Content deleted Content added
m bump pmid; |
change line 1754 parameter to true to hide ISBN/ date compatibility issues. See Help talk:Citation Style 1#ISBN / Date incompatibility and Wikipedia:Administrators' noticeboard/Incidents#Template edit incorrectly creating error cat with 25000+ entries needs reverting |
||
| (89 intermediate revisions by 5 users not shown) | |||
Line 1:
local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates
--[[--------------------------< S E T T I N G S >--------------------------------------------------------------
boolean settings used to control various things. these setting located here to make them easy to find
]]
-- these settings local to this module only
local local_digits_from_mediawiki = false; -- for i18n; when true, module fills date_names['local_digits'] from MediaWiki; manual fill required else; always false at en.wiki
local local_date_names_from_mediawiki = false; -- for i18n; when true, module fills date_names['local']['long'] and date_names['local']['short'] from MediaWiki;
-- manual translation required else; ; always false at en.wiki
-- these settings exported to other modules
local use_identifier_redirects = true; -- when true use redirect name for identifier label links; always true at en.wiki
local local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki
local date_name_auto_xlate_enable = false; -- when true translates English month-names to the local-wiki's language month names; always false at en.wiki
local date_digit_auto_xlate_enable = false; -- when true translates Western date digit to the local-wiki's language digits (date_names['local_digits']); always false at en.wiki
local enable_sort_keys = true; -- when true module adds namespace sort keys to error and maintenance category links
--[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------
List of namespaces identifiers for namespaces that
Same as setting notracking = true by default. For wikis that have a current version of Module:cs1 documentation support, this #invoke will return an unordered
list of namespace names and their associated identifiers:
{{#invoke:cs1 documentation support|uncategorized_namespace_lister|all=<anything>}}
]]
local uncategorized_namespaces_t = {[2]=true}; -- init with user namespace id
for k, _ in pairs (mw.site.talkNamespaces) do -- add all talk namespace ids
uncategorized_namespaces_t[k] = true;
end
local uncategorized_subpages = {'/[Ss]andbox', '/[Tt]estcases', '/[^/]*[Ll]og', '/[Aa]rchive'}; -- list of Lua patterns found in page names of pages we should not categorize
--[[
at en.wiki Greek characters are used as sort keys for certain items in a category so that those items are
placed at the end of a category page. See Wikipedia:Categorization#Sort_keys. That works well for en.wiki
because English is written using the Latn script. This may not work well for other languages. At en.wiki it
is desireable to place content from certain namespaces at the end of a category listing so the module adds sort
keys to error and maintenance category links when rendering a cs1|2 template on a page in that namespace.
i18n: if this does not work well for your language, set <enable_sort_keys> to false.
]]
local name_space_sort_keys = { -- sort keys to be used with these namespaces:
[4] = 'ω', -- wikipedia; omega
[10] = 'τ', -- template; tau
[118] = 'Δ', -- draft; delta
['other'] = 'ο', -- all other non-talk namespaces except main (article); omicron
}
--[[--------------------------< M E S S A G E S >--------------------------------------------------------------
Line 26 ⟶ 69:
['archived-dead'] = 'Archived from $1 on $2',
['archived-live'] = '$1 from the original on $2',
['archived-unfit'] = 'Archived from the original on ',
['archived'] = 'Archived',
Line 33 ⟶ 75:
['editor'] = 'ed.',
['editors'] = 'eds.',
['edition'] = '($1
['episode'] = 'Episode $1',
['et al'] = 'et
['in'] = 'In', -- edited works
['inactive'] = 'inactive',
['inset'] = '$1 inset',
['interview'] = 'Interviewed by $1',
['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1',
['original'] = 'the original',
['origdate'] = ' [$1]',
Line 49 ⟶ 90:
['retrieved'] = 'Retrieved $1',
['season'] = 'Season $1',
['section'] = '§
['sections'] = '§§
['series'] = '$1 $2', -- $1 is sepc, $2 is series
['seriesnum'] = 'Series $1',
Line 58 ⟶ 99:
['vol'] = '$1 Vol. $2', -- $1 is sepc; bold journal style volume is in presentation{}
['vol-no'] = '$1 Vol. $2, no. $3',
['issue'] = '$1 No. $2', -- $1 is sepc
['art'] = '$1 Art. $2', -- $1 is sepc; for {{cite conference}} only
['vol-art'] = '$1 Vol. $2, art. $3', -- sepc, volume, article-number; for {{cite conference}} only
['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{}
['j-issue'] = ' ($1)',
['j-article-num'] = ' $1', -- TODO: any punctuation here? static text?
['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc
Line 84 ⟶ 129:
['help page label'] = 'help',
-- categories
['cat wikilink'] = '[[Category:$1]]', -- $1 is the category name
['cat wikilink sk'] = '[[Category:$1|$2]]', -- $1 is the category name; $2 is namespace sort key
[':cat wikilink'] = '[[:Category:$1|link]]', -- category name as maintenance message wikilink; $1 is the category name
-- Internal errors (should only occur if configuration is bad)
['undefined_error'] = 'Called with an undefined error condition',
['
['unknown_ID_access'] = 'Unrecognized ID access keyword: ', -- an ID access keyword in id_handlers not found in keywords_lists['id-access']{}
['unknown_argument_map'] = 'Argument map not defined for this variable',
['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty',
['warning_msg_e'] = '<span style="color:#d33">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code> templates have errors</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link
['warning_msg_m'] = '<span style="color:#3a3">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code> templates have maintenance messages</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link
}
--[[--------------------------< C I T A T I O N _ C L A S S _ M A P >------------------------------------------
this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when
the value assigned to |CitationClass= is different from the canonical template name. |CitationClass= values are
used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while
the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the
template's documentation when an article is displayed in preview mode.
Most cs1|2 template |CitationClass= values at en.wiki match their canonical template names so are not listed here.
]]
local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n
['arxiv'] = 'arXiv',
['audio-visual'] = 'AV media',
['AV-media-notes'] = 'AV media notes',
['biorxiv'] = 'bioRxiv',
['citeseerx'] = 'CiteSeerX',
['encyclopaedia'] = 'encyclopedia',
['mailinglist'] = 'mailing list',
['medrxiv'] = 'medRxiv',
['pressrelease'] = 'press release',
['ssrn'] = 'SSRN',
['techreport'] = 'tech report',
}
Line 101 ⟶ 181:
local et_al_patterns = {
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$", -- variations on the 'et al' theme
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][
"[;,]? *%f[%a]and [Oo]thers", --
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form
"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax)
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form
}
--[[--------------------------<
Fixed presentation markup. Originally part of citation_config.messages it has
been moved into its own, more semantically correct place.
]]
Line 142 ⟶ 199:
local presentation =
{
-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display
['hidden-error'] = '<span class="cs1-hidden-
['visible-error'] = '<span class="cs1-visible-
['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>',
Line 153 ⟶ 208:
['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like
['cite'] = '<cite class="$1">$2</cite>'; -- for use when citation does not have a namelist and |ref= not set so no id="..." attribute
['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when when |ref= is set or when citation has a namelist
['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc.
['interwiki'] = ' <span class="cs1-format">[in $1]</span>', -- for interwiki-language-linked author, editor, etc
['interproj'] = ' <span class="cs1-format">[at $1]</span>', -- for interwiki-project-linked author, editor, etc (:d: and :s: supported; :w: ignored)
-- various access levels, for |access=, |doi-access=, |arxiv=, ...
-- narrow no-break space   may work better than nowrap CSS. Or not? Browser support?
['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon
['free'] = {class='
['registration'] = {class='
['limited'] = {class='
['subscription'] = {class='
['interwiki-icon'] = '<span class="$1" title="$2">$3</span>',
Line 172 ⟶ 229:
['italic-title'] = "''$1''",
['kern-left'] = '<span class="cs1-kern-left">
['kern-right'] = '$1<span class="cs1-kern-right">
['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span>
Line 187 ⟶ 238:
['parameter'] = '<code class="cs1-code">|$1=</code>',
['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character
['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string)
Line 208 ⟶ 259:
['trans-italic-title'] = "[''$1'']",
['trans-quoted-title'] = "[$1]",
['vol-bold'] = '$1 <b>$2</b>', -- sepc, volume; for bold journal cites; for other cites ['vol'] in messages{}
}
--[[--------------------------< A L I A S E S >
Aliases table for commonly passed parameters.
Parameter names on the right side in the
defined in the Whitelist before they will be recognized as valid parameter names
]]
Line 228 ⟶ 279:
['ArchiveFormat'] = 'archive-format',
['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot
['ArticleNumber'] = 'article-number',
['ASINTLD'] = 'asin-tld',
['At'] = 'at', -- Used by InternetArchiveBot
['Authors'] = {
['BookTitle'] = {'book-title', 'booktitle'},
['Cartography'] = 'cartography',
['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'},
['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format',
'article-format', 'section-format'}; ['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url
['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access',
'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot ['Class'] = 'class', -- cite arxiv and arxiv
['Collaboration'] = 'collaboration',
['Conference'] = {'conference', 'event'},
['ConferenceFormat'] =
['ConferenceURL'] =
['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only
['Degree'] = 'degree',
['DF'] = 'df',
['DisplayAuthors'] = {'display-authors', 'display-subjects
['DisplayContributors'] = 'display-contributors',
['DisplayEditors'] = 'display-editors',
Line 253 ⟶ 307:
['DoiBroken'] = 'doi-broken-date',
['Edition'] = 'edition',
['Embargo'] = 'pmc-embargo-date',
['Encyclopedia'] = {'encyclopedia', 'encyclopaedia', 'dictionary'}, -- cite encyclopedia only
Line 259 ⟶ 312:
['Format'] = 'format',
['ID'] = {'id', 'ID'},
['Inset'] = 'inset',
['Issue'] = {'issue', 'number'},
['Language'] = {'language', 'lang'},
['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only
['Map'] = 'map', -- cite map only
Line 275 ⟶ 322:
['Minutes'] = 'minutes',
['Mode'] = 'mode',
['NameListStyle'] =
['Network'] = 'network',
['Newsgroup'] = 'newsgroup', -- cite newsgroup only
['NoPP'] = {'no-pp', 'nopp'},
['NoTracking'] = {'no-tracking', 'template-doc-demo
['Number'] = 'number', -- this case only for cite techreport
['OrigDate'] = {'orig-date', 'orig-year', 'origyear'},
Line 296 ⟶ 343:
['Ref'] = 'ref',
['Scale'] = 'scale',
['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry',
'script-article', 'script-section'}, ['ScriptEncyclopedia'] = {'script-encyclopedia', 'script-encyclopaedia'}, -- cite encyclopedia only
['ScriptMap'] = 'script-map',
['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper',
'script-periodical', 'script-website', 'script-work'}, ['ScriptQuote'] = 'script-quote',
['ScriptTitle'] = 'script-title', -- Used by InternetArchiveBot
Line 305 ⟶ 355:
['Series'] = {'series', 'version'},
['SeriesLink'] = {'series-link', 'serieslink'},
['SeriesNumber'] = {'series-number', 'series-no
['Sheet'] = 'sheet', -- cite map only
['Sheets'] = 'sheets', -- cite map only
['Station'] = 'station',
['Time'] = 'time',
['TimeCaption'] =
['Title'] = 'title', -- Used by InternetArchiveBot
['TitleLink'] = {'title-link', 'episode-link
['TitleNote'] = {'title-note', 'department'},
['TitleType'] = {'type', 'medium'},
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution',
'trans-entry', 'trans-section'}, ['Transcript'] = 'transcript',
['TranscriptFormat'] = 'transcript-format',
['TranscriptURL'] =
['TransEncyclopedia'] = {'trans-encyclopedia', 'trans-encyclopaedia'}, -- cite encyclopedia only
['TransMap'] = 'trans-map', -- cite map only
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper',
'trans-periodical', 'trans-website', 'trans-work'}, ['TransQuote'] = 'trans-quote',
['TransTitle'] = 'trans-title', -- Used by InternetArchiveBot
Line 332 ⟶ 385:
['Year'] = 'year',
['AuthorList-First'] = {"first#", "author-first#", "author#-first
"subject-first#", "subject#-first", "subject-given#", "subject#-given",
"given#"},
['AuthorList-
"subject-last#", "subject#-last", "subject-surname#", "subject#-surname",
"author#", 'host#', "subject#", "surname#"},
['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#",
"subject#-link", "authorlink#", "author#link"},
['AuthorList-Mask'] = {"author-mask#", "author#-mask", "subject-mask#", "subject#-mask"},
['ContributorList-First'] = {'contributor-first#', 'contributor#-first',
'contributor-given#', 'contributor#-given'}, ['ContributorList-Last'] = {'contributor-last#', 'contributor#-last',
'contributor-surname#', 'contributor#-surname', 'contributor#'}, ['ContributorList-Link'] = {'contributor-link#', 'contributor#-link'},
['ContributorList-Mask'] = {'contributor-mask#', 'contributor#-mask'},
['EditorList-First'] = {"editor-first#", "editor#-first", "editor-given#", "editor#-given"},
['EditorList-Last'] = {"editor-last#", "editor#-last", "editor-surname#",
"editor#-surname", "editor#"}, ['EditorList-Link'] = {"editor-link#", "editor#-
['EditorList-Mask'] = {"editor-mask#", "editor#-mask"},
['InterviewerList-First'] = {'interviewer-first#', 'interviewer#-first',
'interviewer-given#', 'interviewer#-given'}, ['InterviewerList-Last'] = {'interviewer-last#', 'interviewer#-last',
'interviewer-surname#', 'interviewer#-surname', 'interviewer#'}, ['InterviewerList-Link'] = {'interviewer-link#', 'interviewer#-link'},
['InterviewerList-Mask'] = {'interviewer-mask#', 'interviewer#-mask'},
['TranslatorList-First'] = {'translator-first#', 'translator#-first',
'translator-given#', 'translator#-given'}, ['TranslatorList-Last'] = {'translator-last#', 'translator#-last',
'translator-surname#', 'translator#-surname', 'translator#'}, ['TranslatorList-Link'] = {'translator-link#', 'translator#-link'},
['TranslatorList-Mask'] = {'translator-mask#', 'translator#-mask'},
Line 359 ⟶ 424:
--[[--------------------------< P U N C T _ S K I P >
builds a table of parameter names that the extraneous terminal punctuation check should not check.
Line 365 ⟶ 430:
]]
local punct_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref',
'ArchiveURL', 'ChapterURL', 'ConferenceURL
}
local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls
'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls
}
local function build_skip_table (skip_t, meta_params)
for _, meta_param in ipairs (meta_params) do -- for each meta parameter key
local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name
if 'string' == type (params) then
else
for _, param in ipairs (params) do -- get the parameter name
local count;
param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters
if 0 ~= count then -- if removed
end
end
end
end
return skip_t;
end
local punct_skip = {};
local url_skip = {};
--[[--------------------------< S I N G L E - L E T T E R S E C O N D - L E V E L D O M A I N S >----------
this is a list of tlds that are known to have single-letter second-level ___domain names. This list does not include
ccTLDs which are accepted in is_domain_name().
]]
local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'media', 'org', 'today'};
--[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------
This table is primarily here to support internationalization. Translations in
this table are used, for example, when an error message, category name, etc.,
is extracted from the English alias key. There may be other cases where
this translation table may be useful.
]]
local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191';
local special_case_translation = {
['AuthorList'] = 'authors list', -- used to assemble maintenance category names
['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base
['EditorList'] = 'editors list', -- must match the names of the actual categories
['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names()
['TranslatorList'] = 'translators list',
-- Lua patterns to match pseudo-titles used by InternetArchiveBot and others as placeholder for unknown |title= value
['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title
['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki
Line 418 ⟶ 497:
},
-- Lua patterns to match generic titles; usually created by bots
-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
-- generic titles and patterns in this table should be lowercase only
-- leave ['local'] nil except when there is a matching generic title in your language
-- boolean 'true' for plain-text searches; 'false' for pattern searches
['generic_titles'] = {
['accept'] = {
},
['reject'] = {
{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil},
{['en'] = {'are you a robot', true}, ['local'] = nil},
{['en'] = {'hugedomains', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'page not found', true}, ['local'] = nil},
{['en'] = {'subscribe to read', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'website is for sale', true}, ['local'] = nil},
{['en'] = {'^404', false}, ['local'] = nil},
{['en'] = {'error[ %-]404', false}, ['local'] = nil},
{['en'] = {'internet archive wayback machine', true}, ['local'] = nil},
{['en'] = {'log into facebook', true}, ['local'] = nil},
{['en'] = {'login • instagram', true}, ['local'] = nil},
{['en'] = {'redirecting...', true}, ['local'] = nil},
{['en'] = {'usurped title', true}, ['local'] = nil}, -- added by a GreenC bot
{['en'] = {'webcite query result', true}, ['local'] = nil},
{['en'] = {'wikiwix\'s cache', true}, ['local'] = nil},
}
},
-- boolean 'true' for plain-text searches, search string must be lowercase only
-- boolean 'false' for pattern searches
-- leave ['local'] nil except when there is a matching generic name in your language
['generic_names'] = {
['accept'] = {
{['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false}, ['local'] = nil},
},
['reject'] = {
{['en'] = {'about us', true}, ['local'] = nil},
{['en'] = {'%f[%a][Aa]dvisor%f[%A]', false}, ['local'] = nil},
{['en'] = {'allmusic', true}, ['local'] = nil},
{['en'] = {'%f[%a][Aa]uthor%f[%A]', false}, ['local'] = nil},
{['en'] = {'^[Bb]ureau$', false}, ['local'] = nil},
{['en'] = {'business', true}, ['local'] = nil},
{['en'] = {'cnn', true}, ['local'] = nil},
{['en'] = {'collaborator', true}, ['local'] = nil},
{['en'] = {'^[Cc]ompany$', false}, ['local'] = nil},
{['en'] = {'contributor', true}, ['local'] = nil},
{['en'] = {'contact us', true}, ['local'] = nil},
{['en'] = {'correspondent', true}, ['local'] = nil},
{['en'] = {'^[Dd]esk$', false}, ['local'] = nil},
{['en'] = {'directory', true}, ['local'] = nil},
{['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false}, ['local'] = nil},
{['en'] = {'[,%.%s]%f[e]eds?%.?$', false}, ['local'] = nil},
{['en'] = {'^eds?[%.,;]', false}, ['local'] = nil},
{['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]dited%f[%A]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]ditors?%f[%A]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]mail%f[%A]', false}, ['local'] = nil},
{['en'] = {'facebook', true}, ['local'] = nil},
{['en'] = {'google', true}, ['local'] = nil},
{['en'] = {'^[Gg]roup$', false}, ['local'] = nil},
{['en'] = {'home page', true}, ['local'] = nil},
{['en'] = {'^[Ii]nc%.?$', false}, ['local'] = nil},
{['en'] = {'instagram', true}, ['local'] = nil},
{['en'] = {'interviewer', true}, ['local'] = nil},
{['en'] = {'^[Ll]imited$', false}, ['local'] = nil},
{['en'] = {'linkedIn', true}, ['local'] = nil},
{['en'] = {'^[Nn]ews$', false}, ['local'] = nil},
{['en'] = {'[Nn]ews[ %-]?[Rr]oom', false}, ['local'] = nil},
{['en'] = {'pinterest', true}, ['local'] = nil},
{['en'] = {'policy', true}, ['local'] = nil},
{['en'] = {'privacy', true}, ['local'] = nil},
{['en'] = {'reuters', true}, ['local'] = nil},
{['en'] = {'translator', true}, ['local'] = nil},
{['en'] = {'tumblr', true}, ['local'] = nil},
{['en'] = {'twitter', true}, ['local'] = nil},
{['en'] = {'site name', true}, ['local'] = nil},
{['en'] = {'statement', true}, ['local'] = nil},
{['en'] = {'submitted', true}, ['local'] = nil},
{['en'] = {'super.?user', false}, ['local'] = nil},
{['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false}, ['local'] = nil},
{['en'] = {'verfasser', true}, ['local'] = nil},
}
}
}
Line 438 ⟶ 588:
--[[--------------------------< D A T E _ N A M E S >----------------------------------------------------------
This table of tables lists local language date names and fallback English date names.
The code in Date_validation will look first in the local table for valid date names.
If date names are not found in the local table, the code will look in the English table. Because citations can be copied to the local wiki from en.wiki, the English is
required when the date-name translation function date_name_xlate() is used. In these tables, season numbering is defined by
Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/) which became part of ISO 8601 in 2019. See '§Sub-year groupings'.
defines various divisions using numbers 21-41.
EDTF does support the distinction between north and south hemisphere seasons 33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each)
The standard does not address 'named' dates so, for the purposes of CS1|2,
Easter and Christmas are defined here as 98 and 99, which should be out of the local_date_names_from_mediawiki is a boolean. When set to:
true – module will fetch local month names from MediaWiki for both date_names['local']['long'] and date_names['local']['short']; this will unconditionally overwrite manual translations
false – module will *not* fetch local month names from MediaWiki
Caveat lector: There is no guarantee that MediaWiki will provide short month names. At your wiki you can test
the results of the MediaWiki fetch in the debug console with this command (the result is alpha sorted):
=mw.dumpObject (p.date_names['local'])
While the module can fetch month names from MediaWiki, it cannot fetch the quarter, season, and named date names
from MediaWiki. Those must be translated manually.
]]
local local_date_names_from_mediawiki = true; -- when false, manual translation required for date_names['local']['long'] and date_names['local']['short']; overwrites manual translations
-- when true, module fetches long and short month names from MediaWiki
local date_names = {
['en'] = { -- English
Line 465 ⟶ 631:
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
},
-- when local_date_names_from_mediawiki = false
['local'] = { -- replace these English date names with the local language equivalents
['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12},
Line 472 ⟶ 639:
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
},
['
['
['inv_local_quarter'] = {}, -- used in date translation; copy of date_names['local'].quarter where k/v are inverted: [1]='<local name>' etc.
['inv_local_season'] = {}, -- used in date translation; copy of date_names['local'].season where k/v are inverted: [1]='<local name>' etc.
['inv_local_named'] = {}, -- used in date translation; copy of date_names['local'].named where k/v are inverted: [1]='<local name>' etc.
['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9
['xlate_digits'] = {},
}
if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled
local long_t = {};
local short_t = {};
for i=1, 12 do -- loop 12x and
local name = lang_obj:formatDate('F', '2022-' .. i .. '-1'); -- get long month name for each i
long_t[name] = i; -- save it
name = lang_obj:formatDate('M', '2022-' .. i .. '-1'); -- get short month name for each i
short_t[name] = i; -- save it
end
date_names['local']['long'] = long_t; -- write the long table – overwrites manual translation
date_names['local']['short'] = short_t; -- write the short table – overwrites manual translation
end
-- create inverted date-name tables for reformatting and/or translation
for _, invert_t in pairs {{'long', 'inv_local_long'}, {'short', 'inv_local_short'}, {'quarter', 'inv_local_quarter'}, {'season', 'inv_local_season'}, {'named', 'inv_local_named'}} do
for name, i in pairs (date_names['local'][invert_t[1]]) do -- this table is ['name'] = i
date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd
end
end
if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled
local digits_t = {};
for i=0, 9 do -- loop 10x and
digits_t [lang_obj:formatNum (i)] = tostring (i); -- format the loop indexer as local lang table index and assign loop indexer (a string) as the value
end
date_names['local_digits'] = digits_t;
end
Line 505 ⟶ 694:
'{{ *([Mm]DY) *[|}]', -- 0
}
local title_object = mw.title.getCurrentTitle();
local content; -- done this way so that unused templates appear in unused-template-reports; self-transcluded makes them look like they are used
if 10 ~= title_object.namespace then -- all namespaces except Template
content = title_object:getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625
end
local function get_date_format ()
if not content then -- nil content when we're in template
return nil; -- auto-formatting does not work in Template space so don't set global_df
end
for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects
local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format
if match then
if
return match:lower() .. '-' ..
else
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df=
Line 521 ⟶ 718:
end
local global_df; --
--[[
These tables hold cite class values (from the template invocation) and identify those templates that support
Line 536 ⟶ 733:
local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'}
--[[
These tables control when it is appropriate for {{citation}} to render |volume= and/or |issue=. The parameter
names in the tables constrain {{citation}} so that its renderings match the renderings of the equivalent cs1
templates. For example, {{cite web}} does not support |volume= so the equivalent {{citation |website=...}} must
not support |volume=.
]]
local citation_no_volume_t = { -- {{citation}} does not render |volume= when these parameters are used
'website', 'mailinglist', 'script-website',
}
local citation_issue_t = { -- {{citation}} may render |issue= when these parameters are used
'journal', 'magazine', 'newspaper', 'periodical', 'work',
'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work',
}
--[[
Patterns for finding extra text in |volume=, |issue=, |page=, |pages=
]]
local vol_iss_pg_patterns = {
good_ppattern = '^P[^%.PpGg]', -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123); TODO: this allows 'Pages' which it should not
bad_ppatterns = { -- patterns for |page= and |pages=
'^[Pp][PpGg]?%.?[ %d]',
'^[Pp][Pp]?%. ', -- from {{p.}} and {{pp.}} templates
'^[Pp]ages?',
'^[Pp]gs.?',
},
vi_patterns_t = { -- combined to catch volume-like text in |issue= and issue-like text in |volume=
'^volumes?', -- volume-like text
'^vols?[%.:=]?',
'^issues?', --issue-like text
'^iss[%.:=]?',
'^numbers?',
'^nos?%A', -- don't match 'november' or 'nostradamus'
'^nr[%.:=]?',
'^n[%.:= ]', -- might be a valid issue without separator (space char is sep char here)
'^n°', -- 'n' with degree sign (U+00B0)
'^№', -- precomposed unicode numero character (U+2116)
},
}
--[[--------------------------< K E Y W O R D S >
These tables hold keywords for those parameters that have defined sets of acceptable keywords.
Line 543 ⟶ 785:
]]
--[[
this is a list of keywords; each key in the list is associated with a table of
synonymous keywords possibly from different languages. for I18N: add local-language keywords to value table; do not change the key.
For example, adding the German keyword 'ja': ['affirmative'] = {'yes', 'true', 'y', 'ja'},
Because CS1|2 templates from en.wiki articles are often copied to other local wikis,
it is recommended that the English keywords remain in these tables. ]]
local keywords = {
['amp'] = {'&', 'amp', 'ampersand'},
['and'] = {'and', 'serial'},
['affirmative'] = {'yes', 'true', 'y'}, --
['afterword'] = {'afterword'}, -- |contribution=
['bot: unknown'] = {'bot: unknown'}, -- |url-status= -- Used by InternetArchiveBot
['cs1'] = {'cs1'}, -- |mode=
['cs2'] = {'cs2'}, -- |mode=
['dead'] = {'dead', 'deviated'},
['dmy'] = {'dmy'}, -- |df=
['dmy-all'] = {'dmy-all'}, -- |df=
['foreword'] = {'foreword'}, -- |contribution=
['free'] = {'free'}, -- |
['harv'] = {'harv'}, -- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true
['introduction'] = {'introduction'}, -- |contribution=
['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot
Line 584 ⟶ 828:
['ymd'] = {'ymd'}, -- |df=
['ymd-all'] = {'ymd-all'}, -- |df=
-- ['yMd'] = {'yMd'},
-- ['yMd-all'] = {'yMd-all'},
}
--[[
this function builds a list, keywords_xlate{}, of the keywords found in keywords{} where the values from keywords{}
Line 618 ⟶ 862:
--[[
this function assembles, for parameter-value validation, the list of keywords appropriate to that parameter.
Line 638 ⟶ 882:
--[[
this is a list of lists of valid keywords for the various parameters in [key].
Generally the keys in this table are the canonical en.wiki parameter names though
some are contrived because of use in multiple differently named parameters: The function make_keywords_list() extracts the individual keywords from the
appropriate list in keywords{}. The lists in this table are used to validate the keyword assignment for the
parameters named in this table's keys. ]]
Line 654 ⟶ 901:
['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}),
['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all']}),
-- ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all'], keywords.yMd, keywords['yMd-all']}), -- not supported at en.wiki
['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}),
['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}),
['ref'] = make_keywords_list ({keywords.harv}), -- inverted check; |ref=harv no longer supported
['url-access'] = make_keywords_list ({keywords.subscription, keywords.limited, keywords.registration}),
['url-status'] = make_keywords_list ({keywords.dead, keywords.live, keywords.unfit, keywords.usurped, keywords['bot: unknown']}),
Line 663 ⟶ 911:
--[[--------------------------< C S
fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t>
no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked.
Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors,
DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode. The DisplayWhatever metaparameters
accept numeric values only (|display-authors=etal and the like is not supported).
]]
local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table?
local function get_cs1_config ()
if not content then -- nil content when we're in template
return nil; -- auto-formatting does not work in Template space so don't set global_df
end
local start = content:find('{{ *[Cc][Ss]1 config *[|}]'); -- <start> is offset into <content> when {{cs1 config}} found; nil else
if start then
local cs1_config_template = content:match ('%b{}', start); -- get the whole template
if not cs1_config_template then
return nil;
end
local params_t = mw.text.split (cs1_config_template:gsub ('^{{%s*', ''):gsub ('%s*}}$', ''), '%s*|%s*'); -- remove '{{' and '}}'; make a sequence of parameter/value pairs (split on the pipe)
table.remove (params_t, 1); -- remove the template name because it isn't a parameter/value pair
local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'};
local meta_param_map_t = {}; -- list of accepted parameter names usable in {{cs1 config}} goes here
for _, meta_param in ipairs (config_meta_params_t) do -- for i18n using <config_meta_params_t>, map template parameter names to their metaparameter equivalents
if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence,
for _, param in ipairs (aliases[meta_param]) do -- extract its contents
meta_param_map_t[param] = meta_param; -- and add to <meta_param_map_t>
end
else
meta_param_map_t[aliases[meta_param]] = meta_param; -- not a sequence so just add the parameter to <meta_param_map_t>
end
end
local keywords_t = {}; -- map valid keywords to their associate metaparameter; reverse form of <keyword_lists[key] for these metaparameters
for _, metaparam_t in ipairs ({{'NameListStyle', 'name-list-style'}, {'Mode', 'mode'}}) do -- only these metaparameter / keywords_lists key pairs
for _, keyword in ipairs (keywords_lists[metaparam_t[2]]) do -- spin through the list of keywords
keywords_t[keyword] = metaparam_t[1]; -- add [keyword] = metaparameter to the map
end
end
for _, param in ipairs (params_t) do -- spin through the {{cs1 config}} parameters and fill <global_cs1_config_t>
local k, v = param:match ('([^=]-)%s*=%s*(.+)'); -- <k> is the parameter name; <v> is parameter's assigned value
if k then
if k:find ('^display') then -- if <k> is one of the |display-<namelist>= parameters
if v:match ('%d+') then -- the assigned value must be digits; doesn't accept 'etal'
global_cs1_config_t[meta_param_map_t[k]]=v; -- add the display param and its value to globals table
end
else
if keywords_t[v] == meta_param_map_t[k] then -- keywords_t[v] returns nil or the metaparam name; these must be the same
global_cs1_config_t[meta_param_map_t[k]]=v; -- add the parameter and its value to globals table
end
end
end
end
end
end
get_cs1_config (); -- fill <global_cs1_config_t>
--[[---------------------< S T R I P M A R K E R S >----------------------------
Common pattern definition ___location for stripmarkers so that we don't have to go
hunting for them if (when) MediaWiki changes their form.
]]
Line 676 ⟶ 994:
--[[
This table holds non-printing or invisible characters indexed either by name or
by Unicode group. Values are decimal representations of UTF-8 codes. The table because the entries at the top of the table are also found in the ranges specified
by the entries at the bottom of the table. Also here is a pattern that recognizes stripmarkers that begin and end with the
delete characters. The nowiki stripmarker is not an error but some others are
because the parameter values that include them become part of the template's ]]
local invisible_defs = {
del = '\127', -- used to distinguish between stripmarker and del char
zwj = '\226\128\141', -- used with capture because zwj may be allowed
}
local invisible_chars = {
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD
{'zero width joiner', '
{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A
Line 700 ⟶ 1,026:
{'carriage return', '\013'}, -- U+000D (CR), 0D
{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type
{'delete', '
{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-- {'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD
-- {'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'}, -- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD
}
--[[
Indic script makes use of zero width joiner as a character modifier so zwj
characters must be left in. This pattern covers all of the unicode characters
for these languages:
Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf
Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
Line 728 ⟶ 1,056:
Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
the pattern is used by has_invisible_chars() and coins_cleanup()
]]
local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]';
-- list of emoji that use a zwj character (U+200D) to combine with another emoji
-- from: https://unicode.org/Public/emoji/16.0/emoji-zwj-sequences.txt; version: 16.0; 2024-08-14
-- table created by: [[:en:Module:Make emoji zwj table]]
local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx
[8596] = true, -- U+2194 ↔ left right arrow
[8597] = true, -- U+2195 ↕ up down arrow
[9760] = true, -- U+2620 ☠ skull and crossbones
[9792] = true, -- U+2640 ♀ female sign
[9794] = true, -- U+2642 ♂ male sign
[9877] = true, -- U+2695 ⚕ staff of aesculapius
[9878] = true, -- U+2696 ⚖ scales
[9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign
[9992] = true, -- U+2708 ✈ airplane
[10052] = true, -- U+2744 ❄ snowflake
[10084] = true, -- U+2764 ❤ heavy black heart
[10145] = true, -- U+27A1 ➡ black rightwards arrow
[11035] = true, -- U+2B1B ⬛ black large square
[127752] = true, -- U+1F308 🌈 rainbow
[127787] = true, -- U+1F32B 🌫 fog
[127806] = true, -- U+1F33E 🌾 ear of rice
[127859] = true, -- U+1F373 🍳 cooking
[127868] = true, -- U+1F37C 🍼 baby bottle
[127876] = true, -- U+1F384 🎄 christmas tree
[127891] = true, -- U+1F393 🎓 graduation cap
[127908] = true, -- U+1F3A4 🎤 microphone
[127912] = true, -- U+1F3A8 🎨 artist palette
[127979] = true, -- U+1F3EB 🏫 school
[127981] = true, -- U+1F3ED 🏭 factory
[128102] = true, -- U+1F466 👦 boy
[128103] = true, -- U+1F467 👧 girl
[128104] = true, -- U+1F468 👨 man
[128105] = true, -- U+1F469 👩 woman
[128139] = true, -- U+1F48B 💋 kiss mark
[128165] = true, -- U+1F4A5 💥 collision symbol
[128168] = true, -- U+1F4A8 💨 dash symbol
[128171] = true, -- U+1F4AB 💫 dizzy symbol
[128187] = true, -- U+1F4BB 💻 personal computer
[128188] = true, -- U+1F4BC 💼 brief case
[128293] = true, -- U+1F525 🔥 fire
[128295] = true, -- U+1F527 🔧 wrench
[128300] = true, -- U+1F52C 🔬 microscope
[128488] = true, -- U+1F5E8 🗨 left speech bubble
[128640] = true, -- U+1F680 🚀 rocket
[128658] = true, -- U+1F692 🚒 fire engine
[129001] = true, -- U+1F7E9 🟩 large green square
[129003] = true, -- U+1F7EB 🟫 large brown square
[129309] = true, -- U+1F91D 🤝 handshake
[129455] = true, -- U+1F9AF 🦯 probing cane
[129456] = true, -- U+1F9B0 🦰 emoji component red hair
[129457] = true, -- U+1F9B1 🦱 emoji component curly hair
[129458] = true, -- U+1F9B2 🦲 emoji component bald
[129459] = true, -- U+1F9B3 🦳 emoji component white hair
[129466] = true, -- U+1F9BA 🦺 safety vest
[129468] = true, -- U+1F9BC 🦼 motorized wheelchair
[129469] = true, -- U+1F9BD 🦽 manual wheelchair
[129489] = true, -- U+1F9D1 🧑 adult
[129490] = true, -- U+1F9D2 🧒 child
[129657] = true, -- U+1FA79 🩹 adhesive bandage
[129778] = true, -- U+1FAF2 🫲 leftwards hand
}
--[[----------------------< L A N G U A G E S U P P O R T >-------------------
These tables and constants support various language-specific functionality.
Line 742 ⟶ 1,129:
]]
--local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code
local this_wiki_code = lang_obj:getCode(); -- get this wiki's language code
if string.match (mw.site.server, 'wikidata') then
this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead
end
local
local mw_languages_by_name_t = {};
for k, v in pairs (mw_languages_by_tag_t) do -- build a 'reversed' table name/tag language pairs know to MediaWiki; used for |language=
v = mw.ustring.lower (v); -- lowercase for tag fetch; get name's proper case from mw_languages_by_tag_t[<tag>]
if mw_languages_by_name_t[v] then -- when name already in the table
if 2 == #k or 3 == #k then -- if tag does not have subtags
mw_languages_by_name_t[v] = k; -- prefer the shortest tag for this name
end
else -- here when name not in the table
mw_languages_by_name_t[v] = k; -- so add name and matching tag
end
end
local inter_wiki_map = {}; -- map of
for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base
if
inter_wiki_map[v["prefix"]] = true; -- add it to our local map
end
end
--[[
This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character
language codes that apply only to |script-title= and |script-chapter= ]]
local script_lang_codes = {
'ab', 'am', 'ar', 'az', 'be', 'bg', 'bn', 'bo', 'bs', '
'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko
'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni', 'mr', 'my', 'ne', 'or', 'ota
'
'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh', 'zgh'
};
--[[
These tables hold language information that is different (correct) from MediaWiki's definitions
For each ['
lang_tag_remap{}:
key is always lowercase ISO 639-1, -2, -3 language
value is properly spelled and capitalized language name associated with
only one language name per
key/value pair must have matching entry in lang_name_remap{}
lang_name_remap{}:
key is always lowercase language name
value is a table the holds correctly spelled and capitalized language name [1] and associated
may have multiple keys referring to a common preferred name and
['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'
]]
local
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
Line 800 ⟶ 1,198:
['bn'] = 'Bengali', -- MediaWiki returns Bangla
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan
['
['gsw'] = 'Swiss German',
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name
Line 806 ⟶ 1,205:
['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data
['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name
['sr-ec'] = 'Serbian (Cyrillic script)', -- MediaWiki returns српски (ћирилица)
['sr-el'] = 'Serbian (Latin script)', -- MediaWiki returns srpski (latinica)
}
local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase
['alemannic'] = {'Swiss German', 'gsw'}, -- ISO 639-2, -3 alternate for Swiss German; MediaWiki mediawiki returns Alemannic for gsw; en.wiki preferred name
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org
['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap
Line 816 ⟶ 1,218:
['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö)
['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name
['kven'] = {'Kven', 'fkv'}, -- Unicode CLDR have decided not to support English language name for these two...
['kvensk'] = {'Kven', 'fkv'}, -- ...they say to refer to IANA registry for English names
['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639
['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'}, -- special case to get correct tag when |language=sr-ec
['
['swiss german'] = {'Swiss German', 'gsw'},
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
['valencian'] = {'Valencian', 'ca-valencia'},
}
--[[
Properties categories. These are used for investigating qualities of citations.
]]
local prop_cats = {
['
['
['interproj-linked-name'] = 'CS1 interproject-linked names|$1', -- any author, editor, etc that has an interproject link; $1 is interproject tag used as a sort key
['interwiki-linked-name'] = 'CS1 interwiki-linked names|$1', -- any author, editor, etc that has an interwiki link; $1 is interwiki tag used as a sort key; yeilds to interproject
['
['___location-test'] = 'CS1 ___location test',
['
['
['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name
['unfit'] = 'CS1: unfit URL', -- |url-status=unfit or |url-status=usurped; used to be a maint cat
['vanc-accept'] = 'CS1:Vancouver names with accept markup', -- for |vauthors=/|veditors= with accept-as-written markup
['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form
}
--[[
Here we map a template's CitationClass to TitleType (default values for |type= parameter)
Line 855 ⟶ 1,263:
local title_types = {
['AV-media-notes'] = 'Media notes',
['document'] = 'Document',
['interview'] = 'Interview',
['mailinglist'] = 'Mailing list',
Line 861 ⟶ 1,270:
['pressrelease'] = 'Press release',
['report'] = 'Report',
['speech'] = 'Speech',
['techreport'] = 'Technical report',
['thesis'] = 'Thesis',
Line 866 ⟶ 1,276:
--[[--------------------------< B U I L D _ K N O W N _ F R E E _ D O I _ R E G I S T R A N T S _ T A B L E >--
build a table of doi registrants known to be free-to-read In a doi, the registrant ID is the series of digits
between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID
see §3.2.2 DOI prefix of the Doi Handbook p. 43
https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43
]]
local function build_free_doi_registrants_table()
local registrants_t = {};
for _, v in ipairs ({
'1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '1629', '1989', '1999', '2147', '2196', '3285', '3389', '3390',
'3748', '3814', '3847', '3897', '4061', '4089', '4103', '4172', '4175', '4230', '4236', '4239', '4240', '4249', '4251',
'4252', '4253', '4254', '4291', '4292', '4329', '4330', '4331', '5194', '5210', '5306', '5312', '5313', '5314',
'5315', '5316', '5317', '5318', '5319', '5320', '5321', '5334', '5402', '5409', '5410', '5411', '5412',
'5492', '5493', '5494', '5495', '5496', '5497', '5498', '5499', '5500', '5501', '5527', '5528', '5662',
'6064', '6219', '7167', '7217', '7287', '7482', '7490', '7554', '7717', '7759', '7766', '11131', '11569', '11647',
'11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995',
'17645', '18637', '19080', '19173', '20944', '21037', '21468', '21767', '22261', '22323', '22459', '24105', '24196', '24966',
'26775', '30845', '32545', '35711', '35712', '35713', '35995', '36648', '37126', '37532', '37871', '47128',
'47622', '47959', '52437', '52975', '53288', '54081', '54947', '55667', '55914', '57009', '58647', '59081',
}) do
registrants_t[v] = true; -- build a k/v table of known free-to-read doi registrants
end
return registrants_t;
end
local extended_registrants_t = { -- known free registrants identifiable by the doi suffix incipit
['1002'] = {'aelm', 'leap'}, -- Advanced Electronic Materials, Learned Publishing
['1016'] = {'j.heliyon', 'j.nlp', 'j.proche'}, -- Heliyon, Natural Language Processing, Procedia Chemistry
['1017'] = {'nlp'}, -- Natural Language Processing Journal
['1046'] = {'j.1365-8711', 'j.1365-246x'}, -- MNRAS, GJI
['1093'] = {'mnras', 'mnrasl', 'gji', 'rasti'}, -- MNRAS, MNRAS Letters, GJI, RASTI
['1099'] = {'acmi', 'mic', '00221287', 'mgen'}, -- Access Microbiology, Microbiology, Journal of General Microbiology, Microbial Genomics
['1111'] = {'j.1365-2966', 'j.1745-3933', 'j.1365-246X'}, -- MNRAS, MNRAS Letters, GJI
['1210'] = {'jendso','jcemcr'}, -- Journal of the Endocrine Society, JCEM Case Reports
['4171'] = {'dm','mag'}, -- Documenta Mathematica, EMS Magazine
['14231'] = {'ag'}, -- Algebraic Geometry
}
--[[===================<< E R R O R M E S S A G I N G >>======================
]]
--[[
I18N for those messages that are supplemented with additional specific text that
describes the reason for the error TODO: merge this with special_case_translations{}?
Line 884 ⟶ 1,338:
['group'] = 'invalid group id', -- |isbn=
['initials'] = 'initials', -- Vancouver
['invalid language code'] = 'invalid language code', -- |script-<param>=
['journal'] = 'journal', -- |bibcode=
['length'] = 'length', -- |isbn=, |bibcode=, |sbn=
['liveweb'] = 'liveweb', -- |archive-url=
['missing comma'] = 'missing comma', -- Vancouver
['missing prefix'] = 'missing prefix', -- |script-<param>=
['missing title part'] = 'missing title part', -- |script-<param>=
['name'] = 'name', -- Vancouver
['non-Latin char'] = 'non-Latin character', -- Vancouver
Line 896 ⟶ 1,353:
['suffix'] = 'suffix', -- Vancouver
['timestamp'] = 'timestamp', -- |archive-url=
['unknown language code'] = 'unknown language code', -- |script-<param>=
['value'] = 'value', -- |bibcode=
['year'] = 'year', -- |bibcode=
Line 901 ⟶ 1,359:
--[[
Error condition table. This table has two sections: errors at the top, maintenance
at the bottom. Maint 'messaging' does not have a 'message' (message=nil) The following contains a list of IDs for various error conditions defined in the
code. For each ID, we specify a text message to display, an error category to
include, and whether the error message should be wrapped as a hidden comment. Anchor changes require identical changes to matching anchor in Help:CS1 errors
TODO: rename error_conditions{} to something more generic; create separate error
and maint tables inside that? ]]
Line 919 ⟶ 1,379:
message = '<code class="cs1-code">|access-date=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'accessdate_missing_url',
category = '
hidden = false
},
Line 928 ⟶ 1,388:
hidden = false
},
err_archive_date_missing_url = {
message = '<code class="cs1-code">|archive-date=</code> requires <code class="cs1-code">|archive-url=</code>',
anchor = 'archive_date_missing_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_date_url_ts_mismatch = {
message = '<code class="cs1-code">|archive-date=</code> / <code class="cs1-code">|archive-url=</code> timestamp mismatch; $1 suggested',
anchor = 'archive_date_url_ts_mismatch',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_missing_date = {
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|archive-date=</code>',
anchor = 'archive_missing_date',
category = '
hidden = false
},
Line 937 ⟶ 1,409:
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'archive_missing_url',
category = '
hidden = false
},
Line 943 ⟶ 1,415:
message = '<code class="cs1-code">|archive-url=</code> is malformed: $1', -- $1 is error message detail
anchor = 'archive_url',
category = '
hidden = false
},
Line 950 ⟶ 1,422:
anchor = 'arxiv_missing',
category = 'CS1 errors: arXiv', -- same as bad arxiv
hidden = false
},
err_asintld_missing_asin = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|asin=</code>', -- $1 is parameter name
anchor = 'asintld_missing_asin',
category = 'CS1 errors: ASIN TLD',
hidden = false
},
Line 962 ⟶ 1,440:
anchor = 'bad_asin',
category ='CS1 errors: ASIN',
hidden = false
},
err_bad_asin_tld = {
message = 'Check <code class="cs1-code">|asin-tld=</code> value',
anchor = 'bad_asin_tld',
category ='CS1 errors: ASIN TLD',
hidden = false
},
Line 983 ⟶ 1,467:
},
err_bad_date = {
anchor = 'bad_date',
category = 'CS1 errors: dates',
Line 1,023 ⟶ 1,506:
anchor = 'bad_jfm',
category = 'CS1 errors: JFM',
hidden = false
},
err_bad_jstor = {
message = 'Check <code class="cs1-code">|jstor=</code> value',
anchor = 'bad_jstor',
category = 'CS1 errors: JSTOR',
hidden = false
},
Line 1,029 ⟶ 1,518:
anchor = 'bad_lccn',
category = 'CS1 errors: LCCN',
hidden = false
},
err_bad_medrxiv = {
message = 'Check <code class="cs1-code">|medrxiv=</code> value',
anchor = 'bad_medrxiv',
category = 'CS1 errors: medRxiv',
hidden = false
},
Line 1,035 ⟶ 1,530:
anchor = 'bad_mr',
category = 'CS1 errors: MR',
hidden = false
},
err_bad_oclc = {
message = 'Check <code class="cs1-code">|oclc=</code> value',
anchor = 'bad_oclc',
category = 'CS1 errors: OCLC',
hidden = false
},
Line 1,041 ⟶ 1,542:
anchor = 'bad_ol',
category = 'CS1 errors: OL',
hidden = false
},
err_bad_osti = {
message = 'Check <code class="cs1-code">|osti=</code> value',
anchor = 'bad_osti',
category = 'CS1 errors: OSTI',
hidden = false
},
Line 1,061 ⟶ 1,568:
hidden = false
},
message = 'Check <code class="cs1-code">|
anchor = '
category = 'CS1 errors:
hidden = false
},
message = 'Check <code class="cs1-code">|s2cid=</code> value',
anchor = 'bad_s2cid',
Line 1,088 ⟶ 1,595:
message = 'Check $1 value', -- $1 is parameter name
anchor = 'bad_url',
category = '
hidden = false
},
Line 1,100 ⟶ 1,607:
message = 'Check <code class="cs1-code">|zbl=</code> value',
anchor = 'bad_zbl',
category = 'CS1 errors:
hidden = false
},
Line 1,106 ⟶ 1,613:
message = '$1 missing title', -- $1 is parameter name
anchor = 'bare_url_missing_title',
category = '
hidden = false
},
Line 1,124 ⟶ 1,631:
message = 'Missing or empty <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'citation_missing_title',
category = '
hidden = false
},
Line 1,136 ⟶ 1,643:
message = 'Missing or empty <code class="cs1-code">|url=</code>',
anchor = 'cite_web_url',
category = '
hidden = false
},
Line 1,164 ⟶ 1,671:
},
err_disp_name = {
message = 'Invalid <code class="cs1-code">|
anchor = 'disp_name',
category = 'CS1 errors: display-names',
Line 1,173 ⟶ 1,680:
anchor = 'doibroken_missing_doi',
category = 'CS1 errors: DOI',
hidden = false
},
err_embargo_missing_pmc = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|pmc=</code>', -- $1 is parameter name
anchor = 'embargo_missing_pmc',
category = 'CS1 errors: PMC embargo',
hidden = false
},
Line 1,178 ⟶ 1,691:
message = 'Empty citation',
anchor = 'empty_citation',
category = '
hidden = false
},
Line 1,186 ⟶ 1,699:
category = 'CS1 errors: explicit use of et al.',
hidden = false
},
err_extra_text_edition = {
message = '<code class="cs1-code">|edition=</code> has extra text',
anchor = 'extra_text_edition',
category = 'CS1 errors: extra text: edition',
hidden = false,
},
err_extra_text_issue = {
message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_issue',
category = 'CS1 errors: extra text: issue',
hidden = false,
},
err_extra_text_pages = {
message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_pages',
category = 'CS1 errors: extra text: pages',
hidden = false,
},
err_extra_text_volume = {
message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_volume',
category = 'CS1 errors: extra text: volume',
hidden = false,
},
err_first_missing_last = {
Line 1,196 ⟶ 1,733:
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|$2=</code>', -- $1 is format parameter $2 is url parameter
anchor = 'format_missing_url',
category = '
hidden = false
},
err_generic_name = {
message = '<code class="cs1-code">|$1=</code> has generic name', -- $1 is parameter name
anchor = 'generic_name',
category = 'CS1 errors: generic name',
hidden = false,
},
err_generic_title = {
Line 1,204 ⟶ 1,747:
category = 'CS1 errors: generic title',
hidden = false,
},
err_invalid_isbn_date = {
message = 'ISBN / Date incompatibility',
anchor = 'invalid_isbn_date',
category = 'CS1 errors: ISBN date',
hidden = true
},
err_invalid_param_val = {
Line 1,215 ⟶ 1,764:
anchor = 'invisible_char',
category = 'CS1 errors: invisible characters',
hidden = false
},
err_medrxiv_missing = {
message = '<code class="cs1-code">|medrxiv=</code> required',
anchor = 'medrxiv_missing',
category = 'CS1 errors: medRxiv', -- same as bad medRxiv
hidden = false
},
Line 1,227 ⟶ 1,782:
anchor = 'missing_periodical',
category = 'CS1 errors: missing periodical',
hidden =
},
err_missing_pipe = {
Line 1,234 ⟶ 1,789:
category = 'CS1 errors: missing pipe',
hidden = false
},
err_missing_publisher = {
message = 'Cite $1 requires <code class="cs1-code">|$2=</code>', -- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1
anchor = 'missing_publisher',
category = 'CS1 errors: missing publisher',
hidden = false
},
err_numeric_names = {
message = '<code class="cs1-code">|$1=</code> has numeric name', -- $1 is parameter name',
anchor = 'numeric_names',
category = 'CS1 errors: numeric name',
hidden = false,
},
err_param_access_requires_param = {
Line 1,245 ⟶ 1,812:
anchor = 'param_has_ext_link',
category = 'CS1 errors: external links',
hidden = false
},
err_param_has_twl_url = {
message = 'Wikipedia Library link in <code class="cs1-code">$1</code>', -- $1 is parameter name
anchor = 'param_has_twl_url',
category = 'CS1 errors: URL',
hidden = false
},
Line 1,250 ⟶ 1,823:
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name
anchor = 'parameter_ignored',
category = '
hidden = false
},
Line 1,256 ⟶ 1,829:
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored (<code class="cs1-code">|$2=</code> suggested)', -- $1 is unknown parameter $2 is suggested parameter name
anchor = 'parameter_ignored_suggest',
category = '
hidden = false
},
err_periodical_ignored = {
message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name
anchor = 'periodical_ignored',
category = 'CS1 errors: periodical ignored',
hidden = false
},
Line 1,262 ⟶ 1,841:
message = 'More than one of $1 specified', -- $1 is error message detail
anchor = 'redundant_parameters',
category = '
hidden = false
},
Line 1,274 ⟶ 1,853:
message = '<code class="cs1-code">|ssrn=</code> required',
anchor = 'ssrn_missing',
category = 'CS1 errors:
hidden = false
},
Line 1,280 ⟶ 1,859:
message = 'Text "$1" ignored', -- $1 is ignored text
anchor = 'text_ignored',
category = '
hidden = false
},
err_trans_missing_title = {
message = '<code class="cs1-code">|trans-$1=</code> requires <code class="cs1-code">|$1=</code> or
anchor = 'trans_missing_title',
category = 'CS1 errors: translated title',
Line 1,293 ⟶ 1,872:
anchor = 'param_unknown_empty',
category = 'CS1 errors: empty unknown parameters',
hidden =
},
err_vancouver = {
message = 'Vancouver style error: $1 in name $2',
anchor = 'vancouver',
category = 'CS1 errors: Vancouver style',
Line 1,309 ⟶ 1,888:
--[[--------------------------< M A I N T >
maint messages do not have a message (message = nil); otherwise the structure
is the same as error messages ]]
maint_archived_copy = {
message = nil,
Line 1,327 ⟶ 1,901:
hidden = true,
},
message = nil,
anchor = '
category = 'CS1 maint:
hidden = true,
},
maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite
message = nil,
anchor = 'location_no_publisher',
category = 'CS1 maint: ___location missing publisher',
hidden = true,
},
Line 1,336 ⟶ 1,916:
message = nil,
anchor = 'bot:_unknown',
category = 'CS1 maint:
hidden = true,
},
maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki
message = nil,
anchor = 'date_auto_xlated',
category = 'CS1 maint: date auto-translated',
hidden = true,
},
Line 1,367 ⟶ 1,953:
anchor = 'doi_inactive_dated',
category = 'CS1 maint: DOI inactive as of $2$3$1', -- $1 is year, $2 is month-name or empty string, $3 is space or empty string
hidden = true,
},
maint_doi_unflagged_free = {
message = nil,
anchor = 'doi_unflagged_free',
category = 'CS1 maint: unflagged free DOI',
hidden = true,
},
Line 1,375 ⟶ 1,967:
hidden = true,
},
maint_id_limit_load_fail = { -- applies to all cs1|2 templates on a page;
message = nil, -- maint message (category link) never emitted
anchor = '
category = 'CS1 maint:
hidden = true,
},
Line 1,421 ⟶ 2,007:
anchor = 'mult_names',
category = 'CS1 maint: multiple names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
Line 1,439 ⟶ 2,019:
anchor = 'others',
category = 'CS1 maint: others',
hidden = true,
},
maint_others_avm = {
message = nil,
anchor = 'others_avm',
category = 'CS1 maint: others in cite AV media (notes)',
hidden = true,
},
maint_overridden_setting = {
message = nil,
anchor = 'overridden',
category = 'CS1 maint: overridden setting',
hidden = true,
},
Line 1,453 ⟶ 2,045:
hidden = true,
},
message = nil,
anchor = '
category = 'CS1 maint:
hidden = true,
maint_publisher_location = {
message = nil,
anchor = '
category = 'CS1 maint:
hidden = true,
maint_ref_duplicates_default = {
message = nil,
anchor = 'ref_default',
category = 'CS1 maint: ref duplicates default',
hidden = true,
},
maint_unknown_lang = {
message = nil,
Line 1,475 ⟶ 2,073:
anchor = 'untitled',
category = 'CS1 maint: untitled periodical',
hidden = true,
},
maint_url_status = {
message = nil,
anchor = 'url_status',
category = 'CS1 maint: url-status',
hidden = true,
},
maint_year= {
message = nil,
anchor = 'year',
category = 'CS1 maint: year',
hidden = true,
},
Line 1,480 ⟶ 2,090:
message = nil,
anchor = 'zbl',
category = 'CS1 maint:
hidden = true,
},
}
--[[--------------------------< I D _ L I M I T S _ D A T A _ T >----------------------------------------------
fetch id limits for certain identifiers from c:Data:CS1/Identifier limits.tab. This source is a json tabular
data file maintained at wikipedia commons. Convert the json format to a table of k/v pairs.
The values from <id_limits_data_t> are used to set handle.id_limit.
From 2025-02-21, MediaWiki is broken. Use this link to edit the tablular data file:
https://commons.wikimedia.org/w/index.php?title=Data:CS1/Identifier_limits.tab&action=edit
See Phab:T389105
]]
local id_limits_data_t = {};
local use_commons_data = true; -- set to false if your wiki does not have access to mediawiki commons; then,
if false == use_commons_data then -- update this table from https://commons.wikimedia.org/wiki/Data:CS1/Identifier_limits.tab; last update: 2025-02-21
id_limits_data_t = {['OCLC'] = 10450000000, ['OSTI'] = 23010000, ['PMC'] = 11900000, ['PMID'] = 40400000, ['RFC'] = 9300, ['SSRN'] = 5200000, ['S2CID'] = 276000000}; -- this table must be maintained locally
else -- here for wikis that do have access to mediawiki commons
local load_fail_limit = 99999999999; -- very high number to avoid error messages on load failure
id_limits_data_t = {['OCLC'] = load_fail_limit, ['OSTI'] = load_fail_limit, ['PMC'] = load_fail_limit, ['PMID'] = load_fail_limit, ['RFC'] = load_fail_limit, ['SSRN'] = load_fail_limit, ['S2CID'] = load_fail_limit};
local id_limits_data_load_fail = false; -- flag; assume that we will be successful when loading json id limit tabular data
local tab_data_t = mw.ext.data.get ('CS1/Identifier limits.tab').data; -- attempt to load the json limit data from commons into <tab_data_t>
if false == tab_data_t then -- undocumented 'feature': mw.ext.data.get() sometimes returns false
id_limits_data_load_fail = true; -- set the flag so that Module:Citation/CS1 can create an unannotated maint category
else
for _, limit_t in ipairs (tab_data_t) do -- overwrite default <load_fail_limit> values
id_limits_data_t[limit_t[1]] = limit_t[2]; -- <limit[1]> is identifier; <limit[2]> is upper limit for that identifier
end
end
end
--[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
The following contains a list of values for various defined identifiers. For each
identifier we specify a variety of information necessary to properly render the
identifier in the citation. parameters: a list of parameter aliases for this identifier; first in the list is the canonical form
link: Wikipedia article name
redirect: a local redirect to a local Wikipedia article name; at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'
q:
label: the label
redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true
local article name from id_handlers['<id>'].link
suffix: optional third part to be added after the identifier
encode: true if
COinS: identifier link or keyword for use in COinS:
for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn
for
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here)
set to nil to leave the identifier out of the COinS
separator: character or text between label and the identifier in the rendered citation
id_limit: for those identifiers with established limits, this property holds the upper limit
access: use this parameter to set the access level for all instances of this identifier.
custom_access: to enable custom access level for an identifier, set this parameter
]]
Line 1,524 ⟶ 2,171:
q = 'Q118398',
label = 'arXiv',
encode = false,
COinS = 'info:arxiv',
Line 1,537 ⟶ 2,183:
q = 'Q1753278',
label = 'ASIN',
separator = ' ',
encode = false;
Line 1,549 ⟶ 2,194:
q = 'Q25754',
label = 'Bibcode',
prefix = 'https://ui.adsabs.harvard.edu/abs/',
encode = false,
Line 1,562 ⟶ 2,206:
q = 'Q19835482',
label = 'bioRxiv',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
Line 1,575 ⟶ 2,218:
q = 'Q2715061',
label = 'CiteSeerX',
prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
Line 1,588 ⟶ 2,230:
q = 'Q25670',
label = 'doi',
COinS = 'info:doi',
separator = ':',
Line 1,597 ⟶ 2,238:
['EISSN'] = {
parameters = {'eissn', 'EISSN'},
link = '
redirect = 'eISSN (identifier)',
q = 'Q46339674',
label = 'eISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.eissn',
encode = false,
Line 1,613 ⟶ 2,253:
q = 'Q3126718',
label = 'hdl',
COinS = 'info:hdl',
separator = ':',
Line 1,621 ⟶ 2,260:
},
['ISBN'] = { -- Used by InternetArchiveBot
parameters = {'isbn', 'ISBN
link = 'International Standard Book Number',
redirect = 'ISBN (identifier)',
q = 'Q33057',
label = 'ISBN',
prefix = 'Special:BookSources/',
COinS = 'rft.isbn',
Line 1,637 ⟶ 2,275:
q = 'Q1666938',
label = 'ISMN',
prefix = '', -- not currently used;
COinS =
separator = ' ',
},
Line 1,648 ⟶ 2,285:
q = 'Q131276',
label = 'ISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.issn',
encode = false,
Line 1,660 ⟶ 2,296:
q = '',
label = 'JFM',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
Line 1,672 ⟶ 2,307:
q = 'Q1420342',
label = 'JSTOR',
prefix = 'https://www.jstor.org/stable/',
COinS = 'pre', -- use prefix value
encode = false,
Line 1,685 ⟶ 2,319:
q = 'Q620946',
label = 'LCCN',
COinS = 'info:lccn',
encode = false,
separator = ' ',
},
['MEDRXIV'] = {
parameters = {'medrxiv'},
link = 'medRxiv',
redirect = 'medRxiv (identifier)',
q = 'Q58465838',
label = 'medRxiv',
prefix = 'https://www.medrxiv.org/content/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = false,
separator = ' ',
Line 1,697 ⟶ 2,342:
q = 'Q211172',
label = 'MR',
prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=',
COinS = 'pre', -- use prefix value
encode = true,
Line 1,709 ⟶ 2,353:
q = 'Q190593',
label = 'OCLC',
prefix = 'https://search.worldcat.org/oclc/',
COinS = 'info:oclcnum',
encode = true,
separator = ' ',
id_limit = id_limits_data_t.OCLC or 0,
},
['OL'] = {
Line 1,721 ⟶ 2,365:
q = 'Q1201876',
label = 'OL',
separator = ' ',
encode = true,
Line 1,734 ⟶ 2,377:
q = 'Q2015776',
label = 'OSTI',
prefix = 'https://www.osti.gov/biblio/',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit = id_limits_data_t.OSTI or 0,
custom_access = 'osti-access',
},
Line 1,747 ⟶ 2,390:
q = 'Q229883',
label = 'PMC',
prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC',
suffix = '',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit =
access = 'free', -- free to read
},
Line 1,760 ⟶ 2,402:
link = 'PubMed Identifier',
redirect = 'PMID (identifier)',
q = 'Q2082879',
label = 'PMID',
prefix = 'https://pubmed.ncbi.nlm.nih.gov/',
COinS = 'info:pmid',
encode = false,
separator = ' ',
id_limit =
},
['RFC'] = {
Line 1,775 ⟶ 2,416:
q = 'Q212971',
label = 'RFC',
prefix = 'https://tools.ietf.org/html/rfc',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
id_limit = id_limits_data_t.RFC or 0,
access = 'free', -- free to read
},
Line 1,787 ⟶ 2,428:
redirect = 'SBN (identifier)',
label = 'SBN',
prefix = 'Special:BookSources/0-', -- prefix has leading zero necessary to make 9-digit sbn a 10-digit isbn
COinS = nil, -- nil because we can't use pre or rft or info:
Line 1,798 ⟶ 2,438:
q = 'Q7550801',
label = 'SSRN',
prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit =
custom_access = 'ssrn-access',
},
['S2CID'] = {
Line 1,812 ⟶ 2,451:
q = 'Q22908627',
label = 'S2CID',
prefix = 'https://api.semanticscholar.org/CorpusID:',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
id_limit =
custom_access = 's2cid-access',
},
Line 1,826 ⟶ 2,464:
q = 'Q193162',
label = 'Usenet:',
prefix = 'news:',
encode = false,
Line 1,838 ⟶ 2,475:
q = 'Q190269',
label = 'Zbl',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
Line 1,847 ⟶ 2,483:
--[[--------------------------< E X P O R T S >
]]
return {
use_identifier_redirects =
local_lang_cat_enable = local_lang_cat_enable,
date_name_auto_xlate_enable = date_name_auto_xlate_enable,
date_digit_auto_xlate_enable = date_digit_auto_xlate_enable,
enable_sort_keys = enable_sort_keys,
-- tables and variables created when this module is loaded
global_df = get_date_format (), -- this line can be replaced with "global_df = 'dmy-all'," to have all dates auto translated to dmy format.
global_cs1_config_t = global_cs1_config_t, -- global settings from {{cs1 config}}
punct_skip = build_skip_table (punct_skip, punct_meta_params),
url_skip = build_skip_table (url_skip, url_meta_params),
known_free_doi_registrants_t = build_free_doi_registrants_table(),
id_limits_data_load_fail = id_limits_data_load_fail, -- true when commons tabular identifier-limit data fails to load
name_space_sort_keys = name_space_sort_keys,
aliases = aliases,
special_case_translation = special_case_translation,
Line 1,860 ⟶ 2,509:
editor_markup_patterns = editor_markup_patterns,
et_al_patterns = et_al_patterns,
extended_registrants_t = extended_registrants_t,
id_handlers = id_handlers,
keywords_lists = keywords_lists,
keywords_xlate = keywords_xlate,
stripmarkers = stripmarkers,
invisible_chars = invisible_chars,
invisible_defs = invisible_defs,
indic_script = indic_script,
emoji_t = emoji_t,
maint_cats = maint_cats,
messages = messages,
presentation = presentation,
prop_cats = prop_cats,
script_lang_codes = script_lang_codes,
lang_tag_remap = lang_tag_remap,
lang_name_remap = lang_name_remap,
this_wiki_code = this_wiki_code,
title_types = title_types,
uncategorized_namespaces =
uncategorized_subpages = uncategorized_subpages,
templates_using_volume = templates_using_volume,
templates_using_issue = templates_using_issue,
templates_not_using_page = templates_not_using_page,
vol_iss_pg_patterns = vol_iss_pg_patterns,
single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t,
inter_wiki_map = inter_wiki_map,
mw_languages_by_tag_t = mw_languages_by_tag_t,
mw_languages_by_name_t = mw_languages_by_name_t,
citation_class_map_t = citation_class_map_t,
citation_issue_t = citation_issue_t,
citation_no_volume_t = citation_no_volume_t,
}
| |||