs2_lower = function (text) -- if mode is cs2, use lower case if (sepc ~= '.') then return text:lower(); end return text; end local use_lowercase = ( sepc == ',' ); -- controls capitalization of certain static text -- cite map oddities local Cartography = ""; local Scale = ""; local Sheet = A['Sheet'] or ''; local Sheets = A['Sheets'] or ''; if config.CitationClass == "map" then if utilities.is_set (Chapter) then --TODO: make a function for this and similar? utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Chapter_origin)}); -- add error message end Chapter = A['Map']; Chapter_origin = A:ORIGIN('Map'); ChapterURL = A['MapURL']; ChapterURL_origin = A:ORIGIN('MapURL'); TransChapter = A['TransMap']; ScriptChapter = A['ScriptMap'] ScriptChapter_origin = A:ORIGIN('ScriptMap') ChapterUrlAccess = MapUrlAccess; ChapterFormat = A['MapFormat']; Cartography = A['Cartography']; if utilities.is_set ( Cartography ) then Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); end Scale = A['Scale']; if utilities.is_set ( Scale ) then Scale = sepc .. " " .. Scale; end end -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. local Series = A['Series']; if 'episode' == config.CitationClass or 'serial' == config.CitationClass then local SeriesLink = A['SeriesLink']; SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set local Network = A['Network']; local Station = A['Station']; local s, n = {}, {}; -- do common parameters first if utilities.is_set (Network) then table.insert(n, Network); end if utilities.is_set (Station) then table.insert(n, Station); end ID = table.concat(n, sepc .. ' '); if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Season = A['Season']; local SeriesNumber = A['SeriesNumber']; if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set TODO: make a function for this and similar? utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'seriesno')}); -- add error message SeriesNumber = ''; -- unset; prefer |season= over |seriesno= end -- assemble a table of parts concatenated later into Series if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ''; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ScriptChapter_origin = A:ORIGIN('ScriptTitle'); ChapterLink = TitleLink; -- alias |episode-link= TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURL_origin = URL_origin; ChapterFormat = Format; Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL Chapter = utilities.make_wikilink (ChapterLink, Chapter); elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode; Series = utilities.make_wikilink (ChapterLink, Series); end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; Format = ''; 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 utilities.is_set (Series) and utilities.is_set (SeriesLink) then Series = utilities.make_wikilink (SeriesLink, Series); end Series = utilities.wrap_style ('italic-title', Series); -- series is italicized end end -- end of {{cite episode}} stuff -- handle type parameter for those CS1 citations that have default values local TitleType = A['TitleType']; local Degree = A['Degree']; if utilities.in_array (config.CitationClass, {'AV-media-notes', 'document', 'interview', 'mailinglist', 'map', 'podcast', 'pressrelease', 'report', 'speech', 'techreport', 'thesis'}) then TitleType = set_titletype (config.CitationClass, TitleType); if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower(); end end if utilities.is_set (TitleType) then -- if type parameter is specified TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses -- TODO: Hack on TitleType to fix bunched parentheses problem end -- legacy: promote PublicationDate to Date if neither Date nor Year are set. local Date = A['Date']; local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging local PublicationDate = A['PublicationDate']; local Year = A['Year']; if utilities.is_set (Year) then validation.year_check (Year); -- returns nothing; emits maint message when |year= doesn't hold a 'year' value end if not utilities.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 utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set Date = PublicationDate; -- promote PublicationDate to Date PublicationDate = ''; -- unset, no longer needed Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter else Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter end else Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging end if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation --[[ Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where we get the date used in the metadata. Date validation supporting code is in Module:Citation/CS1/Date_validation ]] local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], ''); if not utilities.is_set (DF) then DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template end local ArchiveURL; local ArchiveDate; local ArchiveFormat = A['ArchiveFormat']; local archive_url_timestamp; -- timestamp from wayback machine url ArchiveURL, ArchiveDate, archive_url_timestamp = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL local AccessDate = A['AccessDate']; local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification local DoiBroken = A['DoiBroken']; local Embargo = A['Embargo']; local anchor_year; -- used in the CITEREF identifier do -- create defined block to contain local variables error_message, date_parameters_list, mismatch local error_message = ''; -- AirDate has been promoted to Date so not necessary to check it local date_parameters_list = { ['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')}, ['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')}, ['date'] = {val = Date, name = Date_origin}, ['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')}, ['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')}, ['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')}, ['year'] = {val = Year, name = A:ORIGIN ('Year')}, }; local error_list = {}; anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list); if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed; validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list); end if 0 == #error_list then -- error free dates only; 0 when error_list is empty local modified = false; -- flag if utilities.is_set (DF) then -- if we need to reformat dates modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate end if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate modified = true; utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category end -- for those wikis that can and want to have English date names translated to the local language; not supported at en.wiki if cfg.date_name_auto_xlate_enable and validation.date_name_xlate (date_parameters_list, cfg.date_digit_auto_xlate_enable ) then utilities.set_message ('maint_date_auto_xlated'); -- add maint cat modified = true; end if modified then -- if the date_parameters_list values were modified AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values ArchiveDate = date_parameters_list['archive-date'].val; Date = date_parameters_list['date'].val; DoiBroken = date_parameters_list['doi-broken-date'].val; PublicationDate = date_parameters_list['publication-date'].val; end if archive_url_timestamp and utilities.is_set (ArchiveDate) then validation.archive_date_check (ArchiveDate, archive_url_timestamp, DF); -- does YYYYMMDD in archive_url_timestamp match date in ArchiveDate end else utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}); -- add this error message end end -- end of do if utilities.in_array (config.CitationClass, {'book', 'encyclopaedia'}) or -- {{cite book}}, {{cite encyclopedia}}; TODO: {{cite conference}} and others? ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) or -- {{citation}} as an encylopedia citation ('citation' == config.CitationClass and not utilities.is_set (Periodical)) then -- {{citation}} as a book citation if utilities.is_set (PublicationPlace) then if not utilities.is_set (PublisherName) then local date = COinS_date.rftdate and tonumber (COinS_date.rftdate:match ('%d%d%d%d')); -- get year portion of COinS date (because in Arabic numerals); convert string to number if date and (1850 <= date) then -- location has no publisher; if date is 1850 or later utilities.set_message ('maint_location_no_publisher'); -- add maint cat end else -- PublisherName has a value if cfg.keywords_xlate['none'] == PublisherName then -- if that value is 'none' (only for book and encyclopedia citations) PublisherName = ''; -- unset end end end end local ID_list = {}; -- sequence table of rendered identifiers local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key local Class = A['Class']; -- arxiv class identifier local ID_support = { {A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')}, {DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')}, {Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')}, } ID_list, ID_list_coins = identifiers.identifier_lists_get (args, { DoiBroken = DoiBroken, -- for |doi= ASINTLD = A['ASINTLD'], -- for |asin= Embargo = Embargo, -- for |pmc= Class = Class, -- for |arxiv= CitationClass = config.CitationClass, -- for |arxiv= Year=anchor_year, -- for |isbn= }, ID_support); if 'citation' == config.CitationClass then -- catch ve/citoid malformed book cites in {{citation}} templates for _, id in ipairs (ID_list) do -- search through the ID_list sequence looking for an ISBN identifier string if id:find ('ISBN', 3, true) then -- plain find, start at index 3 ([[ISBN) if utilities.is_set (Periodical) then -- when a |work= alias is set utilities.set_message ('maint_work_isbn'); -- add maint cat end end end end -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite medrxiv}}, {{cite ssrn}}, before generation of COinS data. if utilities.in_array (config.CitationClass, whitelist.preprint_template_list_t) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv=, |citeseerx=, |medrxiv=, |ssrn= required for their templates if not (args[cfg.id_handlers[config.CitationClass:upper()].parameters[1]] or -- can't use ID_list_coins k/v table here because invalid parameters omitted args[cfg.id_handlers[config.CitationClass:upper()].parameters[2]]) then -- which causes unexpected parameter missing error message utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message end Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['medrxiv'] = 'medRxiv', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass]; end -- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled if identifiers.auto_link_urls[auto_select] then -- manual selection URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title= elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title= elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI URL = identifiers.auto_link_urls['doi']; URL_origin = cfg.id_handlers['DOI'].parameters[1]; end end if utilities.is_set (URL) then -- set when using an identifier-created URL if utilities.is_set (AccessDate) then -- |access-date= requires |url=; identifier-created URL is not |url= utilities.set_message ('err_accessdate_missing_url'); -- add an error message AccessDate = ''; -- unset end if utilities.is_set (ArchiveURL) then -- |archive-url= requires |url=; identifier-created URL is not |url= utilities.set_message ('err_archive_missing_url'); -- add an error message ArchiveURL = ''; -- unset end end end -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}); end if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and utilities.in_array (config.CitationClass, {'journal', 'citation'}) and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and ('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites Title = ''; -- set title to empty string utilities.set_message ('maint_untitled'); -- add maint cat end if 'journal' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then if is_page_art_num (((utilities.is_set (Page) and Page) or (utilities.is_set (Pages) and Pages)) or nil, ID_list_coins['DOI']) then -- does |page(s)= look like it holds an article number utilities.set_message ('maint_page_art_num'); -- add maint cat end end -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title -- is the article title, and Chapter is a section within the article. So, we remap local coins_chapter = Chapter; -- default assuming that remapping not required local coins_title = Title; -- et tu if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then coins_chapter = Title; -- remap coins_title = Periodical; end end local coins_author = a; -- default for coins rft.au if 0 < #c then -- but if contributor list coins_author = c; -- use that instead end -- this is the function call to COinS() local OCinSoutput = metadata.COinS({ ['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata ['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS ['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic / accept-as-written markup ['Degree'] = Degree; -- cite thesis only ['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic / accept-as-written markup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, -- COinS_date.* has correctly formatted date values if Date is valid; ['Season'] = COinS_date.rftssn, ['Quarter'] = COinS_date.rftquarter, ['Chron'] = COinS_date.rftchron, ['Series'] = Series, ['Volume'] = Volume, ['Issue'] = Issue, ['ArticleNumber'] = ArticleNumber, ['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links ['Edition'] = Edition, ['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName ['URL'] = first_set ({ChapterURL, URL}, 2), ['Authors'] = coins_author, ['ID_list'] = ID_list_coins, ['RawPage'] = this_page.prefixedText, }, config.CitationClass); -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite medrxiv}}, and {{cite ssrn}} AFTER generation of COinS data. if utilities.in_array (config.CitationClass, whitelist.preprint_template_list_t) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, medRxiv, or ssrn now unset so it isn't displayed Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal end -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil )); end local Editors; local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list local Contributors; -- assembled contributors name list local contributor_etal; local Translators; -- assembled translators name list local translator_etal; local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= local Interviewers; local interviewers_list = {}; interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters local interviewer_etal; -- Now perform various field substitutions. -- We also add leading spaces and surrounding markup and punctuation to the -- various parts of the citation, but only when they are non-nil. do local last_first_list; local control = { format = NameListStyle, -- empty string, '&', 'amp', 'and', or 'vanc' maximum = nil, -- as if display-authors or display-editors not set mode = Mode }; do -- do editor name list first because the now unsupported coauthors used to modify control table local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayEditors'], A['DisplayEditors'], A:ORIGIN ('DisplayEditors'), #e); control.maximum, editor_etal = get_display_names (display_names, #e, 'editors', editor_etal, param); 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 end do -- now do interviewers local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayInterviewers'], A['DisplayInterviewers'], A:ORIGIN ('DisplayInterviewers'), #interviewers_list); control.maximum, interviewer_etal = get_display_names (display_names, #interviewers_list, 'interviewers', interviewer_etal, param); Interviewers = list_people (control, interviewers_list, interviewer_etal); end do -- now do translators local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayTranslators'], A['DisplayTranslators'], A:ORIGIN ('DisplayTranslators'), #t); control.maximum, translator_etal = get_display_names (display_names, #t, 'translators', translator_etal, param); Translators = list_people (control, t, translator_etal); end do -- now do contributors local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayContributors'], A['DisplayContributors'], A:ORIGIN ('DisplayContributors'), #c); control.maximum, contributor_etal = get_display_names (display_names, #c, 'contributors', contributor_etal, param); Contributors = list_people (control, c, contributor_etal); end do -- now do authors local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayAuthors'], A['DisplayAuthors'], A:ORIGIN ('DisplayAuthors'), #a, author_etal); control.maximum, author_etal = get_display_names (display_names, #a, 'authors', author_etal, param); last_first_list = list_people (control, a, author_etal); if utilities.is_set (Authors) then Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al. if author_etal then Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter end else Authors = last_first_list; -- either an author name list or an empty string end end -- end of do if utilities.is_set (Authors) and utilities.is_set (Collaboration) then Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. end end local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); Format = style_format (Format, URL, 'format', 'url'); -- special case for chapter format so no error message or cat when chapter not supported if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); end if not utilities.is_set (URL) then if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for {{cite web}}, {{cite podcast}}, and {{cite mailing list}} ('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website= if not url_was_archive_today then -- is <URL> empty/missing because it was a deprecated archive.today url utilities.set_message ('err_cite_web_url'); -- no; emit an error message for an empty/ missing |url= end end -- do we have |accessdate= without either |url= or |chapter-url=? if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set; utilities.set_message ('err_accessdate_missing_url'); AccessDate = ''; end end local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); local OriginalURL local OriginalURL_origin local OriginalFormat local OriginalAccess; UrlStatus = UrlStatus:lower(); -- used later when assembling archived text if utilities.is_set ( ArchiveURL ) then if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages OriginalFormat = ChapterFormat; -- and original |chapter-format= if 'live' ~= UrlStatus then ChapterURL = ArchiveURL -- swap-in the archive's URL ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages ChapterFormat = ArchiveFormat or ''; -- swap in archive's format ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs end elseif utilities.is_set (URL) then OriginalURL = URL; -- save copy of original source URL OriginalURL_origin = URL_origin; -- name of URL parameter for error messages OriginalFormat = Format; -- and original |format= OriginalAccess = UrlAccess; if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it URL = ArchiveURL -- swap-in the archive's URL URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages Format = ArchiveFormat or ''; -- swap in archive's format UrlAccess = nil; -- restricted access levels do not make sense for archived URLs end end elseif utilities.is_set (UrlStatus) then -- if |url-status= is set when |archive-url= is not set utilities.set_message ('maint_url_status'); -- add maint cat end if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then local chap_param; if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters chap_param = A:ORIGIN ('Chapter') elseif utilities.is_set (TransChapter) then chap_param = A:ORIGIN ('TransChapter') elseif utilities.is_set (ChapterURL) then chap_param = A:ORIGIN ('ChapterURL') elseif utilities.is_set (ScriptChapter) then chap_param = ScriptChapter_origin; else utilities.is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat') end if utilities.is_set (chap_param) then -- if we found one utilities.set_message ('err_chapter_ignored', {chap_param}); -- 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 utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title no_quotes = true; -- then render it unquoted end end Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter if utilities.is_set (Chapter) then Chapter = Chapter .. ChapterFormat ; if 'map' == config.CitationClass and utilities.is_set (TitleType) then Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title end Chapter = Chapter .. sepc .. ' '; elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it end end -- Format main title local plain_title = false; local accept_title; Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title> if accept_title and ('' == Title) then -- only support forced empty for now "(())" Title = cfg.messages['notitle']; -- replace by predefined "No title" message -- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting ScriptTitle = ''; -- just mute for now TransTitle = ''; -- just mute for now plain_title = true; -- suppress text decoration for descriptive title utilities.set_message ('maint_untitled'); -- add maint cat end if not accept_title then -- <Title> not wrapped in accept-as-written markup if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title= Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ... not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.) Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters end if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title end if is_generic ('generic_titles', Title) then utilities.set_message ('err_generic_title'); -- set an error message end end if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'document', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or ('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) 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 = utilities.wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above) Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = utilities.wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle); end if utilities.is_set (TransTitle) then if utilities.is_set (Title) then TransTitle = " " .. TransTitle; else utilities.set_message ('err_trans_missing_title', {'title'}); end end if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs? if utilities.is_set (TitleLink) and utilities.is_set (URL) then utilities.set_message ('err_wikilink_in_url'); -- set an error message because we can't have both TitleLink = ''; -- unset end if not utilities.is_set (TitleLink) and utilities.is_set (URL) then Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. Format; URL = ''; -- unset these because no longer needed Format = ""; elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then local ws_url; ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here if ws_url then Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title}); Title = Title .. TransTitle; else Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle; end else local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink) ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label if ws_url then Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); Title = Title .. TransTitle; else Title = Title .. TransTitle; end end else Title = TransTitle; end if utilities.is_set (Place) then Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; end local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL if utilities.is_set (Conference) then if utilities.is_set (ConferenceURL) then Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil ); end Conference = sepc .. " " .. Conference .. ConferenceFormat; elseif utilities.is_set (ConferenceURL) then Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil ); end local Position = ''; if not utilities.is_set (Position) then local Minutes = A['Minutes']; local Time = A['Time']; if utilities.is_set (Minutes) then if utilities.is_set (Time) then --TODO: make a function for this and similar? utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'time')}); end Position = utilities.substitute (cfg.messages.minutes, Minutes); else if utilities.is_set (Time) then local TimeCaption = A['TimeCaption'] if not utilities.is_set (TimeCaption) then TimeCaption = cs2_lower(cfg.messages['event']); end Position = " " .. TimeCaption .. " " .. Time; end end else Position = " " .. Position; At = ''; end Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); At = utilities.is_set (At) and (sepc .. " " .. At) or ""; Position = utilities.is_set (Position) and (sepc .. " " .. Position) or ""; if config.CitationClass == 'map' then local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier local Inset = A['Inset']; if utilities.is_set ( Inset ) then Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end if utilities.is_set ( Sections ) then Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); elseif utilities.is_set ( Section ) then Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); end At = At .. Inset .. Section; end local Others = A['Others']; if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= if config.CitationClass == "AV-media-notes" or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now utilities.set_message ('maint_others_avm') else utilities.set_message ('maint_others'); end end Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; if utilities.is_set (Translators) then Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc); end if utilities.is_set (Interviewers) then Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc); end local TitleNote = A['TitleNote']; TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; if utilities.is_set (Edition) then if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn. utilities.set_message ('err_extra_text_edition'); -- add error message end Edition = " " .. wrap_msg ('edition', Edition); else Edition = ''; end Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum local Agency = A['Agency'] or ''; -- |agency= is supported by {{cite magazine}}, {{cite news}}, {{cite press release}}, {{cite web}}, and certain {{citation}} templates if utilities.is_set (Agency) then -- this testing done here because {{citation}} supports 'news' citations if utilities.in_array (config.CitationClass, {'magazine', 'news', 'pressrelease', 'web'}) or ('citation' == config.CitationClass and utilities.in_array (Periodical_origin, {"magazine", "newspaper", "work"})) then Agency = wrap_msg ('agency', {sepc, Agency}); -- format for rendering else Agency = ''; -- unset; not supported utilities.set_message ('err_parameter_ignored', {'agency'}); -- add error message end end Volume = format_volume_issue (Volume, Issue, ArticleNumber, config.CitationClass, Periodical_origin, sepc, use_lowercase); if utilities.is_set (AccessDate) then local retrv_text = " " .. cfg.messages['retrieved']; AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format retrv_text = cs2_lower(retrv_text); -- if mode is cs2, lower case AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates end if utilities.is_set (ID) then ID = sepc .. " " .. ID; end local Docket = A['Docket']; if "thesis" == config.CitationClass and utilities.is_set (Docket) then ID = sepc .. " Docket " .. Docket .. ID; end if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set end if utilities.is_set (URL) then URL = " " .. external_link( URL, nil, URL_origin, UrlAccess ); end -- We check length of PostScript here because it will have been nuked by -- the quote parameters. We'd otherwise emit a message even if there wasn't -- a displayed postscript. -- TODO: Should the max size (1) be configurable? -- TODO: Should we check a specific pattern? if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then utilities.set_message ('maint_postscript') end local Archived; if utilities.is_set (ArchiveURL) then if not utilities.is_set (ArchiveDate) then -- ArchiveURL set but ArchiveDate not set utilities.set_message ('err_archive_missing_date'); -- emit an error message ArchiveURL = ''; -- empty string for concatenation ArchiveDate = ''; -- empty string for concatenation end else if utilities.is_set (ArchiveDate) then -- ArchiveURL not set but ArchiveDate is set utilities.set_message ('err_archive_date_missing_url'); -- emit an error message ArchiveURL = ''; -- empty string for concatenation ArchiveDate = ''; -- empty string for concatenation end end if utilities.is_set (ArchiveURL) then local arch_text; if "live" == UrlStatus then if utilities.is_set (ArchiveDate) then Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'], { external_link( ArchiveURL, cs2_lower(cfg.messages['archived']), A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } ); else Archived = ''; end if not utilities.is_set (OriginalURL) then utilities.set_message ('err_archive_missing_url'); Archived = ''; -- empty string for concatenation end elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then Archived = sepc .. ' ' .. utilities.substitute ( cs2_lower(cfg.messages['archived-unfit']), ArchiveDate); if 'bot: unknown' == UrlStatus then utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added else utilities.add_prop_cat ('unfit'); -- and add a category if not already added end else -- UrlStatus is empty, 'dead' if utilities.is_set (ArchiveDate) then Archived = sepc .. ' ' .. utilities.substitute ( cs2_lower(cfg.messages['archived-dead']), { external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); else Archived = ''; -- unset for concatenation end end else -- OriginalUrl not set utilities.set_message ('err_archive_missing_url'); Archived = ''; -- empty string for concatenation end elseif utilities.is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = ''; end local TranscriptURL = A['TranscriptURL'] local TranscriptFormat = A['TranscriptFormat']; TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); local Transcript = A['Transcript']; local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL if utilities.is_set (Transcript) then if utilities.is_set (TranscriptURL) then Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil ); end Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; elseif utilities.is_set (TranscriptURL) then Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil ); end local Publisher; if utilities.is_set (PublicationDate) then PublicationDate = wrap_msg ('published', PublicationDate); end if utilities.is_set (PublisherName) then if utilities.is_set (PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; else Publisher = sepc .. " " .. PublisherName .. PublicationDate; end elseif utilities.is_set (PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; else Publisher = PublicationDate; end -- Several of the above rely upon detecting this as nil, so do it last. if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then if utilities.is_set (Title) or utilities.is_set (TitleNote) then Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); else Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); end end local Language = A['Language']; if utilities.is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc. else Language=''; -- language not specified so make sure this is an empty string; --[[ TODO: need to extract the wrap_msg from language_parameter so that we can solve parentheses bunching problem with Format/Language/TitleType ]] end --[[ Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). ]] if "speech" == config.CitationClass then -- cite speech only TitleNote = TitleType; -- move TitleType to TitleNote so that it renders ahead of |event= TitleType = ''; -- and unset if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter if utilities.is_set (Conference) then -- and if |event= is set Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering end end end -- Piece all bits together at last. Here, all should be non-nil. -- We build things this way because it is more efficient in LUA -- not to keep reassigning to the same string variable over and over. local tcommon; local tcommon2; -- used for book cite when |contributor= is set local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; -- Volume = safe_join ({Volume, pgtext}, sepc); if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc. tcommon = safe_join ({Title, TitleNote}, sepc); -- author and other stuff will come after this and before tcommon2 tcommon2 = safe_join ({TitleType, Series, Language, Volume, Others, Edition, Publisher}, sepc); else tcommon = safe_join ({Title, TitleNote, TitleType, Series, Language, Volume, Others, Edition, Publisher}, sepc); end elseif 'map' == config.CitationClass then -- special cases for cite map if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter tcommon = safe_join ({Title, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc); elseif utilities.is_set (Periodical) then -- map in a periodical tcommon = safe_join ({Title, TitleType, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc); else -- a sheet or stand-alone map tcommon = safe_join ({Title, TitleType, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc); end elseif 'episode' == config.CitationClass then -- special case for cite episode tcommon = safe_join ({Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc); else -- all other CS1 templates tcommon = safe_join ({Title, TitleNote, Conference, Periodical, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc); end if #ID_list > 0 then ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); else ID_list = ID; end local Via = A['Via']; Via = utilities.is_set (Via) and wrap_msg ('via', Via) or ''; local idcommon; if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Quote }, sepc ); else idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Quote }, sepc ); end local text; -- local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; local OrigDate = A['OrigDate']; OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or ''; if utilities.is_set (Date) then if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses 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 .. OrigDate; -- Date does not begin with sepc else Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc end end end if utilities.is_set (Authors) then if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space end if utilities.is_set (Editors) then local in_text = ''; local post_text = ''; if utilities.is_set (Chapter) and 0 == #c then in_text = cfg.messages['in'] .. ' '; in_text = cs2_lower(in_text); -- lowercase for cs2 end if EditorCount <= 1 then post_text = ' (' .. cfg.messages['editor'] .. ')'; -- be consistent with no-author, no-date case else post_text = ' (' .. cfg.messages['editors'] .. ')'; end Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space end if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc. local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; by_text = cs2_lower(by_text); -- lowercase for cs2 Authors = by_text .. Authors; -- author follows title so tweak it here if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space end if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space end text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); -- text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, idcommon }, sepc ); else text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); -- text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, idcommon }, sepc ); end elseif utilities.is_set (Editors) then if utilities.is_set (Date) then if EditorCount <= 1 then Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editor']; else Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editors']; end else if EditorCount <= 1 then Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " else Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " end end text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); -- text = safe_join( {Editors, Date, Chapter, Place, tcommon, idcommon}, sepc ); else if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); -- text = safe_join( {Chapter, Place, tcommon, Date, idcommon}, sepc ); else text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc ); -- text = safe_join( {Chapter, Place, tcommon, Date, idcommon}, sepc ); end end if utilities.is_set (PostScript) and PostScript ~= sepc then text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc. if '.' == sepc then -- remove final seperator if present text = text:gsub ('%' .. sepc .. '$', ''); -- dot must be escaped here else text = mw.ustring.gsub (text, sepc .. '$', ''); -- using ustring for non-dot sepc (likely a non-Latin character) end end text = safe_join( {text, PostScript}, sepc ); -- Now enclose the whole thing in a <cite> element local options_t = {}; options_t.class = cite_class_attribute_make (config.CitationClass, Mode); local Ref = is_valid_parameter_value (A['Ref'], A:ORIGIN('Ref'), cfg.keywords_lists['ref'], nil, true); -- nil when |ref=harv; A['Ref'] else if 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then local namelist_t = {}; -- holds selected contributor, author, editor name list local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation if #c > 0 then -- if there is a contributor list namelist_t = c; -- select it elseif #a > 0 then -- or an author list namelist_t = a; elseif #e > 0 then -- or an editor list namelist_t = e; end local citeref_id; if #namelist_t > 0 then -- if there are names in namelist_t citeref_id = make_citeref_id (namelist_t, year); -- go make the CITEREF anchor if mw.uri.anchorEncode (citeref_id) == ((Ref and mw.uri.anchorEncode (Ref)) or '') then -- Ref may already be encoded (by {{sfnref}}) so citeref_id must be encoded before comparison utilities.set_message ('maint_ref_duplicates_default'); end else citeref_id = ''; -- unset end options_t.id = Ref or citeref_id; end if string.len (text:gsub('%b<>', '')) <= 2 then -- remove html and html-like tags; then get length of what remains; z.error_cats_t = {}; -- blank the categories list z.error_msgs_t = {}; -- blank the error messages list OCinSoutput = nil; -- blank the metadata string text = ''; -- blank the the citation utilities.set_message ('err_empty_citation'); -- set empty citation message and category end local render_t = {}; -- here we collect the final bits for concatenation into the rendered citation if is_preview_mode and (0 ~= #z.error_msgs_t or 0 ~= #z.maint_cats_t) then -- when in preview mode if not utilities.is_set (options_t.id) then -- and when this template has not created an anchor ID math.randomseed (tonumber (mw.getLanguage ('en'):formatDate ('U')) * 10000 + os.clock() * 10000); options_t.id = 'CITEREF_temp_preview_id_' .. math.random (100000, 999999); -- create temporary anchor ID for preview mode end end if utilities.is_set (options_t.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags options_t.id = mw.uri.anchorEncode(options_t.id); -- do this here; also used when adding preview warning messages table.insert (render_t, utilities.substitute (cfg.presentation['cite-id'], {options_t.id, mw.text.nowiki(options_t.class), text})); -- when |ref= is set or when there is a namelist else table.insert (render_t, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options_t.class), text})); -- when |ref=none or when namelist_t empty and |ref= is missing or is empty end if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span table.insert (render_t, utilities.substitute (cfg.presentation['ocins'], OCinSoutput)); -- format and append metadata to the citation end local template_name = cfg.citation_class_map_t[config.CitationClass]; local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]'; local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: '; if 0 ~= #z.error_msgs_t then mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, {template_link, options_t.id})); table.insert (render_t, ' '); -- insert a space between citation and its error messages table.sort (z.error_msgs_t); -- sort the error messages list; sorting includes wrapping <span> and <code> tags; hidden-error sorts ahead of visible-error local hidden = true; -- presume that the only error messages emited by this template are hidden for _, v in ipairs (z.error_msgs_t) do -- spin through the list of error messages if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name hidden = false; -- found one; so don't hide the error message prefix break; -- and done because no need to look further end end z.error_msgs_t[1] = table.concat ({utilities.error_comment (msg_prefix, hidden), z.error_msgs_t[1]}); -- add error message prefix to first error message to prevent extraneous punctuation table.insert (render_t, table.concat (z.error_msgs_t, '; ')); -- make a big string of error messages and add it to the rendering end if 0 ~= #z.maint_cats_t then mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, {template_link, options_t.id})); table.sort (z.maint_cats_t); -- sort the maintenance messages list local maint_msgs_t = {}; -- here we collect all of the maint messages if 0 == #z.error_msgs_t then -- if no error messages table.insert (maint_msgs_t, msg_prefix); -- insert message prefix in maint message livery end for _, v in ipairs( z.maint_cats_t ) do -- append maintenance categories table.insert (maint_msgs_t, -- assemble new maint message and add it to the maint_msgs_t table table.concat ({v, ' (', utilities.substitute (cfg.messages[':cat wikilink'], v), ')'}) ); end table.insert (render_t, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs_t, ' '))); -- wrap the group of maint messages with proper presentation and save end if not no_tracking_cats then local sort_key; local cat_wikilink = 'cat wikilink'; if cfg.enable_sort_keys then -- when namespace sort keys enabled local namespace_number = mw.title.getCurrentTitle().namespace; -- get namespace number for this wikitext sort_key = (0 ~= namespace_number and (cfg.name_space_sort_keys[namespace_number] or cfg.name_space_sort_keys.other)) or nil; -- get sort key character; nil for mainspace cat_wikilink = (not sort_key and 'cat wikilink') or 'cat wikilink sk'; -- make <cfg.messages> key end for _, v in ipairs (z.error_cats_t) do -- append error categories table.insert (render_t, utilities.substitute (cfg.messages[cat_wikilink], {v, sort_key})); end if cfg.id_limits_data_load_fail then -- boolean true when load failed utilities.set_message ('maint_id_limit_load_fail'); -- done here because this maint cat emits no message end for _, v in ipairs (z.maint_cats_t) do -- append maintenance categories table.insert (render_t, utilities.substitute (cfg.messages[cat_wikilink], {v, sort_key})); end for _, v in ipairs (z.prop_cats_t) do -- append properties categories table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); -- no sort keys end end return table.concat (render_t); -- make a big string and done end --[[--------------------------< V A L I D A T E >-------------------------------------------------------------- Looks for a parameter's name in one of several whitelists. Parameters in the whitelist can have three values: true - active, supported parameters false - deprecated, supported parameters nil - unsupported parameters ]] local function validate (name, cite_class, empty) local name = tostring (name); local enum_name; -- parameter name with enumerator (if any) replaced with '#' local state; local function state_test (state, name) -- local function to do testing of state values if true == state then return true; end -- valid actively supported parameter if false == state then if empty then return nil; end -- empty deprecated parameters are treated as unknowns deprecated_parameter (name); -- parameter is deprecated but still supported return true; end if 'tracked' == state then local base_name = name:gsub ('%d', ''); -- strip enumerators from parameter names that have them to get the base name utilities.add_prop_cat ('tracked-param', {base_name}, base_name); -- add a properties category; <base_name> modifies <key> return true; end return nil; end if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted return nil; end -- replace enumerator digit(s) with # (|last25= becomes |last#=) (mw.ustring because non-Western 'local' digits) enum_name = mw.ustring.gsub (name, '%d+$', '#'); -- where enumerator is last charaters in parameter name (these to protect |s2cid=) enum_name = mw.ustring.gsub (enum_name, '%d+([%-l])', '#%1'); -- where enumerator is in the middle of the parameter name; |author#link= is the oddity if 'document' == cite_class then -- special case for {{cite document}} state = whitelist.document_parameters_t[enum_name]; -- this list holds enumerated and nonenumerated parameters if true == state_test (state, name) then return true; end return false; end if utilities.in_array (cite_class, whitelist.preprint_template_list_t) then -- limited parameter sets allowed for these templates state = whitelist.limited_parameters_t[enum_name]; -- this list holds enumerated and nonenumerated parameters if true == state_test (state, name) then return true; end state = whitelist.preprint_arguments_t[cite_class][name]; -- look in the parameter-list for the template identified by cite_class if true == state_test (state, name) then return true; end return false; -- not supported because not found or name is set to nil end -- end limited parameter-set templates if utilities.in_array (cite_class, whitelist.unique_param_template_list_t) then -- template-specific parameters for templates that accept parameters from the basic argument list state = whitelist.unique_arguments_t[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class if true == state_test (state, name) then return true; end end -- if here, fall into general validation state = whitelist.common_parameters_t[enum_name]; -- all other templates; all normal parameters allowed; this list holds enumerated and nonenumerated parameters if true == state_test (state, name) then return true; end return false; -- not supported because not found or name is set to nil end --[=[-------------------------< I N T E R _ W I K I _ C H E C K >---------------------------------------------- check <value> for inter-language interwiki-link markup. <prefix> must be a MediaWiki-recognized language code. when these values have the form (without leading colon): [[<prefix>:link|label]] return label as plain-text [[<prefix>:link]] return <prefix>:link as plain-text return value as is else ]=] local function inter_wiki_check (parameter, value) local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists local _; if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so utilities.set_message ('err_bad_paramlink', parameter); -- emit an error message _, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink end return value; 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. There are two tests made: {{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name {{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki) cs1|2 shares some parameter names with XML/HTML attributes: 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 (parameter, value) local capture; value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc. capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes if capture and validate (capture) then -- if the capture is a valid parameter name utilities.set_message ('err_missing_pipe', parameter); end end --[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >-------------------------------------- look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked ]] local function has_extraneous_punc (param, value) if 'number' == type (param) then return; end param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize if cfg.punct_skip[param] then return; -- parameter name found in the skip table so done end if value:match ('[,;:]$') then utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat end if value:match ('^=') then -- sometimes an extraneous '=' character appears ... utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat end end --[[--------------------------< H A S _ T W L _ U R L >-------------------------------------------------------- look for The Wikipedia Library urls in url-holding parameters. TWL urls are accessible only for readers who are active extended confirmed Wikipedia editors. This function sets an error message when such urls are discovered and when appropriate, sets the |<param>-url-access=subscription. returns nothing. looks for: '.wikipedialibrary.idm.oclc.org' ]] local function has_twl_url (url_params_t, cite_args_t) local url_error_t = {}; -- sequence of url-holding parameters that have a TWL url for param, value in pairs (url_params_t) do if value:find ('%.wikipedialibrary%.idm%.oclc%.org') then -- has the TWL base url? table.insert (url_error_t, param); -- add parameter name to the error list end end if 0 ~= #url_error_t then -- non-zero when there are errors table.sort (url_error_t); -- sor for error messaging for i, param in ipairs (url_error_t) do if cfg.url_access_map_t[param] then -- if <param> has a matching -access parameter cite_args_t[cfg.url_access_map_t[param]] = cfg.keywords_xlate.subscription; -- set |<param>-url-access=subscription end url_error_t[i] = utilities.wrap_style ('parameter', param); -- make the parameter pretty for error message end utilities.set_message ('err_param_has_twl_url', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message end end --[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------ look for extraneous url parameter values; parameters listed in skip table are not checked ]] local function has_extraneous_url (non_url_param_t) local url_error_t = {}; check_for_url (non_url_param_t, url_error_t); -- extraneous url check if 0 ~= #url_error_t then -- non-zero when there are errors table.sort (url_error_t); utilities.set_message ('err_param_has_ext_link', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message end end --[[--------------------------< _ C I T A T I O N >------------------------------------------------------------ Module entry point frame – from template call (citation()); may be nil when called from another module args_t – table of all cs1|2 parameters in the template (the parent frame) config_t – table of template-supplied parameter (the #invoke frame) ]] local function _citation (frame, args_t, config_t) -- save a copy in case we need to display an error message in preview mode if not frame then frame = mw.getCurrentFrame(); -- if called from another module, get a frame for frame-provided functions end -- i18n: set the name that your wiki uses to identify sandbox subpages from sandbox template invoke (or can be set here) local sandbox = ((config_t.SandboxPath and '' ~= config_t.SandboxPath) and config_t.SandboxPath) or '/sandbox'; -- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}} is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true); -- is this invoke the sandbox module? sandbox = is_sandbox and sandbox or ''; -- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else cfg = mw.loadData ('Module:Citation/CS1/Configuration' .. sandbox); -- load sandbox versions of support modules when {{#invoke:Citation/CS1/sandbox|...}}; live modules else whitelist = mw.loadData ('Module:Citation/CS1/Whitelist' .. sandbox); utilities = require ('Module:Citation/CS1/Utilities' .. sandbox); validation = require ('Module:Citation/CS1/Date_validation' .. sandbox); identifiers = require ('Module:Citation/CS1/Identifiers' .. sandbox); metadata = require ('Module:Citation/CS1/COinS' .. sandbox); utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities local cite_args_t = {}; -- because args_t is the parent (template) frame args (which cannot be modified); params and their values will be placed here is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}')); local suggestions = {}; -- table where we store suggestions if we need to loadData them local error_text; -- used as a flag local capture; -- the single supported capture when matching unknown parameters using patterns local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing for k, v in pairs (args_t) do -- get parameters from the parent (template) frame v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string if v ~= '' then if cfg.enum_needs_xlation and 'string' == type (k) then -- for wikis that set date_names['local_digits'] to non-western digits k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- translate 'local' digits enumerators to Western 0-9 end if not validate( k, config_t.CitationClass ) then if type (k) ~= 'string' then -- exclude empty numbered parameters if v:match("%S+") ~= nil then error_text = utilities.set_message ('err_text_ignored', {v}); end elseif validate (k:lower(), config_t.CitationClass) then error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, k:lower()}); -- suggest the lowercase version of the parameter else if nil == suggestions.suggestions then -- if this table is nil then we need to load it suggestions = mw.loadData ('Module:Citation/CS1/Suggestions' .. sandbox); --load sandbox version of suggestion module when {{#invoke:Citation/CS1/sandbox|...}}; live module else 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 capture in pattern else the capture if a match if capture then -- if the pattern matches param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator) if validate (param, config_t.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists) error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message else error_text = utilities.set_message ('err_parameter_ignored', {k}); -- suggested param not supported by this template v = ''; -- unset end end end if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an explicit suggestion? if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config_t.CitationClass) then utilities.set_message ('err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}); else utilities.set_message ('err_parameter_ignored', {k}); v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists) end end end end cite_args_t[k] = v; -- save this parameter and its value elseif not utilities.is_set (v) then -- for empty parameters if not validate (k, config_t.CitationClass, true) then -- is this empty parameter a valid parameter k = ('' == k) and cfg.err_msg_supl.empty_str or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list end end end if 0 ~= #empty_unknowns then -- create empty unknown error message utilities.set_message ('err_param_unknown_empty', { 1 == #empty_unknowns and '' or 's', utilities.make_sep_list (#empty_unknowns, empty_unknowns) }); end local non_url_param_t = {}; -- table of parameters and values that are not url-holding parameters local url_param_t = {}; -- table of url-holding paramters and their values for k, v in pairs (cite_args_t) do if 'string' == type (k) then -- don't evaluate positional parameters has_invisible_chars (k, v); -- look for invisible characters end has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe? cite_args_t[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label if 'string' == type (k) then -- when parameter k is not positional if not cfg.url_skip[k] then -- and not in url skip table non_url_param_t[k] = v; -- make a parameter/value list for extraneous url check else -- and is in url skip table (a url-holding parameter) url_param_t[k] = v; -- make a parameter/value list to check for values that are The Wikipedia Library url end end end if cfg.suppress_archive_today_urls then has_archive_today_url (cite_args_t); -- look for and suppress archive.today urls and dependent parameters for all templates end has_extraneous_url (non_url_param_t); -- look for url in parameter values where a url does not belong has_twl_url (url_param_t, cite_args_t); -- look for url-holding parameters that hold a The Wikipedia Library url return table.concat ({ frame:extensionTag ('templatestyles', '', {src='Module:Citation/CS1' .. sandbox .. '/styles.css'}), citation0 (config_t, cite_args_t) }); end --[[--------------------------< C I T A T I O N >-------------------------------------------------------------- Template entry point ]] local function citation (frame) local config_t = {}; -- table to store parameters from the module {{#invoke:}} local args_t = frame:getParent().args; -- get template's preset parameters for k, v in pairs (frame.args) do -- get parameters from the {{#invoke}} frame config_t[k] = v; -- args_t[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep? end return _citation (frame, args_t, config_t) end --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ ]] return { citation = citation, -- template entry point _citation = _citation, -- module entry point } o0mp7ygqu5bibs2dabkkkkneiickrfx 828 654 9074 2026-05-15T07:13:42Z WikiBayer 737 [[:w:Special:PermanentLink/1340931211|Module:Citation/CS1/Configuration]] 9074 Scribunto text/plain local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates --[[--------------------------< S E T T I N G S >-------------------------------------------------------------- boolean settings used to control various things. these setting located here to make them easy to find ]] -- these settings local to this module only local local_digits_from_mediawiki = false; -- for i18n; when true, module fills date_names['local_digits'] from MediaWiki; manual fill required else; always false at en.wiki local local_date_names_from_mediawiki = false; -- for i18n; when true, module fills date_names['local']['long'] and date_names['local']['short'] from MediaWiki; -- manual translation required else; ; always false at en.wiki -- these settings exported to other modules local use_identifier_redirects = true; -- when true use redirect name for identifier label links; always true at en.wiki local local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki local date_name_auto_xlate_enable = false; -- when true translates English month-names to the local-wiki's language month names; always false at en.wiki local date_digit_auto_xlate_enable = false; -- when true translates Western date digit to the local-wiki's language digits (date_names['local_digits']); always false at en.wiki local enable_sort_keys = true; -- when true module adds namespace sort keys to error and maintenance category links local suppress_archive_today_urls = true; -- when true module suppresses all parameters with an archive.today url and any deprendent parameters --[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------ List of namespaces identifiers for namespaces that will not be included in citation error categories. Same as setting notracking = true by default. For wikis that have a current version of Module:cs1 documentation support, this #invoke will return an unordered list of namespace names and their associated identifiers: {{#invoke:cs1 documentation support|uncategorized_namespace_lister|all=<anything>}} ]] local uncategorized_namespaces_t = {[2]=true}; -- init with user namespace id for k, _ in pairs (mw.site.talkNamespaces) do -- add all talk namespace ids uncategorized_namespaces_t[k] = true; end local uncategorized_subpages = {'/[Ss]andbox', '/[Tt]estcases', '/[^/]*[Ll]og', '/[Aa]rchive'}; -- list of Lua patterns found in page names of pages we should not categorize --[[ at en.wiki Greek characters are used as sort keys for certain items in a category so that those items are placed at the end of a category page. See Wikipedia:Categorization#Sort_keys. That works well for en.wiki because English is written using the Latn script. This may not work well for other languages. At en.wiki it is desireable to place content from certain namespaces at the end of a category listing so the module adds sort keys to error and maintenance category links when rendering a cs1|2 template on a page in that namespace. i18n: if this does not work well for your language, set <enable_sort_keys> to false. ]] local name_space_sort_keys = { -- sort keys to be used with these namespaces: [4] = 'ω', -- wikipedia; omega [10] = 'τ', -- template; tau [118] = 'Δ', -- draft; delta ['other'] = 'ο', -- all other non-talk namespaces except main (article); omicron } --[[--------------------------< M E S S A G E S >-------------------------------------------------------------- Translation table The following contains fixed text that may be output as part of a citation. This is separated from the main body to aid in future translations of this module. ]] local messages = { ['agency'] = '$1 $2', -- $1 is sepc, $2 is agency ['archived-dead'] = 'Archived from $1 on $2', ['archived-live'] = '$1 from the original on $2', ['archived-unfit'] = 'Archived from the original on $1', ['archived'] = 'Archived', ['by'] = 'By', -- contributions to authored works: introduction, foreword, afterword ['cartography'] = 'Cartography by $1', ['editor'] = 'ed.', ['editors'] = 'eds.', ['edition'] = '($1&nbsp;ed.)', ['episode'] = 'Episode $1', ['et al'] = 'et&nbsp;al.', ['in'] = 'In', -- edited works ['inactive'] = ' (inactive $1)', -- $1 is date which the doi was found to be broken in ['inset'] = '$1 inset', ['interview'] = 'Interviewed by $1', invisible_1 = '$1 $2', -- $1 stripmarker name; $2 is text from <invisible_chars[1]> invisible_2 = '$1 character', -- $1 character name from <invisible_chars[1]> ['mismatch'] = '<code class="cs1-code">&#124;$1=</code> / <code class="cs1-code">&#124;$2=</code> mismatch', -- $1 is year param name; $2 is date param name ['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]:&nbsp;$1', ['notitle'] = 'No title', -- for |title=(()) and (in the future) |title=none ['original'] = 'the original', ['origdate'] = ' [$1]', ['published'] = ' (published $1)', ['retrieved'] = 'Retrieved $1', ['season'] = 'Season $1', ['section'] = '§&nbsp;$1', ['sections'] = '§§&nbsp;$1', ['series'] = '$1 $2', -- $1 is sepc, $2 is series ['seriesnum'] = 'Series $1', ['translated'] = 'Translated by $1', ['type'] = ' ($1)', -- for titletype wikidata = 'Wikidata', -- these used for interwikilinked author/editor/... names wikipedia = 'Wikipedia', wikisource = 'Wikisource', ['written'] = 'Written at $1', ['vol'] = '$1 Vol.&nbsp;$2', -- $1 is sepc; bold journal style volume is in presentation{} ['vol-no'] = '$1 Vol.&nbsp;$2, no.&nbsp;$3', -- sepc, volume, issue (alternatively insert $1 after $2, but then we'd also have to change capitalization) ['issue'] = '$1 No.&nbsp;$2', -- $1 is sepc ['art'] = '$1 Art.&nbsp;$2', -- $1 is sepc; for {{cite conference}} only ['vol-art'] = '$1 Vol.&nbsp;$2, art.&nbsp;$3', -- sepc, volume, article-number; for {{cite conference}} only ['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{} ['j-issue'] = ' ($1)', ['j-article-num'] = ' $1', -- TODO: any punctuation here? static text? ['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc ['p-prefix'] = "$1 p.&nbsp;$2", -- $1 is sepc ['pp-prefix'] = "$1 pp.&nbsp;$2", -- $1 is sepc ['j-page(s)'] = ': $1', -- same for page and pages ['sheet'] = '$1 Sheet&nbsp;$2', -- $1 is sepc ['sheets'] = '$1 Sheets&nbsp;$2', -- $1 is sepc ['j-sheet'] = ': Sheet&nbsp;$1', ['j-sheets'] = ': Sheets&nbsp;$1', ['language'] = '(in $1)', ['via'] = " &ndash; via $1", ['event'] = 'Event occurs at', ['minutes'] = ' $1 minutes in', -- $1 is the number of minutes -- Determines the location of the help page ['help page link'] = 'Help:CS1 errors', ['help page label'] = 'help', -- categories ['cat wikilink'] = '[[Category:$1]]', -- $1 is the category name ['cat wikilink sk'] = '[[Category:$1|$2]]', -- $1 is the category name; $2 is namespace sort key [':cat wikilink'] = '[[:Category:$1|link]]', -- category name as maintenance message wikilink; $1 is the category name -- Internal errors (should only occur if configuration is bad) ['undefined_error'] = 'Called with an undefined error condition', ['unknown_ID_key'] = 'Unrecognized ID key: ', -- an ID key in id_handlers not found in ~/Identifiers func_map{} ['unknown_ID_access'] = 'Unrecognized ID access keyword: ', -- an ID access keyword in id_handlers not found in keywords_lists['id-access']{} ['unknown_argument_map'] = 'Argument map not defined for this variable', ['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty', ['warning_msg_e'] = '<span style="color:#d33"><code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code>: this [[#$2|reference]] has errors</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link; $2 is anchor ID ['warning_msg_m'] = '<span style="color:#085"><code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code>: this [[#$2|reference]] has maintenance messages</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link; $2 is anchor ID } --[[--------------------------< C I T A T I O N _ C L A S S _ M A P >------------------------------------------ this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when the value assigned to |CitationClass= is different from the canonical template name. |CitationClass= values are used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the template's documentation when an article is displayed in preview mode. ]] local citation_class_map_t = { -- TODO: in Module:Cite/config write a function to use this table arxiv = 'cite arXiv', -- as the source for known_templates_t and citation_classes_t ['audio-visual'] = 'cite AV media', ['AV-media-notes'] = 'cite AV media notes', biorxiv = 'cite bioRxiv', book = 'cite book', citation = 'citation', citeseerx = 'cite CiteSeerX', conference = 'cite conference', document = 'cite document', encyclopaedia = 'cite encyclopedia', episode = 'cite episode', interview = 'cite interview', journal = 'cite journal', magazine = 'cite magazine', mailinglist = 'cite mailing list', map = 'cite map', medrxiv = 'cite medRxiv', news = 'cite news', newsgroup = 'cite newsgroup', podcast = 'cite podcast', pressrelease = 'cite press release', report = 'cite report', serial = 'cite serial', sign = 'cite sign', speech = 'cite speech', ssrn = 'cite SSRN', techreport = 'cite tech report', thesis = 'cite thesis', web = 'cite web', } --[=[-------------------------< E T _ A L _ P A T T E R N S >-------------------------------------------------- This table provides Lua patterns for the phrase "et al" and variants in name text (author, editor, etc.). The main module uses these to identify and emit the 'etal' message. ]=] local et_al_patterns = { "[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$", -- variations on the 'et al' theme "[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.;,\"']*$", -- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match) "[;,]? *%f[%a]and [Oo]thers", -- an alternative to et al. "%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form "%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax) "[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form } --[[--------------------------< P R E S E N T A T I O N >------------------------ Fixed presentation markup. Originally part of citation_config.messages it has been moved into its own, more semantically correct place. ]] local presentation = { -- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display ['hidden-error'] = '<span class="cs1-hidden-error citation-comment">$1</span>', ['visible-error'] = '<span class="cs1-visible-error citation-comment">$1</span>', ['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>', ['accessdate'] = '<span class="reference-accessdate">$1$2</span>', -- to allow editors to hide accessdate using personal CSS ['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like ['cite'] = '<cite class="$1">$2</cite>'; -- for use when citation does not have a namelist and |ref= not set so no id="..." attribute ['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when when |ref= is set or when citation has a namelist ['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc. ['interwiki'] = ' <span class="cs1-format">[in $1]</span>', -- for interwiki-language-linked author, editor, etc ['interproj'] = ' <span class="cs1-format">[at $1]</span>', -- for interwiki-project-linked author, editor, etc (:d: and :s: supported; :w: ignored) -- various access levels, for |access=, |doi-access=, |arxiv=, ... -- narrow no-break space &#8239; may work better than nowrap CSS. Or not? Browser support? ['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon ['free'] = {class='id-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css ['registration'] = {class='id-lock-registration', title='Free registration required'}, ['limited'] = {class='id-lock-limited', title='Free access subject to limited trial, subscription normally required'}, ['subscription'] = {class='id-lock-subscription', title='Paid subscription required'}, ['interwiki-icon'] = '<span class="$1" title="$2">$3</span>', ['class-wikisource'] = 'cs1-ws-icon', ['italic-title'] = "''$1''", ['kern-left'] = '<span class="cs1-kern-left"></span>$1', -- spacing to use when title contains leading single or double quote mark ['kern-right'] = '$1<span class="cs1-kern-right"></span>', -- spacing to use when title contains trailing single or double quote mark ['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span> ['nowrap2'] = '<span class="nowrap">$1</span> $2', -- for nowrapping portions of an item: <span ...>dd mmmm</span> yyyy (note white space) ['ocins'] = '<span title="$1" class="Z3988"></span>', ['parameter'] = '<code class="cs1-code">&#124;$1=</code>', ['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character ['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string) ['quoted-text'] = '<q>$1</q>', -- for wrapping |quote= content ['quoted-title'] = '"$1"', ['sep_cs1'] = '.', -- CS1 element separator ['sep_cs2'] = ',', -- CS2 separator ['sep_nl'] = ';', -- CS1|2 style name-list separator between names is a semicolon ['sep_nl_and'] = ' and ', -- used as last nl sep when |name-list-style=and and list has 2 items ['sep_nl_end'] = '; and ', -- used as last nl sep when |name-list-style=and and list has 3+ names ['sep_name'] = ', ', -- CS1|2 style last/first separator is <comma><space> ['sep_nl_vanc'] = ',', -- Vancouver style name-list separator between authors is a comma ['sep_name_vanc'] = ' ', -- Vancouver style last/first separator is a space ['sep_list'] = ', ', -- used for |language= when list has 3+ items except for last sep which uses sep_list_end ['sep_list_pair'] = ' and ', -- used for |language= when list has 2 items ['sep_list_end'] = ', and ', -- used as last list sep for |language= when list has 3+ items ['trans-italic-title'] = "&#91;''$1''&#93;", ['trans-quoted-title'] = "&#91;$1&#93;", -- for |trans-title= and |trans-quote= ['vol-bold'] = '$1 <b>$2</b>', -- sepc, volume; for bold journal cites; for other cites ['vol'] in messages{} } --[[--------------------------< A L I A S E S >--------------------------------- Aliases table for commonly passed parameters. Parameter names on the right side in the assignments in this table must have been defined in the Whitelist before they will be recognized as valid parameter names ]] local aliases = { ['AccessDate'] = {'access-date', 'accessdate'}, -- Used by InternetArchiveBot ['Agency'] = 'agency', ['ArchiveDate'] = {'archive-date', 'archivedate'}, -- Used by InternetArchiveBot ['ArchiveFormat'] = 'archive-format', ['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot ['ArticleNumber'] = 'article-number', ['ASINTLD'] = 'asin-tld', ['At'] = 'at', -- Used by InternetArchiveBot ['Authors'] = {'people', 'credits'}, ['BookTitle'] = {'book-title', 'booktitle'}, ['Cartography'] = 'cartography', ['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'}, ['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format', 'article-format', 'section-format'}; ['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url'}, -- Used by InternetArchiveBot ['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access', 'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot ['Class'] = 'class', -- cite arxiv and arxiv identifier ['Collaboration'] = 'collaboration', ['Conference'] = {'conference', 'event'}, ['ConferenceFormat'] = 'conference-format', ['ConferenceURL'] = 'conference-url', -- Used by InternetArchiveBot ['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only ['Degree'] = 'degree', ['DF'] = 'df', ['DisplayAuthors'] = {'display-authors', 'display-subjects'}, ['DisplayContributors'] = 'display-contributors', ['DisplayEditors'] = 'display-editors', ['DisplayInterviewers'] = 'display-interviewers', ['DisplayTranslators'] = 'display-translators', ['Docket'] = 'docket', ['DoiBroken'] = 'doi-broken-date', ['Edition'] = 'edition', ['Embargo'] = 'pmc-embargo-date', ['Encyclopedia'] = {'encyclopedia', 'encyclopaedia', 'dictionary'}, -- cite encyclopedia only ['Episode'] = 'episode', -- cite serial only TODO: make available to cite episode? ['Format'] = 'format', ['ID'] = {'id', 'ID'}, ['Inset'] = 'inset', ['Issue'] = {'issue', 'number'}, ['Language'] = {'language', 'lang'}, ['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only ['Map'] = 'map', -- cite map only ['MapFormat'] = 'map-format', -- cite map only ['MapURL'] = {'map-url', 'mapurl'}, -- cite map only -- Used by InternetArchiveBot ['MapUrlAccess'] = 'map-url-access', -- cite map only -- Used by InternetArchiveBot ['Minutes'] = 'minutes', ['Mode'] = 'mode', ['NameListStyle'] = 'name-list-style', ['Network'] = 'network', ['Newsgroup'] = 'newsgroup', -- cite newsgroup only ['NoPP'] = {'no-pp', 'nopp'}, ['NoTracking'] = {'no-tracking', 'template-doc-demo'}, ['Number'] = 'number', -- this case only for cite techreport ['OrigDate'] = {'orig-date', 'orig-year', 'origyear'}, ['Others'] = 'others', ['Page'] = {'page', 'p'}, -- Used by InternetArchiveBot ['Pages'] = {'pages', 'pp'}, -- Used by InternetArchiveBot ['Periodical'] = {'journal', 'magazine', 'newspaper', 'periodical', 'website', 'work'}, ['Place'] = {'place', 'location'}, ['PostScript'] = 'postscript', ['PublicationDate'] = {'publication-date', 'publicationdate'}, ['PublicationPlace'] = {'publication-place', 'publicationplace'}, ['PublisherName'] = {'publisher', 'institution'}, ['Quote'] = {'quote', 'quotation'}, ['QuotePage'] = 'quote-page', ['QuotePages'] = 'quote-pages', ['Ref'] = 'ref', ['Scale'] = 'scale', ['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry', 'script-article', 'script-section'}, ['ScriptEncyclopedia'] = {'script-encyclopedia', 'script-encyclopaedia'}, -- cite encyclopedia only ['ScriptMap'] = 'script-map', ['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-website', 'script-work'}, ['ScriptQuote'] = 'script-quote', ['ScriptTitle'] = 'script-title', -- Used by InternetArchiveBot ['Season'] = 'season', ['Sections'] = 'sections', -- cite map only ['Series'] = {'series', 'version'}, ['SeriesLink'] = {'series-link', 'serieslink'}, ['SeriesNumber'] = {'series-number', 'series-no'}, ['Sheet'] = 'sheet', -- cite map only ['Sheets'] = 'sheets', -- cite map only ['Station'] = 'station', ['Time'] = 'time', ['TimeCaption'] = 'time-caption', ['Title'] = 'title', -- Used by InternetArchiveBot ['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot ['TitleNote'] = {'title-note', 'department'}, ['TitleType'] = {'type', 'medium'}, ['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', 'trans-entry', 'trans-section'}, ['Transcript'] = 'transcript', ['TranscriptFormat'] = 'transcript-format', ['TranscriptURL'] = 'transcript-url', -- Used by InternetArchiveBot ['TransEncyclopedia'] = {'trans-encyclopedia', 'trans-encyclopaedia'}, -- cite encyclopedia only ['TransMap'] = 'trans-map', -- cite map only ['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', 'trans-periodical', 'trans-website', 'trans-work'}, ['TransQuote'] = 'trans-quote', ['TransTitle'] = 'trans-title', -- Used by InternetArchiveBot ['URL'] = {'url', 'URL'}, -- Used by InternetArchiveBot ['UrlAccess'] = 'url-access', -- Used by InternetArchiveBot ['UrlStatus'] = 'url-status', -- Used by InternetArchiveBot ['Vauthors'] = 'vauthors', ['Veditors'] = 'veditors', ['Via'] = 'via', ['Volume'] = 'volume', ['Year'] = 'year', ['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given", "subject-first#", "subject#-first", "subject-given#", "subject#-given", "given#"}, ['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname", "subject-last#", "subject#-last", "subject-surname#", "subject#-surname", "author#", 'host#', "subject#", "surname#"}, ['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#", "subject#-link", "authorlink#", "author#link"}, ['AuthorList-Mask'] = {"author-mask#", "author#-mask", "subject-mask#", "subject#-mask"}, ['ContributorList-First'] = {'contributor-first#', 'contributor#-first', 'contributor-given#', 'contributor#-given'}, ['ContributorList-Last'] = {'contributor-last#', 'contributor#-last', 'contributor-surname#', 'contributor#-surname', 'contributor#'}, ['ContributorList-Link'] = {'contributor-link#', 'contributor#-link'}, ['ContributorList-Mask'] = {'contributor-mask#', 'contributor#-mask'}, ['EditorList-First'] = {"editor-first#", "editor#-first", "editor-given#", "editor#-given"}, ['EditorList-Last'] = {"editor-last#", "editor#-last", "editor-surname#", "editor#-surname", "editor#"}, ['EditorList-Link'] = {"editor-link#", "editor#-link"}, ['EditorList-Mask'] = {"editor-mask#", "editor#-mask"}, ['InterviewerList-First'] = {'interviewer-first#', 'interviewer#-first', 'interviewer-given#', 'interviewer#-given'}, ['InterviewerList-Last'] = {'interviewer-last#', 'interviewer#-last', 'interviewer-surname#', 'interviewer#-surname', 'interviewer#'}, ['InterviewerList-Link'] = {'interviewer-link#', 'interviewer#-link'}, ['InterviewerList-Mask'] = {'interviewer-mask#', 'interviewer#-mask'}, ['TranslatorList-First'] = {'translator-first#', 'translator#-first', 'translator-given#', 'translator#-given'}, ['TranslatorList-Last'] = {'translator-last#', 'translator#-last', 'translator-surname#', 'translator#-surname', 'translator#'}, ['TranslatorList-Link'] = {'translator-link#', 'translator#-link'}, ['TranslatorList-Mask'] = {'translator-mask#', 'translator#-mask'}, } --[[--------------------------< D E P E N D E N C I E S _ T >-------------------------------------------------- a table of url-holding parameters upon which other parameters are dependent. this table is used by has_archive_today_url() to suppress parameters that are dependant upon a url-holding parameter that has as a value an archive.today (or alternate tld) url. archive.today is deprecated at en.wiki; see Wikipedia:Requests_for_comment/Archive.is_RFC_5 ]] local url_dependency_map_t = { -- table of url-holding parameters and the meta-parameters that are dependent on them ['url'] = {'AccessDate', 'ArchiveURL', 'Format', 'UrlAccess'}, ['archive-url'] = {'ArchiveDate', 'ArchiveFormat', 'UrlStatus'}, ['archiveurl'] = {'ArchiveDate', 'ArchiveFormat', 'UrlStatus'}, ['article-url'] = {'ChapterFormat', 'ChapterUrlAccess'}, ['chapter-url'] = {'ChapterFormat', 'ChapterUrlAccess'}, ['conference-url'] = {'ConferenceFormat'}, ['contribution-url'] = {'ChapterFormat', 'ChapterUrlAccess'}, ['entry-url'] = {'ChapterFormat', 'ChapterUrlAccess'}, ['map-url'] = {'MapFormat', 'MapUrlAccess'}, ['section-url'] = {'ChapterFormat', 'ChapterUrlAccess'}, ['transcript-url'] = {'TranscriptFormat'}, }; local dependencies_t = {}; -- the table of url-holding parameters and their dependent parameters for url_param, meta_parameters_t in pairs (url_dependency_map_t) do -- sequence of meta-parameters (indexes) into <aliases> table local dependant_params_t = {}; -- collection of parameters that are dependent on this <url_param> for _, meta_parameter in ipairs (meta_parameters_t) do -- for each <aliases> meta-parameter (index) if 'string' == type (aliases[meta_parameter]) then -- for single parameter names (no aliases), <aliases[meta_parameter]> will be a string table.insert (dependant_params_t, aliases[meta_parameter]); -- add to this <url_param>'s dependency sequence else for _, alias in ipairs (aliases[meta_parameter]) do -- for each alias in aliases[meta_parameter] (aliases['AccessDate'] for example) table.insert (dependant_params_t, alias); -- add to this <url_param>'s dependency sequence end end end dependencies_t[url_param] = dependant_params_t; -- add the <url_param> and its dependent parameters end --[[--------------------------< P U N C T _ S K I P >--------------------------- builds a table of parameter names that the extraneous terminal punctuation check should not check. ]] local punct_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value 'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters 'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators 'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters } local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls 'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls } local function build_skip_table (skip_t, meta_params) for _, meta_param in ipairs (meta_params) do -- for each meta parameter key local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name if 'string' == type (params) then skip_t[params] = 1; -- just a single parameter else for _, param in ipairs (params) do -- get the parameter name skip_t[param] = 1; -- add the parameter name to the skip table local count; param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters if 0 ~= count then -- if removed skip_t[param] = 1; -- add param name without enumerator marker end end end end return skip_t; end local punct_skip = {}; local url_skip = {}; --[[--------------------------< U R L _ A C C E S S _ M A P >-------------------------------------------------- this table used by the wikipedia library url test, has_twl_url(), which automatically sets a url-access parameter to 'subscription' when it discovers a wikipedia library url in any of the url-holding paramters used as keys in this table. translators: if your wiki uses parameter names for these url-holding parameters and their matching -access parameters, add your wiki's parameters to this list. Leave the English parameters in place. TODO: is there a better way to do this? ]] local url_access_map_t = { ['chapter-url'] = 'chapter-url-access', ['contribution-url'] = 'contribution-url-access', ['entry-url'] = 'entry-url-access', ['article-url'] = 'article-url-access', ['section-url'] = 'section-url-access', ['map-url'] = 'map-url-access', ['mapurl'] = 'map-url-access', ['url'] = 'url-access', ['URL'] = 'url-access' } --[[--------------------------< S I N G L E - L E T T E R S E C O N D - L E V E L D O M A I N S >---------- this is a list of tlds that are known to have single-letter second-level domain names. This list does not include ccTLDs which are accepted in is_domain_name(). ]] local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'media', 'org', 'today'}; --[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------ This table is primarily here to support internationalization. Translations in this table are used, for example, when an error message, category name, etc., is extracted from the English alias key. There may be other cases where this translation table may be useful. ]] local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191'; local special_case_translation = { author = 'author', editor = 'editor', name_list_params = '$1-name-list parameters', -- $1 is 'author' or 'editor'; used with err_redundant_parameters ['AuthorList'] = 'authors list', -- used to assemble maintenance category names ['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base maintenance category names in maint_cats{} table below ['EditorList'] = 'editors list', -- must match the names of the actual categories ['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names() ['TranslatorList'] = 'translators list', -- Lua patterns to match pseudo-titles used by InternetArchiveBot and others as placeholder for unknown |title= value ['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title ['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki ['local'] = nil, -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language }, -- Lua patterns to match generic titles; usually created by bots or reference filling tools -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language -- generic titles and patterns in this table should be lowercase only -- leave ['local'] nil except when there is a matching generic title in your language -- boolean 'true' for plain-text searches; 'false' for pattern searches ['generic_titles'] = { ['accept'] = { }, ['reject'] = { {['en'] = {'^wayback%s+machine$', false}, ['local'] = nil}, {['en'] = {'are you a robot', true}, ['local'] = nil}, {['en'] = {'hugedomains', true}, ['local'] = nil}, {['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil}, {['en'] = {'page not found', true}, ['local'] = nil}, {['en'] = {'subscribe to read', true}, ['local'] = nil}, {['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil}, {['en'] = {'website is for sale', true}, ['local'] = nil}, {['en'] = {'^404', false}, ['local'] = nil}, {['en'] = {'error[ %-]404', false}, ['local'] = nil}, {['en'] = {'internet archive wayback machine', true}, ['local'] = nil}, {['en'] = {'log into facebook', true}, ['local'] = nil}, {['en'] = {'login • instagram', true}, ['local'] = nil}, {['en'] = {'redirecting...', true}, ['local'] = nil}, {['en'] = {'usurped title', true}, ['local'] = nil}, -- added by a GreenC bot {['en'] = {'wayback machine', true}, ['local'] = nil}, {['en'] = {'webcite query result', true}, ['local'] = nil}, {['en'] = {'wikiwix\'s cache', true}, ['local'] = nil}, {['en'] = {'bot verification', true}, ['local'] = nil}, } }, -- boolean 'true' for plain-text searches, search string must be lowercase only -- boolean 'false' for pattern searches -- leave ['local'] nil except when there is a matching generic name in your language ['generic_names'] = { ['accept'] = { {['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false}, ['local'] = nil}, }, ['reject'] = { {['en'] = {'about us', true}, ['local'] = nil}, {['en'] = {'%f[%a][Aa]dvisor%f[%A]', false}, ['local'] = nil}, {['en'] = {'allmusic', true}, ['local'] = nil}, {['en'] = {'%f[%a][Aa]uthor%f[%A]', false}, ['local'] = nil}, {['en'] = {'^[Bb]ureau$', false}, ['local'] = nil}, {['en'] = {'business', true}, ['local'] = nil}, {['en'] = {'cnn', true}, ['local'] = nil}, {['en'] = {'collaborator', true}, ['local'] = nil}, {['en'] = {'^[Cc]ompany$', false}, ['local'] = nil}, {['en'] = {'contributor', true}, ['local'] = nil}, {['en'] = {'contact us', true}, ['local'] = nil}, {['en'] = {'correspondent', true}, ['local'] = nil}, {['en'] = {'^[Dd]esk$', false}, ['local'] = nil}, {['en'] = {'directory', true}, ['local'] = nil}, {['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false}, ['local'] = nil}, {['en'] = {'[,%.%s]%f[e]eds?%.?$', false}, ['local'] = nil}, {['en'] = {'^eds?[%.,;]', false}, ['local'] = nil}, {['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false}, ['local'] = nil}, {['en'] = {'%f[%a][Ee]dited%f[%A]', false}, ['local'] = nil}, {['en'] = {'%f[%a][Ee]ditors?%f[%A]', false}, ['local'] = nil}, {['en'] = {'%f[%a][Ee]mail%f[%A]', false}, ['local'] = nil}, {['en'] = {'facebook', true}, ['local'] = nil}, {['en'] = {'google', true}, ['local'] = nil}, {['en'] = {'^[Gg]roup$', false}, ['local'] = nil}, {['en'] = {'home page', true}, ['local'] = nil}, {['en'] = {'^[Ii]nc%.?$', false}, ['local'] = nil}, {['en'] = {'instagram', true}, ['local'] = nil}, {['en'] = {'interviewer', true}, ['local'] = nil}, {['en'] = {'^[Ll]imited$', false}, ['local'] = nil}, {['en'] = {'linkedIn', true}, ['local'] = nil}, {['en'] = {'^[Nn]ews$', false}, ['local'] = nil}, {['en'] = {'[Nn]ews[ %-]?[Rr]oom', false}, ['local'] = nil}, {['en'] = {'pinterest', true}, ['local'] = nil}, {['en'] = {'policy', true}, ['local'] = nil}, {['en'] = {'privacy', true}, ['local'] = nil}, {['en'] = {'reuters', true}, ['local'] = nil}, {['en'] = {'translator', true}, ['local'] = nil}, {['en'] = {'tumblr', true}, ['local'] = nil}, {['en'] = {'twitter', true}, ['local'] = nil}, {['en'] = {'site name', true}, ['local'] = nil}, {['en'] = {'statement', true}, ['local'] = nil}, {['en'] = {'submitted', true}, ['local'] = nil}, {['en'] = {'super.?user', false}, ['local'] = nil}, {['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false}, ['local'] = nil}, {['en'] = {'updated', true}, ['local'] = nil}, {['en'] = {'verfasser', true}, ['local'] = nil}, } } } --[[--------------------------< D A T E _ N A M E S >---------------------------------------------------------- This table of tables lists local language date names and fallback English date names. The code in Date_validation will look first in the local table for valid date names. If date names are not found in the local table, the code will look in the English table. Because citations can be copied to the local wiki from en.wiki, the English is required when the date-name translation function date_name_xlate() is used. In these tables, season numbering is defined by Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/) which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard defines various divisions using numbers 21-41. CS1|2 only supports generic seasons. EDTF does support the distinction between north and south hemisphere seasons but CS1|2 has no way to make that distinction. 33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each) The standard does not address 'named' dates so, for the purposes of CS1|2, Easter and Christmas are defined here as 98 and 99, which should be out of the ISO 8601 (EDTF) range of uses for a while. local_date_names_from_mediawiki is a boolean. When set to: true – module will fetch local month names from MediaWiki for both date_names['local']['long'] and date_names['local']['short']; this will unconditionally overwrite manual translations false – module will *not* fetch local month names from MediaWiki Caveat lector: There is no guarantee that MediaWiki will provide short month names. At your wiki you can test the results of the MediaWiki fetch in the debug console with this command (the result is alpha sorted): =mw.dumpObject (p.date_names['local']) While the module can fetch month names from MediaWiki, it cannot fetch the quarter, season, and named date names from MediaWiki. Those must be translated manually. ]] local local_date_names_from_mediawiki = true; -- when false, manual translation required for date_names['local']['long'] and date_names['local']['short']; overwrites manual translations -- when true, module fetches long and short month names from MediaWiki local date_names = { ['en'] = { -- English ['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12}, ['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12}, ['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36}, ['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23}, ['named'] = {['Easter'] = 98, ['Christmas'] = 99}, }, -- when local_date_names_from_mediawiki = false ['local'] = { -- replace these English date names with the local language equivalents ['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12}, ['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12}, ['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36}, ['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23}, ['named'] = {['Easter'] = 98, ['Christmas'] = 99}, }, ['inv_local_long'] = {}, -- used in date reformatting & translation; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc. ['inv_local_short'] = {}, -- used in date reformatting & translation; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc. ['inv_local_quarter'] = {}, -- used in date translation; copy of date_names['local'].quarter where k/v are inverted: [1]='<local name>' etc. ['inv_local_season'] = {}, -- used in date translation; copy of date_names['local'].season where k/v are inverted: [1]='<local name>' etc. ['inv_local_named'] = {}, -- used in date translation; copy of date_names['local'].named where k/v are inverted: [1]='<local name>' etc. ['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9 ['xlate_digits'] = {}, } if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled local long_t = {}; local short_t = {}; for i=1, 12 do -- loop 12x and local name = lang_obj:formatDate('F', '2022-' .. i .. '-1'); -- get long month name for each i long_t[name] = i; -- save it name = lang_obj:formatDate('M', '2022-' .. i .. '-1'); -- get short month name for each i short_t[name] = i; -- save it end date_names['local']['long'] = long_t; -- write the long table – overwrites manual translation date_names['local']['short'] = short_t; -- write the short table – overwrites manual translation end -- create inverted date-name tables for reformatting and/or translation for _, invert_t in pairs {{'long', 'inv_local_long'}, {'short', 'inv_local_short'}, {'quarter', 'inv_local_quarter'}, {'season', 'inv_local_season'}, {'named', 'inv_local_named'}} do for name, i in pairs (date_names['local'][invert_t[1]]) do -- this table is ['name'] = i date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd end end if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled local digits_t = {}; for i=0, 9 do -- loop 10x and digits_t [lang_obj:formatNum (i)] = tostring (i); -- format the loop indexer as local lang table index and assign loop indexer (a string) as the value end date_names['local_digits'] = digits_t; end for ld, ed in pairs (date_names.local_digits) do -- make a digit translation table for simple date translation from en to local language using local_digits table date_names.xlate_digits [ed] = ld; -- en digit becomes index with local digit as the value end local df_template_patterns = { -- table of redirects to {{Use dmy dates}} and {{Use mdy dates}} '{{ *[Uu]se +(dmy) +dates *[|}]', -- 1159k -- sorted by approximate transclusion count '{{ *[Uu]se +(mdy) +dates *[|}]', -- 212k '{{ *[Uu]se +(MDY) +dates *[|}]', -- 788 '{{ *[Uu]se +(DMY) +dates *[|}]', -- 343 '{{ *([Mm]dy) *[|}]', -- 176 '{{ *[Uu]se *(dmy) *[|}]', -- 156 + 18 '{{ *[Uu]se *(mdy) *[|}]', -- 149 + 11 '{{ *([Dd]my) *[|}]', -- 56 '{{ *[Uu]se +(MDY) *[|}]', -- 5 '{{ *([Dd]MY) *[|}]', -- 3 '{{ *[Uu]se(mdy)dates *[|}]', -- 1 '{{ *[Uu]se +(DMY) *[|}]', -- 0 '{{ *([Mm]DY) *[|}]', -- 0 } local title_object = mw.title.getCurrentTitle(); local content; -- done this way so that unused templates appear in unused-template-reports; self-transcluded makes them look like they are used if 10 ~= title_object.namespace then -- all namespaces except Template content = title_object:getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625 end local function get_date_format () if not content then -- nil content when we're in template return nil; -- auto-formatting does not work in Template space so don't set global_df end for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format if match then local use_dates_template = content:match ('%b{}', start); -- get the whole template if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)'); else return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df= end end end end local global_df; -- TODO: add this to <global_cs1_config_t>? --[[-----------------< V O L U M E , I S S U E , P A G E S >------------------ These tables hold cite class values (from the template invocation) and identify those templates that support |volume=, |issue=, and |page(s)= parameters. Cite conference and cite map require further qualification which is handled in the main module. ]] local templates_using_volume = {'citation', 'audio-visual', 'book', 'conference', 'encyclopaedia', 'interview', 'journal', 'magazine', 'map', 'news', 'report', 'techreport', 'thesis'} local templates_using_issue = {'citation', 'conference', 'episode', 'interview', 'journal', 'magazine', 'map', 'news', 'podcast'} local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'} --[[ These tables control when it is appropriate for {{citation}} to render |volume= and/or |issue=. The parameter names in the tables constrain {{citation}} so that its renderings match the renderings of the equivalent cs1 templates. For example, {{cite web}} does not support |volume= so the equivalent {{citation |website=...}} must not support |volume=. ]] local citation_no_volume_t = { -- {{citation}} does not render |volume= when these parameters are used 'website', 'mailinglist', 'script-website', } local citation_issue_t = { -- {{citation}} may render |issue= when these parameters are used 'journal', 'magazine', 'newspaper', 'periodical', 'work', 'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work', } --[[ Patterns for finding extra text in |volume=, |issue=, |page=, |pages= ]] local vol_iss_pg_patterns = { good_ppattern = '^P[^%.PpGg]', -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123); TODO: this allows 'Pages' which it should not bad_ppatterns = { -- patterns for |page= and |pages= '^[Pp][PpGg]?%.?[ %d]', '^[Pp][Pp]?%.&nbsp;', -- from {{p.}} and {{pp.}} templates '^[Pp]ages?', '^[Pp]gs.?', }, vi_patterns_t = { -- combined to catch volume-like text in |issue= and issue-like text in |volume= '^volumes?', -- volume-like text '^vols?[%.:=]?', '^issues?', --issue-like text '^iss[%.:=]?', '^numbers?', '^nos?%A', -- don't match 'november' or 'nostradamus' '^nr[%.:=]?', '^n[%.:= ]', -- might be a valid issue without separator (space char is sep char here) '^n°', -- 'n' with degree sign (U+00B0) '^№', -- precomposed unicode numero character (U+2116) }, } --[[--------------------------< K E Y W O R D S >------------------------------- These tables hold keywords for those parameters that have defined sets of acceptable keywords. ]] --[[-------------------< K E Y W O R D S T A B L E >-------------------------- this is a list of keywords; each key in the list is associated with a table of synonymous keywords possibly from different languages. for I18N: add local-language keywords to value table; do not change the key. For example, adding the German keyword 'ja': ['affirmative'] = {'yes', 'true', 'y', 'ja'}, Because CS1|2 templates from en.wiki articles are often copied to other local wikis, it is recommended that the English keywords remain in these tables. ]] local keywords = { ['amp'] = {'&', 'amp', 'ampersand'}, -- |name-list-style= ['and'] = {'and', 'serial'}, -- |name-list-style= ['affirmative'] = {'yes', 'true', 'y'}, -- |no-tracking=, |no-pp= -- Used by InternetArchiveBot ['afterword'] = {'afterword'}, -- |contribution= ['bot: unknown'] = {'bot: unknown'}, -- |url-status= -- Used by InternetArchiveBot ['cs1'] = {'cs1'}, -- |mode= ['cs2'] = {'cs2'}, -- |mode= ['dead'] = {'dead', 'deviated'}, -- |url-status= -- Used by InternetArchiveBot ['dmy'] = {'dmy'}, -- |df= ['dmy-all'] = {'dmy-all'}, -- |df= ['foreword'] = {'foreword'}, -- |contribution= ['free'] = {'free'}, -- |<id>-access= -- Used by InternetArchiveBot ['harv'] = {'harv'}, -- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true ['introduction'] = {'introduction'}, -- |contribution= ['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot ['live'] = {'live'}, -- |url-status= -- Used by InternetArchiveBot ['mdy'] = {'mdy'}, -- |df= ['mdy-all'] = {'mdy-all'}, -- |df= ['none'] = {'none'}, -- |postscript=, |ref=, |title=, |type= -- Used by InternetArchiveBot ['off'] = {'off'}, -- |title= (potentially also: |title-link=, |postscript=, |ref=, |type=) ['preface'] = {'preface'}, -- |contribution= ['registration'] = {'registration'}, -- |url-access= -- Used by InternetArchiveBot ['subscription'] = {'subscription'}, -- |url-access= -- Used by InternetArchiveBot ['unfit'] = {'unfit'}, -- |url-status= -- Used by InternetArchiveBot ['usurped'] = {'usurped'}, -- |url-status= -- Used by InternetArchiveBot ['vanc'] = {'vanc'}, -- |name-list-style= ['ymd'] = {'ymd'}, -- |df= ['ymd-all'] = {'ymd-all'}, -- |df= -- ['yMd'] = {'yMd'}, -- |df=; not supported at en.wiki -- ['yMd-all'] = {'yMd-all'}, -- |df=; not supported at en.wiki } --[[------------------------< X L A T E _ K E Y W O R D S >--------------------- this function builds a list, keywords_xlate{}, of the keywords found in keywords{} where the values from keywords{} become the keys in keywords_xlate{} and the keys from keywords{} become the values in keywords_xlate{}: ['affirmative'] = {'yes', 'true', 'y'}, -- in keywords{} becomes ['yes'] = 'affirmative', -- in keywords_xlate{} ['true'] = 'affirmative', ['y'] = 'affirmative', the purpose of this function is to act as a translator between a non-English keyword and its English equivalent that may be used in other modules of this suite ]] local function xlate_keywords () local out_table = {}; -- output goes here for k, keywords_t in pairs (keywords) do -- spin through the keywords table for _, keyword in ipairs (keywords_t) do -- for each keyword out_table[keyword] = k; -- create an entry in the output table where keyword is the key end end return out_table; end local keywords_xlate = xlate_keywords (); -- the list of translated keywords --[[----------------< M A K E _ K E Y W O R D S _ L I S T >--------------------- this function assembles, for parameter-value validation, the list of keywords appropriate to that parameter. keywords_lists{}, is a table of tables from keywords{} ]] local function make_keywords_list (keywords_lists) local out_table = {}; -- output goes here for _, keyword_list in ipairs (keywords_lists) do -- spin through keywords_lists{} and get a table of keywords for _, keyword in ipairs (keyword_list) do -- spin through keyword_list{} and add each keyword, ... table.insert (out_table, keyword); -- ... as plain text, to the output list end end return out_table; end --[[----------------< K E Y W O R D S _ L I S T S >----------------------------- this is a list of lists of valid keywords for the various parameters in [key]. Generally the keys in this table are the canonical en.wiki parameter names though some are contrived because of use in multiple differently named parameters: ['yes_true_y'], ['id-access']. The function make_keywords_list() extracts the individual keywords from the appropriate list in keywords{}. The lists in this table are used to validate the keyword assignment for the parameters named in this table's keys. ]] local keywords_lists = { ['yes_true_y'] = make_keywords_list ({keywords.affirmative}), ['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}), ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all']}), -- ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all'], keywords.yMd, keywords['yMd-all']}), -- not supported at en.wiki ['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}), ['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}), ['ref'] = make_keywords_list ({keywords.harv}), -- inverted check; |ref=harv no longer supported ['url-access'] = make_keywords_list ({keywords.subscription, keywords.limited, keywords.registration}), ['url-status'] = make_keywords_list ({keywords.dead, keywords.live, keywords.unfit, keywords.usurped, keywords['bot: unknown']}), ['id-access'] = make_keywords_list ({keywords.free}), } --[[--------------------------< C S 1 _ C O N F I G _ G E T >-------------------------------------------------- fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t> no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked. Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors, DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode. The DisplayWhatever metaparameters accept numeric values only (|display-authors=etal and the like is not supported). ]] local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table? local function get_cs1_config () if not content then -- nil content when we're in template return nil; -- auto-formatting does not work in Template space so don't set global_df end local start = content:find('{{ *[Cc][Ss]1 config *[|}]'); -- <start> is offset into <content> when {{cs1 config}} found; nil else if start then local cs1_config_template = content:match ('%b{}', start); -- get the whole template if not cs1_config_template then return nil; end local params_t = mw.text.split (cs1_config_template:gsub ('^{{%s*', ''):gsub ('%s*}}$', ''), '%s*|%s*'); -- remove '{{' and '}}'; make a sequence of parameter/value pairs (split on the pipe) table.remove (params_t, 1); -- remove the template name because it isn't a parameter/value pair local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'}; local meta_param_map_t = {}; -- list of accepted parameter names usable in {{cs1 config}} goes here for _, meta_param in ipairs (config_meta_params_t) do -- for i18n using <config_meta_params_t>, map template parameter names to their metaparameter equivalents if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence, for _, param in ipairs (aliases[meta_param]) do -- extract its contents meta_param_map_t[param] = meta_param; -- and add to <meta_param_map_t> end else meta_param_map_t[aliases[meta_param]] = meta_param; -- not a sequence so just add the parameter to <meta_param_map_t> end end local keywords_t = {}; -- map valid keywords to their associate metaparameter; reverse form of <keyword_lists[key] for these metaparameters for _, metaparam_t in ipairs ({{'NameListStyle', 'name-list-style'}, {'Mode', 'mode'}}) do -- only these metaparameter / keywords_lists key pairs for _, keyword in ipairs (keywords_lists[metaparam_t[2]]) do -- spin through the list of keywords keywords_t[keyword] = metaparam_t[1]; -- add [keyword] = metaparameter to the map end end for _, param in ipairs (params_t) do -- spin through the {{cs1 config}} parameters and fill <global_cs1_config_t> local k, v = param:match ('([^=]-)%s*=%s*(.+)'); -- <k> is the parameter name; <v> is parameter's assigned value if k then if k:find ('^display') then -- if <k> is one of the |display-<namelist>= parameters if v:match ('%d+') then -- the assigned value must be digits; doesn't accept 'etal' global_cs1_config_t[meta_param_map_t[k]]=v; -- add the display param and its value to globals table end else if keywords_t[v] == meta_param_map_t[k] then -- keywords_t[v] returns nil or the metaparam name; these must be the same global_cs1_config_t[meta_param_map_t[k]]=v; -- add the parameter and its value to globals table end end end end end end get_cs1_config (); -- fill <global_cs1_config_t> --[[---------------------< S T R I P M A R K E R S >---------------------------- Common pattern definition location for stripmarkers so that we don't have to go hunting for them if (when) MediaWiki changes their form. ]] local stripmarkers = { ['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127', -- capture returns name of stripmarker ['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127' -- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker() } --[[------------< I N V I S I B L E _ C H A R A C T E R S >--------------------- This table holds non-printing or invisible characters indexed either by name or by Unicode group. Values are decimal representations of UTF-8 codes. The table is organized as a table of tables because the Lua pairs keyword returns table data in an arbitrary order. Here, we want to process the table from top to bottom because the entries at the top of the table are also found in the ranges specified by the entries at the bottom of the table. Also here is a pattern that recognizes stripmarkers that begin and end with the delete characters. The nowiki stripmarker is not an error but some others are because the parameter values that include them become part of the template's metadata before stripmarker replacement. ]] local invisible_defs = { del = '\127', -- used to distinguish between stripmarker and del char zwj = '\226\128\141', -- used with capture because zwj may be allowed } local invisible_chars = { {'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD {'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed {'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B {'hair space', '\226\128\138'}, -- U+200A, E2 80 8A {'soft hyphen', '\194\173'}, -- U+00AD, C2 AD {'horizontal tab', '\009'}, -- U+0009 (HT), 09 {'line feed', '\010'}, -- U+000A (LF), 0A {'no-break space', '\194\160'}, -- U+00A0 (NBSP), C2 A0 {'carriage return', '\013'}, -- U+000D (CR), 0D {'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type {'delete', '('.. invisible_defs.del .. ')'}, -- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker {'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D)) {'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F -- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF -- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF -- {'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD -- {'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'}, -- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD } --[[ Indic script makes use of zero width joiner as a character modifier so zwj characters must be left in. This pattern covers all of the unicode characters for these languages: Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf Bengali 0980–09FF – https://unicode.org/charts/PDF/U0980.pdf Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf Telugu 0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf plus the not-necessarily Indic scripts for Sinhala and Burmese: Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf the pattern is used by has_invisible_chars() and coins_cleanup() ]] local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]'; -- list of emoji that use a zwj character (U+200D) to combine with another emoji -- from: https://unicode.org/Public/emoji/17.0/emoji-zwj-sequences.txt; version: 17.0; 2025-01-08 -- table created by: [[:en:Module:Make emoji zwj table]] local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx [8596] = true, -- U+2194 ↔ left right arrow [8597] = true, -- U+2195 ↕ up down arrow [9760] = true, -- U+2620 ☠ skull and crossbones [9792] = true, -- U+2640 ♀ female sign [9794] = true, -- U+2642 ♂ male sign [9877] = true, -- U+2695 ⚕ staff of aesculapius [9878] = true, -- U+2696 ⚖ scales [9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign [9992] = true, -- U+2708 ✈ airplane [10052] = true, -- U+2744 ❄ snowflake [10084] = true, -- U+2764 ❤ heavy black heart [10145] = true, -- U+27A1 ➡ black rightwards arrow [11035] = true, -- U+2B1B ⬛ black large square [127752] = true, -- U+1F308 🌈 rainbow [127787] = true, -- U+1F32B 🌫 fog [127806] = true, -- U+1F33E 🌾 ear of rice [127859] = true, -- U+1F373 🍳 cooking [127868] = true, -- U+1F37C 🍼 baby bottle [127876] = true, -- U+1F384 🎄 christmas tree [127891] = true, -- U+1F393 🎓 graduation cap [127908] = true, -- U+1F3A4 🎤 microphone [127912] = true, -- U+1F3A8 🎨 artist palette [127979] = true, -- U+1F3EB 🏫 school [127981] = true, -- U+1F3ED 🏭 factory [128048] = true, -- U+1F430 🐰 rabbit face [128102] = true, -- U+1F466 👦 boy [128103] = true, -- U+1F467 👧 girl [128104] = true, -- U+1F468 👨 man [128105] = true, -- U+1F469 👩 woman [128139] = true, -- U+1F48B 💋 kiss mark [128165] = true, -- U+1F4A5 💥 collision symbol [128168] = true, -- U+1F4A8 💨 dash symbol [128171] = true, -- U+1F4AB 💫 dizzy symbol [128187] = true, -- U+1F4BB 💻 personal computer [128188] = true, -- U+1F4BC 💼 brief case [128293] = true, -- U+1F525 🔥 fire [128295] = true, -- U+1F527 🔧 wrench [128300] = true, -- U+1F52C 🔬 microscope [128488] = true, -- U+1F5E8 🗨 left speech bubble [128640] = true, -- U+1F680 🚀 rocket [128658] = true, -- U+1F692 🚒 fire engine [129001] = true, -- U+1F7E9 🟩 large green square [129003] = true, -- U+1F7EB 🟫 large brown square [129309] = true, -- U+1F91D 🤝 handshake [129455] = true, -- U+1F9AF 🦯 probing cane [129456] = true, -- U+1F9B0 🦰 emoji component red hair [129457] = true, -- U+1F9B1 🦱 emoji component curly hair [129458] = true, -- U+1F9B2 🦲 emoji component bald [129459] = true, -- U+1F9B3 🦳 emoji component white hair [129466] = true, -- U+1F9BA 🦺 safety vest [129468] = true, -- U+1F9BC 🦼 motorized wheelchair [129469] = true, -- U+1F9BD 🦽 manual wheelchair [129489] = true, -- U+1F9D1 🧑 adult [129490] = true, -- U+1F9D2 🧒 child [129648] = true, -- U+1FA70 🩰 ballet shoes [129657] = true, -- U+1FA79 🩹 adhesive bandage [129775] = true, -- U+1FAEF 🫯 fight cloud [129778] = true, -- U+1FAF2 🫲 leftwards hand } --[[----------------------< L A N G U A G E S U P P O R T >------------------- These tables and constants support various language-specific functionality. ]] --local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code local this_wiki_code = lang_obj:getCode(); -- get this wiki's language code if string.match (mw.site.server, 'wikidata') then this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead end local mw_languages_by_tag_t = mw.language.fetchLanguageNames (this_wiki_code, 'all'); -- get a table of language tag/name pairs known to Wikimedia; used for interwiki tests local mw_languages_by_name_t = {}; for k, v in pairs (mw_languages_by_tag_t) do -- build a 'reversed' table name/tag language pairs know to MediaWiki; used for |language= v = mw.ustring.lower (v); -- lowercase for tag fetch; get name's proper case from mw_languages_by_tag_t[<tag>] if mw_languages_by_name_t[v] then -- when name already in the table if 2 == #k or 3 == #k then -- if tag does not have subtags mw_languages_by_name_t[v] = k; -- prefer the shortest tag for this name end else -- here when name not in the table mw_languages_by_name_t[v] = k; -- so add name and matching tag end end local inter_wiki_map = {}; -- map of interwiki prefixes that are language-code prefixes for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local) if mw_languages_by_tag_t[v["prefix"]] then -- if the prefix matches a known language tag inter_wiki_map[v["prefix"]] = true; -- add it to our local map end end --[[--------------------< S C R I P T _ L A N G _ C O D E S >------------------- This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character language codes that apply only to |script-title= and |script-chapter= ]] local script_lang_codes = { 'ab', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'ce', 'chr', 'cu', 'dv', 'dz', 'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka', 'kaa', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni', 'mr', 'my', 'ne', 'or', 'ota', 'pa', 'ps', 'ru', 'sd', 'si', 'sr', 'syc', 'ta', 'te', 'tg', 'th', 'ti', 'tkr', 'tt', 'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh', 'zgh' }; --[[---------------< L A N G U A G E R E M A P P I N G >---------------------- These tables hold language information that is different (correct) from MediaWiki's definitions For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{} lang_tag_remap{}: key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag value is properly spelled and capitalized language name associated with <tag> only one language name per <tag>; key/value pair must have matching entry in lang_name_remap{} lang_name_remap{}: key is always lowercase language name value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{}) may have multiple keys referring to a common preferred name and tag; For example: ['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh' ]] local lang_tag_remap = { -- used for |language= and |script-title= / |script-chapter= ['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch ['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org ['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name ['bn'] = 'Bengali', -- MediaWiki returns Bangla ['ca-valencia'] = 'Valencian', -- IETF variant of Catalan ['fkv'] = 'Kven', -- MediaWiki returns Kvensk ['gsw'] = 'Swiss German', ['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name ['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name ['ksh-x-colog'] = 'Colognian', -- override MediaWiki ksh; no IANA/ISO 639 code for Colognian; IETF private code created at Module:Lang/data ['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data ['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name ['sr-ec'] = 'Serbian (Cyrillic script)', -- MediaWiki returns српски (ћирилица) ['sr-el'] = 'Serbian (Latin script)', -- MediaWiki returns srpski (latinica) } local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase ['alemannic'] = {'Swiss German', 'gsw'}, -- ISO 639-2, -3 alternate for Swiss German; MediaWiki mediawiki returns Alemannic for gsw; en.wiki preferred name ['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org ['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap ['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code ['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org ['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replaces 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found ['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name ['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh ['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name ['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö) ['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name ['kven'] = {'Kven', 'fkv'}, -- Unicode CLDR have decided not to support English language name for these two... ['kvensk'] = {'Kven', 'fkv'}, -- ...they say to refer to IANA registry for English names ['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639 ['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'}, -- special case to get correct tag when |language=sr-ec ['serbian (latin script)'] = {'Serbian (Latin script)', 'sr-latn'}, -- special case to get correct tag when |language=sr-el ['swiss german'] = {'Swiss German', 'gsw'}, ['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese ['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found ['valencian'] = {'Valencian', 'ca-valencia'}, -- variant of Catalan; categorizes as Valencian } --[[---------------< P R O P E R T I E S _ C A T E G O R I E S >---------------- Properties categories. These are used for investigating qualities of citations. ]] local prop_cats = { ['foreign-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code ['foreign-lang-source-2'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key ['interproj-linked-name'] = 'CS1 interproject-linked names|$1', -- any author, editor, etc that has an interproject link; $1 is interproject tag used as a sort key ['interwiki-linked-name'] = 'CS1 interwiki-linked names|$1', -- any author, editor, etc that has an interwiki link; $1 is interwiki tag used as a sort key; yeilds to interproject ['local-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false ['location-test'] = 'CS1 location test', ['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters ['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is language tag ['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name ['unfit'] = 'CS1: unfit URL', -- |url-status=unfit or |url-status=usurped; used to be a maint cat ['vanc-accept'] = 'CS1:Vancouver names with accept markup', -- for |vauthors=/|veditors= with accept-as-written markup ['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form } --[[-------------------< T I T L E _ T Y P E S >-------------------------------- Here we map a template's CitationClass to TitleType (default values for |type= parameter) ]] local title_types = { ['AV-media-notes'] = 'Media notes', ['document'] = 'Document', ['interview'] = 'Interview', ['mailinglist'] = 'Mailing list', ['map'] = 'Map', ['podcast'] = 'Podcast', ['pressrelease'] = 'Press release', ['report'] = 'Report', ['speech'] = 'Speech', ['techreport'] = 'Technical report', ['thesis'] = 'Thesis', } --[[--------------------------< B U I L D _ K N O W N _ F R E E _ D O I _ R E G I S T R A N T S _ T A B L E >-- build a table of doi registrants known to be free-to-read In a doi, the registrant ID is the series of digits between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID see §3.2.2 DOI prefix of the Doi Handbook p. 43 https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43 ]] local function build_free_doi_registrants_table() local registrants_t = {}; for _, v in ipairs ({ '1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '1613', '1629', '1989', '1999', '2147', '2196', '3285', '3389', '3390', '3906', '3748', '3814', '3847', '3897', '4061', '4089', '4103', '4172', '4175', '4230', '4236', '4239', '4240', '4249', '4251', '4252', '4253', '4254', '4291', '4292', '4329', '4330', '4331', '5086', '5194', '5210', '5306', '5312', '5313', '5314', '5315', '5316', '5317', '5318', '5319', '5320', '5321', '5334', '5402', '5409', '5410', '5411', '5412', '5492', '5493', '5494', '5495', '5496', '5497', '5498', '5499', '5500', '5501', '5527', '5528', '5662', '6064', '6219', '7167', '7217', '7287', '7482', '7490', '7554', '7717', '7759', '7766', '9778', '11131', '11569', '11647', '11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995', '17645', '18637', '19080', '19173', '20944', '21037', '21105', '21468', '21767', '21425', '22261', '22323', '22459', '24105', '24196', '24966', '26775', '30845', '32545', '35711', '35712', '35713', '35995', '36648', '37126', '37532', '37871', '47128', '47622', '47959', '52437', '52975', '53288', '53347', '54081', '54947', '55667', '55914', '57009', '58647', '59081', }) do registrants_t[v] = true; -- build a k/v table of known free-to-read doi registrants end return registrants_t; end -- known free registrants identifiable by the doi suffix incipit local extended_registrants_t = { -- doi suffix incipits are evaluated as lua patterns ['1002'] = {'aelm', 'leap', 'loe2%.', 'lol2%.'}, -- Advanced Electronic Materials, Learned Publishing, L&O e-Lectures, L&O Letters ['1016'] = {'j%.aace', 'j%.aed', 'j%.aiopen', 'j%.animal', 'j%.apsb', 'j%.addicn', -- AACE Endocrinology and Diabetes, AACE Endocrinology and Diabetes, AI Open, Animal, Acta Pharmaceutica Sinica B, Addiction Neuroscience 'j%.abrep', 'j%.gpb', 'j%.heliyon', 'j%.nlp', 'j%.patter', 'j%.proche', -- Addictive Behaviors Reports, Genomics, Proteomics & Bioinformatics after 2015, Heliyon, Natural Language Processing, Patterns, Procedia Chemistry 'j%.vgie', 'S1672-0229'}, -- VideoGIE, Genomics, Proteomics & Bioinformatics before 2015 ['1017'] = {'apj%.', 'nlp', 'mdh', 'S15574660'}, -- Natural Language Processing Journal, Medical History, Asia Pacific Journal ['1046'] = {'j%.1365-8711', 'j%.1365-246x'}, -- MNRAS, GJI ['1021'] = {'acscentsci', 'acsomega'}, -- ACS Central Science, ACS Omega ['1093'] = {'mnras', 'mnrasl', 'gji', 'pnasnexus', 'rasti'}, -- MNRAS, MNRAS Letters, GJI, PNAS Nexus, RASTI ['1098'] = {'rsbm', 'rsob', 'rsos'}, -- Biographical Memoirs of Fellows of the Royal Society, Open Biology, Royal Society Open Science ['1099'] = {'acmi', 'mic', '00221287', 'mgen'}, -- Access Microbiology, Microbiology, Journal of General Microbiology, Microbial Genomics ['1107'] = {'S20569890', 'S20522525', 'S16005775', 'S24143146'}, -- Acta Crystallographica E, IUCrJ, Journal of Synchrotron Radiation, IUCrData ['1109'] = {'oa', 'oj'}, -- IEEE Open Access..., IEEE Open Journal... ['1111'] = {'aogs', 'j%.1365-2966', 'j%.1745-3933', 'j%.1365-246X'}, -- Acta Obstetricia et Gynecologica Scandinavica, MNRAS, MNRAS Letters, GJI ['1128'] = {'asmcr', 'jmbe', 'mbio', 'mra', 'spectrum', 'msphere', 'msystems'}, --ASM Case Reports, Journal of Microbiology & Biology Education, mBio, Microbiology Resource Announcements, Microbiology Spectrum, mSphere, mSystems ['1136'] = {'bmjopen'}, -- BMJ Open ['1140'] = {'epjc'}, -- European Physical Journal C ['1192'] = {'bjo'}, -- BJPsych Open ['1210'] = {'jendso','jcemcr'}, -- Journal of the Endocrine Society, JCEM Case Reports ['1215'] = {'21573689', '21573698'}, -- L&O Fluids ['1590'] = {'0102-3306'}, -- Acta Botanica Brasilica ['4171'] = {'dm','mag'}, -- Documenta Mathematica, EMS Magazine ['4319'] = {'lo%.', 'lol%.', 'lom%.'}, -- L&O, L&O e-Lectures, L&O Methods ['5852'] = {'ejt'}, -- European Journal of Taxonomy ['7155'] = {'jgaa'}, -- Journal of Graph Algorithms and Applications ['11158'] = {'saasp'}, -- Systematic and Applied Acarology Special Publications ['11646'] = {'megataxa', 'mesozoic'}, -- Megataxa, Mesozoic ['14231'] = {'ag'}, -- Algebraic Geometry ['15446'] = {'abc'}, -- Acta Biológica Colombiana ['17239'] = {'jowr'}, -- Journal of Writing Research ['22073'] = {'pja'}, -- Persian Journal of Acarology ['24310'] = {'abm'}, -- Acta Botanica Malacitana ['24425'] = {'agp'}, -- Acta Geologica Polonica ['35249'] = {'rche'}, -- Revista Chilena de Entomología ['37520'] = {'fi'}, -- Fossil Imprint ['53562'] = {'ajcb'} -- Asian Journal of Conservation Biology } --[[===================<< E R R O R M E S S A G I N G >>====================== ]] --[[----------< E R R O R M E S S A G E S U P P L E M E N T S >------------- I18N for those messages that are supplemented with additional specific text that describes the reason for the error TODO: merge this with special_case_translations{}? ]] local err_msg_supl = { ['char'] = 'invalid character', -- |isbn=, |sbn= ['check'] = 'checksum', -- |isbn=, |sbn= empty_str = '(empty string)', -- empty unknown parameter check when cite has |= ['flag'] = 'flag', -- |archive-url= ['form'] = 'invalid form', -- |isbn=, |sbn= ['group'] = 'invalid group id', -- |isbn= ['initials'] = 'initials', -- Vancouver ['invalid language code'] = 'invalid language code', -- |script-<param>= ['journal'] = 'journal', -- |bibcode= ['length'] = 'length', -- |isbn=, |bibcode=, |sbn= ['liveweb'] = 'liveweb', -- |archive-url= ['missing comma'] = 'missing comma', -- Vancouver ['missing prefix'] = 'missing prefix', -- |script-<param>= ['missing title part'] = 'missing title part', -- |script-<param>= ['name'] = 'name', -- Vancouver ['non-Latin char'] = 'non-Latin character', -- Vancouver ['path'] = 'path', -- |archive-url= ['prefix'] = 'invalid prefix', -- |isbn= ['punctuation'] = 'punctuation', -- Vancouver ['save'] = 'save command', -- |archive-url= ['suffix'] = 'suffix', -- Vancouver ['timestamp'] = 'timestamp', -- |archive-url= ['unknown language code'] = 'unknown language code', -- |script-<param>= ['value'] = 'value', -- |bibcode= ['year'] = 'year', -- |bibcode= } --[[--------------< E R R O R _ C O N D I T I O N S >--------------------------- Error condition table. This table has two sections: errors at the top, maintenance at the bottom. Maint 'messaging' does not have a 'message' (message=nil) The following contains a list of IDs for various error conditions defined in the code. For each ID, we specify a text message to display, an error category to include, and whether the error message should be wrapped as a hidden comment. Anchor changes require identical changes to matching anchor in Help:CS1 errors TODO: rename error_conditions{} to something more generic; create separate error and maint tables inside that? ]] local error_conditions = { err_accessdate_missing_url = { message = '<code class="cs1-code">&#124;access-date=</code> requires <code class="cs1-code">&#124;url=</code>', anchor = 'accessdate_missing_url', category = 'CS1 errors: access-date without URL', hidden = false }, err_apostrophe_markup = { message = 'Italic or bold markup not allowed in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'apostrophe_markup', category = 'CS1 errors: markup', hidden = false }, err_archive_date_missing_url = { message = '<code class="cs1-code">&#124;archive-date=</code> requires <code class="cs1-code">&#124;archive-url=</code>', anchor = 'archive_date_missing_url', category = 'CS1 errors: archive-url', hidden = false }, err_archive_date_url_ts_mismatch = { message = '<code class="cs1-code">&#124;archive-date=</code> / <code class="cs1-code">&#124;archive-url=</code> timestamp mismatch; $1 suggested', anchor = 'archive_date_url_ts_mismatch', category = 'CS1 errors: archive-url', hidden = false }, err_archive_missing_date = { message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;archive-date=</code>', anchor = 'archive_missing_date', category = 'CS1 errors: archive-url', hidden = false }, err_archive_missing_url = { message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;url=</code>', anchor = 'archive_missing_url', category = 'CS1 errors: archive-url', hidden = false }, err_archive_url = { message = '<code class="cs1-code">&#124;archive-url=</code> is malformed: $1', -- $1 is error message detail anchor = 'archive_url', category = 'CS1 errors: archive-url', hidden = false }, err_arxiv_missing = { message = '<code class="cs1-code">&#124;arxiv=</code> required', anchor = 'arxiv_missing', category = 'CS1 errors: arXiv', -- same as bad arxiv hidden = false }, err_asintld_missing_asin = { message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;asin=</code>', -- $1 is parameter name anchor = 'asintld_missing_asin', category = 'CS1 errors: ASIN TLD', hidden = false }, err_bad_arxiv = { message = 'Check <code class="cs1-code">&#124;arxiv=</code> value', anchor = 'bad_arxiv', category = 'CS1 errors: arXiv', hidden = false }, err_bad_asin = { message = 'Check <code class="cs1-code">&#124;asin=</code> value', anchor = 'bad_asin', category ='CS1 errors: ASIN', hidden = false }, err_bad_asin_tld = { message = 'Check <code class="cs1-code">&#124;asin-tld=</code> value', anchor = 'bad_asin_tld', category ='CS1 errors: ASIN TLD', hidden = false }, err_bad_bibcode = { message = 'Check <code class="cs1-code">&#124;bibcode=</code> $1', -- $1 is error message detail anchor = 'bad_bibcode', category = 'CS1 errors: bibcode', hidden = false }, err_bad_biorxiv = { message = 'Check <code class="cs1-code">&#124;biorxiv=</code> value', anchor = 'bad_biorxiv', category = 'CS1 errors: bioRxiv', hidden = false }, err_bad_citeseerx = { message = 'Check <code class="cs1-code">&#124;citeseerx=</code> value', anchor = 'bad_citeseerx', category = 'CS1 errors: citeseerx', hidden = false }, err_bad_date = { message = 'Check date values in: $1', -- $1 is a parameter name list anchor = 'bad_date', category = 'CS1 errors: dates', hidden = false }, err_bad_doi = { message = 'Check <code class="cs1-code">&#124;doi=</code> value', anchor = 'bad_doi', category = 'CS1 errors: DOI', hidden = false }, err_bad_hdl = { message = 'Check <code class="cs1-code">&#124;hdl=</code> value', anchor = 'bad_hdl', category = 'CS1 errors: HDL', hidden = false }, err_bad_isbn = { message = 'Check <code class="cs1-code">&#124;isbn=</code> value: $1', -- $1 is error message detail anchor = 'bad_isbn', category = 'CS1 errors: ISBN', hidden = false }, err_bad_ismn = { message = 'Check <code class="cs1-code">&#124;ismn=</code> value', anchor = 'bad_ismn', category = 'CS1 errors: ISMN', hidden = false }, err_bad_issn = { message = 'Check <code class="cs1-code">&#124;$1issn=</code> value', -- $1 is 'e' or '' for eissn or issn anchor = 'bad_issn', category = 'CS1 errors: ISSN', hidden = false }, err_bad_jfm = { message = 'Check <code class="cs1-code">&#124;jfm=</code> value', anchor = 'bad_jfm', category = 'CS1 errors: JFM', hidden = false }, err_bad_jstor = { message = 'Check <code class="cs1-code">&#124;jstor=</code> value', anchor = 'bad_jstor', category = 'CS1 errors: JSTOR', hidden = false }, err_bad_lccn = { message = 'Check <code class="cs1-code">&#124;lccn=</code> value', anchor = 'bad_lccn', category = 'CS1 errors: LCCN', hidden = false }, err_bad_medrxiv = { message = 'Check <code class="cs1-code">&#124;medrxiv=</code> value', anchor = 'bad_medrxiv', category = 'CS1 errors: medRxiv', hidden = false }, err_bad_mr = { message = 'Check <code class="cs1-code">&#124;mr=</code> value', anchor = 'bad_mr', category = 'CS1 errors: MR', hidden = false }, err_bad_oclc = { message = 'Check <code class="cs1-code">&#124;oclc=</code> value', anchor = 'bad_oclc', category = 'CS1 errors: OCLC', hidden = false }, err_bad_ol = { message = 'Check <code class="cs1-code">&#124;ol=</code> value', anchor = 'bad_ol', category = 'CS1 errors: OL', hidden = false }, err_bad_osti = { message = 'Check <code class="cs1-code">&#124;osti=</code> value', anchor = 'bad_osti', category = 'CS1 errors: OSTI', hidden = false }, err_bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link= message = 'Check <code class="cs1-code">&#124;$1=</code> value', -- $1 is parameter name anchor = 'bad_paramlink', category = 'CS1 errors: parameter link', hidden = false }, err_bad_pmc = { message = 'Check <code class="cs1-code">&#124;pmc=</code> value', anchor = 'bad_pmc', category = 'CS1 errors: PMC', hidden = false }, err_bad_pmid = { message = 'Check <code class="cs1-code">&#124;pmid=</code> value', anchor = 'bad_pmid', category = 'CS1 errors: PMID', hidden = false }, err_bad_rfc = { message = 'Check <code class="cs1-code">&#124;rfc=</code> value', anchor = 'bad_rfc', category = 'CS1 errors: RFC', hidden = false }, err_bad_s2cid = { message = 'Check <code class="cs1-code">&#124;s2cid=</code> value', anchor = 'bad_s2cid', category = 'CS1 errors: S2CID', hidden = false }, err_bad_sbn = { message = 'Check <code class="cs1-code">&#124;sbn=</code> value: $1', -- $1 is error message detail anchor = 'bad_sbn', category = 'CS1 errors: SBN', hidden = false }, err_bad_ssrn = { message = 'Check <code class="cs1-code">&#124;ssrn=</code> value', anchor = 'bad_ssrn', category = 'CS1 errors: SSRN', hidden = false }, err_bad_url = { message = 'Check $1 value', -- $1 is parameter name anchor = 'bad_url', category = 'CS1 errors: URL', hidden = false }, err_bad_usenet_id = { message = 'Check <code class="cs1-code">&#124;message-id=</code> value', anchor = 'bad_message_id', category = 'CS1 errors: message-id', hidden = false }, err_bad_zbl = { message = 'Check <code class="cs1-code">&#124;zbl=</code> value', anchor = 'bad_zbl', category = 'CS1 errors: Zbl', hidden = false }, err_bare_url_missing_title = { message = '$1 missing title', -- $1 is parameter name anchor = 'bare_url_missing_title', category = 'CS1 errors: bare URL', hidden = false }, err_biorxiv_missing = { message = '<code class="cs1-code">&#124;biorxiv=</code> required', anchor = 'biorxiv_missing', category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv hidden = false }, err_chapter_ignored = { message = '<code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name anchor = 'chapter_ignored', category = 'CS1 errors: chapter ignored', hidden = false }, err_citation_missing_title = { message = 'Missing or empty <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'citation_missing_title', category = 'CS1 errors: missing title', hidden = false }, err_citeseerx_missing = { message = '<code class="cs1-code">&#124;citeseerx=</code> required', anchor = 'citeseerx_missing', category = 'CS1 errors: citeseerx', -- same as bad citeseerx hidden = false }, err_cite_web_url = { -- this error applies to cite web and to cite podcast message = 'Missing or empty <code class="cs1-code">&#124;url=</code>', anchor = 'cite_web_url', category = 'CS1 errors: requires URL', hidden = false }, err_class_ignored = { message = '<code class="cs1-code">&#124;class=</code> ignored', anchor = 'class_ignored', category = 'CS1 errors: class', hidden = false }, err_contributor_ignored = { message = '<code class="cs1-code">&#124;contributor=</code> ignored', anchor = 'contributor_ignored', category = 'CS1 errors: contributor', hidden = false }, err_contributor_missing_required_param = { message = '<code class="cs1-code">&#124;contributor=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'contributor_missing_required_param', category = 'CS1 errors: contributor', hidden = false }, err_deprecated_params = { message = 'Cite uses deprecated parameter <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'deprecated_params', category = 'CS1 errors: deprecated parameters', hidden = false }, err_disp_name = { message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name; $2 is the assigned value anchor = 'disp_name', category = 'CS1 errors: display-names', hidden = false, }, err_doibroken_missing_doi = { message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;doi=</code>', -- $1 is parameter name anchor = 'doibroken_missing_doi', category = 'CS1 errors: DOI', hidden = false }, err_embargo_missing_pmc = { message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;pmc=</code>', -- $1 is parameter name anchor = 'embargo_missing_pmc', category = 'CS1 errors: PMC embargo', hidden = false }, err_empty_citation = { message = 'Empty citation', anchor = 'empty_citation', category = 'CS1 errors: empty citation', hidden = false }, err_etal = { message = 'Explicit use of et al. in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'explicit_et_al', category = 'CS1 errors: explicit use of et al.', hidden = false }, err_extra_text_edition = { message = '<code class="cs1-code">&#124;edition=</code> has extra text', anchor = 'extra_text_edition', category = 'CS1 errors: extra text: edition', hidden = false, }, err_extra_text_issue = { message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name anchor = 'extra_text_issue', category = 'CS1 errors: extra text: issue', hidden = false, }, err_extra_text_pages = { message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name anchor = 'extra_text_pages', category = 'CS1 errors: extra text: pages', hidden = false, }, err_extra_text_volume = { message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name anchor = 'extra_text_volume', category = 'CS1 errors: extra text: volume', hidden = false, }, err_first_missing_last = { message = '<code class="cs1-code">&#124;$1=</code> missing <code class="cs1-code">&#124;$2=</code>', -- $1 is first alias, $2 is matching last alias anchor = 'first_missing_last', category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator hidden = false }, err_format_missing_url = { message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;$2=</code>', -- $1 is format parameter $2 is url parameter anchor = 'format_missing_url', category = 'CS1 errors: format without URL', hidden = false }, err_generic_name = { message = '<code class="cs1-code">&#124;$1=</code> has generic name', -- $1 is parameter name anchor = 'generic_name', category = 'CS1 errors: generic name', hidden = false, }, err_generic_title = { message = 'Cite uses generic title', anchor = 'generic_title', category = 'CS1 errors: generic title', hidden = false, }, err_invalid_isbn_date = { message = 'ISBN / Date incompatibility', anchor = 'invalid_isbn_date', category = 'CS1 errors: ISBN date', hidden = true }, err_invalid_param_val = { message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name $2 is parameter value anchor = 'invalid_param_val', category = 'CS1 errors: invalid parameter value', hidden = false }, err_invisible_char = { message = '$1 in $2 at position $3', -- $1 is invisible char $2 is parameter name $3 is position number anchor = 'invisible_char', category = 'CS1 errors: invisible characters', hidden = false }, err_medrxiv_missing = { message = '<code class="cs1-code">&#124;medrxiv=</code> required', anchor = 'medrxiv_missing', category = 'CS1 errors: medRxiv', -- same as bad medRxiv hidden = false }, err_missing_name = { message = 'Missing <code class="cs1-code">&#124;$1$2=</code>', -- $1 is modified NameList; $2 is enumerator anchor = 'missing_name', category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator hidden = false }, err_missing_periodical = { message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>', -- $1 is cs1 template name; $2 is canonical periodical parameter name for cite $1 anchor = 'missing_periodical', category = 'CS1 errors: missing periodical', hidden = false }, err_missing_pipe = { message = 'Missing pipe in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'missing_pipe', category = 'CS1 errors: missing pipe', hidden = false }, err_missing_publisher = { message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>', -- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1 anchor = 'missing_publisher', category = 'CS1 errors: missing publisher', hidden = false }, err_numeric_names = { message = '<code class="cs1-code">&#124;$1=</code> has numeric name', -- $1 is parameter name', anchor = 'numeric_names', category = 'CS1 errors: numeric name', hidden = false, }, err_param_access_requires_param = { message = '<code class="cs1-code">&#124;$1-access=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name anchor = 'param_access_requires_param', category = 'CS1 errors: param-access', hidden = false }, err_param_has_ext_link = { message = 'External link in <code class="cs1-code">$1</code>', -- $1 is parameter name anchor = 'param_has_ext_link', category = 'CS1 errors: external links', hidden = false }, err_param_has_twl_url = { message = 'Wikipedia Library link in <code class="cs1-code">$1</code>', -- $1 is parameter name anchor = 'param_has_twl_url', category = 'CS1 errors: URL', hidden = false }, err_parameter_ignored = { message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name anchor = 'parameter_ignored', category = 'CS1 errors: unsupported parameter', hidden = false }, err_parameter_ignored_suggest = { message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored (<code class="cs1-code">&#124;$2=</code> suggested)', -- $1 is unknown parameter $2 is suggested parameter name anchor = 'parameter_ignored_suggest', category = 'CS1 errors: unsupported parameter', hidden = false }, err_periodical_ignored = { message = '<code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name anchor = 'periodical_ignored', category = 'CS1 errors: periodical ignored', hidden = false }, err_redundant_parameters = { message = 'More than one of $1 specified', -- $1 is error message detail anchor = 'redundant_parameters', category = 'CS1 errors: redundant parameter', hidden = false }, err_script_parameter = { message = 'Invalid <code class="cs1-code">&#124;$1=</code>: $2', -- $1 is parameter name $2 is script language code or error detail anchor = 'script_parameter', category = 'CS1 errors: script parameters', hidden = false }, err_ssrn_missing = { message = '<code class="cs1-code">&#124;ssrn=</code> required', anchor = 'ssrn_missing', category = 'CS1 errors: SSRN', hidden = false }, err_text_ignored = { message = 'Text "$1" ignored', -- $1 is ignored text anchor = 'text_ignored', category = 'CS1 errors: unrecognized parameter', hidden = false }, err_trans_missing_title = { message = '<code class="cs1-code">&#124;trans-$1=</code> requires <code class="cs1-code">&#124;$1=</code> or <code class="cs1-code">&#124;script-$1=</code>', -- $1 is base parameter name anchor = 'trans_missing_title', category = 'CS1 errors: translated title', hidden = false }, err_param_unknown_empty = { message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is emty unknown param list anchor = 'param_unknown_empty', category = 'CS1 errors: empty unknown parameters', hidden = false }, err_vancouver = { message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name anchor = 'vancouver', category = 'CS1 errors: Vancouver style', hidden = false }, err_wikilink_in_url = { message = 'URL–wikilink conflict', -- uses ndash anchor = 'wikilink_in_url', category = 'CS1 errors: URL–wikilink conflict', -- uses ndash hidden = false }, --[[--------------------------< M A I N T >------------------------------------- maint messages do not have a message (message = nil); otherwise the structure is the same as error messages ]] maint_archive_origin = { message = nil, anchor = 'archive_origin', category = 'CS1 maint: archive origin', hidden = true, }, maint_archived_copy = { message = nil, anchor = 'archived_copy', category = 'CS1 maint: archived copy as title', hidden = true, }, maint_bibcode = { message = nil, anchor = 'bibcode', category = 'CS1 maint: bibcode', hidden = true, }, maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite message = nil, anchor = 'location_no_publisher', category = 'CS1 maint: location missing publisher', hidden = true, }, maint_bot_unknown = { message = nil, anchor = 'bot:_unknown', category = 'CS1 maint: bot: original URL status unknown', hidden = true, }, maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki message = nil, anchor = 'date_auto_xlated', category = 'CS1 maint: date auto-translated', hidden = true, }, maint_date_format = { message = nil, anchor = 'date_format', category = 'CS1 maint: date format', hidden = true, }, maint_date_year = { message = nil, anchor = 'date_year', category = 'CS1 maint: date and year', hidden = true, }, maint_deprecated_archive = { message = nil, anchor = 'deprecated_archive', category = 'CS1 maint: deprecated archival service', hidden = true, }, maint_doi_ignore = { message = nil, anchor = 'doi_ignore', category = 'CS1 maint: ignored DOI errors', hidden = true, }, maint_doi_inactive = { message = nil, anchor = 'doi_inactive', category = 'CS1 maint: DOI inactive', hidden = true, }, maint_doi_inactive_dated = { message = nil, anchor = 'doi_inactive_dated', category = 'CS1 maint: DOI inactive as of $2$3$1', -- $1 is year, $2 is month-name or empty string, $3 is space or empty string hidden = true, }, maint_doi_unflagged_free = { message = nil, anchor = 'doi_unflagged_free', category = 'CS1 maint: unflagged free DOI', hidden = true, }, maint_extra_punct = { message = nil, anchor = 'extra_punct', category = 'CS1 maint: extra punctuation', hidden = true, }, maint_id_limit_load_fail = { -- applies to all cs1|2 templates on a page; message = nil, -- maint message (category link) never emitted anchor = 'id_limit_load_fail', category = 'CS1 maint: ID limit load fail', hidden = true, }, maint_isbn_ignore = { message = nil, anchor = 'ignore_isbn_err', category = 'CS1 maint: ignored ISBN errors', hidden = true, }, maint_issn_ignore = { message = nil, anchor = 'ignore_issn', category = 'CS1 maint: ignored ISSN errors', hidden = true, }, maint_jfm_format = { message = nil, anchor = 'jfm_format', category = 'CS1 maint: JFM format', hidden = true, }, maint_location = { message = nil, anchor = 'location', category = 'CS1 maint: location', hidden = true, }, maint_missing_class = { message = nil, anchor = 'missing_class', category = 'CS1 maint: missing class', hidden = true, }, maint_mr_format = { message = nil, anchor = 'mr_format', category = 'CS1 maint: MR format', hidden = true, }, maint_mult_names = { message = nil, anchor = 'mult_names', category = 'CS1 maint: multiple names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table hidden = true, }, maint_numeric_names = { message = nil, anchor = 'numeric_names', category = 'CS1 maint: numeric names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table hidden = true, }, maint_others = { message = nil, anchor = 'others', category = 'CS1 maint: others', hidden = true, }, maint_others_avm = { message = nil, anchor = 'others_avm', category = 'CS1 maint: others in cite AV media (notes)', hidden = true, }, maint_overridden_setting = { message = nil, anchor = 'overridden', category = 'CS1 maint: overridden setting', hidden = true, }, maint_page_art_num = { message = nil, anchor = 'page_art_num', category = 'CS1 maint: article number as page number', hidden = true, }, maint_pmc_embargo = { message = nil, anchor = 'embargo', category = 'CS1 maint: PMC embargo expired', hidden = true, }, maint_pmc_format = { message = nil, anchor = 'pmc_format', category = 'CS1 maint: PMC format', hidden = true, }, maint_postscript = { message = nil, anchor = 'postscript', category = 'CS1 maint: postscript', hidden = true, }, maint_publisher_location = { message = nil, anchor = 'publisher_location', category = 'CS1 maint: publisher location', hidden = true, }, maint_ref_duplicates_default = { message = nil, anchor = 'ref_default', category = 'CS1 maint: ref duplicates default', hidden = true, }, maint_shortened_archive_url = { message = nil, anchor = 'shortened_archive_url', category = 'CS1 maint: shortened archive url', hidden = true, }, maint_unknown_lang = { message = nil, anchor = 'unknown_lang', category = 'CS1 maint: unrecognized language', hidden = true, }, maint_untitled = { message = nil, anchor = 'untitled', category = 'CS1 maint: untitled periodical', hidden = true, }, maint_url_status = { message = nil, anchor = 'url_status', category = 'CS1 maint: url-status', hidden = true, }, maint_work_isbn = { message = nil, anchor = 'work_isbn', category = 'CS1 maint: work parameter with ISBN', hidden = true, }, maint_year= { message = nil, anchor = 'year', category = 'CS1 maint: year', hidden = true, }, maint_zbl = { message = nil, anchor = 'zbl', category = 'CS1 maint: Zbl', hidden = true, }, } --[[--------------------------< I D _ L I M I T S _ D A T A _ T >---------------------------------------------- fetch id limits for certain identifiers from c:Data:CS1/Identifier limits.tab. This source is a json tabular data file maintained at wikipedia commons. Convert the json format to a table of k/v pairs. The values from <id_limits_data_t> are used to set handle.id_limit. From 2025-02-21, MediaWiki is broken. Use this link to edit the tablular data file: https://commons.wikimedia.org/w/index.php?title=Data:CS1/Identifier_limits.tab&action=edit See Phab:T389105 ]] local id_limits_data_t = {}; local use_commons_data = true; -- set to false if your wiki does not have access to mediawiki commons; then, if false == use_commons_data then -- update this table from https://commons.wikimedia.org/wiki/Data:CS1/Identifier_limits.tab; last update: 2025-02-21 id_limits_data_t = {['OCLC'] = 10450000000, ['OSTI'] = 23010000, ['PMC'] = 11900000, ['PMID'] = 40400000, ['RFC'] = 9300, ['SSRN'] = 5200000, ['S2CID'] = 276000000}; -- this table must be maintained locally else -- here for wikis that do have access to mediawiki commons local load_fail_limit = 99999999999; -- very high number to avoid error messages on load failure id_limits_data_t = {['OCLC'] = load_fail_limit, ['OSTI'] = load_fail_limit, ['PMC'] = load_fail_limit, ['PMID'] = load_fail_limit, ['RFC'] = load_fail_limit, ['SSRN'] = load_fail_limit, ['S2CID'] = load_fail_limit}; local id_limits_data_load_fail = false; -- flag; assume that we will be successful when loading json id limit tabular data if mw.ext.data == nil then id_limits_data_load_fail = true; -- safeguard against Lua errors if mw.ext.data is not available for some reason else local tab_data_t = mw.ext.data.get ('CS1/Identifier limits.tab'); -- attempt to load the tabular data from commons into <tab_data_t> if false == tab_data_t then -- undocumented 'feature': mw.ext.data.get() sometimes returns false id_limits_data_load_fail = true; -- set the flag so that Module:Citation/CS1 can create an unannotated maint category else for _, limit_t in ipairs (tab_data_t.data) do -- overwrite default <load_fail_limit> values from the data table in the tabular data id_limits_data_t[limit_t[1]] = limit_t[2]; -- <limit[1]> is identifier; <limit[2]> is upper limit for that identifier end end end end --[[--------------------------< I D _ H A N D L E R S >-------------------------------------------------------- The following contains a list of values for various defined identifiers. For each identifier we specify a variety of information necessary to properly render the identifier in the citation. parameters: a list of parameter aliases for this identifier; first in the list is the canonical form link: Wikipedia article name redirect: a local redirect to a local Wikipedia article name; at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number' q: Wikidata q number for the identifier label: the label preceding the identifier; label is linked to a Wikipedia article (in this order): redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q local article name from id_handlers['<id>'].link prefix: the first part of a URL that will be concatenated with a second part which usually contains the identifier suffix: optional third part to be added after the identifier encode: true if URI should be percent-encoded; otherwise false COinS: identifier link or keyword for use in COinS: for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn for |asin= and |ol=, which require assembly, use the keyword: url for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here) set to nil to leave the identifier out of the COinS separator: character or text between label and the identifier in the rendered citation id_limit: for those identifiers with established limits, this property holds the upper limit access: use this parameter to set the access level for all instances of this identifier. the value must be a valid access level for an identifier (see ['id-access'] in this file). custom_access: to enable custom access level for an identifier, set this parameter to the parameter that should control it (normally 'id-access') ]] local id_handlers = { ['ARXIV'] = { parameters = {'arxiv', 'eprint'}, link = 'arXiv', redirect = 'arXiv (identifier)', q = 'Q118398', label = 'arXiv', prefix = 'https://arxiv.org/abs/', encode = false, COinS = 'info:arxiv', separator = ':', access = 'free', -- free to read }, ['ASIN'] = { parameters = { 'asin', 'ASIN' }, link = 'Amazon Standard Identification Number', redirect = 'ASIN (identifier)', q = 'Q1753278', label = 'ASIN', prefix = 'https://www.amazon.', COinS = 'url', separator = '&nbsp;', encode = false; }, ['BIBCODE'] = { parameters = {'bibcode'}, link = 'Bibcode', redirect = 'Bibcode (identifier)', q = 'Q25754', label = 'Bibcode', prefix = 'https://ui.adsabs.harvard.edu/abs/', encode = false, COinS = 'info:bibcode', separator = ':', custom_access = 'bibcode-access', }, ['BIORXIV'] = { parameters = {'biorxiv'}, link = 'bioRxiv', redirect = 'bioRxiv (identifier)', q = 'Q19835482', label = 'bioRxiv', prefix = 'https://doi.org/', COinS = 'pre', -- use prefix value access = 'free', -- free to read encode = true, separator = '&nbsp;', }, ['CITESEERX'] = { parameters = {'citeseerx'}, link = 'CiteSeerX', redirect = 'CiteSeerX (identifier)', q = 'Q2715061', label = 'CiteSeerX', prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=', COinS = 'pre', -- use prefix value access = 'free', -- free to read encode = true, separator = '&nbsp;', }, ['DOI'] = { -- Used by InternetArchiveBot parameters = { 'doi', 'DOI'}, link = 'Digital object identifier', redirect = 'doi (identifier)', q = 'Q25670', label = 'doi', prefix = 'https://doi.org/', COinS = 'info:doi', separator = ':', encode = true, custom_access = 'doi-access', }, ['EISSN'] = { parameters = {'eissn', 'EISSN'}, link = 'International Standard Serial Number#Electronic ISSN', redirect = 'eISSN (identifier)', q = 'Q46339674', label = 'eISSN', prefix = 'https://search.worldcat.org/issn/', COinS = 'rft.eissn', encode = false, separator = '&nbsp;', }, ['HDL'] = { parameters = { 'hdl', 'HDL' }, link = 'Handle System', redirect = 'hdl (identifier)', q = 'Q3126718', label = 'hdl', prefix = 'https://hdl.handle.net/', COinS = 'info:hdl', separator = ':', encode = true, custom_access = 'hdl-access', }, ['ISBN'] = { -- Used by InternetArchiveBot parameters = {'isbn', 'ISBN'}, link = 'International Standard Book Number', redirect = 'ISBN (identifier)', q = 'Q33057', label = 'ISBN', prefix = 'Special:BookSources/', COinS = 'rft.isbn', separator = '&nbsp;', }, ['ISMN'] = { parameters = {'ismn', 'ISMN'}, link = 'International Standard Music Number', redirect = 'ISMN (identifier)', q = 'Q1666938', label = 'ISMN', prefix = '', -- not currently used; COinS = nil, -- nil because we can't use pre or rft or info: separator = '&nbsp;', }, ['ISSN'] = { parameters = {'issn', 'ISSN'}, link = 'International Standard Serial Number', redirect = 'ISSN (identifier)', q = 'Q131276', label = 'ISSN', prefix = 'https://search.worldcat.org/issn/', COinS = 'rft.issn', encode = false, separator = '&nbsp;', }, ['JFM'] = { parameters = {'jfm', 'JFM'}, link = 'Jahrbuch über die Fortschritte der Mathematik', redirect = 'JFM (identifier)', q = '', label = 'JFM', prefix = 'https://zbmath.org/?format=complete&q=an:', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', }, ['JSTOR'] = { parameters = {'jstor', 'JSTOR'}, link = 'JSTOR', redirect = 'JSTOR (identifier)', q = 'Q1420342', label = 'JSTOR', prefix = 'https://www.jstor.org/stable/', COinS = 'pre', -- use prefix value encode = false, separator = '&nbsp;', custom_access = 'jstor-access', }, ['LCCN'] = { parameters = {'lccn', 'LCCN'}, link = 'Library of Congress Control Number', redirect = 'LCCN (identifier)', q = 'Q620946', label = 'LCCN', prefix = 'https://lccn.loc.gov/', COinS = 'info:lccn', encode = false, separator = '&nbsp;', }, ['MEDRXIV'] = { parameters = {'medrxiv'}, link = 'medRxiv', redirect = 'medRxiv (identifier)', q = 'Q58465838', label = 'medRxiv', prefix = 'https://www.medrxiv.org/content/', COinS = 'pre', -- use prefix value access = 'free', -- free to read encode = false, separator = '&nbsp;', }, ['MR'] = { parameters = {'mr', 'MR'}, link = 'Mathematical Reviews', redirect = 'MR (identifier)', q = 'Q211172', label = 'MR', prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', }, ['OCLC'] = { parameters = {'oclc', 'OCLC'}, link = 'OCLC', redirect = 'OCLC (identifier)', q = 'Q190593', label = 'OCLC', prefix = 'https://search.worldcat.org/oclc/', COinS = 'info:oclcnum', encode = true, separator = '&nbsp;', id_limit = id_limits_data_t.OCLC or 0, }, ['OL'] = { parameters = { 'ol', 'OL' }, link = 'Open Library', redirect = 'OL (identifier)', q = 'Q1201876', label = 'OL', prefix = 'https://openlibrary.org/', COinS = 'url', separator = '&nbsp;', encode = true, custom_access = 'ol-access', }, ['OSTI'] = { parameters = {'osti', 'OSTI'}, link = 'Office of Scientific and Technical Information', redirect = 'OSTI (identifier)', q = 'Q2015776', label = 'OSTI', prefix = 'https://www.osti.gov/biblio/', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', id_limit = id_limits_data_t.OSTI or 0, custom_access = 'osti-access', }, ['PMC'] = { parameters = {'pmc', 'PMC'}, link = 'PubMed Central', redirect = 'PMC (identifier)', q = 'Q229883', label = 'PMC', prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC', suffix = '', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', id_limit = id_limits_data_t.PMC or 0, access = 'free', -- free to read }, ['PMID'] = { parameters = {'pmid', 'PMID'}, link = 'PubMed Identifier', redirect = 'PMID (identifier)', q = 'Q2082879', label = 'PMID', prefix = 'https://pubmed.ncbi.nlm.nih.gov/', COinS = 'info:pmid', encode = false, separator = '&nbsp;', id_limit = id_limits_data_t.PMID or 0, }, ['RFC'] = { parameters = {'rfc', 'RFC'}, link = 'Request for Comments', redirect = 'RFC (identifier)', q = 'Q212971', label = 'RFC', prefix = 'https://tools.ietf.org/html/rfc', COinS = 'pre', -- use prefix value encode = false, separator = '&nbsp;', id_limit = id_limits_data_t.RFC or 0, access = 'free', -- free to read }, ['SBN'] = { parameters = {'sbn', 'SBN'}, link = 'Standard Book Number', -- redirect to International_Standard_Book_Number#History redirect = 'SBN (identifier)', label = 'SBN', prefix = 'Special:BookSources/0-', -- prefix has leading zero necessary to make 9-digit sbn a 10-digit isbn COinS = nil, -- nil because we can't use pre or rft or info: separator = '&nbsp;', }, ['SSRN'] = { parameters = {'ssrn', 'SSRN'}, link = 'Social Science Research Network', redirect = 'SSRN (identifier)', q = 'Q7550801', label = 'SSRN', prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', id_limit = id_limits_data_t.SSRN or 0, custom_access = 'ssrn-access', }, ['S2CID'] = { parameters = {'s2cid', 'S2CID'}, link = 'Semantic Scholar', redirect = 'S2CID (identifier)', q = 'Q22908627', label = 'S2CID', prefix = 'https://api.semanticscholar.org/CorpusID:', COinS = 'pre', -- use prefix value encode = false, separator = '&nbsp;', id_limit = id_limits_data_t.S2CID or 0, custom_access = 's2cid-access', }, ['USENETID'] = { parameters = {'message-id'}, link = 'Usenet', redirect = 'Usenet (identifier)', q = 'Q193162', label = 'Usenet:', prefix = 'news:', encode = false, COinS = 'pre', -- use prefix value separator = '&nbsp;', }, ['ZBL'] = { parameters = {'zbl', 'ZBL' }, link = 'Zentralblatt MATH', redirect = 'Zbl (identifier)', q = 'Q190269', label = 'Zbl', prefix = 'https://zbmath.org/?format=complete&q=an:', COinS = 'pre', -- use prefix value encode = true, separator = '&nbsp;', }, } --[[--------------------------< E X P O R T S >--------------------------------- ]] return { use_identifier_redirects = use_identifier_redirects, -- booleans defined in the settings at the top of this module local_lang_cat_enable = local_lang_cat_enable, date_name_auto_xlate_enable = date_name_auto_xlate_enable, date_digit_auto_xlate_enable = date_digit_auto_xlate_enable, enable_sort_keys = enable_sort_keys, suppress_archive_today_urls = suppress_archive_today_urls, -- tables and variables created when this module is loaded dependencies_t = dependencies_t, -- used to suppress parameters dependent on url-holding parameters holding archive.today urls enum_needs_xlation = '1' ~= date_names.xlate_digits['1'], -- to avoid unnecessary enumerator translation global_df = get_date_format (), -- this line can be replaced with "global_df = 'dmy-all'," to have all dates auto translated to dmy format. global_cs1_config_t = global_cs1_config_t, -- global settings from {{cs1 config}} id_limits_data_load_fail = id_limits_data_load_fail, -- true when commons tabular identifier-limit data fails to load known_free_doi_registrants_t = build_free_doi_registrants_table(), punct_skip = build_skip_table (punct_skip, punct_meta_params), url_skip = build_skip_table (url_skip, url_meta_params), archive_today_tlds_t = {['today'] = true, ['ph'] = true, ['is'] = true, ['md'] = true, ['li'] = true, ['fo'] = true, ['vn'] = true}; -- used by is_archive_today_url() name_space_sort_keys = name_space_sort_keys, aliases = aliases, special_case_translation = special_case_translation, date_names = date_names, err_msg_supl = err_msg_supl, error_conditions = error_conditions, editor_markup_patterns = editor_markup_patterns, et_al_patterns = et_al_patterns, extended_registrants_t = extended_registrants_t, id_handlers = id_handlers, keywords_lists = keywords_lists, keywords_xlate = keywords_xlate, stripmarkers = stripmarkers, invisible_chars = invisible_chars, invisible_defs = invisible_defs, indic_script = indic_script, emoji_t = emoji_t, maint_cats = maint_cats, messages = messages, presentation = presentation, prop_cats = prop_cats, script_lang_codes = script_lang_codes, lang_tag_remap = lang_tag_remap, lang_name_remap = lang_name_remap, this_wiki_code = this_wiki_code, title_types = title_types, uncategorized_namespaces = uncategorized_namespaces_t, uncategorized_subpages = uncategorized_subpages, templates_using_volume = templates_using_volume, templates_using_issue = templates_using_issue, templates_not_using_page = templates_not_using_page, vol_iss_pg_patterns = vol_iss_pg_patterns, single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t, url_access_map_t = url_access_map_t, inter_wiki_map = inter_wiki_map, mw_languages_by_tag_t = mw_languages_by_tag_t, mw_languages_by_name_t = mw_languages_by_name_t, citation_class_map_t = citation_class_map_t, citation_issue_t = citation_issue_t, citation_no_volume_t = citation_no_volume_t, } 7oukcgh6jfipsgm5ag4ypttwht4cce8 828 655 9075 2026-05-15T07:14:52Z WikiBayer 737 [[:w:Special:PermanentLink/1240835177|Module:Citation/CS1/Whitelist]] 9075 Scribunto text/plain --[[--------------------------< S U P P O R T E D P A R A M E T E R S >-------------------------------------- Because a steady-state signal conveys no useful information, whitelist.basic_arguments[] list items can have three values: true - these parameters are valid and supported parameters false - these parameters are deprecated but still supported tracked - these parameters are valid and supported parameters tracked in an eponymous properties category nil - these parameters are no longer supported. remove entirely ]] local basic_arguments_t = { ['accessdate'] = true, ['access-date'] = true, ['agency'] = true, ['archivedate'] = true, ['archive-date'] = true, ['archive-format'] = true, ['archiveurl'] = true, ['archive-url'] = true, ['article'] = true, ['article-format'] = true, ['article-number'] = true, -- {{cite journal}}, {{cite conference}}; {{citation}} when |journal= has a value ['article-url'] = true, ['article-url-access'] = true, ['arxiv'] = true, -- cite arxiv; here because allowed in cite ... as identifier ['asin'] = true, ['ASIN'] = true, ['asin-tld'] = true, ['at'] = true, ['author'] = true, ['author-first'] = true, ['author-given'] = true, ['author-last'] = true, ['author-surname'] = true, ['authorlink'] = true, ['author-link'] = true, ['author-mask'] = true, ['bibcode'] = true, ['bibcode-access'] = true, ['biorxiv'] = true, -- cite biorxiv; here because allowed in cite ... as identifier ['chapter'] = true, ['chapter-format'] = true, ['chapter-url'] = true, ['chapter-url-access'] = true, ['citeseerx'] = true, -- cite citeseerx; here because allowed in cite ... as identifier ['collaboration'] = true, ['contribution'] = true, ['contribution-format'] = true, ['contribution-url'] = true, ['contribution-url-access'] = true, ['contributor'] = true, ['contributor-first'] = true, ['contributor-given'] = true, ['contributor-last'] = true, ['contributor-surname'] = true, ['contributor-link'] = true, ['contributor-mask'] = true, ['date'] = true, ['department'] = true, ['df'] = true, ['dictionary'] = true, ['display-authors'] = true, ['display-contributors'] = true, ['display-editors'] = true, ['display-interviewers'] = true, ['display-subjects'] = true, ['display-translators'] = true, ['doi'] = true, ['DOI'] = true, ['doi-access'] = true, ['doi-broken-date'] = true, ['edition'] = true, ['editor'] = true, ['editor-first'] = true, ['editor-given'] = true, ['editor-last'] = true, ['editor-surname'] = true, ['editor-link'] = true, ['editor-mask'] = true, ['eissn'] = true, ['EISSN'] = true, ['encyclopaedia'] = true, ['encyclopedia'] = true, ['entry'] = true, ['entry-format'] = true, ['entry-url'] = true, ['entry-url-access'] = true, ['eprint'] = true, -- cite arxiv; here because allowed in cite ... as identifier ['first'] = true, ['format'] = true, ['given'] = true, ['hdl'] = true, ['HDL'] = true, ['hdl-access'] = true, ['host'] = true, -- unique to certain templates? ['id'] = true, ['ID'] = true, ['institution'] = true, -- constrain to cite thesis? ['interviewer'] = true, ['interviewer-first'] = true, ['interviewer-given'] = true, ['interviewer-last'] = true, ['interviewer-surname'] = true, ['interviewer-link'] = true, ['interviewer-mask'] = true, ['isbn'] = true, ['ISBN'] = true, ['ismn'] = true, ['ISMN'] = true, ['issn'] = true, ['ISSN'] = true, ['issue'] = true, ['jfm'] = true, ['JFM'] = true, ['journal'] = true, ['jstor'] = true, ['JSTOR'] = true, ['jstor-access'] = true, ['lang'] = true, ['language'] = true, ['last'] = true, ['lccn'] = true, ['LCCN'] = true, ['location'] = true, ['magazine'] = true, ['medium'] = true, ['medrxiv'] = true, -- cite medrxiv; here because allowed in cite ... as identifier ['minutes'] = true, -- constrain to cite AV media and podcast? ['mode'] = true, ['mr'] = true, ['MR'] = true, ['name-list-style'] = true, ['newspaper'] = true, ['no-pp'] = true, ['no-tracking'] = true, ['number'] = true, ['oclc'] = true, ['OCLC'] = true, ['ol'] = true, ['OL'] = true, ['ol-access'] = true, ['orig-date'] = true, ['origyear'] = true, ['orig-year'] = true, ['osti'] = true, ['OSTI'] = true, ['osti-access'] = true, ['others'] = true, ['p'] = true, ['page'] = true, ['pages'] = true, ['periodical'] = true, ['place'] = true, ['pmc'] = true, ['PMC'] = true, ['pmc-embargo-date'] = true, ['pmid'] = true, ['PMID'] = true, ['postscript'] = true, ['pp'] = true, ['publication-date'] = true, ['publication-place'] = true, ['publisher'] = true, ['quotation'] = true, ['quote'] = true, ['quote-page'] = true, ['quote-pages'] = true, ['ref'] = true, ['rfc'] = true, ['RFC'] = true, ['sbn'] = true, ['SBN'] = true, ['scale'] = true, ['script-article'] = true, ['script-chapter'] = true, ['script-contribution'] = true, ['script-encyclopaedia'] = true, ['script-encyclopedia'] = true, ['script-entry'] = true, ['script-journal'] = true, ['script-magazine'] = true, ['script-newspaper'] = true, ['script-periodical'] = true, ['script-quote'] = true, ['script-section'] = true, ['script-title'] = true, ['script-website'] = true, ['script-work'] = true, ['section'] = true, ['section-format'] = true, ['section-url'] = true, ['section-url-access'] = true, ['series'] = true, ['ssrn'] = true, -- cite ssrn; these three here because allowed in cite ... as identifier ['SSRN'] = true, ['ssrn-access'] = true, ['subject'] = true, ['subject-first'] = true, ['subject-given'] = true, ['subject-last'] = true, ['subject-link'] = true, ['subject-mask'] = true, ['subject-surname'] = true, ['surname'] = true, ['s2cid'] = true, ['S2CID'] = true, ['s2cid-access'] = true, ['template-doc-demo'] = true, ['time'] = true, -- constrain to cite av media and podcast? ['time-caption'] = true, -- constrain to cite av media and podcast? ['title'] = true, ['title-link'] = true, ['title-note'] = true, ['translator'] = true, ['translator-first'] = true, ['translator-given'] = true, ['translator-last'] = true, ['translator-surname'] = true, ['translator-link'] = true, ['translator-mask'] = true, ['trans-article'] = true, ['trans-chapter'] = true, ['trans-contribution'] = true, ['trans-encyclopaedia'] = true, ['trans-encyclopedia'] = true, ['trans-entry'] = true, ['trans-journal'] = true, ['trans-magazine'] = true, ['trans-newspaper'] = true, ['trans-periodical'] = true, ['trans-quote'] = true, ['trans-section'] = true, ['trans-title'] = true, ['trans-website'] = true, ['trans-work'] = true, ['type'] = true, ['url'] = true, ['URL'] = true, ['url-access'] = true, ['url-status'] = true, ['vauthors'] = true, ['veditors'] = true, ['version'] = true, ['via'] = true, ['volume'] = true, ['website'] = true, ['work'] = true, ['year'] = true, ['zbl'] = true, ['ZBL'] = true, } local numbered_arguments_t = { ['author#'] = true, ['author-first#'] = true, ['author#-first'] = true, ['author-given#'] = true, ['author#-given'] = true, ['author-last#'] = true, ['author#-last'] = true, ['author-surname#'] = true, ['author#-surname'] = true, ['author-link#'] = true, ['author#-link'] = true, ['authorlink#'] = true, ['author#link'] = true, ['author-mask#'] = true, ['author#-mask'] = true, ['contributor#'] = true, ['contributor-first#'] = true, ['contributor#-first'] = true, ['contributor-given#'] = true, ['contributor#-given'] = true, ['contributor-last#'] = true, ['contributor#-last'] = true, ['contributor-surname#'] = true, ['contributor#-surname'] = true, ['contributor-link#'] = true, ['contributor#-link'] = true, ['contributor-mask#'] = true, ['contributor#-mask'] = true, ['editor#'] = true, ['editor-first#'] = true, ['editor#-first'] = true, ['editor-given#'] = true, ['editor#-given'] = true, ['editor-last#'] = true, ['editor#-last'] = true, ['editor-surname#'] = true, ['editor#-surname'] = true, ['editor-link#'] = true, ['editor#-link'] = true, ['editor-mask#'] = true, ['editor#-mask'] = true, ['first#'] = true, ['given#'] = true, ['host#'] = true, ['interviewer#'] = true, ['interviewer-first#'] = true, ['interviewer#-first'] = true, ['interviewer-given#'] = true, ['interviewer#-given'] = true, ['interviewer-last#'] = true, ['interviewer#-last'] = true, ['interviewer-surname#'] = true, ['interviewer#-surname'] = true, ['interviewer-link#'] = true, ['interviewer#-link'] = true, ['interviewer-mask#'] = true, ['interviewer#-mask'] = true, ['last#'] = true, ['subject#'] = true, ['subject-first#'] = true, ['subject#-first'] = true, ['subject-given#'] = true, ['subject#-given'] = true, ['subject-last#'] = true, ['subject#-last'] = true, ['subject-link#'] = true, ['subject#-link'] = true, ['subject-mask#'] = true, ['subject#-mask'] = true, ['subject-surname#'] = true, ['subject#-surname'] = true, ['surname#'] = true, ['translator#'] = true, ['translator-first#'] = true, ['translator#-first'] = true, ['translator-given#'] = true, ['translator#-given'] = true, ['translator-last#'] = true, ['translator#-last'] = true, ['translator-surname#'] = true, ['translator#-surname'] = true, ['translator-link#'] = true, ['translator#-link'] = true, ['translator-mask#'] = true, ['translator#-mask'] = true, } --[[--------------------------< P R E P R I N T S U P P O R T E D P A R A M E T E R S >-------------------- Cite arXiv, cite biorxiv, cite citeseerx, cite medrxiv, and cite ssrn are preprint templates that use the limited set of parameters defined in the limited_basic_arguments and limited_numbered_arguments tables. Those lists are supplemented with a template-specific list of parameters that are required by the particular template and may be exclusive to one of the preprint templates. Some of these parameters may also be available to the general cs1|2 templates. Same conventions for true/false/tracked/nil as above. ]] local preprint_arguments_t = { arxiv = { ['arxiv'] = true, -- cite arxiv and arxiv identifiers ['class'] = true, ['eprint'] = true, -- cite arxiv and arxiv identifiers }, biorxiv = { ['biorxiv'] = true, }, citeseerx = { ['citeseerx'] = true, }, medrxiv = { ['medrxiv'] = true, }, ssrn = { ['ssrn'] = true, ['SSRN'] = true, ['ssrn-access'] = true, }, } --[[--------------------------< L I M I T E D S U P P O R T E D P A R A M E T E R S >---------------------- cite arxiv, cite biorxiv, cite citeseerx, cite medrxiv, and cite ssrn templates are preprint templates so are allowed only a limited subset of parameters allowed to all other cs1|2 templates. The limited subset is defined here. This list of parameters also used by {{cite document}} Same conventions for true/false/tracked/nil as above. ]] local limited_basic_arguments_t = { ['at'] = true, ['author'] = true, ['author-first'] = true, ['author-given'] = true, ['author-last'] = true, ['author-surname'] = true, ['author-link'] = true, ['authorlink'] = true, ['author-mask'] = true, ['collaboration'] = true, ['date'] = true, ['df'] = true, ['display-authors'] = true, ['first'] = true, ['given'] = true, ['language'] = true, ['last'] = true, ['mode'] = true, ['name-list-style'] = true, ['no-tracking'] = true, ['p'] = true, ['page'] = true, ['pages'] = true, ['postscript'] = true, ['pp'] = true, ['quotation'] = true, ['quote'] = true, ['ref'] = true, ['surname'] = true, ['template-doc-demo'] = true, ['title'] = true, ['trans-title'] = true, ['vauthors'] = true, ['year'] = true, } local limited_numbered_arguments_t = { ['author#'] = true, ['author-first#'] = true, ['author#-first'] = true, ['author-given#'] = true, ['author#-given'] = true, ['author-last#'] = true, ['author#-last'] = true, ['author-surname#'] = true, ['author#-surname'] = true, ['author-link#'] = true, ['author#-link'] = true, ['authorlink#'] = true, ['author#link'] = true, ['author-mask#'] = true, ['author#-mask'] = true, ['first#'] = true, ['given#'] = true, ['last#'] = true, ['surname#'] = true, } --[[--------------------------< U N I Q U E _ A R G U M E N T S >---------------------------------------------- Some templates have unique parameters. Those templates and their unique parameters are listed here. Keys in this table are the template's CitationClass parameter value Same conventions for true/false/tracked/nil as above. ]] local unique_arguments_t = { ['audio-visual'] = { ['people'] = true, ['transcript'] = true, ['transcript-format'] = true, ['transcript-url'] = true, }, conference = { ['book-title'] = true, ['conference'] = true, ['conference-format'] = true, ['conference-url'] = true, ['event'] = true, }, episode = { ['airdate'] = true, ['air-date'] = true, ['credits'] = true, ['episode-link'] = true, -- alias of |title-link= ['network'] = true, ['people'] = true, ['season'] = true, ['series-link'] = true, ['series-no'] = true, ['series-number'] = true, ['station'] = true, ['transcript'] = true, ['transcript-format'] = true, ['transcript-url'] = true, }, mailinglist = { ['mailing-list'] = true, }, map = { ['cartography'] = true, ['inset'] = true, ['map'] = true, ['map-format'] = true, ['map-url'] = true, ['map-url-access'] = true, ['script-map'] = true, ['sections'] = true, ['sheet'] = true, ['sheets'] = true, ['trans-map'] = true, }, newsgroup = { ['message-id'] = true, ['newsgroup'] = true, }, report = { ['docket'] = true, }, serial = { ['airdate'] = true, ['air-date'] = true, ['credits'] = true, ['episode'] = true, -- cite serial only TODO: make available to cite episode? ['episode-link'] = true, -- alias of |title-link= ['network'] = true, ['people'] = true, ['series-link'] = true, ['station'] = true, }, speech = { ['conference'] = true, ['conference-format'] = true, ['conference-url'] = true, ['event'] = true, }, thesis = { ['degree'] = true, ['docket'] = true, }, } --[[--------------------------< C I T E _ D O C U M E N T >---------------------------------------------------- Special case for cite document. This template takes the limited basic and limited enumerated parameters plus others that are apply only to standalone published sources that cannot be cited any other way; no url, book, periodical, etc parameters; limited support for name lists and named identifiers. when validating parameters in {{cite document}} templates, the basic and ]] local document_arguments_t = { ['bibcode'] = true, ['bibcode-access'] = true, ['doi'] = true, ['DOI'] = true, ['doi-access'] = true, ['doi-broken-date'] = true, ['hdl'] = true, ['HDL'] = true, ['hdl-access'] = true, ['id'] = true, ['ID'] = true, ['jfm'] = true, ['JFM'] = true, ['lang'] = true, ['location'] = true, ['mr'] = true, ['MR'] = true, ['no-pp'] = true, ['orig-date'] = true, ['origyear'] = true, ['orig-year'] = true, ['osti'] = true, ['OSTI'] = true, ['osti-access'] = true, ['place'] = true, ['publisher'] = true, ['quote-page'] = true, ['quote-pages'] = true, ['script-quote'] = true, ['script-title'] = true, ['title-link'] = true, ['translator'] = true, ['translator-first'] = true, ['translator-given'] = true, ['translator-last'] = true, ['translator-surname'] = true, ['translator-link'] = true, ['translator-mask'] = true, ['trans-quote'] = true, ['type'] = true, ['zbl'] = true, ['ZBL'] = true, } local document_numbered_arguments_t = { ['translator#'] = true, ['translator-first#'] = true, ['translator#-first'] = true, ['translator-given#'] = true, ['translator#-given'] = true, ['translator-last#'] = true, ['translator#-last'] = true, ['translator-surname#'] = true, ['translator#-surname'] = true, ['translator-link#'] = true, ['translator#-link'] = true, ['translator-mask#'] = true, ['translator#-mask'] = true, } --[[--------------------------< L I S T _ C O M B I N E >------------------------------------------------------ makes one table from a list of tables. <lists_t> is a sequence of tables to be combined ]] local function list_combine (lists_t) local out_t = {}; for _, list_t in ipairs (lists_t) do -- for each list in <lists_t> for k, v in pairs (list_t) do -- extract each k/v pair out_t[k] = v; -- add to <out_t> end end return out_t; -- and done end --[[--------------------------< T E M P L A T E _ L I S T _ G E T >-------------------------------------------- gets a list of the templates from table t ]] local function template_list_get (t) local out_t = {}; -- a table for output for k, _ in pairs (t) do -- spin through the table and collect the keys table.insert (out_t, k) -- add each key to the output table end return out_t; -- and done end --[[--------------------------< E X P O R T E D T A B L E S >------------------------------------------------ ]] return { preprint_arguments_t = preprint_arguments_t, preprint_template_list_t = template_list_get (preprint_arguments_t), -- make a template list from preprint_arguments{} table unique_arguments_t = unique_arguments_t, unique_param_template_list_t = template_list_get (unique_arguments_t), -- make a template list from unique_arguments{} table document_parameters_t = list_combine ({limited_basic_arguments_t, limited_numbered_arguments_t, document_arguments_t, document_numbered_arguments_t}); common_parameters_t = list_combine ({basic_arguments_t, numbered_arguments_t}); limited_parameters_t = list_combine ({limited_basic_arguments_t, limited_numbered_arguments_t}); }; baub5v4d976tff8ebf3konhoua4ojgu 828 656 9076 2026-05-15T07:18:51Z WikiBayer 737 [[:w:Special:PermanentLink/1333433114|Module:Citation/CS1/Utilities]] 9076 Scribunto text/plain local z = { error_cats_t = {}; -- for categorizing citations that contain errors error_ids_t = {}; -- list of error identifiers; used to prevent duplication of certain errors; local to this module error_msgs_t = {}; -- sequence table of error messages maint_cats_t = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work prop_cats_t = {}; -- for categorizing citations based on certain properties, language of source for instance prop_keys_t = {}; -- for adding classes to the citation's <cite> tag }; --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration --[[--------------------------< I S _ S E T >------------------------------------------------------------------ Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. ]] local function is_set (var) return not (var == nil or var == ''); end --[[--------------------------< I N _ A R R A Y >-------------------------------------------------------------- Whether needle is in haystack ]] local function in_array (needle, haystack) if needle == nil then return false; end for n, v in ipairs (haystack) do if v == needle then return n; end end return false; end --[[--------------------------< H A S _ A C C E P T _ A S _ W R I T T E N >------------------------------------ When <str> is wholly wrapped in accept-as-written markup, return <str> without markup and true; return <str> and false else with allow_empty = false, <str> must have at least one character inside the markup with allow_empty = true, <str> the markup frame can be empty like (()) to distinguish an empty template parameter from the specific condition "has no applicable value" in citation-context. After further evaluation the two cases might be merged at a later stage, but should be kept separated for now. ]] local function has_accept_as_written (str, allow_empty) if not is_set (str) then return str, false; end local count; if true == allow_empty then str, count = str:gsub ('^%(%((.*)%)%)$', '%1'); -- allows (()) to be an empty set else str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); end return str, 0 ~= count; end --[[--------------------------< S U B S T I T U T E >---------------------------------------------------------- Populates numbered arguments in a message string using an argument table. <args> may be a single string or a sequence table of multiple strings. ]] local function substitute (msg, args) return args and mw.message.newRawMessage (msg, args):plain() or msg; end --[[--------------------------< E R R O R _ C O M M E N T >---------------------------------------------------- Wraps error messages with CSS markup according to the state of hidden. <content> may be a single string or a sequence table of multiple strings. ]] local function error_comment (content, hidden) return substitute (hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content); end --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- Converts a hyphen, endash, emdash to endash under certain conditions. The hyphen/en/em must separate like items; unlike items are returned unmodified. These forms are modified: letter - letter (A-B) digit - digit (4-5) digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5) digitletter - digitletter (5a-5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d) any other forms are returned unmodified. str may be a comma- or semicolon-separated list of page ranges with/without single pages ]] local function hyphen_to_dash (str) if not is_set (str) then return str; end str = str:gsub ("(%(%(.-%)%))", function(m) return m:gsub(",", "，"):gsub(";", "；") end) -- replace commas and semicolons in accept-as-written markup with similar unicode characters so they'll be ignored during the split str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split str = str:gsub ('&#45;', '-'); -- replace HTML numeric entity with hyphen character str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character local out = {}; local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any local accept; -- boolean for _, item in ipairs (list) do -- for each item in the list item, accept = has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[—–-]%s*%w*[%.%-]?%w+$') then -- if pagination uses <hyphen|dot> separators with hyphen/endash/emdash <range separator> if mw.ustring.match (item, '^%a+[%.%-]%d+%s*[—–-]%s*%a+[%.%-]%d+$') or -- letter<hyphen|dot>digit <range separator> letter<hyphen|dot>digit (requires <hyphen|dot> separator between letter and digit) mw.ustring.match (item, '^%d+[%.%-]%a+%s*[—–-]%s*%d+[%.%-]%a+$') or -- digit<hyphen|dot>letter <range separator> digit<hyphen|dot>letter (requires <hyphen|dot> separator between digit and letter) mw.ustring.match (item, '^%d+[%.%-]%d+%s*[—–-]%s*%d+[%.%-]%d+$') then -- digit<hyphen|dot>digit <range separator> digit<hyphen|dot>digit (requires <hyphen|dot> separator between digit and digit) item = mw.ustring.gsub (item, '(%w*[%.%-]%w+)%s*[—–-]%s*(%w*[%.%-]%w+)', '<span class="nowrap">%1 –</span> <span class="nowrap">%2</span>'); -- replace <range separator>, with spaced endash elseif mw.ustring.match (item, '^%d+%a+%s*[—–-]%s*%d+%a+$') or -- digitletter <range separator> digitletter mw.ustring.match (item, '^%a+%d+%s*[—–-]%s*%a+%d+$') or -- letterdigit <range separator> letterdigit mw.ustring.match (item, '^%d+%s*[—–-]%s*%d+$') or -- digit <range separator> digit mw.ustring.match (item, '^%a+%s*[—–-]%s*%a+$') then -- letter<range separator> letter item = mw.ustring.gsub (item, '(%w+)%s*[—–-]%s*(%w+)', '<span class="nowrap">%1–</span>%2'); -- replace <range separator> with endash, remove extraneous space characters else -- item = mw.ustring.gsub (item, '%s*[—–-]%s*', '–'); -- disabled; here when 'unlike' items so return <item> as is end end table.insert (out, item); -- add the (possibly modified) item to the output table end local temp_str = ''; -- concatenate the output table into a comma separated string temp_str, accept = has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out if accept then temp_str = has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value return temp_str:gsub("，", ","):gsub("；", ";"); else return temp_str:gsub("，", ","):gsub("；", ";"); -- else, return assembled temp_str end end --[=[-------------------------< M A K E _ W I K I L I N K >---------------------------------------------------- Makes a wikilink; when both link and display text is provided, returns a wikilink in the form [[L|D]]; if only link is provided (or link and display are the same), returns a wikilink in the form [[L]]; if neither are provided or link is omitted, returns an empty string. ]=] local function make_wikilink (link, display) if not is_set (link) then return '' end if is_set (display) and link ~= display then return table.concat ({'[[', link, '|', display, ']]'}); else return table.concat ({'[[', link, ']]'}); end end --[[--------------------------< S E T _ M E S S A G E >---------------------------------------------------------- Sets an error message using the ~/Configuration error_conditions{} table along with arguments supplied in the function call, inserts the resulting message in z.error_msgs_t{} sequence table, and returns the error message. <error_id> – key value for appropriate error handler in ~/Configuration error_conditions{} table <arguments> – may be a single string or a sequence table of multiple strings to be subsititued into error_conditions[error_id].message <raw> – boolean true – causes this function to return the error message not wrapped in visible-error, hidden-error span tag; returns error_conditions[error_id].hidden as a second return value does not add message to z.error_msgs_t sequence table false, nil – adds message wrapped in visible-error, hidden-error span tag to z.error_msgs_t returns the error message wrapped in visible-error, hidden-error span tag; there is no second return value <prefix> – string to be prepended to <message> -- TODO: remove support for these unused(?) arguments? <suffix> – string to be appended to <message> TODO: change z.error_cats_t and z.maint_cats_t to have the form cat_name = true? this to avoid dups without having to have an extra table ]] local added_maint_cats = {} -- list of maintenance categories that have been added to z.maint_cats_t; TODO: figure out how to delete this table local function set_message (error_id, arguments, raw, prefix, suffix) local error_state = cfg.error_conditions[error_id]; prefix = prefix or ''; suffix = suffix or ''; if error_state == nil then error (cfg.messages['undefined_error'] .. ': ' .. error_id); -- because missing error handler in Module:Citation/CS1/Configuration elseif is_set (error_state.category) then if error_state.message then -- when error_state.message defined, this is an error message table.insert (z.error_cats_t, error_state.category); else if not added_maint_cats[error_id] then added_maint_cats[error_id] = true; -- note that we've added this category table.insert (z.maint_cats_t, substitute (error_state.category, arguments)); -- make cat name then add to table end return; -- because no message, nothing more to do end end local message = substitute (error_state.message, arguments); message = table.concat ( { message, ' (', make_wikilink ( table.concat ( { cfg.messages['help page link'], '#', error_state.anchor }), cfg.messages['help page label']), ')' }); z.error_ids_t[error_id] = true; if z.error_ids_t['err_citation_missing_title'] and -- if missing-title error already noted in_array (error_id, {'err_bare_url_missing_title', 'err_trans_missing_title'}) then -- and this error is one of these return '', false; -- don't bother because one flavor of missing title is sufficient end message = table.concat ({prefix, message, suffix}); if true == raw then return message, error_state.hidden; -- return message not wrapped in visible-error, hidden-error span tag end message = error_comment (message, error_state.hidden); -- wrap message in visible-error, hidden-error span tag table.insert (z.error_msgs_t, message); -- add it to the messages sequence table return message; -- and done; return value generally not used but is used as a flag in various functions of ~/Identifiers end --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- This function is used by select_one() to determine if one of a list of alias parameters is in the argument list provided by the template. Input: args – pointer to the arguments table from calling template alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration index – for enumerated parameters, identifies which one enumerated – true/false flag used to choose how enumerated aliases are examined value – value associated with an alias that has previously been selected; nil if not yet selected selected – the alias that has previously been selected; nil if not yet selected error_list – list of aliases that are duplicates of the alias already selected Returns: value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected ]] local function is_alias_used (args, alias, index, enumerated, value, selected, error_list) if enumerated then -- is this a test for an enumerated parameters? alias = alias:gsub ('#', index); -- replace '#' with the value in index else alias = alias:gsub ('#', ''); -- remove '#' if it exists end if is_set (args[alias]) then -- alias is in the template's argument list if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases local skip; for _, v in ipairs (error_list) do -- spin through the error list to see if we've added this alias if v == alias then skip = true; break; -- has been added so stop looking end end if not skip then -- has not been added so table.insert (error_list, alias); -- add error alias to the error list end else value = args[alias]; -- not yet selected an alias, so select this one selected = alias; end end return value, selected; -- return newly selected alias, or previously selected alias end --[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------ Adds a category to z.maint_cats_t using names from the configuration file with additional text if any. To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maint_cats_t. ]] local function add_maint_cat (key, arguments) if not added_maint_cats [key] then added_maint_cats [key] = true; -- note that we've added this category table.insert (z.maint_cats_t, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table end end --[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- Adds a category to z.prop_cats_t using names from the configuration file with additional text if any. foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages may be categorized but multiples of the same language are not categorized. added_prop_cats is a table declared in page scope variables above ]] local added_prop_cats = {}; -- list of property categories that have been added to z.prop_cats_t local function add_prop_cat (key, arguments, key_modifier) local key_modified = key .. ((key_modifier and key_modifier) or ''); -- modify <key> with <key_modifier> if present and not nil if not added_prop_cats [key_modified] then added_prop_cats [key_modified] = true; -- note that we've added this category table.insert (z.prop_cats_t, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table table.insert (z.prop_keys_t, 'cs1-prop-' .. key); -- convert key to class for use in the citation's <cite> tag end 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 '' ... '' Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that they will be inverted (i.e. unitalicized) in the resulting references. In addition, <i> and '' tend to interact poorly under Mediawiki's HTML tidy. ]] local function safe_for_italics (str) if not is_set (str) then return str end if str:sub (1, 1) == "'" then str = "<span></span>" .. str; end if str:sub (-1, -1) == "'" then str = str .. "<span></span>"; end return str:gsub ('\n', ' '); -- Remove newlines as they break italics. 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 --[[--------------------------< M A K E _ S E P _ L I S T >------------------------------------------------------------ make a separated list of items using provided separators. <sep_list> - typically '<comma><space>' <sep_list_pair> - typically '<space>and<space>' <sep_list_end> - typically '<comma><space>and<space>' or '<comma><space>&<space>' defaults to cfg.presentation['sep_list'], cfg.presentation['sep_list_pair'], and cfg.presentation['sep_list_end'] if <sep_list_end> is specified, <sep_list> and <sep_list_pair> must also be supplied ]] local function make_sep_list (count, list_seq, sep_list, sep_list_pair, sep_list_end) local list = ''; if not sep_list then -- set the defaults sep_list = cfg.presentation['sep_list']; sep_list_pair = cfg.presentation['sep_list_pair']; sep_list_end = cfg.presentation['sep_list_end']; end if 2 >= count then list = table.concat (list_seq, sep_list_pair); -- insert separator between two items; returns list_seq[1] then only one item elseif 2 < count then list = table.concat (list_seq, sep_list, 1, count - 1); -- concatenate all but last item with plain list separator list = table.concat ({list, list_seq[count]}, sep_list_end); -- concatenate last item onto end of <list> with final separator end return list; end --[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'. Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities. Generates an error if more than one match is present. ]] local function select_one (args, aliases_list, error_condition, index) local value = nil; -- the value assigned to the selected parameter local selected = ''; -- the name of the parameter we have chosen local error_list = {}; if index ~= nil then index = tostring(index); end for _, alias in ipairs (aliases_list) do -- for each alias in the aliases list if alias:match ('#') then -- if this alias can be enumerated if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias end value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias else value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- test for non-enumerated alias end end if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names() for i, v in ipairs (error_list) do error_list[i] = wrap_style ('parameter', v); end table.insert (error_list, wrap_style ('parameter', selected)); set_message (error_condition, {make_sep_list (#error_list, error_list)}); end return value, selected; end --[=[-------------------------< R E M O V E _ W I K I _ L I N K >---------------------------------------------- Gets the display text from a wikilink like [[A|B]] or [[B]] gives B The str:gsub() returns either A|B froma [[A|B]] or B from [[B]] or B from B (no wikilink markup). In l(), l:gsub() removes the link and pipe (if they exist); the second :gsub() trims whitespace from the label if str was wrapped in wikilink markup. Presumably, this is because without wikimarkup in str, there is no match in the initial gsub, the replacement function l() doesn't get called. ]=] local function remove_wiki_link (str) return (str:gsub ("%[%[([^%[%]]*)%]%]", function(l) return l:gsub ("^[^|]*|(.*)$", "%1" ):gsub ("^%s*(.-)%s*$", "%1"); end)); end --[=[-------------------------< I S _ W I K I L I N K >-------------------------------------------------------- Determines if str is a wikilink, extracts, and returns the wikilink type, link text, and display text parts. If str is a complex wikilink ([[L|D]]): returns wl_type 2 and D and L from [[L|D]]; if str is a simple wikilink ([[D]]) returns wl_type 1 and D from [[D]] and L as empty string; if not a wikilink: returns wl_type 0, str as D, and L as empty string. trims leading and trailing whitespace and pipes from L and D ([[L|]] and [[|D]] are accepted by MediaWiki and treated like [[D]]; while [[|D|]] is not accepted by MediaWiki, here, we accept it and return D without the pipes). ]=] local function is_wikilink (str) local D, L local wl_type = 2; -- assume that str is a complex wikilink [[L|D]] if not str:match ('^%[%[[^%]]+%]%]$') then -- is str some sort of a wikilink (must have some sort of content) return 0, str, ''; -- not a wikilink; return wl_type as 0, str as D, and empty string as L end L, D = str:match ('^%[%[([^|]+)|([^%]]+)%]%]$'); -- get L and D from [[L|D]] if not is_set (D) then -- if no separate display D = str:match ('^%[%[([^%]]*)|*%]%]$'); -- get D from [[D]] or [[D|]] wl_type = 1; end D = mw.text.trim (D, '%s|'); -- trim white space and pipe characters return wl_type, D, L or ''; 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. Returns the argument without wiki markup and a number; the number is more-or-less meaningless except as a flag to indicate that markup was replaced; do not rely on it as an indicator of how many of any kind of markup was removed; returns the argument and nil when no markup removed ]] local function strip_apostrophe_markup (argument) if not is_set (argument) then return argument, nil; -- no argument, nothing to do end if nil == argument:find ( "''", 1, true ) then -- Is there at least one double apostrophe? If not, exit. return argument, nil; end local flag; while true do if argument:find ("'''''", 1, true) then -- bold italic (5) argument, flag = argument:gsub ("%'%'%'%'%'", ""); -- remove all instances of it elseif argument:find ("''''", 1, true) then -- italic start and end without content (4) argument, flag=argument:gsub ("%'%'%'%'", ""); elseif argument:find ("'''", 1, true) then -- bold (3) argument, flag=argument:gsub ("%'%'%'", ""); elseif argument:find ("''", 1, true) then -- italic (2) argument, flag = argument:gsub ("%'%'", ""); else break; end end return argument, flag; -- done end --[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >-------------------------------------- Sets local cfg table to same (live or sandbox) as that used by the other modules. ]] local function set_selected_modules (cfg_table_ptr) cfg = cfg_table_ptr; end --[[--------------------------< E X P O R T S >---------------------------------------------------------------- ]] return { add_maint_cat = add_maint_cat, -- exported functions add_prop_cat = add_prop_cat, error_comment = error_comment, has_accept_as_written = has_accept_as_written, hyphen_to_dash = hyphen_to_dash, in_array = in_array, is_set = is_set, is_wikilink = is_wikilink, make_sep_list = make_sep_list, make_wikilink = make_wikilink, remove_wiki_link = remove_wiki_link, safe_for_italics = safe_for_italics, select_one = select_one, set_message = set_message, set_selected_modules = set_selected_modules, strip_apostrophe_markup = strip_apostrophe_markup, substitute = substitute, wrap_style = wrap_style, z = z, -- exported table } ipuk2skv52zxnbboa2zzah6ug9yuin7 828 657 9077 2026-05-15T07:21:21Z WikiBayer 737 [[:w:Special:PermanentLink/1333433129|Module:Citation/CS1/Date validation]] 9077 Scribunto text/plain --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local add_prop_cat, is_set, in_array, set_message, substitute, wrap_style; -- imported functions from selected Module:Citation/CS1/Utilities local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration --[[--------------------------< F I L E - S C O P E D E C L A R A T I O N S >-------------------------------- File-scope variables are declared here ]] local lang_object = mw.getContentLanguage(); -- used by is_valid_accessdate(), is_valid_year(), date_name_xlate(); TODO: move to ~/Configuration? local year_limit; -- used by is_valid_year() --[=[-------------------------< I S _ V A L I D _ A C C E S S D A T E >---------------------------------------- returns true if: Wikipedia start date <= accessdate < today + 2 days Wikipedia start date is 2001-01-15T00:00:00 UTC which is 979516800 seconds after 1970-01-01T00:00:00 UTC (the start of Unix time) accessdate is the date provided in |access-date= at time 00:00:00 UTC today is the current date at time 00:00:00 UTC plus 48 hours if today is 2015-01-01T00:00:00 then adding 24 hours gives 2015-01-02T00:00:00 – one second more than today adding 24 hours gives 2015-01-03T00:00:00 – one second more than tomorrow This function does not work if it is fed month names for languages other than English. Wikimedia #time: parser apparently doesn't understand non-English date month names. This function will always return false when the date contains a non-English month name because good1 is false after the call to lang.formatDate(). To get around that call this function with YYYY-MM-DD format dates. ]=] local function is_valid_accessdate (accessdate) local good1, good2; local access_ts, tomorrow_ts; -- to hold Unix time stamps representing the dates good1, access_ts = pcall (lang_object.formatDate, lang_object, 'U', accessdate ); -- convert accessdate value to Unix timestamp good2, tomorrow_ts = pcall (lang_object.formatDate, lang_object, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which which tonumber() may not understand access_ts = tonumber (access_ts) or lang_object:parseFormattedNumber (access_ts); -- convert to numbers for the comparison; tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts); else return false; -- one or both failed to convert to Unix time stamp end if 979516800 <= access_ts and access_ts < tomorrow_ts then -- Wikipedia start date <= accessdate < tomorrow's date return true; else return false; -- accessdate out of range end end --[[--------------------------< G E T _ M O N T H _ N U M B E R >---------------------------------------------- returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct. If not a valid month, returns 0 ]] local function get_month_number (month) return cfg.date_names['local'].long[month] or cfg.date_names['local'].short[month] or -- look for local names first cfg.date_names['en'].long[month] or cfg.date_names['en'].short[month] or -- failing that, look for English names 0; -- not a recognized month name end --[[--------------------------< G E T _ S E A S O N _ N U M B E R >-------------------------------------------- returns a number according to the sequence of seasons in a year: 21 for Spring, etc. Capitalization and spelling must be correct. If not a valid season, returns 0. 21-24 = Spring, Summer, Autumn, Winter, independent of “Hemisphere” returns 0 when <param> is not |date= Season numbering is defined by Extended Date/Time Format (EDTF) specification (https://www.loc.gov/standards/datetime/) which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard defines various divisions using numbers 21-41. cs1|2 only supports generic seasons. EDTF does support the distinction between north and south hemisphere seasons but cs1|2 has no way to make that distinction. These additional divisions not currently supported: 25-28 = Spring - Northern Hemisphere, Summer- Northern Hemisphere, Autumn - Northern Hemisphere, Winter - Northern Hemisphere 29-32 = Spring – Southern Hemisphere, Summer– Southern Hemisphere, Autumn – Southern Hemisphere, Winter - Southern Hemisphere 33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each) 37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each) 40-41 = Semestral 1, Semestral-2 (6 months each) ]] local function get_season_number (season, param) if 'date' ~= param then return 0; -- season dates only supported by |date= end return cfg.date_names['local'].season[season] or -- look for local names first cfg.date_names['en'].season[season] or -- failing that, look for English names 0; -- not a recognized season name end --[[--------------------------< G E T _ Q U A R T E R _ N U M B E R >------------------------------------------ returns a number according to the sequence of quarters in a year: 33 for first quarter, etc. Capitalization and spelling must be correct. If not a valid quarter, returns 0. 33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each) returns 0 when <param> is not |date= Quarter numbering is defined by Extended Date/Time Format (EDTF) specification (https://www.loc.gov/standards/datetime/) which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard defines various divisions using numbers 21-41. cs1|2 only supports generic seasons and quarters. These additional divisions not currently supported: 37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each) 40-41 = Semestral 1, Semestral-2 (6 months each) ]] local function get_quarter_number (quarter, param) if 'date' ~= param then return 0; -- quarter dates only supported by |date= end quarter = mw.ustring.gsub (quarter, ' +', ' '); -- special case replace multiple space chars with a single space char return cfg.date_names['local'].quarter[quarter] or -- look for local names first cfg.date_names['en'].quarter[quarter] or -- failing that, look for English names 0; -- not a recognized quarter name end --[[--------------------------< G E T _ P R O P E R _ N A M E _ N U M B E R >---------------------------------- returns a non-zero number if date contains a recognized proper-name. Capitalization and spelling must be correct. returns 0 when <param> is not |date= ]] local function get_proper_name_number (name, param) if 'date' ~= param then return 0; -- proper-name dates only supported by |date= end return cfg.date_names['local'].named[name] or -- look for local names dates first cfg.date_names['en'].named[name] or -- failing that, look for English names 0; -- not a recognized named date end --[[--------------------------< G E T _ E L E M E N T _ N U M B E R <------------------------------------------ returns true if month or season or quarter or proper name is valid (properly spelled, capitalized, abbreviated) ]] local function get_element_number (element, param) local num; local funcs = {get_month_number, get_season_number, get_quarter_number, get_proper_name_number}; -- list of functions to execute in order for _, func in ipairs (funcs) do -- spin through the function list num = func (element, param); -- call the function and get the returned number if 0 ~= num then -- non-zero when valid month season quarter return num; -- return that number end end return nil; -- not valid end --[[--------------------------< I S _ V A L I D _ Y E A R >---------------------------------------------------- Function gets current year from the server and compares it to year from a citation parameter. Years more than one year in the future are not acceptable. Special case for |pmc-embargo-date=: years more than two years in the future are not acceptable ]] local function is_valid_year (year, param) if not is_set (year_limit) then year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once end year = tonumber (year) or lang_object:parseFormattedNumber (year); -- convert to number for the comparison if year and (100 > year) then -- years less than 100 not supported return false; end if 'pmc-embargo-date' == param then -- special case for |pmc-embargo-date= return year and (year <= tonumber(os.date("%Y"))+2) or false; -- years more than two years in the future are not accepted end return year and (year <= year_limit) or false; end --[[--------------------------< I S _ V A L I D _ D A T E >---------------------------------------------------- Returns true if day is less than or equal to the number of days in month and year is no farther into the future than next year; else returns false. Assumes Julian calendar prior to year 1582 and Gregorian calendar thereafter. Accounts for Julian calendar leap years before 1582 and Gregorian leap years after 1582. Where the two calendars overlap (1582 to approximately 1923) dates are assumed to be Gregorian. ]] local function is_valid_date (year, month, day, param) local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31}; local month_length; if not is_valid_year (year, param) then -- no farther into the future than next year except |pmc-embargo-date= no more than two years in the future return false; end month = tonumber (month); -- required for YYYY-MM-DD dates if (2 == month) then -- if February month_length = 28; -- then 28 days unless if 1582 > tonumber(year) then -- Julian calendar if 0 == (year%4) then -- is a leap year? month_length = 29; -- if leap year then 29 days in February end else -- Gregorian calendar if (0 == (year%4) and (0 ~= (year%100) or 0 == (year%400))) then -- is a leap year? month_length = 29; -- if leap year then 29 days in February end end else month_length = days_in_month[month] or 0; -- invalid month number is nil so default <month_length> to 0 end if tonumber (day) > month_length then return false; end return true; end --[[--------------------------< I S _ V A L I D _ M O N T H _ R A N G E _ S T Y L E >-------------------------- Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August. This function looks in cfg.date_names{} to see if both month names are listed in the long subtable or both are listed in the short subtable. When both have the same style (both are listed in the same table), returns true; false else ]] local function is_valid_month_range_style (month1, month2) if (cfg.date_names.en.long[month1] and cfg.date_names.en.long[month2]) or -- are both English names listed in the long subtable? (cfg.date_names.en.short[month1] and cfg.date_names.en.short[month2]) or -- are both English names listed in the short subtable? (cfg.date_names['local'].long[month1] and cfg.date_names['local'].long[month2]) or -- are both local names listed in the long subtable? (cfg.date_names['local'].short[month1] and cfg.date_names['local'].short[month2]) then -- are both local names listed in the short subtable? return true; end return false; -- names are mixed end --[[--------------------------< I S _ V A L I D _ M O N T H _ S E A S O N _ R A N G E >------------------------ Check a pair of months or seasons to see if both are valid members of a month or season pair. Month pairs are expected to be left to right, earliest to latest in time. All season ranges are accepted as valid because there are publishers out there who have published a Summer–Spring YYYY issue, hence treat as ok ]] local function is_valid_month_season_range(range_start, range_end, param) local range_start_number = get_month_number (range_start); local range_end_number; if 0 == range_start_number then -- is this a month range? range_start_number = get_season_number (range_start, param); -- not a month; is it a season? get start season number range_end_number = get_season_number (range_end, param); -- get end season number if (0 ~= range_start_number) and (0 ~= range_end_number) and (range_start_number ~= range_end_number) then return true; -- any season pairing is accepted except when both are the same end return false; -- range_start and/or range_end is not a season end -- here when range_start is a month range_end_number = get_month_number (range_end); -- get end month number if range_start_number < range_end_number and -- range_start is a month; does range_start precede range_end? is_valid_month_range_style (range_start, range_end) then -- do months have the same style? return true; -- proper order and same style end return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month end --[[--------------------------< M A K E _ C O I N S _ D A T E >------------------------------------------------ This function receives a table of date parts for one or two dates and an empty table reference declared in Module:Citation/CS1. The function is called only for |date= parameters and only if the |date=<value> is determined to be a valid date format. The question of what to do with invalid date formats is not answered here. The date parts in the input table are converted to an ISO 8601 conforming date string: single whole dates: yyyy-mm-dd month and year dates: yyyy-mm year dates: yyyy ranges: yyyy-mm-dd/yyyy-mm-dd yyyy-mm/yyyy-mm yyyy/yyyy Dates in the Julian calendar are reduced to year or year/year so that we don't have to do calendar conversion from Julian to Proleptic Gregorian. The input table has: year, year2 – always present; if before 1582, ignore months and days if present month, month2 – 0 if not provided, 1-12 for months, 21-24 for seasons; 99 Christmas day, day2 – 0 if not provided, 1-31 for days the output table receives: rftdate: an ISO 8601 formatted date rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and proper-name dates) rftssn: one of four season keywords: winter, spring, summer, fall (lowercase) rftquarter: one of four values: 1, 2, 3, 4 ]] local function make_COinS_date (input, tCOinS_date) local date; -- one date or first date in a range local date2 = ''; -- end of range date input.year = tonumber (input.year) or lang_object:parseFormattedNumber (input.year); -- language-aware tonumber() input.year2 = tonumber (input.year2) or lang_object:parseFormattedNumber (input.year2); -- COinS dates are pseudo-ISO 8601 so convert to Arabic numerals if ((1582 == input.year) and (10 > tonumber(input.month))) or (1582 > input.year) then -- if a Julian calendar date tCOinS_date.rftdate = tostring (input.year); -- &rft.date gets year only return; -- done end -- here for all forms of Gregorian dates if 20 < tonumber (input.month) then -- if season, quarter, or proper-name date date = input.year; -- &rft.date gets year only if 0 ~= input.year2 and input.year ~= input.year2 then -- if a range, only the second year portion when not the same as range start year date = string.format ('%.4d/%.4d', input.year, input.year2) -- assemble the date range end local season = {[24] = 'winter', [21] = 'spring', [22] = 'summer', [23] = 'fall', [33] = '1', [34] = '2', [35] = '3', [36] = '4', [98] = 'Easter', [99] = 'Christmas'}; -- seasons lowercase, no autumn; proper-names use title case if 0 == input.month2 then -- single season, quarter, or proper-name date if 40 < tonumber(input.month) then tCOinS_date.rftchron = season[input.month]; -- proper-name date; used in journal metadata only elseif 30 < tonumber(input.month) then tCOinS_date.rftquarter = season[input.month]; -- quarter date; used in journal metadata only else tCOinS_date.rftssn = season[input.month]; -- season date; used in journal metadata only end else -- season ranges are lumped into &rft.chron; &rft.ssn and &rft.quarter are left blank if input.year ~= input.year2 then -- season year – season year range or season year–year if 0 ~= input.month2 then tCOinS_date.rftchron = string.format ('%s %s – %s %s', season[input.month], input.year, season[input.month2], input.year2); -- used in journal metadata only end else -- season–season year range tCOinS_date.rftchron = season[input.month] .. '–' .. season[input.month2]; -- season–season year range; used in journal metadata only end end tCOinS_date.rftdate = tostring (date); return; -- done end -- here for gregorian calendar dates if 0 ~= input.day then date = string.format ('%s-%.2d-%.2d', input.year, tonumber(input.month), tonumber(input.day)); -- whole date elseif 0 ~= input.month then date = string.format ('%s-%.2d', input.year, tonumber(input.month)); -- year and month else date = string.format ('%s', input.year); -- just year end if 0 ~= input.year2 then if 0 ~= input.day2 then date2 = string.format ('/%s-%.2d-%.2d', input.year2, tonumber(input.month2), tonumber(input.day2)); -- whole date elseif 0 ~= input.month2 then date2 = string.format ('/%s-%.2d', input.year2, tonumber(input.month2)); -- year and month else date2 = string.format ('/%s', input.year2); -- just year end end tCOinS_date.rftdate = date .. date2; -- date2 has the '/' separator return; end --[[--------------------------< P A T T E R N S _ T >---------------------------------------------------------- this is the list of patterns for date formats that this module recognizes. Approximately the first half of these patterns represent formats that might be reformatted into another format. Those that might be reformatted have 'indicator' letters that identify the content of the matching capture: 'd' (day), 'm' (month), 'a' (anchor year), 'y' (year); second day, month, year have a '2' suffix. These patterns are used for both date validation and for reformatting. This table should not be moved to ~/Configuration because changes to this table require changes to check_date() and to reformatter() and reformat_date() ]] local patterns_t = { -- year-initial numerical year-month-day ['ymd'] = {'^([1-9]%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'}, -- month-initial: month day, year ['Mdy'] = {'^(%D-) +([1-9]%d?), +(([1-9]%d%d%d?)%a?)$', 'm', 'd', 'a', 'y'}, -- month-initial day range: month day–day, year; days are separated by endash ['Md-dy'] = {'^(%D-) +([1-9]%d?)[%-–]([1-9]%d?), +(([1-9]%d%d%d?)%a?)$', 'm', 'd', 'd2', 'a', 'y'}, -- day-initial: day month year ['dMy'] = {'^([1-9]%d?) +(%D-) +(([1-9]%d%d%d?)%a?)$', 'd', 'm', 'a', 'y'}, -- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki -- ['yMd'] = {'^(([1-9]%d%d%d?)%a?) +(%D-) +(%d%d?)$', 'a', 'y', 'm', 'd'}, -- day-range-initial: day–day month year; days are separated by endash ['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +(([1-9]%d%d%d?)%a?)$', 'd', 'd2', 'm', 'a', 'y'}, -- day initial month-day-range: day month - day month year; uses spaced endash ['dM-dMy'] = {'^([1-9]%d?) +(%D-) +[%-–] +([1-9]%d?) +(%D-) +(([1-9]%d%d%d?)%a?)$', 'd', 'm', 'd2', 'm2', 'a', 'y'}, -- month initial month-day-range: month day – month day, year; uses spaced endash ['Md-Mdy'] = {'^(%D-) +([1-9]%d?) +[%-–] +(%D-) +([1-9]%d?), +(([1-9]%d%d%d?)%a?)$','m', 'd', 'm2', 'd2', 'a', 'y'}, -- day initial month-day-year-range: day month year - day month year; uses spaced endash ['dMy-dMy'] = {'^([1-9]%d?) +(%D-) +([1-9]%d%d%d?) +[%-–] +([1-9]%d?) +(%D-) +(([1-9]%d%d%d?)%a?)$', 'd', 'm', 'y', 'd2', 'm2', 'a', 'y2'}, -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash ['Mdy-Mdy'] = {'^(%D-) +([1-9]%d?), +([1-9]%d%d%d?) +[%-–] +(%D-) +([1-9]%d?), +(([1-9]%d%d%d?)%a?)$', 'm', 'd', 'y', 'm2', 'd2', 'a', 'y2'}, -- these date formats cannot be converted, per se, but month name can be rendered short or long -- month/season year - month/season year; separated by spaced endash ['My-My'] = {'^(%D-) +([1-9]%d%d%d?) +[%-–] +(%D-) +(([1-9]%d%d%d?)%a?)$', 'm', 'y', 'm2', 'a', 'y2'}, -- month/season range year; months separated by endash ['M-My'] = {'^(%D-)[%-–](%D-) +(([1-9]%d%d%d?)%a?)$', 'm', 'm2', 'a', 'y'}, -- month/season year or proper-name year; quarter year when First Quarter YYYY etc. ['My'] = {'^([^%d–]-) +(([1-9]%d%d%d?)%a?)$', 'm', 'a', 'y'}, -- this way because endash is a member of %D; %D- will match January–March 2019 when it shouldn't -- these date formats cannot be converted ['Sy4-y2'] = {'^(%D-) +(([1-9]%d)%d%d)[%-–]((%d%d)%a?)$'}, -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash ['Sy-y'] = {'^(%D-) +([1-9]%d%d%d?)[%-–](([1-9]%d%d%d?)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash ['y-y'] = {'^([1-9]%d%d%d?)[%-–](([1-9]%d%d%d?)%a?)$'}, -- year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999 ['y4-y2'] = {'^(([1-9]%d)%d%d)[%-–]((%d%d)%a?)$'}, -- year range: YYYY–YY; separated by unspaced endash ['y'] = {'^(([1-9]%d%d%d?)%a?)$'}, -- year; here accept either YYY or YYYY } --[[--------------------------< I S _ V A L I D _ E M B A R G O _ D A T E >------------------------------------ returns true and date value if that value has proper dmy, mdy, ymd format. returns false and 9999 (embargoed forever) when date value is not proper format; assumes that when |pmc-embargo-date= is set, the editor intended to embargo a PMC but |pmc-embargo-date= does not hold a single date. ]] local function is_valid_embargo_date (v) if v:match (patterns_t['ymd'][1]) or -- ymd v:match (patterns_t['Mdy'][1]) or -- dmy v:match (patterns_t['dMy'][1]) then -- mdy return true, v; end return false, '9999'; -- if here not good date so return false and set embargo date to long time in future end --[[--------------------------< C H E C K _ D A T E >---------------------------------------------------------- Check date format to see that it is one of the formats approved by WP:DATESNO or WP:DATERANGE. Exception: only allowed range separator is endash. Additionally, check the date to see that it is a real date: no 31 in 30-day months; no 29 February when not a leap year. Months, both long-form and three character abbreviations, and seasons must be spelled correctly. Future years beyond next year are not allowed. If the date fails the format tests, this function returns false and does not return values for anchor_year and COinS_date. When this happens, the date parameter is (DEBUG: not?) used in the COinS metadata and the CITEREF identifier gets its year from the year parameter if present otherwise CITEREF does not get a date value. Inputs: date_string - date string from date-holding parameters (date, year, publication-date, access-date, pmc-embargo-date, archive-date, lay-date) Returns: false if date string is not a real date; else true, anchor_year, COinS_date anchor_year can be used in CITEREF anchors COinS_date is ISO 8601 format date; see make_COInS_date() ]] local function check_date (date_string, param, tCOinS_date) local year; -- assume that year2, months, and days are not used; local year2 = 0; -- second year in a year range local month = 0; local month2 = 0; -- second month in a month range local day = 0; local day2 = 0; -- second day in a day range local anchor_year; local coins_date; if date_string:match (patterns_t['ymd'][1]) then -- year-initial numerical year month day format year, month, day = date_string:match (patterns_t['ymd'][1]); if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar anchor_year = year; elseif mw.ustring.match(date_string, patterns_t['Mdy'][1]) then -- month-initial: month day, year month, day, anchor_year, year = mw.ustring.match(date_string, patterns_t['Mdy'][1]); month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months elseif mw.ustring.match(date_string, patterns_t['Md-dy'][1]) then -- month-initial day range: month day–day, year; days are separated by endash month, day, day2, anchor_year, year = mw.ustring.match(date_string, patterns_t['Md-dy'][1]); if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same; month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months month2=month; -- for metadata year2 = year; elseif mw.ustring.match(date_string, patterns_t['dMy'][1]) then -- day-initial: day month year day, month, anchor_year, year = mw.ustring.match(date_string, patterns_t['dMy'][1]); month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months --[[ NOT supported at en.wiki elseif mw.ustring.match(date_string, patterns_t['yMd'][1]) then -- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed anchor_year, year, month, day = mw.ustring.match(date_string, patterns_t['yMd'][1]); month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months -- end NOT supported at en.wiki ]] elseif mw.ustring.match(date_string, patterns_t['d-dMy'][1]) then -- day-range-initial: day–day month year; days are separated by endash day, day2, month, anchor_year, year = mw.ustring.match(date_string, patterns_t['d-dMy'][1]); if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same; month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months month2 = month; -- for metadata year2 = year; elseif mw.ustring.match(date_string, patterns_t['dM-dMy'][1]) then -- day initial month-day-range: day month - day month year; uses spaced endash day, month, day2, month2, anchor_year, year = mw.ustring.match(date_string, patterns_t['dM-dMy'][1]); if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end -- date range order is left to right: earlier to later; month = get_month_number (month); -- for metadata month2 = get_month_number (month2); year2 = year; elseif mw.ustring.match(date_string, patterns_t['Md-Mdy'][1]) then -- month initial month-day-range: month day – month day, year; uses spaced endash month, day, month2, day2, anchor_year, year = mw.ustring.match(date_string, patterns_t['Md-Mdy'][1]); if (not is_valid_month_season_range(month, month2, param)) or not is_valid_year(year) then return false; end month = get_month_number (month); -- for metadata month2 = get_month_number (month2); year2 = year; elseif mw.ustring.match(date_string, patterns_t['dMy-dMy'][1]) then -- day initial month-day-year-range: day month year - day month year; uses spaced endash day, month, year, day2, month2, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['dMy-dMy'][1]); if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style month = get_month_number (month); -- for metadata month2 = get_month_number (month2); if 0 == month or 0 == month2 then return false; end -- both must be valid elseif mw.ustring.match(date_string, patterns_t['Mdy-Mdy'][1]) then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash month, day, year, month2, day2, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['Mdy-Mdy'][1]); if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style month = get_month_number (month); -- for metadata month2 = get_month_number(month2); if 0 == month or 0 == month2 then return false; end -- both must be valid elseif mw.ustring.match(date_string, patterns_t['Sy4-y2'][1]) then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash local century; month, year, century, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['Sy4-y2'][1]); if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer anchor_year = year .. '–' .. anchor_year; -- assemble anchor_year from both years year2 = century..year2; -- add the century to year2 for comparisons if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later if not is_valid_year(year2) then return false; end -- no year farther in the future than next year month = get_season_number(month, param); elseif mw.ustring.match(date_string, patterns_t['Sy-y'][1]) then -- special case Winter/Summer year-year; year separated with unspaced endash month, year, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['Sy-y'][1]); month = get_season_number (month, param); -- <month> can only be winter or summer; also for metadata if (month ~= cfg.date_names['en'].season['Winter']) and (month ~= cfg.date_names['en'].season['Summer']) then return false; -- not Summer or Winter; abandon end anchor_year = year .. '–' .. anchor_year; -- assemble anchor_year from both years if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later if not is_valid_year(year2) then return false; end -- no year farther in the future than next year elseif mw.ustring.match(date_string, patterns_t['My-My'][1]) then -- month/season year - month/season year; separated by spaced endash month, year, month2, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['My-My'][1]); anchor_year = year .. '–' .. anchor_year; -- assemble anchor_year from both years if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same if not is_valid_year(year2) then return false; end -- no year farther in the future than next year if 0 ~= get_month_number(month) and 0 ~= get_month_number(month2) and is_valid_month_range_style(month, month2) then -- both must be month year, same month style month = get_month_number(month); month2 = get_month_number(month2); elseif 0 ~= get_season_number(month, param) and 0 ~= get_season_number(month2, param) then -- both must be season year, not mixed month = get_season_number(month, param); month2 = get_season_number(month2, param); else return false; end elseif mw.ustring.match(date_string, patterns_t['M-My'][1]) then -- month/season range year; months separated by endash month, month2, anchor_year, year = mw.ustring.match(date_string, patterns_t['M-My'][1]); if (not is_valid_month_season_range(month, month2, param)) or (not is_valid_year(year)) then return false; end if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season month = get_month_number(month); month2 = get_month_number(month2); if 0 == month or 0 == month2 then return false; end else month = get_season_number(month, param); month2 = get_season_number(month2, param); end year2 = year; elseif mw.ustring.match(date_string, patterns_t['My'][1]) then -- month/season/quarter/proper-name year month, anchor_year, year = mw.ustring.match(date_string, patterns_t['My'][1]); if not is_valid_year(year) then return false; end month = get_element_number(month, param); -- get month season quarter proper-name number or nil if not month then return false; end -- not valid whatever it is elseif mw.ustring.match(date_string, patterns_t['y-y'][1]) then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999 year, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['y-y'][1]); anchor_year = year .. '–' .. anchor_year; -- assemble anchor year from both years if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same if not is_valid_year(year2) then return false; end -- no year farther in the future than next year elseif mw.ustring.match(date_string, patterns_t['y4-y2'][1]) then -- Year range: YYYY–YY; separated by unspaced endash local century; year, century, anchor_year, year2 = mw.ustring.match(date_string, patterns_t['y4-y2'][1]); anchor_year = year .. '–' .. anchor_year; -- assemble anchor year from both years if 13 > tonumber(year2) then return false; end -- don't allow 2003-05 which might be May 2003 year2 = century .. year2; -- add the century to year2 for comparisons if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same if not is_valid_year(year2) then return false; end -- no year farther in the future than next year if in_array (param, {'date', 'publication-date', 'year'}) then -- here when 'valid' abbreviated year range; if one of these parameters add_prop_cat ('year-range-abbreviated'); -- add properties cat end elseif mw.ustring.match(date_string, patterns_t['y'][1]) then -- year; here accept either YYY or YYYY anchor_year, year = mw.ustring.match(date_string, patterns_t['y'][1]); if false == is_valid_year(year) then return false; end else return false; -- date format not one of the MOS:DATE approved formats end if param ~= 'date' then -- CITEREF disambiguation only allowed in |date=; |year= & |publication-date= promote to date if anchor_year:match ('%l$') then return false; end end if 'access-date' == param then -- test access-date here because we have numerical date parts if 0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required 0 == year2 and 0 == month2 and 0 == day2 then -- none of these; access-date must not be a range if not is_valid_accessdate(year .. '-' .. month .. '-' .. day) then return false; -- return false when access-date out of bounds end else return false; -- return false when access-date is a range of two dates end end if 'archive-date' == param then -- test archive-date here because we have numerical date parts if not (0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required 0 == year2 and 0 == month2 and 0 == day2) then -- none of these; archive-date must not be a range return false; -- return false when archive-date is a range of two dates end end local result=true; -- check whole dates for validity; assume true because not all dates will go through this test if 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 == month2 and 0 == day2 then -- YMD (simple whole date) result = is_valid_date (year, month, day, param); -- <param> for |pmc-embargo-date= elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 == month2 and 0 ~= day2 then -- YMD-d (day range) result = is_valid_date (year, month, day); result = result and is_valid_date (year, month, day2); elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 ~= month2 and 0 ~= day2 then -- YMD-md (day month range) result = is_valid_date (year, month, day); result = result and is_valid_date (year, month2, day2); elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 ~= year2 and 0 ~= month2 and 0 ~= day2 then -- YMD-ymd (day month year range) result = is_valid_date(year, month, day); result = result and is_valid_date(year2, month2, day2); end if false == result then return false; end if nil ~= tCOinS_date then -- this table only passed into this function when testing |date= parameter values make_COinS_date ({year = year, month = month, day = day, year2 = year2, month2 = month2, day2 = day2}, tCOinS_date); -- make an ISO 8601 date string for COinS end return true, anchor_year; -- format is good and date string represents a real date end --[[--------------------------< D A T E S >-------------------------------------------------------------------- Cycle the date-holding parameters in passed table date_parameters_list through check_date() to check compliance with MOS:DATE. For all valid dates, check_date() returns true. The |date= parameter test is unique, it is the only date holding parameter from which values for anchor_year (used in CITEREF identifiers) and COinS_date (used in the COinS metadata) are derived. The |date= parameter is the only date-holding parameter that is allowed to contain the no-date keywords "n.d." or "nd" (without quotes). Unlike most error messages created in this module, only one error message is created by this function. Because all of the date holding parameters are processed serially, parameters with errors are added to the <error_list> sequence table as the dates are tested. ]] local function dates(date_parameters_list, tCOinS_date, error_list) local anchor_year; -- will return as nil if the date being tested is not |date= local COinS_date; -- will return as nil if the date being tested is not |date= local embargo_date; -- if embargo date is a good dmy, mdy, ymd date then holds original value else reset to 9999 local good_date = false; for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list if is_set(v.val) then -- if the parameter has a value v.val = mw.ustring.gsub(v.val, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9 if v.val:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year= local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested if 'date' == k then anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter good_date = is_valid_year(year); elseif 'year' == k then good_date = is_valid_year(year); else good_date = false; end elseif 'date' == k then -- if the parameter is |date= if v.val:match("^n%.d%.%a?$") then -- ToDo: I18N -- if |date=n.d. with or without a CITEREF disambiguator good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); -- ToDo: I18N -- "n.d."; no error when date parameter is set to no date elseif v.val:match("^nd%a?$") then -- ToDo: I18N -- if |date=nd with or without a CITEREF disambiguator good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); -- ToDo: I18N -- "nd"; no error when date parameter is set to no date else good_date, anchor_year, COinS_date = check_date (v.val, k, tCOinS_date); -- go test the date end elseif 'year' == k then -- if the parameter is |year= it should hold only a year value if v.val:match("^[1-9]%d%d%d?%a?$") then -- if |year = 3 or 4 digits only with or without a CITEREF disambiguator good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)"); else good_date = false; end elseif 'pmc-embargo-date' == k then -- if the parameter is |pmc-embargo-date= good_date = check_date (v.val, k); -- go test the date if true == good_date then -- if the date is a valid date good_date, embargo_date = is_valid_embargo_date (v.val); -- is |pmc-embargo-date= date a single dmy, mdy, or ymd formatted date? yes: returns embargo date; no: returns 9999 end else -- any other date-holding parameter good_date = check_date (v.val, k); -- go test the date end if false == good_date then -- assemble one error message so we don't add the tracking category multiple times table.insert (error_list, wrap_style ('parameter', v.name)); -- make parameter name suitable for error message list end end end return anchor_year, embargo_date; -- and done end --[[--------------------------< Y E A R _ C H E C K >---------------------------------------------------------- Temporary function to test |year= for acceptable values: YYY, YYYY, year-only ranges, their circa forms, with or without CITEREF disambiguators. When |year= holds some form of date that is not one of these year-only dates, emit a maintenance message. This function necessary because many non-cs1|2 templates have a |year= parameter so cirrus searches are more-or- less useless ]] local function year_check (year) year = year:gsub ('c%. *', ''); -- remove circa annotation (if present) before testing <year> for _, index in ipairs ({'y-y', 'y4-y2', 'y'}) do -- spin through these indexes into patterns_t if mw.ustring.match (year, patterns_t[index][1]) then return; -- if a match then |year= holds a valid 'year' end end set_message ('maint_year'); -- if here, |year= value is not an accepted value; add a maint cat end --[[--------------------------< Y E A R _ D A T E _ C H E C K >------------------------------------------------ Compare the value provided in |year= with the year value(s) provided in |date=. This function sets a local numeric value: 0 - year value does not match the year value in date 1 - (default) year value matches the year value in date or one of the year values when date contains two years 2 - year value matches the year value in date when date is in the form YYYY-MM-DD and year is disambiguated (|year=YYYYx) the numeric value in <result> determines the 'output' if any from this function: 0 – adds error message to error_list sequence table 1 – adds maint cat 2 – does nothing ]] local function year_date_check (year_string, year_origin, date_string, date_origin, error_list) local year; local date1; local date2; local result = 1; -- result of the test; assume that the test passes year = year_string:match ('(%d%d%d%d?)'); if date_string:match ('%d%d%d%d%-%d%d%-%d%d') then --special case where both date and year are required YYYY-MM-DD and YYYYx date1 = date_string:match ('(%d%d%d%d)'); year = year_string:match ('(%d%d%d%d)'); if year ~= date1 then result = 0; -- years don't match elseif year_string:match ('%d%d%d%d%a') then result = 2; -- years match; but because disambiguated, don't add to maint cat end elseif date_string:match ("%d%d%d%d?.-%d%d%d%d?") then -- any of the standard range formats of date with two three- or four-digit years date1, date2 = date_string:match ("(%d%d%d%d?).-(%d%d%d%d?)"); if year ~= date1 and year ~= date2 then result = 0; end elseif mw.ustring.match(date_string, "%d%d%d%d[%-–]%d%d") then -- YYYY-YY date ranges local century; date1, century, date2 = mw.ustring.match(date_string, "((%d%d)%d%d)[%-–]+(%d%d)"); date2 = century..date2; -- convert YY to YYYY if year ~= date1 and year ~= date2 then result = 0; end elseif date_string:match ("%d%d%d%d?") then -- any of the standard formats of date with one year date1 = date_string:match ("(%d%d%d%d?)"); if year ~= date1 then result = 0; end else -- should never get here; this function called only when no other date errors result = 0; -- no recognizable year in date end if 0 == result then -- year / date mismatch table.insert (error_list, substitute (cfg.messages['mismatch'], {year_origin, date_origin})); -- add error message to error_list sequence table elseif 1 == result then -- redundant year / date set_message ('maint_date_year'); -- add a maint cat end end --[[--------------------------< R E F O R M A T T E R >-------------------------------------------------------- reformat 'date' into new format specified by format_param if pattern_idx (the current format of 'date') can be reformatted. Does the grunt work for reformat_dates(). The table re_formats maps pattern_idx (current format) and format_param (desired format) to a table that holds: format string used by string.format() identifier letters ('d', 'm', 'y', 'd2', 'm2', 'y2') that serve as indexes into a table t{} that holds captures from mw.ustring.match() for the various date parts specified by patterns_t[pattern_idx][1] Items in patterns_t{} have the general form: ['ymd'] = {'^(%d%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'}, where: ['ymd'] is pattern_idx patterns_t['ymd'][1] is the match pattern with captures for mw.ustring.match() patterns_t['ymd'][2] is an indicator letter identifying the content of the first capture patterns_t['ymd'][3] ... the second capture etc. when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifier characters as indexes into t{} For the above, a ymd date is in t{} as: t.y = first capture (year), t.m = second capture (month), t.d = third capture (day) To reformat, this function is called with the pattern_idx that matches the current format of the date and with format_param set to the desired format. This function loads table t{} as described and then calls string.format() with the format string specified by re_format[pattern_idx][format_param][1] using values taken from t{} according to the capture identifier letters specified by patterns_t[pattern_idx][format_param][n] where n is 2.. ]] local re_formats = { ['ymd'] = { -- date format is ymd; reformat to: ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy -- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki }, ['Mdy'] = { -- date format is Mdy; reformat to: ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- for long/short reformatting ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd -- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki }, ['dMy'] = { -- date format is dMy; reformat to: ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd -- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki }, ['Md-dy'] = { -- date format is Md-dy; reformat to: ['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- for long/short reformatting ['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- |df=dmy -> d-dMy }, ['d-dMy'] = { -- date format is d-d>y; reformat to: ['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- |df=mdy -> Md-dy }, ['dM-dMy'] = { -- date format is dM-dMy; reformat to: ['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- |df=mdy -> Md-Mdy }, ['Md-Mdy'] = { -- date format is Md-Mdy; reformat to: ['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- for long/short reformatting ['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- |df=dmy -> dM-dMy }, ['dMy-dMy'] = { -- date format is dMy-dMy; reformat to: ['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- for long/short reformatting ['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- |df=mdy -> Mdy-Mdy }, ['Mdy-Mdy'] = { -- date format is Mdy-Mdy; reformat to: ['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- for long/short reformatting ['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- |df=dmy -> dMy-dMy }, ['My-My'] = { -- these for long/short reformatting ['any'] = {'%s %s – %s %s', 'm', 'y', 'm2', 'y2'}, -- dmy/mdy agnostic }, ['M-My'] = { -- these for long/short reformatting ['any'] = {'%s–%s %s', 'm', 'm2', 'y'}, -- dmy/mdy agnostic }, ['My'] = { -- these for long/short reformatting ['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic }, -- ['yMd'] = { -- not supported at en.wiki -- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy -- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy -- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd -- }, } local function reformatter (date, pattern_idx, format_param, mon_len) if not in_array (pattern_idx, {'ymd', 'Mdy', 'Md-dy', 'dMy', 'yMd', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My-My', 'M-My', 'My'}) then return; -- not in this set of date format patterns_t then not a reformattable date end if 'ymd' == format_param and in_array (pattern_idx, {'ymd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My-My', 'M-My', 'My'}) then return; -- ymd date ranges not supported at en.wiki; no point in reformatting ymd to ymd end if in_array (pattern_idx, {'My', 'M-My', 'My-My'}) then -- these are not dmy/mdy so can't be 'reformatted' into either format_param = 'any'; -- so format-agnostic end -- yMd is not supported at en.wiki; when yMd is supported at your wiki, uncomment the next line -- if 'yMd' == format_param and in_array (pattern_idx, {'yMd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy'}) then -- these formats not convertable; yMd not supported at en.wiki if 'yMd' == format_param then -- yMd not supported at en.wiki; when yMd is supported at your wiki, remove or comment-out this line return; -- not a reformattable date end local c1, c2, c3, c4, c5, c6, c7; -- these hold the captures specified in patterns_t[pattern_idx][1] c1, c2, c3, c4, c5, c6, c7 = mw.ustring.match (date, patterns_t[pattern_idx][1]); -- get the captures local t = { -- table that holds k/v pairs of date parts from the captures and patterns_t[pattern_idx][2..] [patterns_t[pattern_idx][2]] = c1; -- at minimum there is always one capture with a matching indicator letter [patterns_t[pattern_idx][3] or 'x'] = c2; -- patterns_t can have a variable number of captures; each capture requires an indicator letter; [patterns_t[pattern_idx][4] or 'x'] = c3; -- where there is no capture, there is no indicator letter so n in patterns_t[pattern_idx][n] will be nil; [patterns_t[pattern_idx][5] or 'x'] = c4; -- the 'x' here spoofs an indicator letter to prevent 'table index is nil' error [patterns_t[pattern_idx][6] or 'x'] = c5; [patterns_t[pattern_idx][7] or 'x'] = c6; [patterns_t[pattern_idx][8] or 'x'] = c7; }; if t.a then -- if this date has an anchor year capture (all convertable date formats except ymd) if t.y2 then -- for year range date formats t.y2 = t.a; -- use the anchor year capture when reassembling the date else -- here for single date formats (except ymd) t.y = t.a; -- use the anchor year capture when reassembling the date end end if tonumber(t.m) then -- if raw month is a number (converting from ymd) if 's' == mon_len then -- if we are to use abbreviated month names t.m = cfg.date_names['inv_local_short'][tonumber(t.m)]; -- convert it to a month name else t.m = cfg.date_names['inv_local_long'][tonumber(t.m)]; -- convert it to a month name end t.d = t.d:gsub ('0(%d)', '%1'); -- strip leading '0' from day if present elseif 'ymd' == format_param then -- when converting to ymd t.y = t.y:gsub ('%a', ''); -- strip CITREF disambiguator if present; anchor year already known so process can proceed; TODO: maint message? if 1582 > tonumber (t.y) then -- ymd format dates not allowed before 1582 return; end t.m = string.format ('%02d', get_month_number (t.m)); -- make sure that month and day are two digits t.d = string.format ('%02d', t.d); elseif mon_len then -- if mon_len is set to either 'short' or 'long' for _, mon in ipairs ({'m', 'm2'}) do -- because there can be two month names, check both if t[mon] then t[mon] = get_month_number (t[mon]); -- get the month number for this month (is length agnostic) if 0 == t[mon] then return; end -- seasons and named dates can't be converted t[mon] = (('s' == mon_len) and cfg.date_names['inv_local_short'][t[mon]]) or cfg.date_names['inv_local_long'][t[mon]]; -- fetch month name according to length end end end local new_date = string.format (re_formats[pattern_idx][format_param][1], -- format string t[re_formats[pattern_idx][format_param][2]], -- named captures from t{} t[re_formats[pattern_idx][format_param][3]], t[re_formats[pattern_idx][format_param][4]], t[re_formats[pattern_idx][format_param][5]], t[re_formats[pattern_idx][format_param][6]], t[re_formats[pattern_idx][format_param][7]], t[re_formats[pattern_idx][format_param][8]] ); return new_date; end --[[-------------------------< R E F O R M A T _ D A T E S >-------------------------------------------------- Reformats existing dates into the format specified by format. format is one of several manual keywords: dmy, dmy-all, mdy, mdy-all, ymd, ymd-all. The -all version includes access- and archive-dates; otherwise these dates are not reformatted. This function allows automatic date formatting. In ~/Configuration, the article source is searched for one of the {{use xxx dates}} templates. If found, xxx becomes the global date format as xxx-all. If |cs1-dates= in {{use xxx dates}} has legitimate value then that value determines how cs1|2 dates will be rendered. Legitimate values for |cs1-dates= are: l - all dates are rendered with long month names ls - publication dates use long month names; access-/archive-dates use abbreviated month names ly - publication dates use long month names; access-/archive-dates rendered in ymd format s - all dates are rendered with abbreviated (short) month names sy - publication dates use abbreviated month names; access-/archive-dates rendered in ymd format y - all dates are rendered in ymd format the format argument for automatic date formatting will be the format specified by {{use xxx dates}} with the value supplied by |cs1-dates so one of: xxx-l, xxx-ls, xxx-ly, xxx-s, xxx-sy, xxx-y, or simply xxx (|cs1-dates= empty, omitted, or invalid) where xxx shall be either of dmy or mdy. dates are extracted from date_parameters_list, reformatted (if appropriate), and then written back into the list in the new format. Dates in date_parameters_list are presumed here to be valid (no errors). This function returns true when a date has been reformatted, false else. Actual reformatting is done by reformatter(). ]] local function reformat_dates (date_parameters_list, format) local all = false; -- set to false to skip access- and archive-dates local len_p = 'l'; -- default publication date length shall be long local len_a = 'l'; -- default access-/archive-date length shall be long local result = false; local new_date; if format:match('%a+%-all') then -- manual df keyword; auto df keyword when length not specified in {{use xxx dates}}; format = format:match('(%a+)%-all'); -- extract the format all = true; -- all dates are long format dates because this keyword doesn't specify length elseif format:match('%a+%-[lsy][sy]?') then -- auto df keywords; internal only all = true; -- auto df applies to all dates; use length specified by capture len_p for all dates format, len_p, len_a = format:match('(%a+)%-([lsy])([sy]?)'); -- extract the format and length keywords if 'y' == len_p then -- because allowed by MOS:DATEUNIFY (sort of) range dates and My dates not reformatted format = 'ymd'; -- override {{use xxx dates}} elseif (not is_set(len_a)) or (len_p == len_a) then -- no access-/archive-date length specified or same length as publication dates then len_a = len_p; -- in case len_a not set end end -- else only publication dates and they are long for param_name, param_val in pairs (date_parameters_list) do -- for each date-holding parameter in the list if is_set (param_val.val) then -- if the parameter has a value if not (not all and in_array (param_name, {'access-date', 'archive-date'})) then -- skip access- or archive-date unless format is xxx-all; yeah, ugly; TODO: find a better way for pattern_idx, pattern in pairs (patterns_t) do if mw.ustring.match (param_val.val, pattern[1]) then if all and in_array (param_name, {'access-date', 'archive-date'}) then -- if this date is an access- or archive-date new_date = reformatter (param_val.val, pattern_idx, (('y' == len_a) and 'ymd') or format, len_a); -- choose ymd or dmy/mdy according to len_a setting else -- all other dates new_date = reformatter (param_val.val, pattern_idx, format, len_p); end if new_date then -- set when date was reformatted date_parameters_list[param_name].val = new_date; -- update date in date list result = true; -- and announce that changes have been made break; end end -- if end -- for end -- if end -- if end -- for return result; -- declare boolean result and done end --[[--------------------------< D A T E _ H Y P H E N _ T O _ D A S H >---------------------------------------- Loops through the list of date-holding parameters and converts any hyphen to an ndash. Not called if the cs1|2 template has any date errors. Modifies the date_parameters_list and returns true if hyphens are replaced, else returns false. ]] local function date_hyphen_to_dash (date_parameters_list) local result = false; local n; for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list if is_set (param_val.val) and not mw.ustring.match (param_val.val, patterns_t.ymd[1]) then -- for those that are not ymd dates (ustring because here digits may not be Western) param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash if 0 ~= n then date_parameters_list[param_name].val = param_val.val; -- update the list result = true; end end end return result; -- so we know if any hyphens were replaced end --[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------ Attempts to translate English date names to local-language date names using names supplied by MediaWiki's date parser function. This is simple name-for-name replacement and may not work for all languages. if xlat_dig is true, this function will also translate Western (English) digits to the local language's digits. This will also translate ymd dates. ]] local function date_name_xlate (date_parameters_list, xlt_dig) local xlate; local mode; -- long or short month names local modified = false; local date; local sources_t = { {cfg.date_names.en.long, cfg.date_names.inv_local_long}, -- for translating long English month names to long local month names {cfg.date_names.en.short, cfg.date_names.inv_local_short}, -- short month names {cfg.date_names.en.quarter, cfg.date_names.inv_local_quarter}, -- quarter date names {cfg.date_names.en.season, cfg.date_names.inv_local_season}, -- season date nam {cfg.date_names.en.named, cfg.date_names.inv_local_named}, -- named dates } local function is_xlateable (month) -- local function to get local date name that replaces existing English-language date name for _, date_names_t in ipairs (sources_t) do -- for each sequence table in date_names_t if date_names_t[1][month] then -- if date name is English month (long or short), quarter, season or named and if date_names_t[2][date_names_t[1][month]] then -- if there is a matching local date name return date_names_t[2][date_names_t[1][month]]; -- return the local date name end end end end for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list if is_set(param_val.val) then -- if the parameter has a value date = param_val.val; for month in mw.ustring.gmatch (date, '[%a ]+') do -- iterate through all date names in the date (single date or date range) month = mw.text.trim (month); -- this because quarterly dates contain whitespace xlate = is_xlateable (month); -- get translate <month>; returns translation or nil if xlate then date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation date_parameters_list[param_name].val = date; -- save the translated date modified = true; end end if xlt_dig then -- shall we also translate digits? date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from Western to 'local digits' date_parameters_list[param_name].val = date; -- save the translated date modified = true; end end end return modified; end --[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >-------------------------------------- Sets local imported functions table to same (live or sandbox) as that used by the other modules. ]] local function set_selected_modules (cfg_table_ptr, utilities_page_ptr) add_prop_cat = utilities_page_ptr.add_prop_cat ; -- import functions from selected Module:Citation/CS1/Utilities module is_set = utilities_page_ptr.is_set; in_array = utilities_page_ptr.in_array; set_message = utilities_page_ptr.set_message; substitute = utilities_page_ptr.substitute; wrap_style = utilities_page_ptr.wrap_style; cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration end --[[--------------------------< A R C H I V E _ D A T E _ C H E C K >------------------------------------------ Compare value in |archive-date= with the timestamp in Wayback machine urls. Emits an error message with suggested date from the |archive-url= timestamp in an appropriate format when the value in |archive-date= does not match the timestamp. this function never called when any date in a cs1|2 template has errors error message suggests new |archive-date= value in an appropriate format specified by <df>. <df> is either |df= or cfg.global_df in that order. If <df> is nil, suggested date has format from |archive-date=. There is a caveat: when |df=dmy or |df=mdy, the reformatter leaves |access-date= and |archive-date= formats as they are. The error message suggested date is passed to the formatter as YYYY-MM-DD so when |df=dmy or |df=mdy, the format is not changed. ]] local function archive_date_check (archive_date, archive_url_timestamp, df) local archive_date_format = 'dmy-y'; -- holds the date format of date in |archive-date; default to ymd; 'dmy' used here to spoof reformat_dates() for _, v_t in ipairs ({{'dMy', 'dmy-all'}, {'Mdy', 'mdy-all'}}) do -- is |archive-date= format dmy or mdy? if archive_date:match (patterns_t[v_t[1]][1]) then -- does the pattern match? archive_date_format = cfg.keywords_xlate[v_t[2]]; -- get appropriate |df= supported keyword from the i18n translator table break; end end local dates_t = {}; dates_t['archive-date'] = {val=archive_date, name=''}; -- setup to call reformat_dates(); never called when errors so <name> unset as not needed reformat_dates (dates_t, 'dmy-y'); -- reformat |archive-date= to ymd; 'dmy' used here to spoof reformat_dates() local archive_url_date = archive_url_timestamp:gsub ('(%d%d%d%d)(%d%d)(%d%d)%d*', '%1-%2-%3'); -- make ymd format date from timestamp if dates_t['archive-date'].val == archive_url_date then -- are the two dates the same return; -- yes, done else dates_t['archive-date'] = {val=archive_url_date, name=''}; -- setup to call reformat_dates() with the timestamp date reformat_dates (dates_t, df or archive_date_format); -- reformat timestamp to format specified by <df> or format used in |archive-date= archive_url_date = dates_t['archive-date'].val; set_message ('err_archive_date_url_ts_mismatch', archive_url_date); -- emit an error message end end --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ ]] return { -- return exported functions archive_date_check = archive_date_check, date_hyphen_to_dash = date_hyphen_to_dash, date_name_xlate = date_name_xlate, dates = dates, is_valid_date = is_valid_date, reformat_dates = reformat_dates, set_selected_modules = set_selected_modules, year_check = year_check, year_date_check = year_date_check, } 039z8dc7ugbbv8w4tsnejz5bfud8dgw 828 658 9078 2026-05-15T07:23:14Z WikiBayer 737 [[:w:Special:PermanentLink/1333753785|Module:Citation/CS1/Identifiers]] 9078 Scribunto text/plain --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local has_accept_as_written, is_set, in_array, set_message, select_one, -- functions in Module:Citation/CS1/Utilities substitute, make_wikilink; local z; -- table of tables defined in Module:Citation/CS1/Utilities local cfg; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration --[[--------------------------< P A G E S C O P E V A R I A B L E S >-------------------------------------- declare variables here that have page-wide scope that are not brought in from other modules; that are created here and used here ]] local auto_link_urls = {}; -- holds identifier URLs for those identifiers that can auto-link |title= --============================<< H E L P E R F U N C T I O N S >>============================================ --[[--------------------------< W I K I D A T A _ A R T I C L E _ N A M E _ G E T >---------------------------- as an aid to internationalizing identifier-label wikilinks, gets identifier article names from Wikidata. returns w:<lang code>:<article title> when <q> has an <article title> for <lang code>; nil else. 'w:<lang code>' ensures that sister project (like wiktionary) will link to the <lang code>.wikipedia article. for identifiers that do not have <q>, returns nil for wikis that do not have mw.wikibase installed, returns nil ]] local function wikidata_article_name_get (q) if not is_set (q) or (q and not mw.wikibase) then -- when no q number or when a q number but mw.wikibase not installed on this wiki return nil; -- abandon end local wd_article; local this_wiki_code = cfg.this_wiki_code; -- Wikipedia subdomain; 'en' for en.wikipedia.org wd_article = mw.wikibase.getSitelink (q, this_wiki_code .. 'wiki'); -- fetch article title from WD; nil when no title available at this wiki if wd_article then wd_article = table.concat ({'w:', this_wiki_code, ':', wd_article}); -- interwiki-style link without brackets if taken from WD; leading 'w:' required end return wd_article; -- article title from WD; nil else end --[[--------------------------< L A B E L _ L I N K _ M A K E >------------------------------------------------ common function to create a link for an identifier label from handler table or from Wikidata returns the first available of: 1. redirect from local wiki's handler table (if enabled) 2. Wikidata sitelink to the local language wikipedia article (if there is a Wikidata entry for this identifier in the local language) 3. link to wikipedia article specified in the local wiki's handler table ]] local function label_link_make (handler) local wd_article; if not (cfg.use_identifier_redirects and is_set (handler.redirect)) then -- redirect has priority so if enabled and available don't fetch from Wikidata because expensive wd_article = wikidata_article_name_get (handler.q); -- if Wikidata has an article title for this wiki, get it; end return (cfg.use_identifier_redirects and is_set (handler.redirect) and handler.redirect) or wd_article or handler.link; end --[[--------------------------< E X T E R N A L _ L I N K _ I D >---------------------------------------------- Formats a wiki-style external link ]] local function external_link_id (options) local url_string = options.id; local ext_link; local this_wiki_code = cfg.this_wiki_code; -- Wikipedia subdomain; 'en' for en.wikipedia.org local wd_article; -- article title from Wikidata if options.encode == true or options.encode == nil then url_string = mw.uri.encode (url_string, 'PATH'); end if options.auto_link and is_set (options.access) then auto_link_urls[options.auto_link] = table.concat ({options.prefix, url_string, options.suffix}); end ext_link = mw.ustring.format ('[%s%s%s %s]', options.prefix, url_string, options.suffix or "", mw.text.nowiki (options.id)); if is_set (options.access) then ext_link = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[options.access].class, cfg.presentation[options.access].title, ext_link}); -- add the free-to-read / paywall lock end return table.concat ({ make_wikilink (label_link_make (options), options.label), -- redirect, Wikidata link, or locally specified link (in that order) options.separator or '&nbsp;', ext_link }); end --[[--------------------------< I N T E R N A L _ L I N K _ I D >---------------------------------------------- Formats a wiki-style internal link TODO: Does not currently need to support options.access, options.encode, auto-linking and COinS (as in external_link_id), but may be needed in the future for :m:Interwiki_map custom-prefixes like :arxiv:, :bibcode:, :DOI:, :hdl:, :ISSN:, :JSTOR:, :Openlibrary:, :PMID:, :RFC:. ]] local function internal_link_id (options) local id = mw.ustring.gsub (options.id, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9 return table.concat ( { make_wikilink (label_link_make (options), options.label), -- wiki-link the identifier label options.separator or '&nbsp;', -- add the separator make_wikilink ( table.concat ( { options.prefix, id, -- translated to Western digits options.suffix or '' }), substitute (cfg.presentation['bdi'], {'', mw.text.nowiki (options.id)}) -- bdi tags to prevent Latin script identifiers from being reversed at RTL language wikis ); -- nowiki because MediaWiki still has magic links for ISBN and the like; TODO: is it really required? }); 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 |pmc-embargo-date= against today's date. If embargo date is in the future, returns the content of |pmc-embargo-date=; otherwise, returns an empty string because the embargo has expired or because |pmc-embargo-date= was not set in this cite. ]] local function is_embargoed (embargo) if is_set (embargo) then local lang = mw.getContentLanguage(); local good1, embargo_date, todays_date; good1, embargo_date = pcall (lang.formatDate, lang, 'U', embargo); todays_date = lang:formatDate ('U'); if good1 then -- if embargo date is a good date if tonumber (embargo_date) >= tonumber (todays_date) then -- is embargo date is in the future? return embargo; -- still embargoed else set_message ('maint_pmc_embargo'); -- embargo has expired; add main cat return ''; -- unset because embargo has expired end end end return ''; -- |pmc-embargo-date= not set return empty string end --[=[-------------------------< I S _ V A L I D _ R X I V _ D A T E >------------------------------------------ for biorxiv, returns true if: 2019-12-11T00:00Z <= biorxiv_date < today + 2 days for medrxiv, returns true if: 2020-01-01T00:00Z <= medrxiv_date < today + 2 days The dated form of biorxiv identifier has a start date of 2019-12-11. The Unix timestamp for that date is {{#time:U|2019-12-11}} = 1576022400 The medrxiv identifier has a start date of 2020-01-01. The Unix timestamp for that date is {{#time:U|2020-01-01}} = 1577836800 <rxiv_date> is the date provided in those |biorxiv= parameter values that are dated and in |medrxiv= parameter values at time 00:00:00 UTC <today> is the current date at time 00:00:00 UTC plus 48 hours if today's date is 2023-01-01T00:00:00 then adding 24 hours gives 2023-01-02T00:00:00 – one second more than today adding 24 hours gives 2023-01-03T00:00:00 – one second more than tomorrow inputs: <y>, <m>, <d> – year, month, day parts of the date from the birxiv or medrxiv identifier <select> 'b' for biorxiv, 'm' for medrxiv; defaults to 'b' ]=] local function is_valid_rxiv_date (y, m, d, select) if 0 == tonumber (m) and 12 < tonumber (m) then -- <m> must be a number 1–12 return false; end if 0 == tonumber (d) and 31 < tonumber (d) then -- <d> must be a number 1–31; TODO: account for month length and leap yer? return false; end local rxiv_date = table.concat ({y, m, d}, '-'); -- make ymd date string local good1, good2; local rxiv_ts, tomorrow_ts; -- to hold Unix timestamps representing the dates local lang_object = mw.getContentLanguage(); good1, rxiv_ts = pcall (lang_object.formatDate, lang_object, 'U', rxiv_date); -- convert rxiv_date value to Unix timestamp good2, tomorrow_ts = pcall (lang_object.formatDate, lang_object, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which tonumber() may not understand rxiv_ts = tonumber (rxiv_ts) or lang_object:parseFormattedNumber (rxiv_ts); -- convert to numbers for the comparison; tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts); else return false; -- one or both failed to convert to Unix timestamp end local limit_ts = ((select and ('m' == select)) and 1577836800) or 1576022400; -- choose the appropriate limit timesatmp return ((limit_ts <= rxiv_ts) and (rxiv_ts < tomorrow_ts)) -- limit_ts <= rxiv_date < tomorrow's 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 isbn(). If the number is valid the result will be 0. Before calling this function, ISBN/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 --[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >----------------------------------------------- ISBN-13 and ISMN validator code calculates checksum across all 13 ISBN/ISMN digits including the check digit. If the number is valid, the result will be 0. Before calling this function, ISBN-13/ISMN must be checked for length and stripped of dashes, spaces and other non-ISxN-13 characters. ]] local function is_valid_isxn_13 (isxn_str) local temp=0; isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39 for i, v in ipairs (isxn_str) do temp = temp + (3 - 2*(i % 2)) * tonumber (string.char (v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit end return temp % 10 == 0; -- sum modulo 10 is zero when ISBN-13/ISMN is correct end --[[--------------------------< N O R M A L I Z E _ L C C N >-------------------------------------------------- LCCN normalization (https://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 --============================<< I D E N T I F I E R F U N C T I O N S >>==================================== --[[--------------------------< A R X I V >-------------------------------------------------------------------- See: https://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 9107 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; not the same as |class= parameter which is not supported in this form <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 (options) local id = options.id; local class = options.Class; -- TODO: lowercase? local handler = options.handler; local year, month, version; local err_msg = false; -- assume no error message local text; -- output 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 9107-0703 format with or without version year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$"); year = tonumber (year); month = tonumber (month); if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month ((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok? err_msg = true; -- flag for error message end elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 with or without version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); 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 -- when year is 07, is month invalid (before April)? err_msg = true; -- flag for 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 with or without 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_msg = true; -- flag for error message end else err_msg = true; -- not a recognized format; flag for error message end if err_msg then options.coins_list_t['ARXIV'] = nil; -- when error, unset so not included in COinS end local err_msg_t = {}; if err_msg then set_message ('err_bad_arxiv'); end text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access}); if is_set (class) then if id:match ('^%d+') then text = table.concat ({text, ' [[https://arxiv.org/archive/', class, ' ', class, ']]'}); -- external link within square brackets, not wikilink else set_message ('err_class_ignored'); end else -- class not set if id:match ('^%d+') and options.CitationClass == 'arxiv' then -- new (post 2007) format; {{cite arxiv}} only set_message ('maint_missing_class'); -- add maint cat end end return text; end --[[--------------------------< B I B C O D E >-------------------------------------------------------------------- Validates (sort of) and formats a bibcode ID. Format for bibcodes is specified here: https://adsabs.harvard.edu/abs_doc/help_pages/data.html#bibcodes But, this: 2015arXiv151206696F is apparently valid so apparently, the only things that really matter are length, 19 characters and first four digits must be a year. This function makes these tests: length must be 19 characters characters in position 1–4 must be digits and must represent a year in the range of 1000 – next year 5 must be a letter 6–8 must be letter, digit, ampersand, or dot (ampersand cannot directly precede a dot; &. ) 9–18 must be letter, digit, or dot 19 must be a letter or dot ]] local function bibcode (options) local id = options.id; local access = options.access; local handler = options.handler; local ignore_invalid = options.accept; local err_type; local err_msg = ''; local year; local text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = access}); if 19 ~= id:len() then err_type = cfg.err_msg_supl.length; else year = id:match ("^(%d%d%d%d)[%a][%w&%.][%w&%.][%w&%.][%w.]+[%a%.]$"); if not year then -- if nil then no pattern match err_type = cfg.err_msg_supl.value; -- so value error else local next_year = tonumber (os.date ('%Y')) + 1; -- get the current year as a number and add one for next year year = tonumber (year); -- convert year portion of bibcode to a number if (1000 > year) or (year > next_year) then err_type = cfg.err_msg_supl.year; -- year out of bounds end if id:find('&%.') then err_type = cfg.err_msg_supl.journal; -- journal abbreviation must not have '&.' (if it does it's missing a letter) end if id:match ('.........%.tmp%.') then -- temporary bibcodes when positions 10–14 are '.tmp.' set_message ('maint_bibcode'); end end end if is_set (err_type) and not ignore_invalid then -- if there was an error detected and accept-as-written markup not used set_message ('err_bad_bibcode', {err_type}); options.coins_list_t['BIBCODE'] = nil; -- when error, unset so not included in COinS end return text; end --[[--------------------------< B I O R X I V >----------------------------------------------------------------- Format bioRxiv ID and do simple error checking. Before 2019-12-11, biorXiv IDs were 10.1101/ followed by exactly 6 digits. After 2019-12-11, biorXiv IDs retained the six-digit identifier but prefixed that with a yyyy.mm.dd. date and suffixed with an optional version identifier. From December 2025 biorxiv added a new 'doi' prefix: 10.64898: 10.64898/2025.12.10.693067 The bioRxiv ID is the string of characters: https://doi.org/10.1101/078733 -> 10.1101/078733 or a date followed by a six-digit number followed by an optional version indicator 'v' and one or more digits: https://www.biorxiv.org/content/10.1101/2019.12.11.123456v2 -> 10.1101/2019.12.11.123456v2 see https://www.biorxiv.org/about-biorxiv ]] local function biorxiv (options) local id = options.id; local handler = options.handler; local err_msg = true; -- flag; assume that there will be an error local patterns = { '^10%.1101/%d%d%d%d%d%d$', -- simple 6-digit identifier (before 2019-12-11) '^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%dv%d+$', -- y.m.d. date + 6-digit identifier + version (after 2019-12-11) '^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d$', -- y.m.d. date + 6-digit identifier (after 2019-12-11) '^10%.64898/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%dv%d+$', -- y.m.d. date + 6-digit identifier + version (from December 2025) '^10%.64898/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d$', -- y.m.d. date + 6-digit identifier (from December 2025) } for _, pattern in ipairs (patterns) do -- spin through the patterns looking for a match if id:match (pattern) then local y, m, d = id:match (pattern); -- found a match, attempt to get year, month and date from the identifier if m then -- m is nil when id is the six-digit form if not is_valid_rxiv_date (y, m, d, 'b') then -- validate the encoded date; 'b' for biorxiv limit break; -- date fail; break out early so we don't unset the error message end end err_msg = nil; -- we found a match so unset the error message break; -- and done end end -- err_cat remains set here when no match if err_msg then options.coins_list_t['BIORXIV'] = nil; -- when error, unset so not included in COinS set_message ('err_bad_biorxiv'); -- and set the error message end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access}); end --[[--------------------------< C I T E S E E R X >------------------------------------------------------------ CiteSeerX use their own notion of "doi" (not to be confused with the identifiers resolved via doi.org). The description of the structure of this identifier can be found at Help_talk:Citation_Style_1/Archive_26#CiteSeerX_id_structure ]] local function citeseerx (options) local id = options.id; local handler = options.handler; local matched; local text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access}); matched = id:match ("^10%.1%.1%.[1-9]%d?%d?%d?%.[1-9]%d?%d?%d?$"); if not matched then set_message ('err_bad_citeseerx' ); options.coins_list_t['CITESEERX'] = nil; -- when error, unset so not included in COinS end return text; end --[[--------------------------< D O I >------------------------------------------------------------------------ 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. https://www.doi.org/doi_handbook/2_Numbering.html -- 2.2 Syntax of a DOI name https://www.doi.org/doi_handbook/2_Numbering.html#2.2.2 -- 2.2.2 DOI prefix ]] local function doi (options) local id = options.id; local inactive = options.DoiBroken local access = options.access; local ignore_invalid = options.accept; local handler = options.handler; local err_flag; local function is_extended_free (registrant, suffix) -- local function to check those few registrants that are mixed; identifiable by the doi suffix <incipit> suffix = suffix:lower(); -- ascii [a-z] same as [A-Z] in doi names; see §3.4.4 Case Insensitivity of the Doi Name if cfg.extended_registrants_t[registrant] then -- if this registrant has known free-to-read extentions for _, incipit in ipairs (cfg.extended_registrants_t[registrant]) do -- loop through the registrant's incipits if mw.ustring.find (suffix, '^' .. incipit:lower()) then -- ascii [a-z] same as [A-Z] in doi names return true; -- if foundm done end end end end local text; if is_set (inactive) then local inactive_year = inactive:match("%d%d%d%d"); -- try to get the year portion from the inactive date local inactive_month, good; if is_set (inactive_year) then if 4 < inactive:len() then -- inactive date has more than just a year (could be anything) local lang_obj = mw.getContentLanguage(); -- get a language object for this wiki good, inactive_month = pcall (lang_obj.formatDate, lang_obj, 'F', inactive); -- try to get the month name from the inactive date if not good then inactive_month = nil; -- something went wrong so make sure this is unset end end end -- otherwise, |doi-broken-date= has something but it isn't a date if is_set (inactive_year) and is_set (inactive_month) then set_message ('maint_doi_inactive_dated', {inactive_year, inactive_month, ' '}); elseif is_set (inactive_year) then set_message ('maint_doi_inactive_dated', {inactive_year, '', ''}); else set_message ('maint_doi_inactive'); end inactive = substitute (cfg.messages['inactive'], inactive ); end local suffix; local registrant, suffix = mw.ustring.match (id, '^10%.([^/]+)/([^%s–]-[^%.,])$'); -- registrant and suffix set when DOI has the proper basic form; both nil else local registrant_err_patterns = { -- these patterns are for code ranges that are not supported '^[^1-3]%d%d%d%d%.%d+$', -- 5 digits with subcode (reject 0xxxx, 40000+); accepts: 10000–39999 '^[^1-8]%d%d%d%d$', -- 5 digits without subcode (reject 0xxxx, 90000+); accepts: 10000–89999 '^[^1-9]%d%d%d%.%d+$', -- 4 digits with subcode (reject 0xxx); accepts: 1000–9999 '^[^1-9]%d%d%d$', -- 4 digits without subcode (reject 0xxx); accepts: 1000–9999 '^%d%d%d%d%d%d+', -- 6 or more digits '^%d%d?%d?$', -- less than 4 digits without subcode (3 digits with subcode is legitimate) '^%d%d?%.[%d%.]+', -- 1 or 2 digits with subcode '^5555$', -- test registrant will never resolve '[^%d%.]', -- any character that isn't a digit or a dot } if not ignore_invalid then if registrant then -- when DOI has proper form for i, pattern in ipairs (registrant_err_patterns) do -- spin through error patterns if registrant:match (pattern) then -- to validate registrant codes err_flag = set_message ('err_bad_doi'); -- when found, mark this DOI as bad break; -- and done end end else err_flag = set_message ('err_bad_doi'); -- invalid directory or malformed end else set_message ('maint_doi_ignore'); end if err_flag then options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS else -- here when doi has no errors or has been wrapped in accept-as-written markup suffix = mw.ustring.match (id, '^10%.[^/]+/(.+)'); -- refetch suffix because doi may have been wrapped in accept-as-written markup if not access and (cfg.known_free_doi_registrants_t[registrant] or is_extended_free (registrant, suffix)) then -- |doi-access=free not set and <registrant> is known to be free set_message ('maint_doi_unflagged_free'); -- set a maint cat end end text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = access, auto_link = not (err_flag or is_set (inactive) or ignore_invalid) and 'doi' or nil -- do not auto-link when |doi-broken-date= has a value or when there is a DOI error or (to play it safe, after all, auto-linking is not essential) when invalid DOIs are ignored }) .. (inactive or ''); return text; end --[[--------------------------< H D L >------------------------------------------------------------------------ Formats an HDL with minor error checking. HDL names contain two parts: prefix and suffix separated by a forward slash. Prefix: character string using any character in the UCS-2 character set except '/' Suffix: character string of any length using any character in the UCS-2 character set chosen by the registrant This function checks a HDL name for: prefix/suffix. If the HDL name contains spaces, endashes, or, if it ends with a period or a comma, this function will emit a bad_hdl error message. HDL names are case-insensitive and can incorporate any printable Unicode characters so the test for endashes and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in HDLs. Query string parameters are named here: https://www.handle.net/proxy_servlet.html. query strings are not displayed but since '?' is an allowed character in an HDL, '?' followed by one of the query parameters is the only way we have to detect the query string so that it isn't URL-encoded with the rest of the identifier. ]] local function hdl (options) local id = options.id; local access = options.access; local handler = options.handler; local query_params = { -- list of known query parameters from https://www.handle.net/proxy_servlet.html 'noredirect', 'ignore_aliases', 'auth', 'cert', 'index', 'type', 'urlappend', 'locatt', 'action', } local hdl, suffix, param = id:match ('(.-)(%?(%a+).+)$'); -- look for query string local found; if hdl then -- when there are query strings, this is the handle identifier portion for _, q in ipairs (query_params) do -- spin through the list of query parameters if param:match ('^' .. q) then -- if the query string begins with one of the parameters found = true; -- announce a find break; -- and stop looking end end end if found then id = hdl; -- found so replace id with the handle portion; this will be URL-encoded, suffix will not else suffix = ''; -- make sure suffix is empty string for concatenation else end local text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, suffix = suffix, separator = handler.separator, encode = handler.encode, access = access}) if nil == id:match("^[^%s–]-/[^%s–]-[^%.,]$") then -- HDL must contain a forward slash, must not contain spaces, endashes, and must not end with period or comma set_message ('err_bad_hdl' ); options.coins_list_t['HDL'] = nil; -- when error, unset so not included in COinS end return text; end --[[--------------------------< I S B N >---------------------------------------------------------------------- Determines whether an ISBN string is valid ]] local function isbn (options_t) local isbn_str = options_t.id; local ignore_invalid = options_t.accept; local handler = options_t.handler; local year = options_t.Year; -- when set, valid anchor_year; may have a disambiguator which must be removed local function return_result (check, err_type) -- local function to handle the various returns local ISBN = internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect, prefix = handler.prefix, id = isbn_str, separator = handler.separator}); if ignore_invalid then -- if ignoring ISBN errors set_message ('maint_isbn_ignore'); -- add a maint category even when there is no error else -- here when not ignoring if not check then -- and there is an error options_t.coins_list_t['ISBN'] = nil; -- when error, unset so not included in COinS set_message ('err_bad_isbn', err_type); -- set an error message return ISBN; -- return id text end end return ISBN; -- return id text end if year and not ignore_invalid then -- year = year:match ('%d%d%d%d?'); -- strip disambiguator if present if year and (1965 > tonumber(year)) then -- <year> will be nil here when |year=n.d. or |year=nd set_message ('err_invalid_isbn_date'); -- set an error message return internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect, prefix = handler.prefix, id = isbn_str, separator = handler.separator}); end end if nil ~= isbn_str:match ('[^%s-0-9X]') then return return_result (false, cfg.err_msg_supl.char); -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X end local id = isbn_str:gsub ('[%s-]', ''); -- remove hyphens and whitespace local len = id:len(); if len ~= 10 and len ~= 13 then return return_result (false, cfg.err_msg_supl.length); -- fail if incorrect length end if len == 10 then if id:match ('^%d*X?$') == nil then -- fail if isbn_str has 'X' anywhere but last position return return_result (false, cfg.err_msg_supl.form); end if not is_valid_isxn (id, 10) then -- test isbn-10 for numerical validity return return_result (false, cfg.err_msg_supl.check); -- fail if isbn-10 is not numerically valid end if id:find ('^63[01]') then -- 630xxxxxxx and 631xxxxxxx are (apparently) not valid isbn group ids but are used by amazon as numeric identifiers (asin) return return_result (false, cfg.err_msg_supl.group); -- fail if isbn-10 begins with 630/1 end return return_result (true, cfg.err_msg_supl.check); -- pass if isbn-10 is numerically valid else if id:match ('^%d+$') == nil then return return_result (false, cfg.err_msg_supl.char); -- fail if ISBN-13 is not all digits end if id:match ('^97[89]%d*$') == nil then return return_result (false, cfg.err_msg_supl.prefix); -- fail when ISBN-13 does not begin with 978 or 979 end if id:match ('^9790') then return return_result (false, cfg.err_msg_supl.group); -- group identifier '0' is reserved to ISMN end return return_result (is_valid_isxn_13 (id), cfg.err_msg_supl.check); end end --[[--------------------------< A S I 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 ISBN-10, if mixed and first character is a digit. |asin=630....... and |asin=631....... are (apparently) not a legitimate ISBN though it checksums as one; these do not cause this function to emit the maint_asin message This function is positioned here because it calls isbn() ]] local function asin (options) local id = options.id; local domain = options.ASINTLD; local err_flag; if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then err_flag = set_message ('err_bad_asin'); -- ASIN is not a mix of 10 uppercase alpha and numeric characters else if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X) if is_valid_isxn (id, 10) then -- see if ASIN value is or validates as ISBN-10 if not id:find ('^63[01]') then -- 630xxxxxxx and 631xxxxxxx are (apparently) not a valid isbn prefixes but are used by amazon as a numeric identifier err_flag = set_message ('err_bad_asin'); -- ASIN has ISBN-10 form but begins with something other than 630/1 so probably an isbn end elseif not is_set (err_flag) then err_flag = set_message ('err_bad_asin'); -- ASIN is not ISBN-10 end elseif not id:match("^%u[%d%u]+$") then err_flag = set_message ('err_bad_asin'); -- asin doesn't begin with uppercase alpha end end if (not is_set (domain)) or in_array (domain, {'us'}) then -- default: United States domain = "com"; elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom domain = "co." .. domain; elseif in_array (domain, {'z.cn'}) then -- China domain = "cn"; elseif in_array (domain, {'au', 'br', 'mx', 'sg', 'tr'}) then -- Australia, Brazil, Mexico, Singapore, Turkey domain = "com." .. domain; elseif not in_array (domain, {'ae', 'ca', 'cn', 'de', 'es', 'fr', 'in', 'it', 'nl', 'pl', 'sa', 'se', 'co.jp', 'co.uk', 'com', 'com.au', 'com.br', 'com.mx', 'com.sg', 'com.tr'}) then -- Arabic Emirates, Canada, China, Germany, Spain, France, Indonesia, Italy, Netherlands, Poland, Saudi Arabia, Sweden (as of 2021-03 Austria (.at), Liechtenstein (.li) and Switzerland (.ch) still redirect to the German site (.de) with special settings, so don't maintain local ASINs for them) err_flag = set_message ('err_bad_asin_tld'); -- unsupported asin-tld value end local handler = options.handler; if not is_set (err_flag) then options.coins_list_t['ASIN'] = handler.prefix .. domain .. "/dp/" .. id; -- asin for coins else options.coins_list_t['ASIN'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix .. domain .. "/dp/", id = id, encode = handler.encode, separator = handler.separator}) end --[[--------------------------< I S M N >---------------------------------------------------------------------- Determines whether an ISMN string is valid. Similar to ISBN-13, ISMN is 13 digits beginning 979-0-... and uses the same check digit calculations. See https://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf section 2, pages 9–12. ismn value not made part of COinS metadata because we don't have a url or isn't a COinS-defined identifier (rft.xxx) or an identifier registered at info-uri.info (info:) ]] local function ismn (options) local id = options.id; local handler = options.handler; local text; local valid_ismn = true; local id_copy; id_copy = id; -- save a copy because this testing is destructive id = id:gsub ('[%s-]', ''); -- remove hyphens and white space if 13 ~= id:len() or id:match ("^9790%d*$" ) == nil then -- ISMN must be 13 digits and begin with 9790 valid_ismn = false; else valid_ismn=is_valid_isxn_13 (id); -- validate ISMN end -- text = internal_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, -- use this (or external version) when there is some place to link to -- prefix = handler.prefix, id = id_copy, separator = handler.separator, encode = handler.encode}) text = table.concat ( -- because no place to link to yet { make_wikilink (label_link_make (handler), handler.label), handler.separator, id_copy }); if false == valid_ismn then options.coins_list_t['ISMN'] = nil; -- when error, unset so not included in COinS; not really necessary here because ismn not made part of COinS set_message ('err_bad_ismn'); -- create an error message if the ISMN is invalid end return text; 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: [https://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 (options) local id = options.id; local handler = options.handler; local ignore_invalid = options.accept; local issn_copy = id; -- save a copy of unadulterated ISSN; use this version for display if ISSN does not validate local text; local valid_issn = true; id = id:gsub ('[%s-]', ''); -- remove hyphens and whitespace if 8 ~= id:len() or nil == id:match ("^%d*X?$" ) then -- validate the ISSN: 8 digits long, containing only 0-9 or X in the last position valid_issn = false; -- wrong length or improper character else valid_issn = is_valid_isxn (id, 8); -- validate ISSN end if true == valid_issn then id = string.sub (id, 1, 4 ) .. "-" .. string.sub (id, 5 ); -- if valid, display correctly formatted version else id = issn_copy; -- if not valid, show the invalid ISSN with error message end text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}) if ignore_invalid then set_message ('maint_issn_ignore'); else if false == valid_issn then options.coins_list_t['ISSN'] = nil; -- when error, unset so not included in COinS set_message ('err_bad_issn', (options.hkey == 'EISSN') and 'e' or ''); -- create an error message if the ISSN is invalid end end return text; end --[[--------------------------< J F M >----------------------------------------------------------------------- A numerical identifier in the form nn.nnnn.nn ]] local function jfm (options) local id = options.id; local handler = options.handler; local id_num; id_num = id:match ('^[Jj][Ff][Mm](.*)$'); -- identifier with jfm prefix; extract identifier if is_set (id_num) then set_message ('maint_jfm_format'); else -- plain number without JFM prefix id_num = id; -- if here id does not have prefix end if id_num and id_num:match('^%d%d%.%d%d%d%d%.%d%d$') then id = id_num; -- jfm matches pattern else set_message ('err_bad_jfm' ); -- set an error message options.coins_list_t['JFM'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}); end --[[--------------------------< J S T O R >-------------------------------------------------------------------- Format a JSTOR with some error checking ]] local function jstor (options) local id = options.id; local access = options.access; local handler = options.handler; if id:find ('[Jj][Ss][Tt][Oo][Rr]') or id:find ('^https?://') or id:find ('%s') then set_message ('err_bad_jstor'); -- set an error message options.coins_list_t['JSTOR'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = access}); end --[[--------------------------< L C C N >---------------------------------------------------------------------- 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. https://oclc-research.github.io/infoURI-Frozen/info-uri.info/info:lccn/reg.html length = 8 then all digits length = 9 then lccn[1] is lowercase alpha length = 10 then lccn[1] and lccn[2] are both lowercase alpha or both digits length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lowercase alpha or both digits length = 12 then lccn[1] and lccn[2] are both lowercase alpha ]] local function lccn (options) local lccn = options.id; local handler = options.handler; local err_flag; -- 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_flag = set_message ('err_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_flag = set_message ('err_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_flag = set_message ('err_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_flag = set_message ('err_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_flag = set_message ('err_bad_lccn'); -- no match, set an error message end else err_flag = set_message ('err_bad_lccn'); -- wrong length, set an error message end if not is_set (err_flag) and nil ~= lccn:find ('%s') then err_flag = set_message ('err_bad_lccn'); -- lccn contains a space, set an error message end if is_set (err_flag) then options.coins_list_t['LCCN'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = lccn, separator = handler.separator, encode = handler.encode}); end --[[--------------------------< M E D R X I V >----------------------------------------------------------------- Format medRxiv ID and do simple error checking. Similar to later bioRxiv IDs, medRxiv IDs are prefixed with a yyyy.mm.dd. date and suffixed with an optional version identifier. Ealiest date accepted is 2020.01.01 The medRxiv ID is a date followed by an eight-digit number followed by an optional version indicator 'v' and one or more digits: https://www.medrxiv.org/content/10.1101/2020.11.16.20232009v2 -> 10.1101/2020.11.16.20232009v2 ]] local function medrxiv (options) local id = options.id; local handler = options.handler; local err_msg_flag = true; -- flag; assume that there will be an error local patterns = { '^%d%d%d%d%d%d%d%d$', -- simple 8-digit identifier; these should be relatively rare '^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%dv%d+$', -- y.m.d. date + 8-digit identifier + version (2020-01-01 and later) '^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%d$', -- y.m.d. date + 8-digit identifier (2020-01-01 and later) '^10%.64898/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%dv%d+$', -- y.m.d. date + 8-digit identifier + version (2025-12-01 and later) '^10%.64898/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%d$', -- y.m.d. date + 8-digit identifier (2025-12-01 and later) } for _, pattern in ipairs (patterns) do -- spin through the patterns looking for a match if id:match (pattern) then local y, m, d = id:match (pattern); -- found a match, attempt to get year, month and date from the identifier if m then -- m is nil when id is the 8-digit form if not is_valid_rxiv_date (y, m, d, 'b') then -- validate the encoded date; 'b' for medrxiv limit break; -- date fail; break out early so we don't unset the error message end end err_msg_flag = nil; -- we found a match so unset the error message break; -- and done end end -- <err_msg_flag> remains set here when no match if err_msg_flag then options.coins_list_t['MEDRXIV'] = nil; -- when error, unset so not included in COinS set_message ('err_bad_medrxiv'); -- and set the error message end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access}); end --[[--------------------------< M R >-------------------------------------------------------------------------- A seven digit number; if not seven digits, zero-fill leading digits to make seven digits. ]] local function mr (options) local id = options.id; local handler = options.handler; local id_num; local id_len; id_num = id:match ('^[Mm][Rr](%d+)$'); -- identifier with mr prefix if is_set (id_num) then set_message ('maint_mr_format'); -- add maint cat else -- plain number without mr prefix id_num = id:match ('^%d+$'); -- if here id is all digits end id_len = id_num and id_num:len() or 0; if (7 >= id_len) and (0 ~= id_len) then id = string.rep ('0', 7-id_len) .. id_num; -- zero-fill leading digits else set_message ('err_bad_mr'); -- set an error message options.coins_list_t['MR'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}); end --[[--------------------------< O C L C >---------------------------------------------------------------------- Validate and format an OCLC ID. https://www.oclc.org/batchload/controlnumber.en.html {{dead link}} archived at: https://web.archive.org/web/20161228233804/https://www.oclc.org/batchload/controlnumber.en.html ]] local function oclc (options) local id = options.id; local handler = options.handler; local number; if id:match('^ocm%d%d%d%d%d%d%d%d$') then -- ocm prefix and 8 digits; 001 field (12 characters) number = id:match('ocm(%d+)'); -- get the number elseif id:match('^ocn%d%d%d%d%d%d%d%d%d$') then -- ocn prefix and 9 digits; 001 field (12 characters) number = id:match('ocn(%d+)'); -- get the number elseif id:match('^on%d%d%d%d%d%d%d%d%d%d+$') then -- on prefix and 10 or more digits; 001 field (12 characters) number = id:match('^on(%d%d%d%d%d%d%d%d%d%d+)$'); -- get the number elseif id:match('^%(OCoLC%)[1-9]%d*$') then -- (OCoLC) prefix and variable number digits; no leading zeros; 035 field number = id:match('%(OCoLC%)([1-9]%d*)'); -- get the number if 9 < number:len() then number = nil; -- constrain to 1 to 9 digits; change this when OCLC issues 10-digit numbers end elseif id:match('^%d+$') then -- no prefix number = id; -- get the number if tonumber (id) > handler.id_limit then number = nil; -- unset when id value exceeds the limit end end if number then -- proper format id = number; -- exclude prefix, if any, from external link else set_message ('err_bad_oclc') -- add an error message if the id is malformed options.coins_list_t['OCLC'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}); end --[[--------------------------< O P E N L I B R A R Y >-------------------------------------------------------- Formats an OpenLibrary link, and checks for associated errors. ]] local function openlibrary (options) local id = options.id; local access = options.access; local handler = options.handler; local ident, code = id:gsub('^OL', ''):match("^(%d+([AMW]))$"); -- strip optional OL prefix followed immediately by digits followed by 'A', 'M', or 'W'; local err_flag; local prefix = { -- these are appended to the handler.prefix according to code ['A']='authors/OL', ['M']='books/OL', ['W']='works/OL', ['X']='OL' -- not a code; spoof when 'code' in id is invalid }; if not ident then code = 'X'; -- no code or id completely invalid ident = id; -- copy id to ident so that we display the flawed identifier err_flag = set_message ('err_bad_ol'); end if not is_set (err_flag) then options.coins_list_t['OL'] = handler.prefix .. prefix[code] .. ident; -- experiment for ol coins else options.coins_list_t['OL'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix .. prefix[code], id = ident, separator = handler.separator, encode = handler.encode, access = access}); end --[[--------------------------< O S T I >---------------------------------------------------------------------- Format OSTI and do simple error checking. OSTIs are sequential numbers beginning at 1 and counting up. This code checks the OSTI to see that it contains only digits and is less than test_limit specified in the configuration; the value in test_limit will need to be updated periodically as more OSTIs are issued. NB. 1018 is the lowest OSTI number found in the wild (so far) and resolving OK on the OSTI site ]] local function osti (options) local id = options.id; local access = options.access; local handler = options.handler; if id:match("[^%d]") then -- if OSTI has anything but digits set_message ('err_bad_osti'); -- set an error message options.coins_list_t['OSTI'] = nil; -- when error, unset so not included in COinS else -- OSTI is only digits local id_num = tonumber (id); -- convert id to a number for range testing if 1018 > id_num or handler.id_limit < id_num then -- if OSTI is outside test limit boundaries set_message ('err_bad_osti'); -- set an error message options.coins_list_t['OSTI'] = nil; -- when error, unset so not included in COinS end end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = access}); 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 (options) local id = options.id; local embargo = options.Embargo; -- TODO: lowercase? local handler = options.handler; local err_flag; local id_num; local text; id_num = id:match ('^[Pp][Mm][Cc](%d+)$'); -- identifier with PMC prefix if is_set (id_num) then set_message ('maint_pmc_format'); else -- plain number without PMC prefix id_num = id:match ('^%d+$'); -- if here id is all digits end if is_set (id_num) then -- id_num has a value so test it id_num = tonumber (id_num); -- convert id_num to a number for range testing if 1 > id_num or handler.id_limit < id_num then -- if PMC is outside test limit boundaries err_flag = set_message ('err_bad_pmc'); -- set an error message else id = tostring (id_num); -- make sure id is a string end else -- when id format incorrect err_flag = set_message ('err_bad_pmc'); -- set an error message end if is_set (embargo) and is_set (is_embargoed (embargo)) then -- is PMC is still embargoed? text = table.concat ( -- still embargoed so no external link { make_wikilink (label_link_make (handler), handler.label), handler.separator, id, }); else text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, -- no embargo date or embargo has expired, ok to link to article prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access, auto_link = not err_flag and 'pmc' or nil -- do not auto-link when PMC has error }); end if err_flag then options.coins_list_t['PMC'] = nil; -- when error, unset so not included in COinS end return text; end --[[--------------------------< P M I D >---------------------------------------------------------------------- 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 (options) local id = options.id; local handler = options.handler; if id:match("[^%d]") then -- if PMID has anything but digits set_message ('err_bad_pmid'); -- set an error message options.coins_list_t['PMID'] = nil; -- when error, unset so not included in COinS else -- PMID is only digits local id_num = tonumber (id); -- convert id to a number for range testing if 1 > id_num or handler.id_limit < id_num then -- if PMID is outside test limit boundaries set_message ('err_bad_pmid'); -- set an error message options.coins_list_t['PMID'] = nil; -- when error, unset so not included in COinS end end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}); end --[[--------------------------< R F C >------------------------------------------------------------------------ Format RFC and do simple error checking. RFCs are sequential numbers beginning at 1 and counting up. This code checks the RFC to see that it contains only digits and is less than test_limit specified in the configuration; the value in test_limit will need to be updated periodically as more RFCs are issued. An index of all RFCs is here: https://tools.ietf.org/rfc/ ]] local function rfc (options) local id = options.id; local handler = options.handler; if id:match("[^%d]") then -- if RFC has anything but digits set_message ('err_bad_rfc'); -- set an error message options.coins_list_t['RFC'] = nil; -- when error, unset so not included in COinS else -- RFC is only digits local id_num = tonumber (id); -- convert id to a number for range testing if 1 > id_num or handler.id_limit < id_num then -- if RFC is outside test limit boundaries set_message ('err_bad_rfc'); -- set an error message options.coins_list_t['RFC'] = nil; -- when error, unset so not included in COinS end end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = handler.access}); end --[[--------------------------< S 2 C I D >-------------------------------------------------------------------- Format an S2CID, do simple error checking S2CIDs are sequential numbers beginning at 1 and counting up. This code checks the S2CID to see that it is only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more S2CIDs are issued. ]] local function s2cid (options) local id = options.id; local access = options.access; local handler = options.handler; local id_num; local text; id_num = id:match ('^[1-9]%d*$'); -- id must be all digits; must not begin with 0; no open access flag if is_set (id_num) then -- id_num has a value so test it id_num = tonumber (id_num); -- convert id_num to a number for range testing if handler.id_limit < id_num then -- if S2CID is outside test limit boundaries set_message ('err_bad_s2cid'); -- set an error message options.coins_list_t['S2CID'] = nil; -- when error, unset so not included in COinS end else -- when id format incorrect set_message ('err_bad_s2cid'); -- set an error message options.coins_list_t['S2CID'] = nil; -- when error, unset so not included in COinS end text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = access}); return text; end --[[--------------------------< S B N >------------------------------------------------------------------------ 9-digit form of ISBN-10; uses same check-digit validation when SBN is prefixed with an additional '0' to make 10 digits sbn value not made part of COinS metadata because we don't have a url or isn't a COinS-defined identifier (rft.xxx) or an identifier registered at info-uri.info (info:) ]] local function sbn (options) local id = options.id; local ignore_invalid = options.accept; local handler = options.handler; local function return_result (check, err_type) -- local function to handle the various returns local SBN = internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator}); if not ignore_invalid then -- if not ignoring SBN errors if not check then options.coins_list_t['SBN'] = nil; -- when error, unset so not included in COinS; not really necessary here because sbn not made part of COinS set_message ('err_bad_sbn', {err_type}); -- display an error message return SBN; end else set_message ('maint_isbn_ignore'); -- add a maint category even when there is no error (ToDo: Possibly switch to separate message for SBNs only) end return SBN; end if id:match ('[^%s-0-9X]') then return return_result (false, cfg.err_msg_supl.char); -- fail if SBN contains anything but digits, hyphens, or the uppercase X end local ident = id:gsub ('[%s-]', ''); -- remove hyphens and whitespace; they interfere with the rest of the tests if 9 ~= ident:len() then return return_result (false, cfg.err_msg_supl.length); -- fail if incorrect length end if ident:match ('^%d*X?$') == nil then return return_result (false, cfg.err_msg_supl.form); -- fail if SBN has 'X' anywhere but last position end return return_result (is_valid_isxn ('0' .. ident, 10), cfg.err_msg_supl.check); end --[[--------------------------< S S R N >---------------------------------------------------------------------- Format an SSRN, do simple error checking SSRNs are sequential numbers beginning at 100? and counting up. This code checks the SSRN to see that it is only digits and is greater than 99 and less than test_limit; the value in local variable test_limit will need to be updated periodically as more SSRNs are issued. ]] local function ssrn (options) local id = options.id; local handler = options.handler; local id_num; local text; id_num = id:match ('^%d+$'); -- id must be all digits if is_set (id_num) then -- id_num has a value so test it id_num = tonumber (id_num); -- convert id_num to a number for range testing if 100 > id_num or handler.id_limit < id_num then -- if SSRN is outside test limit boundaries set_message ('err_bad_ssrn'); -- set an error message options.coins_list_t['SSRN'] = nil; -- when error, unset so not included in COinS end else -- when id format incorrect set_message ('err_bad_ssrn'); -- set an error message options.coins_list_t['SSRN'] = nil; -- when error, unset so not included in COinS end text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode, access = options.access}); return text; end --[[--------------------------< U S E N E T _ 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 usenet_id (options) local id = options.id; local handler = options.handler; local text = external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, 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 '>' set_message ('err_bad_usenet_id') -- add an error message if the message id is invalid options.coins_list_t['USENETID'] = nil; -- when error, unset so not included in COinS end return text; end --[[--------------------------< Z B L >----------------------------------------------------------------------- A numerical identifier in the form nnnn.nnnnn - leading zeros in the first quartet optional format described here: http://emis.mi.sanu.ac.rs/ZMATH/zmath/en/help/search/ temporary format is apparently eight digits. Anything else is an error ]] local function zbl (options) local id = options.id; local handler = options.handler; if id:match('^%d%d%d%d%d%d%d%d$') then -- is this identifier using temporary format? set_message ('maint_zbl'); -- yes, add maint cat elseif not id:match('^%d?%d?%d?%d%.%d%d%d%d%d$') then -- not temporary, is it normal format? set_message ('err_bad_zbl'); -- no, set an error message options.coins_list_t['ZBL'] = nil; -- when error, unset so not included in COinS end return external_link_id ({link = handler.link, label = handler.label, q = handler.q, redirect = handler.redirect, prefix = handler.prefix, id = id, separator = handler.separator, encode = handler.encode}); end --============================<< I N T E R F A C E F U N C T I O N S >>========================================== --[[--------------------------< E X T R A C T _ I D S >------------------------------------------------------------ Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for any of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value to the identifier list. Emits redundant error message if more than one alias exists in args ]] local function extract_ids (args) local id_list = {}; -- list of identifiers found in args for k, v in pairs (cfg.id_handlers) do -- k is uppercase identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table v = select_one (args, v.parameters, 'err_redundant_parameters' ); -- v.parameters is a table of aliases for k; here we pick one from args if present if is_set (v) then id_list[k] = v; end -- if found in args, add identifier to our list end return id_list; end --[[--------------------------< E X T R A C T _ I D _ A C C E S S _ L E V E L S >-------------------------------------- Fetches custom id access levels from arguments using configuration settings. Parameters which have a predefined access level (e.g. arxiv) do not use this function as they are directly rendered as free without using an additional parameter. returns a table of k/v pairs where k is same as the identifier's key in cfg.id_handlers and v is the assigned (valid) keyword access-level values must match the case used in cfg.keywords_lists['id-access'] (lowercase unless there is some special reason for something else) ]] local function extract_id_access_levels (args, id_list) local id_accesses_list = {}; for k, v in pairs (cfg.id_handlers) do local access_param = v.custom_access; -- name of identifier's access-level parameter if is_set (access_param) then local access_level = args[access_param]; -- get the assigned value if there is one if is_set (access_level) then if not in_array (access_level, cfg.keywords_lists['id-access']) then -- exact match required set_message ('err_invalid_param_val', {access_param, access_level}); access_level = nil; -- invalid so unset end if not is_set (id_list[k]) then -- identifier access-level must have a matching identifier set_message ('err_param_access_requires_param', {k:lower()}); -- parameter name is uppercase in cfg.id_handlers (k); lowercase for error message end id_accesses_list[k] = cfg.keywords_xlate[access_level]; -- get translated keyword end end end return id_accesses_list; end --[[--------------------------< B U I L D _ I D _ L I S T >---------------------------------------------------- render the identifiers into a sorted sequence table <ID_list_coins_t> is a table of k/v pairs where k is same as key in cfg.id_handlers and v is the assigned value <options_t> is a table of various k/v option pairs provided in the call to new_build_id_list(); modified by this function and passed to all identifier rendering functions <access_levels_t> is a table of k/v pairs where k is same as key in cfg.id_handlers and v is the assigned value (if valid) returns a sequence table of sorted (by hkey - 'handler' key) rendered identifier strings ]] local function build_id_list (ID_list_coins_t, options_t, access_levels_t) local ID_list_t = {}; local accept; local func_map = { --function map points to functions associated with hkey identifier ['ARXIV'] = arxiv, ['ASIN'] = asin, ['BIBCODE'] = bibcode, ['BIORXIV'] = biorxiv, ['CITESEERX'] = citeseerx, ['DOI'] = doi, ['EISSN'] = issn, ['HDL'] = hdl, ['ISBN'] = isbn, ['ISMN'] = ismn, ['ISSN'] = issn, ['JFM'] = jfm, ['JSTOR'] = jstor, ['LCCN'] = lccn, ['MEDRXIV'] = medrxiv, ['MR'] = mr, ['OCLC'] = oclc, ['OL'] = openlibrary, ['OSTI'] = osti, ['PMC'] = pmc, ['PMID'] = pmid, ['RFC'] = rfc, ['S2CID'] = s2cid, ['SBN'] = sbn, ['SSRN'] = ssrn, ['USENETID'] = usenet_id, ['ZBL'] = zbl, } for hkey, v in pairs (ID_list_coins_t) do v, accept = has_accept_as_written (v); -- remove accept-as-written markup if present; accept is boolean true when markup removed; false else -- every function gets the options table with value v and accept boolean options_t.hkey = hkey; -- ~/Configuration handler key options_t.id = v; -- add that identifier value to the options table options_t.accept = accept; -- add the accept boolean flag options_t.access = access_levels_t[hkey]; -- add the access level for those that have an |<identifier-access= parameter options_t.handler = cfg.id_handlers[hkey]; options_t.coins_list_t = ID_list_coins_t; -- pointer to ID_list_coins_t; for |asin= and |ol=; also to keep erroneous values out of the citation's metadata options_t.coins_list_t[hkey] = v; -- id value without accept-as-written markup for metadata if options_t.handler.access and not in_array (options_t.handler.access, cfg.keywords_lists['id-access']) then error (cfg.messages['unknown_ID_access'] .. options_t.handler.access); -- here when handler access key set to a value not listed in list of allowed id access keywords end if func_map[hkey] then local id_text = func_map[hkey] (options_t); -- call the function to get identifier text and any error message table.insert (ID_list_t, {hkey, id_text}); -- add identifier text to the output sequence table else error (cfg.messages['unknown_ID_key'] .. hkey); -- here when func_map doesn't have a function for hkey end end local function comp (a, b) -- used by following table.sort() return a[1]:lower() < b[1]:lower(); -- sort by hkey end table.sort (ID_list_t, comp); -- sequence table of tables sort for k, v in ipairs (ID_list_t) do -- convert sequence table of tables to simple sequence table of strings ID_list_t[k] = v[2]; -- v[2] is the identifier rendering from the call to the various functions in func_map{} end return ID_list_t; end --[[--------------------------< O P T I O N S _ C H E C K >---------------------------------------------------- check that certain option parameters have their associated identifier parameters with values <ID_list_coins_t> is a table of k/v pairs where k is same as key in cfg.id_handlers and v is the assigned value <ID_support_t> is a sequence table of tables created in citation0() where each subtable has four elements: [1] is the support parameter's assigned value; empty string if not set [2] is a text string same as key in cfg.id_handlers [3] is cfg.error_conditions key used to create error message [4] is original ID support parameter name used to create error message returns nothing; on error emits an appropriate error message ]] local function options_check (ID_list_coins_t, ID_support_t) for _, v in ipairs (ID_support_t) do if is_set (v[1]) and not ID_list_coins_t[v[2]] then -- when support parameter has a value but matching identifier parameter is missing or empty set_message (v[3], (v[4])); -- emit the appropriate error message end end end --[[--------------------------< I D E N T I F I E R _ L I S T S _ G E T >-------------------------------------- Creates two identifier lists: a k/v table of identifiers and their values to be used locally and for use in the COinS metadata, and a sequence table of the rendered identifier strings that will be included in the rendered citation. ]] local function identifier_lists_get (args_t, options_t, ID_support_t) local ID_list_coins_t = extract_ids (args_t); -- get a table of identifiers and their values for use locally and for use in COinS options_check (ID_list_coins_t, ID_support_t); -- ID support parameters must have matching identifier parameters local ID_access_levels_t = extract_id_access_levels (args_t, ID_list_coins_t); -- get a table of identifier access levels local ID_list_t = build_id_list (ID_list_coins_t, options_t, ID_access_levels_t); -- get a sequence table of rendered identifier strings return ID_list_t, ID_list_coins_t; -- return the tables end --[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >-------------------------------------- Sets local cfg table and imported functions table to same (live or sandbox) as that used by the other modules. ]] local function set_selected_modules (cfg_table_ptr, utilities_page_ptr) cfg = cfg_table_ptr; has_accept_as_written = utilities_page_ptr.has_accept_as_written; -- import functions from select Module:Citation/CS1/Utilities module is_set = utilities_page_ptr.is_set; in_array = utilities_page_ptr.in_array; set_message = utilities_page_ptr.set_message; select_one = utilities_page_ptr.select_one; substitute = utilities_page_ptr.substitute; make_wikilink = utilities_page_ptr.make_wikilink; z = utilities_page_ptr.z; -- table of tables in Module:Citation/CS1/Utilities end --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ ]] return { auto_link_urls = auto_link_urls, -- table of identifier URLs to be used when auto-linking |title= identifier_lists_get = identifier_lists_get, -- experiment to replace individual calls to build_id_list(), extract_ids, extract_id_access_levels is_embargoed = is_embargoed; set_selected_modules = set_selected_modules; } e4jc9mw0kujge8fok9aztk214jmz0lr 828 659 9079 2026-05-15T07:24:38Z WikiBayer 737 [[:w:Special:PermanentLink/1285233596|Module:Citation/CS1/COinS]] 9079 Scribunto text/plain --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local has_accept_as_written, is_set, in_array, remove_wiki_link, strip_apostrophe_markup; -- functions in Module:Citation/CS1/Utilities local cfg; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration --[[--------------------------< 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 corrupted with strings of %27%27... ]] local function make_coins_title (title, script) title = has_accept_as_written (title); 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 --[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >---------------------------------- Returns a string where all of Lua's magic characters have been escaped. This is important because functions like string.gsub() treat their pattern and replace strings as patterns, not literal strings. ]] local function escape_lua_magic_chars (argument) argument = argument:gsub("%%", "%%%%"); -- replace % with %% argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other Lua magic pattern characters return argument; end --[[--------------------------< 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 (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like? pages = pages:gsub ('%b<>', ''); -- remove html-like tags; spans are added to <Pages> by utilities.hyphen_to_dash() which should not appear in COinS metadata return pages; end --[=[-------------------------< C O I N S _ R E P L A C E _ M A T H _ S T R I P M A R K E R >------------------ There are three options for math markup rendering that depend on the editor's math preference settings. These settings are at [[Special:Preferences#mw-prefsection-rendering]] and are PNG images TeX source MathML with SVG or PNG fallback All three are heavy with HTML and CSS which doesn't belong in the metadata. Without this function, the metadata saved in the raw wikitext contained the rendering determined by the settings of the last editor to save the page. This function gets the rendered form of an equation according to the editor's preference before the page is saved. It then searches the rendering for the text equivalent of the rendered equation and replaces the rendering with that so that the page is saved without extraneous HTML/CSS markup and with a reasonably readable text form of the equation. When a replacement is made, this function returns true and the value with replacement; otherwise false and the initial value. To replace multipe equations it is necessary to call this function from within a loop. ]=] local function coins_replace_math_stripmarker (value) local stripmarker = cfg.stripmarkers['math']; local rendering = value:match (stripmarker); -- is there a math stripmarker if not rendering then -- when value doesn't have a math stripmarker, abandon this test return false, value; end rendering = mw.text.unstripNoWiki (rendering); -- convert stripmarker into rendered value (or nil? ''? when math render error) if rendering:match ('alt="[^"]+"') then -- if PNG math option rendering = rendering:match ('alt="([^"]+)"'); -- extract just the math text elseif rendering:match ('$%s+.+%s+%$') then -- if TeX math option; $ is legit character that is escapes as \$ rendering = rendering:match ('$%s+(.+)%s+%$') -- extract just the math text elseif rendering:match ('<annotation[^>]+>.+</annotation>') then -- if MathML math option rendering = rendering:match ('<annotation[^>]+>(.+)</annotation>') -- extract just the math text else return false, value; -- had math stripmarker but not one of the three defined forms end return true, value:gsub (stripmarker, rendering, 1); end --[[--------------------------< C O I N S _ C L E A N U P >---------------------------------------------------- Cleanup parameter values for the metadata by removing or replacing invisible characters and certain HTML entities. 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaces math stripmarkers with the appropriate content when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible characters table? ]] local function coins_cleanup (value) local replaced = true; -- default state to get the do loop running while replaced do -- loop until all math stripmarkers replaced replaced, value = coins_replace_math_stripmarker (value); -- replace math stripmarker with text representation of the equation end value = value:gsub (cfg.stripmarkers['math'], "MATH RENDER ERROR"); -- one or more couldn't be replaced; insert vague error message value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">&#39;(s?)</span>', "'%1"); -- replace {{'}} or {{'s}} with simple apostrophe or apostrophe-s value = value:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with plain space value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space if not mw.ustring.find (value, cfg.indic_script) then -- don't remove zero-width joiner characters from indic script value = value:gsub ('&zwj;', ''); -- remove &zwj; entities value = mw.ustring.gsub (value, '[\226\128\141\226\128\139\194\173]', ''); -- remove zero-width joiner, zero-width space, soft hyphen end value = value:gsub ('[\009\010\013 ]+', ' '); -- replace horizontal tab, line feed, carriage return with plain space return value; end --[[--------------------------< C O I N S >-------------------------------------------------------------------- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information. ]] local function COinS(data, class) if 'table' ~= type(data) or nil == next(data) then return ''; end for k, v in pairs (data) do -- spin through all of the metadata parameter values if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) data[k] = coins_cleanup (v); end end local ctx_ver = "Z39.88-2004"; -- treat table strictly as an array with only set values. local OCinSoutput = setmetatable( {}, { __newindex = function(self, key, value) if is_set(value) then rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } ); end end }); if in_array (class, {'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn', 'journal', 'news', 'magazine'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or ('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier if in_array (class, {'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) then -- set genre according to the type of citation template we are rendering OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv, cite biorxiv, cite citeseerx, cite medrxiv, cite ssrn elseif 'conference' == class then OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set) elseif 'web' == class then OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set) else OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles end OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only OCinSoutput["rft.atitle"] = data.Title; -- 'periodical' article titles -- these used only for periodicals OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall OCinSoutput["rft.quarter"] = data.Quarter; -- single digits 1->first quarter, etc. OCinSoutput["rft.chron"] = data.Chron; -- free-form date components OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books OCinSoutput["rft.issue"] = data.Issue; OCinSoutput['rft.artnum'] = data.ArticleNumber; -- {{cite journal}} only OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier if 'report' == class or 'techreport' == class then -- cite report and cite techreport OCinSoutput["rft.genre"] = "report"; elseif 'conference' == class then -- cite conference when Periodical not set OCinSoutput["rft.genre"] = "conference"; OCinSoutput["rft.atitle"] = data.Chapter; -- conference paper as chapter in proceedings (book) elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then if is_set (data.Chapter) then OCinSoutput["rft.genre"] = "bookitem"; OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title else if 'map' == class or 'interview' == class then OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview else OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia end end else -- {'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'} OCinSoutput["rft.genre"] = "unknown"; end OCinSoutput["rft.btitle"] = data.Title; -- book only OCinSoutput["rft.place"] = data.PublicationPlace; -- book only OCinSoutput["rft.series"] = data.Series; -- book only OCinSoutput["rft.pages"] = data.Pages; -- book, journal OCinSoutput["rft.edition"] = data.Edition; -- book only OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation else -- cite thesis OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported) OCinSoutput["rft.degree"] = data.Degree; -- dissertation only OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation end -- NB. Not currently supported are "info:ofi/fmt:kev:mtx:patent", "info:ofi/fmt:kev:mtx:dc", "info:ofi/fmt:kev:mtx:sch_svc", "info:ofi/fmt:kev:mtx:ctx" -- and now common parameters (as much as possible) OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? if k == 'ISBN' then v = v:gsub( "[^-0-9X]", "" ); end local id = cfg.id_handlers[k].COinS; if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry OCinSoutput["rft_id"] = table.concat{ id, "/", v }; elseif string.sub (id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc. that have defined COinS keywords OCinSoutput[ id ] = v; elseif 'url' == id then -- for urls that are assembled in ~/Identifiers; |asin= and |ol= OCinSoutput["rft_id"] = table.concat ({data.ID_list[k], "#id-name=", cfg.id_handlers[k].label}); elseif id then -- when cfg.id_handlers[k].COinS is not nil so urls created here OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v, cfg.id_handlers[k].suffix or '', "#id-name=", cfg.id_handlers[k].label }; -- others; provide a URL and indicate identifier name as #fragment (human-readable, but transparent to browsers) end end local last, first; for k, v in ipairs( data.Authors ) do last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki stripmarkers, non-printing or invisible characters if k == 1 then -- for the first author name only if is_set(last) and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation elseif is_set(last) then OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name end else -- for all other authors if is_set(last) and is_set(first) then OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation elseif is_set(last) then OCinSoutput["rft.au"] = last; -- book, journal, dissertation end -- TODO: At present we do not report "et al.". Add anything special if this condition applies? end end OCinSoutput.rft_id = data.URL; OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage }; -- TODO: Add optional extra info: -- rfr_dat=#REVISION<version> (referrer private data) -- ctx_id=<data.RawPage>#<ref> (identifier for the context object) -- ctx_tim=<ts> (timestamp in format yyyy-mm-ddThh:mm:ssTZD or yyyy-mm-dd) -- ctx_enc=info:ofi/enc:UTF-8 (character encoding) 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 --[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >-------------------------------------- Sets local cfg table and imported functions table to same (live or sandbox) as that used by the other modules. ]] local function set_selected_modules (cfg_table_ptr, utilities_page_ptr) cfg = cfg_table_ptr; has_accept_as_written = utilities_page_ptr.has_accept_as_written; -- import functions from selected Module:Citation/CS1/Utilities module is_set = utilities_page_ptr.is_set; in_array = utilities_page_ptr.in_array; remove_wiki_link = utilities_page_ptr.remove_wiki_link; strip_apostrophe_markup = utilities_page_ptr.strip_apostrophe_markup; end --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ ]] return { make_coins_title = make_coins_title, get_coins_pages = get_coins_pages, COinS = COinS, set_selected_modules = set_selected_modules, } 2eba9cn0u4yseyeujt1vmrglxrgcllo 828 660 9080 2026-05-15T07:29:02Z WikiBayer 737 [[:w:Special:PermanentLink/1333433106|Module:Citation/CS1/styles.css]] 9080 sanitized-css text/css /* Protection icon the following line controls the page-protection icon in the upper right corner it must remain within this comment {{sandbox other||{{pp-template}}}} */ /* Overrides Some wikis do not override user agent default styles for HTML <cite> and <q>, unlike en.wp. On en.wp, keep these the same as [[MediaWiki:Common.css]]. The word-wrap and :target styles were moved here from Common.css. On en.wp, keep these the same as [[Template:Citation/styles.css]]. */ cite.citation { font-style: inherit; /* Remove italics for <cite> */ /* Break long urls, etc., rather than overflowing box */ word-wrap: break-word; } .citation q { quotes: '"' '"' "'" "'"; /* Straight quote marks for <q> */ } /* Highlight linked elements (such as clicked references) in blue */ .citation:target { /* ignore the linter - all browsers of interest implement this */ background-color: rgba(0, 127, 255, 0.133); } /* ID and URL access Both core and Common.css have selector .mw-parser-output a[href$=".pdf"].external for PDF pages. All TemplateStyles pages are hoisted to .mw-parser-output. We need to have specificity equal to a[href$=".pdf"].external for locks to override PDF icon. That's essentially 2 classes and 1 element. the .id-lock-... selectors are for use by non-citation templates like {{Catalog lookup link}} bg-size `contain` in Minerva and Timeless is too large, so we set a size for them and then exclude them later */ .id-lock-free.id-lock-free a { background: url(//upload.wikimedia.org/wikipedia/commons/6/65/Lock-green.svg) right 0.1em center/9px no-repeat; } .id-lock-limited.id-lock-limited a, .id-lock-registration.id-lock-registration a { background: url(//upload.wikimedia.org/wikipedia/commons/d/d6/Lock-gray-alt-2.svg) right 0.1em center/9px no-repeat; } .id-lock-subscription.id-lock-subscription a { background: url(//upload.wikimedia.org/wikipedia/commons/a/aa/Lock-red-alt-2.svg) right 0.1em center/9px no-repeat; } /* Wikisource Wikisource icon when |chapter= or |title= is wikilinked to Wikisource as in cite wikisource */ .cs1-ws-icon a { background: url(//upload.wikimedia.org/wikipedia/commons/4/4c/Wikisource-logo.svg) right 0.1em center/12px no-repeat; } body:not(.skin-timeless):not(.skin-minerva) .id-lock-free a, body:not(.skin-timeless):not(.skin-minerva) .id-lock-limited a, body:not(.skin-timeless):not(.skin-minerva) .id-lock-registration a, body:not(.skin-timeless):not(.skin-minerva) .id-lock-subscription a, body:not(.skin-timeless):not(.skin-minerva) .cs1-ws-icon a { background-size: contain; /* Common.css has a padding set for PDF URLs. bg-contain expands to the * size of the padding which makes the icons very large. we "reset" the * padding here. 1em picked out of a hat based on console having a similar * rule from elsewhere */ padding: 0 1em 0 0; } /* Errors and maintenance */ .cs1-code { /* <code>...</code> style override: mediawiki's css definition is specified here: https://git.wikimedia.org/blob/mediawiki%2Fcore.git/ 69cd73811f7aadd093050dbf20ed70ef0b42a713/skins%2Fcommon%2FcommonElements.css#L199 */ color: inherit; background: inherit; border: none; padding: inherit; } .cs1-hidden-error { display: none; color: var(--color-error, #bf3c2c); } .cs1-visible-error { color: var(--color-error, #bf3c2c); } .cs1-maint { display: none; color: #085; margin-left: 0.3em; } /* kerning */ .cs1-kern-left { padding-left: 0.2em; } .cs1-kern-right { padding-right: 0.2em; } /* selflinks – avoid bold font style when cs1|2 template links to the current page */ .citation .mw-selflink { font-weight: inherit; } @media screen { /* Small text size Set small text size in one place. 0.95 (here) * 0.9 (from references list) is ~0.85, which is the lower bound for size for accessibility. Old styling for this was just 0.85. We could write the rule so that when this template is inside references/reflist, only then does it multiply by 0.95; else multiply by 0.85 */ .cs1-format { font-size: 95%; } html.skin-theme-clientpref-night .cs1-maint { color: #18911f; } } @media screen and (prefers-color-scheme: dark) { html.skin-theme-clientpref-os .cs1-maint { color: #18911f; } } 2wrho6o1q12cvwhaslan5n9g140q3wl