--url= if |doi= and |doi-access=free are present; see WP:VPPRO#Auto-linking_titles_in_citations_of_works_with_free-to-read_DOIs2020-05-24: disable auto-linking for both PMC and DOI when a |title-link= is provided; see Help_talk:Citation_Style_1#Auto-linking_titles_with_free_DOIs2020-05-31: fix a typo and missing space in the documentation2020-06-02: tweak cite conference error messaging; see Help_talk:Citation_Style_1#Issues_with_"cite_conference"_template
----------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
local dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation date_name_xlate
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink, strip_apostrophe_markup;
local z =; -- tables in Module:Citation/CS1/Utilities
local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS
local cfg = ; -- table of configuration tables that are defined in Module:Citation/CS1/Configurationlocal whitelist = ; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
----------------------------< P A G E S C O P E V A R I A B L E S >--------------------------------------
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 oncelocal added_prop_cats = ; -- list of property categories that have been added to z.properties_catslocal added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category
local Frame; -- holds the module's frame table
----------------------------< 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 pairsversion the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminatethe for-loop before it reached the actual end of the list.
local function first_set (list, count) local i = 1; while i <= count do -- loop through all items in list if is_set(list[i]) then return list[i]; -- return the first set list member end i = i + 1; -- point to next endend
----------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languagesmay be categorized but multiples of the same language are not categorized.
added_prop_cats is a table declared in page scope variables above
local function add_prop_cat (key, arguments) if not added_prop_cats [key] then added_prop_cats [key] = true; -- note that we've added this category key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?[%a%-]*', '%1'); -- strip lang code from keyname table.insert(z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table endend
----------------------------< 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) if not added_vanc_errs then added_vanc_errs = true; -- note that we've added this category table.insert(z.message_tail,); endend
--
local function is_scheme (scheme) return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the patternend
--[=[-------------------------< 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
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Betweenthe first and last characters the name may use letters, digits, and the hyphen.
Also allowed are IPv4 addresses. IPv6 not supported
domain is expected to be stripped of any path so that the last character in the last character of the tld. tldis two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be strippedhere. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
There are several tests: the first character of the whole domain name including subdomains must be a letter or a digit internationalized domain name (ascii characters with .xn-- ASCII Compatible Encoding (ACE) 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 =
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 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 isend
----------------------------< I S _ U R L >------------------------------------------------------------------
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
This function is the last step in the validation process. This function is separate because there are cases thatare not covered by split_url, for example is_parameter_ext_wikilink which is looking for bracketted externalwikilinks.
local function is_url (scheme, domain) if is_set (scheme) then -- if scheme is set check it and domain return is_scheme (scheme) and is_domain_name (domain); else return is_domain_name (domain); -- scheme not set when url is protocol relative endend
----------------------------< 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 (oneor more '/' characters immediately following the scheme's colon), make sure that there are only 2.
Strip off any port and path;
local function split_url (url_str) local scheme, authority, domain; 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 authority = authority:gsub ('//', , 1); -- replace place 1 pair of '/' with nothing; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return scheme; -- return scheme only making domain nil which will cause an error message end domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present end return scheme, domain;end
--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|-link= parameter is ok); else false when value appears to be a valid url (the |-link= parameter is NOT ok).
local function link_param_ok (value) local scheme, domain; if value:find ('[<>%[%]|]') then -- if any prohibited characters return false; end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url; return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid urlend
---link= value and its matching |
|
local function link_title_ok (link, lorig, title, torig)local orig;
if is_set (link) then -- don't bother if -link doesn't have a value if not link_param_ok (link) then -- check |-link= markup orig = lorig; -- identify the failing link parameter elseif title:find ('%[%[') then -- check |title= for wikilink markup orig = torig; -- identify the failing |title= parameter end end if is_set (orig) then table.insert(z.message_tail, { set_error('bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=; end 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
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url; if 'news:'
--[=[-------------------------< 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 firstnon-space characters following the opening bracket appear to be a url. The test will also find external wikilinksthat use protocol relative urls. Also finds bare urls.
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests thatfind bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=//Husis possible as might be .
]=]
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+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain else 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 urlend
---------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
local function check_for_url (parameter_list)local error_message = ; for k, v in pairs (parameter_list) do -- for each parameter in the list if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message if is_set(error_message) then -- once we've added the first portion of the error message ... error_message=error_message .. ", "; -- ... add a comma space separator end error_message=error_message .. "|" .. k .. "="; -- add the failed parameter end end if is_set (error_message) then -- done looping, if there is an error message, display it table.insert(z.message_tail,); endend
----------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
Escape sequences for content that will be used for URL descriptions
local function safe_for_url(str) if str:match("%[%[.-%]%]") ~= nil then table.insert(z.message_tail,); end return str:gsub('[%[%]\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 error_str = ""; local domain; local path; local base_url;
if not is_set(label) then label = URL; if is_set(source) then error_str = set_error('bare_url_missing_title',, false, " "); else error(cfg.messages["bare_url_no_origin"]); end end if not check_url(URL) then error_str = set_error('bad_url',, false, " ") .. error_str; 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 ('[%[%]]',); -- replace '[' and ']' with their percent encoded values URL = table.concat ; -- and reassemble end
base_url = table.concat; -- assemble a wikimarkup url
if is_set (access) then -- access level (subscription, registration, limited) base_url = substitute (cfg.presentation['ext-link-access-signal'],); -- add the appropriate icon end return table.concat ;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 theoffending parameter name to the error message. Only one error message is emitted regardless of the number of deprecatedparameters 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 table.insert(z.message_tail,); -- add error message endend
--[=[-------------------------< K E R N _ Q U O T E S >-------------------------------------------------------- Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value. This function will positive kern either single or double quotes: "'Unkerned title with leading and trailing single quote marks'" " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example) Double single quotes (italic or bold wikimarkup) are not kerned. Replaces unicode quotemarks in plain text or in the label portion of a [[L|D]] style wikilink with typewriterquote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple D wikilinks.
Call this function for chapter titles, for website titles, etc; not for book titles.
]=]
local function kern_quotes (str) local cap=; local cap2=; local wl_type, label, link;
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, D; 2, D if 1
else -- plain text or D; text in label variable label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) label= mw.ustring.gsub (label, '[‘’]', '\); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) if is_set (cap) then label = substitute (cfg.presentation['kern-left'],); end cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) if is_set (cap) then label = substitute (cfg.presentation['kern-right'],); end if 2
--script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts shouldnot be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrappedin italic markup.
Regardless of language, all values provided by |script-title= are wrapped in ... 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 ISO639-1 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 ISO639-1 language code, the lang attribute (lang="ja") is added to the tag so that browsers canknow the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attributeis not added. At this time there is no error message for this condition.
Supports |script-title=, |script-chapter=, |script-
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 is_set (lang) then table.insert(z.message_tail,); -- 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_code_remap[lang] or mw.language.fetchLanguageName(lang, cfg.this_wiki_code); -- get language name so that we can use it to categorize if is_set (name) then -- is prefix a proper ISO 639-1 language code? script_value = script_value:gsub ('^%l+%s*:%s*', ); -- strip prefix from script -- is prefix one of these language codes? if in_array (lang, cfg.script_lang_codes) then add_prop_cat ('script_with_name',) else table.insert(z.message_tail,); -- unknown script-language; add error message end lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute else table.insert(z.message_tail,); -- invalid language code; add error message lang = ; -- invalid so set lang to empty string end else table.insert(z.message_tail,); -- no language code prefix; add error message end script_value = substitute (cfg.presentation['bdi'], ); -- isolate in case script is rtl
return script_value;end
--title= and |script-title=, this function concatenates those two parameter values after the script value has been wrapped in tags.
local function script_concatenate (title, script, script_param) if is_set (script) then script = format_script_value (script, script_param); -- tags, lang atribute, categorization, etc; returns empty string on error if 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_listconfiguration taking one argument. Supports lower case text for templates. Additional text takenfrom citation_config.messages - the reason this function is similar to but separate from wrap_style.
local function wrap_msg (key, str, lower) if not is_set(str) then return ""; end if true
--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 ;
wl_type, D, L = is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
if 0
wl_type then -- simple wikilink: str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace if is_set (str) then ws_url = table.concat ; ws_label = str; -- label for the url end elseif 2
return ws_url, ws_label, L or D; -- return proper url or nil and a label or nilend
--script-
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) local periodical_error = ;
if not is_set (periodical) then periodical = ; -- to be safe for concatenation else periodical = wrap_style ('italic-title', periodical); -- style end
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- tags, lang atribute, categorization, etc; must be done after title is wrapped
if is_set (trans_periodical) then trans_periodical = wrap_style ('trans-italic-title', trans_periodical); if is_set (periodical) then periodical = periodical .. ' ' .. trans_periodical; else -- here when trans-periodical without periodical or script-periodical periodical = trans_periodical; periodical_error = ' ' .. set_error ('trans_missing_title',); end end
return periodical .. periodical_error;end
--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, chapter_url, chapter_url_source, no_quotes, access) local chapter_error = ;
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 separaters with space characters chapter = ws_label; end
if not is_set (chapter) then chapter = ; -- to be safe for concatenation else if false
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- tags, lang atribute, categorization, etc; must be done after title is wrapped
if 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 .. ' ', '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 = substitute (cfg.presentation['interwiki-icon'],); end
if is_set (trans_chapter) then trans_chapter = wrap_style ('trans-quoted-title', trans_chapter); if is_set (chapter) then chapter = chapter .. ' ' .. trans_chapter; else -- here when trans_chapter without chapter or script-chapter chapter = trans_chapter; chapter_error = ' ' .. set_error ('trans_missing_title',); end end
return chapter .. chapter_error;end
----------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
This function searches a parameter's value for nonprintable or invisible characters. The search stops at thefirst match.
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 stripmarkerthat was detected along with its position (or, for multi-byte characters, the position of its first byte) in theparameter value.
local function has_invisible_chars (param, v) local position = ; -- position of invisible char or starting position of stripmarker local dummy; -- end of matching string; not used but required to hold end position when a capture is returned local capture; -- used by stripmarker detection to hold name of the stripmarker local i=1; local stripmarker, apostrophe; capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true if capture
while cfg.invisible_chars[i] do local char=cfg.invisible_chars[i][1] -- the character or group name local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern if position and (char
capture or 'math'
capture and in_array (param,)) then -- templatestyles stripmarker allowed in these parameters stripmarker = true; -- set a flag elseif true
char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker position = nil; -- unset else local err_msg; if capture then err_msg = capture .. ' ' .. char; else err_msg = char .. ' ' .. 'character'; end
table.insert(z.message_tail,); -- add error message return; -- and done with this parameter end end i=i+1; -- bump our index endend
----------------------------< 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 thatmultiple names can be transparently aliased to single internal variable.
local function argument_wrapper(args) local origin = ; return setmetatable;end
--
local function nowrap_date (date) local cap=; local cap2=;
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date); elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$"); date = substitute (cfg.presentation['nowrap2'],); end return date;end
--type=
local function set_titletype (cite_class, title_type) if is_set (title_type) then if 'none'
return cfg.title_types [cite_class] or ; -- set template's default title type; else empty string for concatenationend
--
local function hyphen_to_dash(str) if not is_set (str) then return str; end str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str if 0 ~= count then -- non-zero when markup removed; zero else return str; -- nothing to do, we're done end str = str:gsub ('&[nm]dash;',); -- replace - and - entities with their characters; semicolon mucks up the text.split str = str:gsub ('-', '-'); -- replace html numeric entity with hyphen character str = str:gsub (' ', ' '); -- replace 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
for _, item in ipairs (list) do -- for each item in the list if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter) item:match ('^%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+$') or -- digit separator digit hyphen digit separator digit item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters else item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space end end item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup table.insert (out, item); -- add the (possibly modified) item to the output table end
return table.concat (out, ', '); -- concatenate the output table into a comma separated stringend
----------------------------< 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 'dupicate character' if 1
local str = ; -- the output string local comp = ; -- what does 'comp' mean? local end_chr = ; local trim; for _, value in ipairs(tbl) do if value
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)
duplicate_char then -- if same as separator str = f.sub(str, 1,-2); -- remove it elseif end_chr
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 four chars of str are sepc] trim = true; -- same question end elseif end_chr
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 two chars of str are sepc] external link trim = true; elseif f.sub(str, -4,-1)
" " then -- if last char of output string is a space if f.sub(str, -2,-1)
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 is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
local function is_suffix (suffix) if in_array (suffix,) or suffix:match ('^%dth$') then return true; end return false;end
--first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets C0 Controls and Basic Latin 0041–005A, 0061–007A C1 Controls and Latin-1 Supplement 00C0–00D6, 00D8–00F6, 00F8–00FF Latin Extended-A 0100–017F 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 (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") thenwas written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessaryto use an external editor to maintain this code.
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls) \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B) \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
local function is_good_vanc_name (last, first, suffix) if not suffix then if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix first = first:match ('(.-)[,%s]+'); -- get name/initials suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix end end if is_set (suffix) then if not is_suffix (suffix) then add_vanc_error (cfg.err_msg_supl.suffix); return false; -- not a name with an appropriate suffix end end if nil
mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then add_vanc_error (cfg.err_msg_supl['non-Latin char']); return false; -- not a string of latin characters; Vancouver requires Romanization end; return true;end
--name-list-format=vanc.
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name .
local function reduce_to_initials(first) local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
if not name then -- if not initials and a suffix name = mw.ustring.match(first, "^(%u+)$"); -- is it just intials? end
if name then -- if first is initials with or without suffix if 3 > mw.ustring.len (name) then -- if one or two initials if suffix then -- if there is a suffix if is_suffix (suffix) then -- is it legitimate? return first; -- one or two initials and a valid suffix so nothing to do else add_vanc_error (cfg.err_msg_supl.suffix); -- one or two initials with invalid suffix so error message return first; -- and return first unmolested end else return first; -- one or two initials without suffix; nothing to do end end end -- if here then name has 3 or more uppercase letters so treat them as a word
local initials, names =, ; -- tables to hold name parts and initials local i = 1; -- counter for number of initials
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
while names[i] do -- loop through the table if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot) names[i] = names[i]:gsub ('%.', ); -- remove terminal dot if present if is_suffix (names[i]) then -- if a legitimate suffix table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table break; -- and done because suffix must fall at the end of a name end -- no error message if not a suffix; possibly because of Romanization end if 3 > i then table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table end i = i+1; -- bump the counter end return table.concat(initials) -- Vancouver format does not include spaces.end
----------------------------< L I S T _ P E O P L E >-------------------------------------------------------
Formats a list of people (e.g. authors / editors)
local function list_people(control, people, etal) local sep; local namesep; local format = control.format local maximum = control.maximum local lastauthoramp = control.lastauthoramp; local text =
if 'vanc'
format) then -- if vancouver format one = one:gsub ('%.', ); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested first = reduce_to_initials(first) -- attempt to convert first name(s) to initials end end one = one .. namesep .. first; end end if is_set (person.link) then one = make_wikilink (person.link, one); -- link author/editor end table.insert (text, one) table.insert (text, sep_one) end end
local count = #text / 2; -- (number of names + number of separators) divided by 2 if count > 0 then if count > 1 and is_set(lastauthoramp) and not etal then text[#text-2] = " & "; -- replace last separator with ampersand text end text[#text] = nil; -- erase the last separator end local result = table.concat(text) -- construct list if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al. end return result, countend
----------------------------< A N C H O R _ I D >------------------------------------------------------------
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
local function anchor_id (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
--display-
local function name_has_etal (name, etal, nocat, param)
if 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-
return name, etal; -- end
--last=A. Green (1922-1987) does not get caught in the current version of this test but |first=(1888) is caught.
returns nothing
local function name_is_numeric (name, list_name) if is_set (name) then if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters add_maint_cat ('numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template end endend
--
local function name_has_ed_markup (name, list_name) local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
if is_set (name) then for _, pattern in ipairs (patterns) do -- spin through patterns table and if name:match (pattern) then add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template break; end end endend
----------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names areindicated if there is more than one comma and or semicolon. If found, the function adds the multiple name(author or editor) maintenance category.
returns nothing
local function name_has_mult_names (name, list_name) local _, count; if is_set (name) then _, count = name:gsub ('[;,]', ); -- count the number of separator-like characters if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template end endend
----------------------------< N A M E _ C H E C K S >--------------------------------------------------------
This function calls various name checking functions used to validate the content of the various name-holdingparameters.
local function name_checks (last, first, list_name) if is_set (last) then if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written last = last:match ('^%(%((.*)%)%)$'); -- strip parens else name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation name_is_numeric (last, list_name); -- check for names that are compsed of digits and punctuation end end if is_set (first) then if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written first = first:match ('^%(%((.*)%)%)$'); -- strip parens else name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation name_is_numeric (first, list_name); -- check for names that are compsed of digits and punctuation end end return last, first; -- done end
--lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn'tfind |last4= and |last5= then the search is done.
This 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) returnedthat will cause list_people to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the template's metadata. When this occurs, the page is added to a maintenance category.
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 = select_one(args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i); -- search through args for name components beginning at 1 first, first_alias = select_one(args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i); link, link_alias = select_one(args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i); mask = select_one(args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i);
last, etal = name_has_etal (last, etal, false, 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); -- multiple names, extraneous annotation, etc checks if first and not last then -- if there is a firstn without a matching lastn table.insert(z.message_tail,); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1; -- number of times we haven't found last and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there is a two-name hole in the list; can't tell which end else -- we have last with or without a first link_title_ok (link, link_alias, last, last_alias); -- check for improper wikimarkup if first then link_title_ok (link, link_alias, first, first_alias); -- check for improper wikimarkup end
names[n] = ; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1
--language= parameter if not an ISO639-1 or 639-2 code.
Returns the language name and associated two- or three-character code. Because case of the source may be incorrector different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match isfound, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, wereturn the original language name string.
mw.language.fetchLanguageNames(
Names that are included in the list will be found if that name is provided in the |language= parameter. For example,if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are foundand the associated code is not two or three characters, this function returns only the WikiMedia language name.
Some language names have multiple entries under different codes: Aromanian has code rup and code roa-rupWhen this occurs, this function returns the language name and the 2- or 3-character code
Adapted from code taken from Module:Check ISO 639-1.
local function get_iso639_code (lang, this_wiki_code) if cfg.lang_name_remap[lang:lower] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct) return cfg.lang_name_remap[lang:lower][1], cfg.lang_name_remap[lang:lower][2]; -- for this language 'name', return a possibly new name and appropriate code end
local ietf_code; -- because some languages have both ietf-like codes and iso 639-like codes local ietf_name; local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia -- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language if langlc
code:len or 3
--language= contains a recognized language (either code or name), the page is assigned to the category forthat code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assignedto the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources.
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-characterequivalents of two-character codes: code 'ar' is recognized but code 'ara' is not.
This function supports multiple languages in the form |language=nb, French, th where the language names or codes areseparated from each other by commas with optional space characters.
local function language_parameter (lang) local code; -- the two- or three-character language code local name; -- the language name local language_list = ; -- table of language names to be rendered local names_table = ; -- table made from the value assigned to |language=
local this_wiki_name = mw.language.fetchLanguageName(cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
for _, lang in ipairs (names_table) do -- reuse lang name = cfg.lang_code_remap[lang:lower]; -- first see if this is a code that is not supported by MediaWiki but is in remap
if name then -- there was a remapped code so if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private ietf tag lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietf tags from code end else lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any ietf-like tags from code if 2
lang:len then -- if two-or three-character code name = mw.language.fetchLanguageName (lang:lower, cfg.this_wiki_code); -- get language name if |language= is a proper code end end
if is_set (name) then -- if |language= specified a valid code code = lang:lower; -- save it else name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) end if is_set (code) then -- only 2- or 3-character codes name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language if 2
name then return ; -- if one language and that language is this wiki's return an empty string (no annotation) end return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' --end
--
local function set_cs1_style (ps) if not is_set (ps) then -- unless explicitly set to something ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation end return cfg.presentation['sep_cs1'], ps; -- element separatorend
--
local function set_cs2_style (ps, ref) if not is_set (ps) then -- if |postscript= has not been set, set cs2 default ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation end if not is_set (ref) then -- if |ref= is not set ref = "harv"; -- set default |ref=harv end return cfg.presentation['sep_cs2'], ps, ref; -- element separatorend
--mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establishrendered style.
local function get_settings_from_cite_class (ps, ref, cite_class) local sep; if (cite_class
return sep, ps, ref -- return them allend
--mode= if set and valid or usesconfig.CitationClass from the template's #invoke: to establish style.
local function set_style (mode, ps, ref, cite_class) local sep; if 'cs2'
mode then -- if this template is to be rendered in CS1 (cite xxx) style sep, ps = set_cs1_style (ps); else -- anything but cs1 or cs2 sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass end
if cfg.keywords_xlate[ps:lower]
--[=[-------------------------< 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]] whenapplying 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#') or url:match ('%.pdf#');end
--format=, |chapter-format=, etc. Also emits an error message if the format parameter doesnot have a matching url parameter. If the format parameter is not set and the url contains a file extension thatis recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) withthe appropriate styling.
local function style_format (format, url, fmt_param, url_param) if is_set (format) then format = wrap_style ('format', format); -- add leading space, parentheses, resize if not is_set (url) then format = format .. set_error('format_missing_url',); -- add an error message end elseif is_pdf (url) then -- format is not set so if url is a pdf file then format = wrap_style ('format', 'PDF'); -- set format to pdf else format = ; -- empty string for concatenation end return format;end
--display-xxxxors= is a number greater than or equal to zero, return the number andthe previous state of the 'etal' flag (false by default but may have been set to true if the name list containssome variant of the text 'et al.').
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than thenumber of authors in the list and set the 'etal' flag true. This will cause the list_people to display all ofthe names in the name list followed by 'et al.'
In all other cases, returns nil and the previous state of the 'etal' flag.
inputs: max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal count: #a or #e list_name: 'authors' or 'editors' etal: author_etal or editor_etal
local function get_display_names (max, count, list_name, etal) if is_set (max) then if 'etal'
--page= or |pages= has what appears to be some form of p. or pp. abbreviation in the first characters of the parameter content.
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
local function extra_text_in_page_check (page) local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg? local bad_pattern = '^[Pp]?[Pp]%.?[%d]';
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then add_maint_cat ('extra_text'); endend
--[=[-------------------------< 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 parnetheses 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 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 place holder local i = 1; while name_table[i] do if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens local name = name_table[i]; i=i+1; -- bump indexer to next segment while name_table[i] do name = name .. ', ' .. name_table[i]; -- concatenate with previous segments if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens break; -- and done reassembling so end i=i+1; -- bump indexer end table.insert (output_table, name); -- and add corporate name to the output table table.insert (output_link_table, ); -- no wikilink else wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, D; 2, D table.insert (output_table, label); -- add this name if 1
--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 namesmay sometimes be required and because such names will often fail the is_good_vanc_name and other format compliancetests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
local function parse_vauthors_veditors (args, vparam, list_name) local names = ; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = ; local 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 if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses corporate = true; -- flag used in list_people elseif string.find(v_name, "%s") then if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; add_vanc_error (cfg.err_msg_supl.punctuation); end local lastfirstTable = lastfirstTable = mw.text.split(v_name, "%s+") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be intials or generational suffix
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-latin characters suffix = first; -- not initials so assume that whatever we got is a generational suffix first = table.remove(lastfirstTable); -- get what should be the initials from the table end last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix if not is_set (last) then first = ; -- unset last = v_name; -- last empty because something wrong with first add_vanc_error (cfg.err_msg_supl.name); end if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then add_vanc_error (cfg.err_msg_supl['missing comma']); -- matches last II last; the case when a comma is missing end if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test add_vanc_error (cfg.err_msg_supl.name); -- matches a space between two intiials end else last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end if is_set (first) then if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else add_vanc_error (cfg.err_msg_supl.initials); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials end is_good_vanc_name (last, first, suffix); -- check first and last before restoring the suffix which may have a non-Latin digit if is_set (suffix) then first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials suffix = ; -- unset so we don't add this suffix to all subsequent names end else if not corporate then is_good_vanc_name (last, ); end end
link = select_one(args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i) or v_link_table[i]; mask = select_one(args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i); names[i] = ; -- add this assembled name to our names list end return names, etal; -- all done, return our list of namesend
--authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list orselect one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest andsimilarly, |editorn= (and aliases) highest and |editors= lowest
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the secondtest which mimicks the test used in extract_names when looking for a hole in the author name list. There may be a betterway to do this, I just haven't discovered what that way is.
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) local lastfirst = false; if select_one(args, cfg.aliases[list_name .. '-Last'], 'none', 1) or -- do this twice incase we have a |first1= without a |last1=; this ... select_one(args, cfg.aliases[list_name .. '-First'], 'none', 1) or -- ... also catches the case where |first= is used with |vauthors= select_one(args, cfg.aliases[list_name .. '-Last'], 'none', 2) or select_one(args, cfg.aliases[list_name .. '-First'], 'none', 2) then lastfirst=true; end
if (is_set (vxxxxors) and true
lastfirst and is_set (xxxxors)) then local err_name; if 'AuthorList'
if true
----------------------------< 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 numberof allowable values (yes, y, true, live, dead, etc). When the parameter value has not been assigned a value (missingor empty in the source template) the function returns the value specified by ret_val. If the parameter value is oneof the list of allowed values returns the translated value; else, emits an error message and returns the valuespecified by ret_val.
local function is_valid_parameter_value (value, name, possible, ret_val) if not is_set (value) then return ret_val; -- an empty parameter is ok elseif in_array (value, possible) then return cfg.keywords_xlate[value]; -- return translation of parameter keyword else table.insert(z.message_tail,); -- not an allowed value so add error message return ret_val; endend
----------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a spacewhen the last character is not a sepc character or when the last three characters are not sepc followed by twoclosing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with asingle space character.
local function terminate_name_list (name_list, sepc) if (string.sub (name_list,-3,-1)
sepc) or (string.sub (name_list,-3,-1)
---------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volumeor formatted issue, or an empty string if neither are set.
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) if not is_set (volume) and not is_set (issue) then return ; end if 'magazine'origin) then if is_set (volume) and is_set (issue) then return wrap_msg ('vol-no',, lower); elseif is_set (volume) then return wrap_msg ('vol',, lower); else return wrap_msg ('issue',, lower); end end
if 'podcast'
local vol = ; -- here for all cites except magazine if is_set (volume) then if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals vol = substitute (cfg.presentation['vol-bold'],); -- render in bold face elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters vol = substitute (cfg.messages['j-vol'],); -- not bold add_prop_cat ('long_vol'); else -- four or less characters vol = substitute (cfg.presentation['vol-bold'],); -- bold end end if is_set (issue) then return vol .. substitute (cfg.messages['j-issue'], issue); end return vol;end
--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'
origin then return , , wrap_msg ('j-sheet', sheet, lower), ; else return , , wrap_msg ('sheet',, lower), ; end elseif is_set (sheets) then if 'journal'
local is_journal = 'journal'
origin); if is_set (page) then if is_journal then return substitute (cfg.messages['j-page(s)'], page), , , ; elseif not nopp then return substitute (cfg.messages['p-prefix'],), , , ; else return substitute (cfg.messages['nopp'],), , , ; end elseif is_set(pages) then if is_journal then return substitute (cfg.messages['j-page(s)'], pages), , , ; elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number return , substitute (cfg.messages['p-prefix'],), , ; elseif not nopp then return , substitute (cfg.messages['pp-prefix'],), , ; else return , substitute (cfg.messages['nopp'],), , ; end end return , , , ; -- return empty stringsend
--
local function insource_loc_get (page, pages, at) local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
if is_set (page) then if is_set (pages) or is_set(at) then pages = ; -- unset the others at = ; end extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label if ws_url then page = external_link (ws_url, ws_label .. ' ', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? page = substitute (cfg.presentation['interwiki-icon'],); coins_pages = ws_label; end elseif is_set (pages) then if is_set (at) then at = ; -- unset end extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label if ws_url then pages = external_link (ws_url, ws_label .. ' ', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? pages = substitute (cfg.presentation['interwiki-icon'],); coins_pages = ws_label; end elseif is_set (at) then ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label if ws_url then at = external_link (ws_url, ws_label .. ' ', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? at = substitute (cfg.presentation['interwiki-icon'],); coins_pages = ws_label; end end return page, pages, at, coins_pages;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 placeotherwise returns |archive-url= and |archive-date=
There are two mostly compatible archive.org urls: //web.archive.org/
The old form does not support or map to the new form when it contains a display flag. There are four identified flags('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)we don't check for these specific flags but we do check the form.
This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modifiedarchive url: for save command errors, return undated wildcard (/*/) for timestamp errors when the timestamp has a wildcard, return the url unmodified for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
]=]
local function archive_url_check (url, date) local err_msg = ; -- start with the error message empty local path, timestamp, flag; -- portions of the archive.or url if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate end
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page err_msg = 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 is_set(timestamp) or 14 ~= timestamp:len then -- path and flag optional, must have 14-digit timestamp here err_msg = cfg.err_msg_supl.timestamp; if '*' ~= flag then url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat) end elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element err_msg = cfg.err_msg_supl.path; elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element) err_msg = cfg.err_msg_supl.flag; elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element) err_msg = cfg.err_msg_supl.flag; else return url, date; -- return ArchiveURL and ArchiveDate end end -- if here, something not right so table.insert(z.message_tail,); -- add error message and if is_set (Frame:preprocess('')) then return , ; -- return empty strings for ArchiveURL and ArchiveDate else return url, date; -- preview mode so return ArchiveURL and ArchiveDate endend
--place=, |publication-place=, |location= to see if these params include digits. This function added becausemany editors mis-use 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 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 add_maint_cat ('location'); -- yep, add maint cat end return param_val; -- and doneend
----------------------------< 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 Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], );
local author_etal; local a = ; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authors;
local NameListFormat = is_valid_parameter_value (A['NameListFormat'], A:ORIGIN('NameListFormat'), cfg.keywords_lists['name-list-format'], ); 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 NameListFormat = 'vanc'; -- override whatever |name-list-format= might be a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= elseif 3
A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors= add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO: end end if is_set (Collaboration) then author_etal = true; -- so that |display-authors=etal not required end end
local Others = A['Others'];
local editor_etal; local e = ; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= local Editors;
do -- to limit scope of selected local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList'); if 1
selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might be e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= elseif 3
local translator_etal; local t = ; -- translators list from |translator-lastn= / translator-firstn= pairs local Translators; -- assembled translators name list t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
local interviewer_etal; local interviewers_list = ; local Interviewers; -- used later interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
local contributor_etal; local c = ; -- contributors list from |contributor-lastn= / contributor-firstn= pairs local Contributors; -- assembled contributors name list
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases local Chapter_origin = A:ORIGIN ('Chapter'); local Contribution; -- because contribution is required for contributor(s) if 'contribution'
if in_array(config.CitationClass,) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= if 0 < #c then if not is_set (Contribution) then -- |contributor= requires |contribution= table.insert(z.message_tail,); -- add missing contribution error message c = ; -- blank the contributors' table; it is used as a flag later end if 0
if is_set (Others) then if 0
#e then -- add maint cat when |others= has value and used without |author=, |editor= add_maint_cat ('others'); end end
local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- Get title data local Title = A['Title']; local ScriptTitle = A['ScriptTitle']; local BookTitle = A['BookTitle']; local Conference = A['Conference']; local TransTitle = A['TransTitle']; local TransTitle_origin = A:ORIGIN ('TransTitle'); local TitleNote = A['TitleNote']; local TitleLink = A['TitleLink']; link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
local Section = ; -- only; preset to empty string for concatnation if not used if 'map'
A:ORIGIN ('Chapter') then Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in Chapter = ; -- unset for now; will be reset later from |map= if present end
local ScriptChapter = A['ScriptChapter']; local ScriptChapter_origin = A:ORIGIN ('ScriptChapter'); local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode local TransChapter = A['TransChapter']; local TransChapter_origin = A:ORIGIN ('TransChapter'); local TitleType = A['TitleType']; local Degree = A['Degree']; local Docket = A['Docket']; local ArchiveFormat = A['ArchiveFormat'];
local ArchiveDate; local ArchiveURL;
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], );
local URL = A['URL'] local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical']; local Periodical_origin = ; if is_set (Periodical) then Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter local i; Periodical, i = strip_apostrophe_markup (Periodical); -- strip appostrophe markup so that metadata isn't contaminated if i then -- non-zero when markup was stripped so emit an error message table.insert(z.message_tail,); end end
if 'mailinglist'
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is Periodical_origin = A:ORIGIN('MailingList'); end
local ScriptPeriodical = A['ScriptPeriodical']; local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); -- 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 (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter -- local p = ; -- for error message local p = ; -- for error message if p[config.CitationClass] then table.insert(z.message_tail,); end end
local TransPeriodical = A['TransPeriodical']; local TransPeriodical_origin = A:ORIGIN ('TransPeriodical');
local Series = A['Series']; local Volume; local Issue; local Page; local Pages; local At;
if 'citation'
if 'citation'
local Position = ; if not in_array (config.CitationClass, cfg.templates_not_using_page) then Page = A['Page']; Pages = hyphen_to_dash (A['Pages']); At = A['At']; end
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 is_set (PublisherName) then local i=0; PublisherName, i = strip_apostrophe_markup (PublisherName); -- strip appostrophe markup so that metadata isn't contaminated; publisher is never italicized
if i then -- non-zero when markup was stripped so emit an error message table.insert(z.message_tail,); end end
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup? local Newsgroup_origin = A:ORIGIN('Newsgroup');
if 'newsgroup'
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS end
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); if not is_set(URL) and is_set(UrlAccess) then UrlAccess = nil; table.insert(z.message_tail,); end local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then ChapterUrlAccess = nil; table.insert(z.message_tail,); end
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil); if not is_set(A['MapURL']) and is_set(MapUrlAccess) then MapUrlAccess = nil; table.insert(z.message_tail,); end
local Via = A['Via']; local AccessDate = A['AccessDate']; local Agency = A['Agency'];
local Language = A['Language']; local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local DoiBroken = A['DoiBroken']; local ID = A['ID']; local ASINTLD = A['ASINTLD']; local IgnoreISBN = is_valid_parameter_value (A['IgnoreISBN'], A:ORIGIN('IgnoreISBN'), cfg.keywords_lists['yes_true_y'], nil); local Embargo = A['Embargo']; local Class = A['Class']; -- arxiv class identifier
local ID_list = extract_ids(args); if is_set (DoiBroken) and not ID_list['DOI'] then table.insert(z.message_tail,); end local ID_access_levels = extract_id_access_levels(args, ID_list);
local Quote = A['Quote'];
local LayFormat = A['LayFormat']; local LayURL = A['LayURL']; local LaySource = A['LaySource']; local Transcript = A['Transcript']; local TranscriptFormat = A['TranscriptFormat']; local TranscriptURL = A['TranscriptURL'] local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
local LastAuthorAmp = is_valid_parameter_value (A['LastAuthorAmp'], A:ORIGIN('LastAuthorAmp'), cfg.keywords_lists['yes_true_y'], nil);
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
--local variables that are not cs1 parameters local use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.getCurrentTitle; -- also used for COinS and for language local anchor_year; -- used in the CITEREF identifier local COinS_date = ; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], ); if not is_set (DF) then DF = cfg.global_df; -- local df if present overrides global df set by template end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma local PostScript; local Ref = A['Ref']; if 'harv'
','); -- used to control capitalization for certain static text
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page if in_array (this_page.nsText, cfg.uncategorized_namespaces) then no_tracking_cats = "true"; -- set no_tracking_cats end for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end end -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) select_one (args,, '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, Pages, At);
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
if is_set (PublicationPlace) and is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together if PublicationPlace
if PublicationPlace
|trans-title maps to |trans-chapter when |title is re-mapped |url maps to |chapterurl when |title is remapped All other combinations of |encyclopedia, |title, and |article are not modified
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
if is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than Encyclopedia: or if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then table.insert (z.message_tail,); Encyclopedia = nil; -- unset because not supported by this template end end
if ('encyclopaedia'
config.CitationClass and is_set (Encyclopedia)) then if is_set (Periodical) and is_set (Encyclopedia) then -- when both set emit an error table.insert (z.message_tail,); end
if is_set (Encyclopedia) then Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia Periodical_origin = A:ORIGIN ('Encyclopedia'); end
if is_set (Periodical) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then if not is_set(Chapter) then Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title ScriptChapter = ScriptTitle; ScriptChapter_origin = A:ORIGIN('ScriptTitle') TransChapter = TransTitle; ChapterURL = URL; ChapterURL_origin = A:ORIGIN('URL')
ChapterUrlAccess = UrlAccess;
if not is_set (ChapterURL) and is_set (TitleLink) then Chapter = make_wikilink (TitleLink, Chapter); end Title = Periodical; ChapterFormat = Format; Periodical = ; -- redundant so unset TransTitle = ; URL = ; Format = ; TitleLink = ; ScriptTitle = ; end elseif is_set (Chapter) then -- |title not set Title = Periodical; -- |encyclopedia set and |article set so map |encyclopedia to |title Periodical = ; -- redundant so unset end end end
-- Special case for cite techreport. if (config.CitationClass
-- Account for the oddity that is, before generation of COinS data. if 'conference'
-- cite map oddities local Cartography = ""; local Scale = ""; local Sheet = A['Sheet'] or ; local Sheets = A['Sheets'] or ; if config.CitationClass
ChapterUrlAccess = MapUrlAccess; ChapterFormat = A['MapFormat'];
Cartography = A['Cartography']; if is_set(Cartography) then Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); end Scale = A['Scale']; if is_set(Scale) then Scale = sepc .. " " .. Scale; end end
-- Account for the oddities that are and, before generation of COinS data. if 'episode'
config.CitationClass then local SeriesLink = A['SeriesLink'];
link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
local Network = A['Network']; local Station = A['Station']; local s, n =, ; -- do common parameters first if is_set(Network) then table.insert(n, Network); end if is_set(Station) then table.insert(n, Station); end ID = table.concat(n, sepc .. ' '); if 'episode'
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set table.insert(z.message_tail,); -- add error message SeriesNumber = ; -- unset; prefer |season= over |seriesno= end -- assemble a table of parts concatenated later into Series if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ScriptChapter_origin = A:ORIGIN('ScriptTitle'); ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterUrlAccess = UrlAccess; ChapterURL_origin = A:ORIGIN('URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = make_wikilink (ChapterLink, Chapter); elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; Series = make_wikilink (ChapterLink, Series); end URL = ; -- unset TransTitle = ; ScriptTitle = ; else -- now oddities that are cite serial Issue = ; -- unset because this parameter no longer supported by the citation/core version of cite serial Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? if is_set (Series) and is_set (SeriesLink) then Series = make_wikilink (SeriesLink, Series); end Series = wrap_style ('italic-title', Series); -- series is italicized end end -- end of stuff
-- Account for the oddities that are,,,, before generation of COinS data. do if in_array (config.CitationClass, whitelist.preprint_template_list) then if not is_set (ID_list[config.CitationClass:upper]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates table.insert(z.message_tail,); -- add error message end
Periodical = [config.CitationClass]; end end
-- handle type parameter for those CS1 citations that have default values if in_array(config.CitationClass,) then TitleType = set_titletype (config.CitationClass, TitleType); if is_set(Degree) and "Thesis"
if is_set(TitleType) then -- if type parameter is specified TitleType = substitute(cfg.messages['type'], TitleType); -- display it in parentheses -- TODO: Hack on TitleType to fix bunched parentheses problem end
-- legacy: promote PublicationDate to Date if neither Date nor Year are set. local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
if not is_set (Date) then Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set Date = PublicationDate; -- promote PublicationDate to Date PublicationDate = ; -- unset, no longer needed 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
-- 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 = ; anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
-- start temporary Julian / Gregorian calendar uncertainty categorization if COinS_date.inter_cal_cat then add_prop_cat ('jul_greg_uncertainty'); end-- end temporary Julian / Gregorian calendar uncertainty categorization
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; local mismatch = year_date_check (Year, Date) if 0
mismatch then -- |year= matches year-value in |date= add_maint_cat ('date_year'); end end if not is_set(error_message) then -- error free dates only local modified = false; -- flag if is_set (DF) then -- if we need to reformat dates modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate end
if true
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; LayDate = date_parameters_list['lay-date'].val; PublicationDate = date_parameters_list['publication-date'].val; end else table.insert(z.message_tail,); -- add this error message end end -- end of do
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free -- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date Embargo = is_embargoed (Embargo); if config.CitationClass
"free" then URL=cfg.id_handlers['DOI'].prefix .. ID_list['DOI']; URL_origin = cfg.id_handlers['DOI'].parameters[1]; end if is_set(URL) and is_set(AccessDate) then -- access date requires |url=; pmc or doi created url is not |url= table.insert(z.message_tail,); AccessDate = ; -- unset end end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not is_set(Title) and not is_set(TransTitle) and not is_set(ScriptTitle) then -- has special case for cite episode table.insert(z.message_tail,); end
if cfg.keywords_xlate[Title]
Periodical_origin or 'script-journal'
check_for_url ;
-- COinS metadata (see
config.CitationClass and is_set (Encyclopedia)) then if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then coins_chapter = Title; -- remap coins_title = Periodical; end end local coins_author = a; -- default for coins rft.au if 0 < #c then -- but if contributor list coins_author = c; -- use that instead end -- this is the function call to COinS local OCinSoutput = COinS(config.CitationClass);
-- Account for the oddities that are,,, and AFTER generation of COinS data. if in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, 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'
-- Now perform various field substitutions. -- We also add leading spaces and surrounding markup and punctuation to the -- various parts of the citation, but only when they are non-nil. local EditorCount; -- used only for choosing