Module:Citation/CS1/Configuration: Difference between revisions

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

--[[--------------------------------------------------------

List of namespaces that ~~should~~ not be included in citation error categories.

List of namespaces identifiers for namespaces that will not be included in citation error categories.

Same as setting notracking = true by default.

~~Note~~: ~~Namespace~~ names ~~should use underscores instead of spaces.~~

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~~ = { ~~'User', 'Talk', 'User_talk', 'Wikipedia_talk',~~

local uncategorized_namespaces_t = {[2]=true}; -- init with user namespace id

~~'File_talk', 'Template_talk', 'Help_talk', 'Category_talk', 'Portal_talk'~~,

for k, _ in pairs (mw.site.talkNamespaces) do -- add all talk namespace ids

~~'Book_talk', 'Draft_talk', 'Education_Program_talk', 'Module_talk', 'MediaWiki_talk' }~~;

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 29:

Line 69:

['archived-dead'] = 'Archived from $1 on $2',

['archived-live'] = '$1 from the original on $2',

['archived-~~missing~~'] = 'Archived from the original$1 ~~on $2',~~

['archived-unfit'] = 'Archived from the original on $1',

~~['archived-unfit'] = 'Archived from the original on~~ ',

['archived'] = 'Archived',

['by'] = 'By', -- contributions to authored works: introduction, foreword, afterword

Line 40:

Line 79:

['et al'] = 'et al.',

['in'] = 'In', -- edited works

['inactive'] = 'inactive',

['inactive'] = ' (inactive $1)', -- $1 is date which the doi was found to be broken in

['inset'] = '$1 inset',

['interview'] = 'Interviewed by $1',

['~~lay summary~~'] = '~~Lay summary~~',

invisible_1 = '$1 $2', -- $1 stripmarker name; $2 is text from <invisible_chars[1]>

invisible_2 = '$1 character', -- $1 character name from <invisible_chars[1]>

['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name

['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1',

Line 58:

Line 98:

['translated'] = 'Translated by $1',

['type'] = ' ($1)', -- for titletype

wikidata = 'Wikidata', -- these used for interwikilinked author/editor/... names

wikipedia = 'Wikipedia',

wikisource = 'Wikisource',

['written'] = 'Written at $1',

['vol'] = '$1 Vol. $2', -- $1 is sepc; bold journal style volume is in presentation{}

['vol-no'] = '$1 Vol. $2 no. $3', -- sepc, volume, issue

['vol-no'] = '$1 Vol. $2, no. $3', -- sepc, volume, issue (alternatively insert $1 after $2, but then we'd also have to change capitalization)

['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 81:

Line 130:

['via'] = " – via $1",

['event'] = 'Event occurs at',

['minutes'] = 'minutes in',

['minutes'] = ' $1 minutes in', -- $1 is the number of minutes

-- Determines the location of the help page

Line 89:

Line 138:

-- categories

['cat wikilink'] = '[[Category:$1]]', -- $1 is the category name

['cat wikilink sk'] = '[[Category:$1|$2]]', -- $1 is the category name; $2 is namespace sort key

[':cat wikilink'] = '[[:Category:$1|link]]', -- category name as maintenance message wikilink; $1 is the category name

-- Internal errors (should only occur if configuration is bad)

['undefined_error'] = 'Called with an undefined error condition',

['unknown_ID_key'] = 'Unrecognized ID key', -- an ID key in id_handlers not found in ~/Identifiers func_map{}

['unknown_ID_key'] = 'Unrecognized ID key: ', -- an ID key in id_handlers not found in ~/Identifiers func_map{}

['unknown_ID_access'] = 'Unrecognized ID access keyword: ', -- an ID access keyword in id_handlers not found in keywords_lists['id-access']{}

['unknown_argument_map'] = 'Argument map not defined for this variable',

['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty',

['warning_msg_e'] = '<code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code>: this [[#$2|reference]] has errors; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link; $2 is anchor ID

['warning_msg_m'] = '<code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code>: this [[#$2|reference]] has maintenance messages; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link; $2 is anchor ID

}

--[[--------------------------< C I T A T I O N _ C L A S S _ M A P >------------------------------------------

this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when

the value assigned to |CitationClass= is different from the canonical template name. |CitationClass= values are

used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while

the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the

template's documentation when an article is displayed in preview mode.

]]

local citation_class_map_t = { -- TODO: in Module:Cite/config write a function to use this table

arxiv = 'cite arXiv', -- as the source for known_templates_t and citation_classes_t

['audio-visual'] = 'cite AV media',

['AV-media-notes'] = 'cite AV media notes',

biorxiv = 'cite bioRxiv',

book = 'cite book',

citation = 'citation',

citeseerx = 'cite CiteSeerX',

conference = 'cite conference',

document = 'cite document',

encyclopaedia = 'cite encyclopedia',

episode = 'cite episode',

interview = 'cite interview',

journal = 'cite journal',

magazine = 'cite magazine',

mailinglist = 'cite mailing list',

map = 'cite map',

medrxiv = 'cite medRxiv',

news = 'cite news',

newsgroup = 'cite newsgroup',

podcast = 'cite podcast',

pressrelease = 'cite press release',

report = 'cite report',

serial = 'cite serial',

sign = 'cite sign',

speech = 'cite speech',

ssrn = 'cite SSRN',

techreport = 'cite tech report',

thesis = 'cite thesis',

web = 'cite web',

}

Line 107:

Line 204:

local et_al_patterns = {

"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$", -- variations on the 'et al' theme

"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$", -- variations on the 'et al' theme

"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.\"']*$", -- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)

"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.;,\"']*$", -- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)

"[;,]? *%f[%a]and [Oo]thers", -- an alternative to et al.

"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form

"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax)

"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form

}

--[[--------------------------< E ~~D I~~ T ~~O R _ M A R K U P _ P~~ A T ~~T E R~~ N S >~~----------~~------------------------

--[[--------------------------------------------------

~~This table provides Lua patterns for the phrase "ed" and variants in name text~~

Fixed presentation markup. Originally part of citation_config.messages it has

~~(author, editor, etc~~.). ~~The main module uses these to identify and emit the~~

been moved into its own, more semantically correct place.

~~'extra_text_names' message. (It is not the only series of patterns for this message~~.)

]]

~~local editor_markup_patterns = { -- these patterns match annotations at end of name~~

~~'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'~~

~~'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)~~

~~'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'~~

~~'[,%.%s]%f[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive~~

~~-- these patterns match annotations at beginning of name~~

~~'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.'~~

~~'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'~~

~~'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also square brackets, case insensitive, optional brackets, 's'~~

~~'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also square brackets, case insensitive, optional brackets~~

~~-- these patterns match annotations that are the 'name'~~

local presentation =

~~'^[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors; case insensitive~~

}

~~--[[--------------------------------------------------~~

~~Fixed presentation markup. Originally part of citation_config.messages it has~~

~~been moved into its own, more semantically correct place.~~

]]

local presentation =

{

~~-- Error output~~

~~-- .error class is specified at https://git.wikimedia.org/blob/mediawiki%2Fcore.git/9553bd02a5595da05c184f7521721fb1b79b3935/skins%2Fcommon%2Fshared.css#L538~~

-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display

['hidden-error'] = '$1',

['hidden-error'] = '$1',

['visible-error'] = '$1',

['visible-error'] = '$1',

['hidden-maint'] = '$1',

Line 160:

Line 231:

['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like

['cite'] = '<cite class="$1">$2</cite>'; -- |ref= not set so no id="..." attribute

['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 |ref= is set

['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when when |ref= is set or when citation has a namelist

['format'] = ' ($1)', -- for |format=, |chapter-format=, etc.

['interwiki'] = ' [in $1]', -- for interwiki-language-linked author, editor, etc

['interproj'] = ' [at $1]', -- for interwiki-project-linked author, editor, etc (:d: and :s: supported; :w: ignored)

-- various access levels, for |access=, |doi-access=, |arxiv=, ...

Line 169:

Line 242:

['ext-link-access-signal'] = '$3', -- external link with appropriate lock icon

['free'] = {class='~~cs1~~-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css

['free'] = {class='id-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css

['registration'] = {class='~~cs1~~-lock-registration', title='Free registration required'},

['registration'] = {class='id-lock-registration', title='Free registration required'},

['limited'] = {class='~~cs1~~-lock-limited', title='Free access subject to limited trial, subscription normally required'},

['limited'] = {class='id-lock-limited', title='Free access subject to limited trial, subscription normally required'},

['subscription'] = {class='~~cs1~~-lock-subscription', title='Paid subscription required'},

['subscription'] = {class='id-lock-subscription', title='Paid subscription required'},

['interwiki-icon'] = '$3',

Line 179:

Line 252:

['italic-title'] = "''$1''",

['kern-left'] = '$1$2', -- spacing to use when title contains leading single or double quote mark

['kern-left'] = '$1', -- spacing to use when title contains leading single or double quote mark

['kern-right'] = '$1$2', -- spacing to use when title contains trailing single or double quote mark

['kern-right'] = '$1', -- spacing to use when title contains trailing single or double quote mark

~~-- these for simple wikilinked titles [["text]], [[text"]] and [["text"]]~~

~~-- span wraps entire wikilink~~

~~['kern-wl-left'] = '$1', -- when title contains leading single or double quote mark~~

~~['kern-wl-right'] = '$1', -- when title contains trailing single or double quote mark~~

~~['kern-wl-both'] = '$1', -- when title contains leading and trailing single or double quote marks~~

['nowrap1'] = '$1', -- for nowrapping an item: yyyy-mm-dd

Line 194:

Line 261:

['parameter'] = '<code class="cs1-code">|$1=</code>',

['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character

['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string)

['quoted-text'] = '<q>$1</q>', -- for wrapping |quote= content

['quoted-title'] = '\'$1\'',

['quoted-title'] = '"$1"',

['sep_cs1'] = '.', -- CS1 element separator

Line 206:

Line 273:

['sep_nl_and'] = ' and ', -- used as last nl sep when |name-list-style=and and list has 2 items

['sep_nl_end'] = '; and ', -- used as last nl sep when |name-list-style=and and list has 3+ names

['sep_name'] = ' ', -- CS1|2 style last/first separator is <comma><space>

['sep_name'] = ', ', -- CS1|2 style last/first separator is <comma><space>

['sep_nl_vanc'] = ',', -- Vancouver style name-list separator between authors is a comma

['sep_name_vanc'] = ' ', -- Vancouver style last/first separator is a space

Line 235:

Line 302:

['ArchiveFormat'] = 'archive-format',

['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot

['ArticleNumber'] = 'article-number',

['ASINTLD'] = 'asin-tld',

['At'] = 'at', -- Used by InternetArchiveBot

['Authors'] = {~~'authors',~~ 'people', 'credits'},

['Authors'] = {'people', 'credits'},

['BookTitle'] = {'book-title', 'booktitle'},

['Cartography'] = 'cartography',

['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'},

~~['ChapterWikilink'] = {'chapter-wikilink'},~~

['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format',

'article-format', 'section-format'};

['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url',

['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url'}, -- Used by InternetArchiveBot

'section-url~~', 'chapterurl~~'}, -- Used by InternetArchiveBot

['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access',

'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot

['Class'] = 'class', -- cite arxiv and arxiv ~~identifiers~~

['Class'] = 'class', -- cite arxiv and arxiv identifier

['Collaboration'] = 'collaboration',

['Conference'] = {'conference', 'event'},

Line 272:

Line 338:

['Issue'] = {'issue', 'number'},

['Language'] = {'language', 'lang'},

~~['LayDate'] = 'lay-date',~~

~~['LayFormat'] = 'lay-format',~~

~~['LaySource'] = 'lay-source',~~

~~['LayURL'] = 'lay-url',~~

['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only

['Map'] = 'map', -- cite map only

Line 306:

Line 368:

['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',

Line 323:

Line 386:

['Title'] = 'title', -- Used by InternetArchiveBot

['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot

['TitleNote'] = 'department',

['TitleNote'] = {'title-note', 'department'},

['TitleType'] = {'type', 'medium'},

['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution',

Line 329:

Line 392:

['Transcript'] = 'transcript',

['TranscriptFormat'] = 'transcript-format',

['TranscriptURL'] = {'transcript-url', '~~transcripturl~~'}, -- ~~Used by InternetArchiveBot~~

['TranscriptURL'] = 'transcript-url', -- Used by InternetArchiveBot

['TransEncyclopedia'] = {'trans-encyclopedia', 'trans-encyclopaedia'}, -- cite encyclopedia only

['TransMap'] = 'trans-map', -- cite map only

['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper',

Line 344:

Line 408:

['Year'] = 'year',

['AuthorList-First'] = {"first#", "author-first#", "author#-first", "given#",

['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given",

"~~author~~-given#", "~~author~~#-given"},

"subject-first#", "subject#-first", "subject-given#", "subject#-given",

['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "surname#",

"given#"},

"~~author~~-surname#", "~~author~~#-surname", "author#", "subject#", ~~'host~~#'},

['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname",

"subject-last#", "subject#-last", "subject-surname#", "subject#-surname",

"author#", 'host#', "subject#", "surname#"},

['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#",

"subject#-link", "authorlink#", "author#link"},

Line 387:

Line 453:

]]

local ~~punct_skip~~ = {};

local punct_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value

~~local meta_params = {~~ -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value

'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters

'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators

'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous

'ArchiveURL', 'ChapterURL', 'ConferenceURL', '~~LayURL~~', 'MapURL', 'TranscriptURL', 'URL', -- ~~URL~~-~~holding parameters~~

'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters

}

local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value

'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls

'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls

}

local function build_skip_table (skip_t, meta_params)

for _, meta_param in ipairs (meta_params) do -- for each meta parameter key

local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name

if 'string' == type (params) then

~~punct_skip~~[params] = 1; -- just a single parameter

skip_t[params] = 1; -- just a single parameter

else

for _, param in ipairs (params) do -- get the parameter name

~~punct_skip~~[param] = 1; -- add the parameter name to the skip table

skip_t[param] = 1; -- add the parameter name to the skip table

local count;

param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters

if 0 ~= count then -- if removed

~~punct_skip~~[param] = 1; -- add param name without enumerator marker

skip_t[param] = 1; -- add param name without enumerator marker

end

return skip_t;

end

local punct_skip = {};

local url_skip = {};

--[[----------------------------------------------------------------------------

this table used by the wikipedia library url test, has_twl_url(), which automatically sets a url-access parameter

to 'subscription' when it discovers a wikipedia library url in any of the url-holding paramters used as keys in

this table.

--~~[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------~~

translators: if your wiki uses parameter names for these url-holding parameters and their matching -access parameters,

add your wiki's parameters to this list. Leave the English parameters in place.

~~This table~~ is ~~primarily here~~ to ~~support internationalization. Translations in~~

TODO: is there a better way to do this?

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 special_case_translation = {

local url_access_map_t = {

['chapter-url'] = 'chapter-url-access',

['contribution-url'] = 'contribution-url-access',

['entry-url'] = 'entry-url-access',

['article-url'] = 'article-url-access',

['section-url'] = 'section-url-access',

['map-url'] = 'map-url-access',

['mapurl'] = 'map-url-access',

['url'] = 'url-access',

['URL'] = 'url-access'

}

--[[--------------------------< S I N G L E - L E T T E R S E C O N D - L E V E L D O M A I N S >----------

this is a list of tlds that are known to have single-letter second-level domain names. This list does not include

ccTLDs which are accepted in is_domain_name().

]]

local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'media', 'org', 'today'};

--[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------

This table is primarily here to support internationalization. Translations in

this table are used, for example, when an error message, category name, etc.,

is extracted from the English alias key. There may be other cases where

this translation table may be useful.

]]

local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191';

local special_case_translation = {

author = 'author',

editor = 'editor',

name_list_params = '$1-name-list parameters', -- $1 is 'author' or 'editor'; used with err_redundant_parameters

['AuthorList'] = 'authors list', -- used to assemble maintenance category names

['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base ~~mainenance~~ category names in maint_cats{} table below

['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base maintenance category names in maint_cats{} table below

['EditorList'] = 'editors list', -- must match the names of the actual categories

['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names()

Line 437:

Line 552:

-- Lua patterns to match generic titles; usually created by bots or reference filling tools

-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language

~~['generic_titles'] = {~~

-- generic titles and patterns in this table should be lowercase only

-- patterns in this table should be lowercase only

-- leave ['local'] nil except when there is a matching generic title in your language

~~-- generic titles must be lowercase~~

-- boolean 'true' for plain-text searches; 'false' for pattern searches

{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil},

{['en'] = {'are you a robot', true}, ['local'] = nil},

['generic_titles'] = {

{['en'] = {'hugedomains~~.com~~', true}, ['local'] = nil},

['accept'] = {

{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil},

},

{['en'] = {'page not found', true}, ['local'] = nil},

['reject'] = {

{['en'] = {'subscribe to read', true}, ['local'] = nil},

{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil},

{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil},

{['en'] = {'are you a robot', true}, ['local'] = nil},

{['en'] = {'website is for sale', true}, ['local'] = nil},

{['en'] = {'hugedomains', true}, ['local'] = nil},

{['en'] = {'^404', ~~true~~}, ['local'] = nil},

{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil},

{['en'] = {'internet archive wayback machine', true}, ['local'] = nil},

{['en'] = {'page not found', true}, ['local'] = nil},

{['en'] = {'log into facebook', true}, ['local'] = nil},

{['en'] = {'subscribe to read', true}, ['local'] = nil},

{['en'] = {'redirecting...', true}, ['local'] = nil},

{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil},

{['en'] = {'webcite query result', true}, ['local'] = nil},

{['en'] = {'website is for sale', true}, ['local'] = nil},

{['en'] = {'wikiwix\'s cache', 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},

{['en'] = {'bot verification', true}, ['local'] = nil},

}

},

-- boolean 'true' for plain-text searches, search string must be lowercase only

-- boolean 'false' for pattern searches

-- leave ['local'] nil except when there is a matching generic name in your language

['generic_names'] = {

['accept'] = {

{['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false}, ['local'] = nil},

},

['reject'] = {

{['en'] = {'about us', true}, ['local'] = nil},

{['en'] = {'%f[%a][Aa]dvisor%f[%A]', false}, ['local'] = nil},

{['en'] = {'allmusic', true}, ['local'] = nil},

{['en'] = {'%f[%a][Aa]uthor%f[%A]', false}, ['local'] = nil},

{['en'] = {'^[Bb]ureau$', false}, ['local'] = nil},

{['en'] = {'business', true}, ['local'] = nil},

{['en'] = {'cnn', true}, ['local'] = nil},

{['en'] = {'collaborator', true}, ['local'] = nil},

{['en'] = {'^[Cc]ompany$', false}, ['local'] = nil},

{['en'] = {'contributor', true}, ['local'] = nil},

{['en'] = {'contact us', true}, ['local'] = nil},

{['en'] = {'correspondent', true}, ['local'] = nil},

{['en'] = {'^[Dd]esk$', false}, ['local'] = nil},

{['en'] = {'directory', true}, ['local'] = nil},

{['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false}, ['local'] = nil},

{['en'] = {'[,%.%s]%f[e]eds?%.?$', false}, ['local'] = nil},

{['en'] = {'^eds?[%.,;]', false}, ['local'] = nil},

{['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false}, ['local'] = nil},

{['en'] = {'%f[%a][Ee]dited%f[%A]', false}, ['local'] = nil},

{['en'] = {'%f[%a][Ee]ditors?%f[%A]', false}, ['local'] = nil},

{['en'] = {'%f[%a][Ee]mail%f[%A]', false}, ['local'] = nil},

{['en'] = {'facebook', true}, ['local'] = nil},

{['en'] = {'google', true}, ['local'] = nil},

{['en'] = {'^[Gg]roup$', false}, ['local'] = nil},

{['en'] = {'home page', true}, ['local'] = nil},

{['en'] = {'^[Ii]nc%.?$', false}, ['local'] = nil},

{['en'] = {'instagram', true}, ['local'] = nil},

{['en'] = {'interviewer', true}, ['local'] = nil},

{['en'] = {'^[Ll]imited$', false}, ['local'] = nil},

{['en'] = {'linkedIn', true}, ['local'] = nil},

{['en'] = {'^[Nn]ews$', false}, ['local'] = nil},

{['en'] = {'[Nn]ews[ %-]?[Rr]oom', false}, ['local'] = nil},

{['en'] = {'pinterest', true}, ['local'] = nil},

{['en'] = {'policy', true}, ['local'] = nil},

{['en'] = {'privacy', true}, ['local'] = nil},

{['en'] = {'reuters', true}, ['local'] = nil},

{['en'] = {'translator', true}, ['local'] = nil},

{['en'] = {'tumblr', true}, ['local'] = nil},

{['en'] = {'twitter', true}, ['local'] = nil},

{['en'] = {'site name', true}, ['local'] = nil},

{['en'] = {'statement', true}, ['local'] = nil},

{['en'] = {'submitted', true}, ['local'] = nil},

{['en'] = {'super.?user', false}, ['local'] = nil},

{['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false}, ['local'] = nil},

{['en'] = {'updated', true}, ['local'] = nil},

{['en'] = {'verfasser', true}, ['local'] = nil},

}

Line 481:

Line 662:

Easter and Christmas are defined here as 98 and 99, which should be out of the

ISO 8601 (EDTF) range of uses for a while.

local_date_names_from_mediawiki is a boolean. When set to:

true – module will fetch local month names from MediaWiki for both date_names['local']['long'] and date_names['local']['short']; this will unconditionally overwrite manual translations

false – module will *not* fetch local month names from MediaWiki

Caveat lector: There is no guarantee that MediaWiki will provide short month names. At your wiki you can test

the results of the MediaWiki fetch in the debug console with this command (the result is alpha sorted):

=mw.dumpObject (p.date_names['local'])

While the module can fetch month names from MediaWiki, it cannot fetch the quarter, season, and named date names

from MediaWiki. Those must be translated manually.

]]

local local_date_names_from_mediawiki = true; -- when false, manual translation required for date_names['local']['long'] and date_names['local']['short']; overwrites manual translations

-- when true, module fetches long and short month names from MediaWiki

local date_names = {

['en'] = { -- English

Line 492:

Line 686:

['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 499:

Line 694:

['named'] = {['Easter'] = 98, ['Christmas'] = 99},

},

['~~inv_local_l~~'] = {}, -- used in date reformatting; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.

['inv_local_long'] = {}, -- used in date reformatting & translation; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.

['~~inv_local_s~~'] = {}, -- used in date reformatting; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.

['inv_local_short'] = {}, -- used in date reformatting & translation; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.

['inv_local_quarter'] = {}, -- used in date translation; copy of date_names['local'].quarter where k/v are inverted: [1]='<local name>' etc.

['inv_local_season'] = {}, -- used in date translation; copy of date_names['local'].season where k/v are inverted: [1]='<local name>' etc.

['inv_local_named'] = {}, -- used in date translation; copy of date_names['local'].named where k/v are inverted: [1]='<local name>' etc.

['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9

['xlate_digits'] = {},

}

for name, i in pairs (date_names['local']~~.long~~) do -- this table is ['name'] = i

if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled

date_names[~~'inv_local_l'~~][i] = name; -- invert to get [i] = 'name' for conversions from ymd

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

for ~~name~~, ~~i in pairs (date_names['local'].short)~~ do -- ~~this table is~~ [~~'name'~~] = i

if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled

date_names['~~inv_local_s~~'~~][i~~] = ~~name~~; ~~-- invert to get [i] = 'name' for conversions from ymd~~

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 532:

Line 749:

'{{ *([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 ()

~~local~~ content ~~= mw.title.getCurrentTitle():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~~

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

~~content~~ = content:match ('%b{}', start); -- get the whole template

local use_dates_template = content:match ('%b{}', start); -- get the whole template

if ~~content~~:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length

if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length

return match:lower() .. '-' .. ~~content~~:match ('| *cs1%-dates *= *([lsy][sy]?)');

return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)');

else

return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df=

Line 548:

Line 773:

end

local global_df ~~= get_date_format ()~~;

local global_df; -- TODO: add this to <global_cs1_config_t>?

Line 563:

Line 788:

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',

}

--[[

Line 574:

Line 815:

bad_ppatterns = { -- patterns for |page= and |pages=

'^[Pp][PpGg]?%.?[ %d]',

'^[Pp][Pp]?%. ', -- from {{p.}} and {{pp.}} templates

'^[Pp]ages?',

'^[Pp]gs.?',

},

~~vpatterns~~ = { -- ~~patterns for~~ |volume=

vi_patterns_t = { -- combined to catch volume-like text in |issue= and issue-like text in |volume=

'^volumes?',

'^volumes?', -- volume-like text

'^vols?[%.:=]?'

'^vols?[%.:=]?',

},

~~ipatterns = { -- patterns for |issue=~~

'^issues?', --issue-like text

'^issues?',

'^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[%.:= ]', -- 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)

},

}

Line 619:

Line 862:

['cs1'] = {'cs1'}, -- |mode=

['cs2'] = {'cs2'}, -- |mode=

['dead'] = {'dead'}, -- |url-status= -- Used by InternetArchiveBot

['dead'] = {'dead', 'deviated'}, -- |url-status= -- Used by InternetArchiveBot

['dmy'] = {'dmy'}, -- |df=

['dmy-all'] = {'dmy-all'}, -- |df=

['foreword'] = {'foreword'}, -- |contribution=

['free'] = {'free'}, -- |~~url~~-access= -- Used by InternetArchiveBot

['free'] = {'free'}, -- |<id>-access= -- Used by InternetArchiveBot

['harv'] = {'harv'}, -- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true

['introduction'] = {'introduction'}, -- |contribution=

['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot

Line 715:

Line 959:

['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 721:

Line 966:

--[[---------------------< S ~~T R~~ I ~~P M A R K~~ E ~~R S~~ >----------------------------

--[[--------------------------< C S 1 _ C O N F I G _ G E T >--------------------------------------------------

fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t>

no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked.

~~Common pattern definition location for stripmarkers so that we don't have to go~~

Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors,

~~hunting for them if~~ (~~when~~) ~~MediaWiki changes their form~~.

DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode. The DisplayWhatever metaparameters

accept numeric values only (|display-authors=etal and the like is not supported).

]]

local ~~stripmarkers~~ = {

local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table?

~~['any'] = '\127[^\127]*UNIQ%~~-%-(~~%a+~~)%-~~[%a%d]+%~~-~~QINU[^\127]*\127~~', -- ~~capture returns name of stripmarker~~

~~['math']~~ = '~~\127~~[~~^\127~~]*UNIQ%-%-math%-[~~%a%d~~]~~+%-QINU~~[~~^\127~~]*\127' -- ~~math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()~~

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

~~This~~ table ~~holds non~~-~~printing or invisible characters indexed either by name or~~

local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'};

~~by Unicode group. Values are decimal representations of UTF~~-~~8 codes. The table~~

local meta_param_map_t = {}; -- list of accepted parameter names usable in {{cs1 config}} goes here

~~is organized as~~ a ~~table~~ of ~~tables because~~ the ~~Lua pairs~~ keyword ~~returns table~~

~~data~~ in ~~an arbitrary order~~. ~~Here, we want to process~~ the ~~table from top to bottom~~

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

~~because~~ the ~~entries at~~ the ~~top of~~ the table ~~are also found in the ranges specified~~

if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence,

by the ~~entries at~~ the ~~bottom of~~ the table.

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

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

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

~~Also here is a pattern that recognizes stripmarkers that begin and end with the~~

get_cs1_config (); -- fill <global_cs1_config_t>

~~delete characters. The nowiki stripmarker is not an error but some others are~~

~~because the parameter values that include them become part of the template's~~

~~metadata before stripmarker replacement.~~

]]

~~local invisible_defs = {~~

--[[---------------------< S T R I P M A R K E R S >----------------------------

~~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 = {~~

Common pattern definition location for stripmarkers so that we don't have to go

{'~~replacement', '\239\191\189'}, -- U+FFFD, EF BF BD~~

hunting for them if (when) MediaWiki changes their form.

~~{'zero width joiner', '~~('.~~. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed~~

~~{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B~~

]]

{~~'hair space', '\226\128\138'}, -- U+200A, E2 80 8A~~

{'~~soft hyphen~~', '\~~194~~\~~173'},~~ -- U+~~00AD, C2 AD~~

local stripmarkers = {

~~{'horizontal tab', '\009'}, -- U+0009 (HT~~)~~, 09~~

['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127', -- capture returns name of stripmarker

~~{'line feed', '\010'},~~ -~~- U~~+~~000A (LF), 0A~~

['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127' -- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()

~~{'no~~-~~break space', '~~\~~194~~\~~160'}, -- U+00A0 (NBSP), C2 A0~~

~~{'carriage return', '\013'}, -- U+000D (CR), 0D~~

~~{'stripmarker~~', ~~stripmarkers.any},~~ -- ~~stripmarker; may or may not be an error;~~ capture returns ~~the stripmaker type~~

~~{'delete', '('.. invisible_defs.del .. ')'}, -- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part~~ of stripmarker

~~{'C0 control~~', '~~[\000-\008\011\012\014-\031~~]'~~}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))~~

~~{'C1 control', '[\194\128-\194~~\~~159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F~~

~~-- {'Specials', '~~[\~~239\191\185-\239\191\191~~]~~'},~~ -- ~~U+FFF9~~-~~U+FFFF, EF BF B9 – EF BF BF~~

~~-- {'Private use area', '~~[~~\238\128\128-\239\163\191~~]~~'}, -- U~~+~~E000–U+F8FF, EE 80 80 – EF A3 BF~~

~~-- {'Supplementary Private Use Area~~-~~A', '~~[\~~243\176\128\128-\243\191\191\189~~]~~'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD~~

~~-- {'Supplementary Private Use Area-B', '[\244~~\~~128\128\128-\244\143\191\189]~~'}, -- ~~U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD~~

}

--[[

~~Indic script makes use of zero width joiner as a character modifier so zwj~~

--[[---------------------------------

~~characters must be left in.~~ This ~~pattern covers all of the unicode~~ characters

~~for these languages:~~

This table holds non-printing or invisible characters indexed either by name or

~~Devanagari 0900–097F – https://unicode~~.~~org/charts/PDF/U0900~~.~~pdf~~

by Unicode group. Values are decimal representations of UTF-8 codes. The table

~~Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf~~

is organized as a table of tables because the Lua pairs keyword returns table

~~Bengali 0980–09FF – https://unicode~~.~~org/charts/PDF/U0980.pdf~~

data in an arbitrary order. Here, we want to process the table from top to bottom

~~Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf~~

because the entries at the top of the table are also found in the ranges specified

~~Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80~~.~~pdf~~

by the entries at the bottom of the table.

~~Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf~~

~~Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf~~

Also here is a pattern that recognizes stripmarkers that begin and end with the

~~Telugu 0C00–0C7F – https://unicode~~.~~org/charts/PDF/U0C00.pdf~~

delete characters. The nowiki stripmarker is not an error but some others are

~~Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf~~

because the parameter values that include them become part of the template's

~~Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf~~

metadata before stripmarker replacement.

~~plus~~ the ~~not-necessarily Indic scripts for Sinhala and Burmese:~~

~~Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf~~

~~Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf~~

~~Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf~~

~~Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0~~.~~pdf~~

~~the pattern is used by has_invisible_chars() and coins_cleanup()~~

]]

local ~~indic_script~~ = '[\~~224\164\128~~-~~\224\181\191\224\163\160~~-\~~224\183\191\225~~\128\~~128~~-~~\225\130\159\234\167\160~~-~~\234\167\191\234\169\160-\234\169\191]';~~

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

}

~~-- list of emoji that use zwj character (U+200D) to combine with another emoji~~

local invisible_chars = {

local ~~emoji~~ = { ~~-- indexes are decimal forms of the hex values in U+xxxx~~

{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD

~~[127752] = true~~, -- U+~~1F308 🌈 rainbow~~

{'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed

~~[127806] = true~~, -- U+~~1F33E 🌾 ear of rice~~

{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B

~~[127859] = true~~, -- U+~~1F373 🍳 cooking~~

{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A

~~[127891] = true~~, -- U+~~1F393 🎓 graduation cap~~

{'soft hyphen', '\194\173'}, -- U+00AD, C2 AD

~~[127908] = true~~, -- U+~~1F3A4 🎤 microphone~~

{'horizontal tab', '\009'}, -- U+0009 (HT), 09

~~[127912] = true~~, -- U+~~1F3A8 🎨 artist palette~~

{'line feed', '\010'}, -- U+000A (LF), 0A

~~[127979] = true~~, -- U+~~1F3EB 🏫 school~~

{'no-break space', '\194\160'}, -- U+00A0 (NBSP), C2 A0

~~[127981] = true~~, -- U+~~1F3ED 🏭 factory~~

{'carriage return', '\013'}, -- U+000D (CR), 0D

~~[128102] = true~~, -- U+~~1F466 👦 boy~~

{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type

~~[128103] = true~~, -- ~~U+1F467 👧 girl~~

{'delete', '('.. invisible_defs.del .. ')'}, -- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker

~~[128104] = true~~, -- U+~~1F468 👨 man~~

{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))

[~~128105] = true,~~ -- ~~U+1F469 👩 woman~~

{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F

~~[128139~~] ~~= true~~, -- U+~~1F48B 💋 kiss mark~~

-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF

[~~128187~~] ~~= true~~, -- U+~~1F4BB 💻 personal computer~~

-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF

~~[128188] = true,~~ -- ~~U+1F4BC 💼 brief case~~

-- {'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

[~~128295~~] ~~= true~~, -- U+~~1F527 🔧 wrench~~

-- {'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

~~[128300] = true, -~~- U+~~1F52C 🔬 microscope~~

~~[128488] = true,~~ -- ~~U+1F5E8 🗨 left speech bubble~~

~~[128640] = true~~, ~~-- U+1F680 🚀 rocket~~

[~~128658] = true,~~ -~~- U+1F692 🚒 fire engine~~

~~[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~~

~~[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~~

~~[9992] = true, -- U~~+~~2708 ✈ airplane~~

~~[10084] = true~~, ~~-- U+2764 ❤ heavy black heart~~

}

--[[

--[[---~~-------------------< L~~ A ~~N G U A G E S U P P O R T >---------------~~----

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

~~These tables~~ and ~~constants support various language-specific functionality.~~

for these languages:

Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf

Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf

Bengali 0980–09FF – https://unicode.org/charts/PDF/U0980.pdf

Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf

Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf

Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf

Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf

Telugu 0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf

Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf

Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf

plus the not-necessarily Indic scripts for Sinhala and Burmese:

Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf

Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf

Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf

Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf

the pattern is used by has_invisible_chars() and coins_cleanup()

]]

local ~~this_wiki_code~~ = ~~mw.getContentLanguage():getCode();~~ -- ~~get this wiki's language code~~

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]';

~~if string.match (mw.site.server, 'wikidata') then~~

~~this_wiki_code = mw.getCurrentFrame():preprocess('{{int:lang}}~~'); ~~-- on Wikidata so use interface language setting instead~~

~~end~~

~~local languages = mw.language.fetchLanguageNames (this_wiki_code, 'all');~~ -- ~~get a~~ list of ~~language names known~~ to ~~Wikimedia~~; ~~used for |language= and interwiki tests~~

-- list of emoji that use a zwj character (U+200D) to combine with another emoji

-- from: https://unicode.org/Public/emoji/17.0/emoji-zwj-sequences.txt; version: 17.0; 2025-01-08

local ~~inter_wiki_map~~ = {}; -- ~~map~~ of ~~interwiki prefixes that are language~~-~~code prefixes~~

-- table created by: [[:en:Module:Make emoji zwj table]]

~~for k~~, ~~v in pairs (mw.site.interwikiMap ('local')) do~~ -- ~~spin through the base interwiki map (limited to local)~~

local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx

~~if languages~~[v[~~"prefix"~~]] ~~then~~ -- ~~if the prefix matches a known language code~~

[8596] = true, -- U+2194 ↔ left right arrow

~~inter_wiki_map~~[v[~~"prefix"~~]] = true; -- ~~add it to our local map~~

[8597] = true, -- U+2195 ↕ up down arrow

~~end~~

[9760] = true, -- U+2620 ☠ skull and crossbones

~~end~~

[9792] = true, -- U+2640 ♀ female sign

[9794] = true, -- U+2642 ♂ male sign

~~local local_lang_cat_enable~~ = ~~false;~~ -- ~~set to~~ true ~~to categorize pages where |language~~=~~<local wiki's language>~~

[9877] = true, -- U+2695 ⚕ staff of aesculapius

[9878] = true, -- U+2696 ⚖ scales

[9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign

--[[--------------------~~< S C R I P T _ L A N G _ C O D E S >~~-------------------

[9992] = true, -- U+2708 ✈ airplane

[10052] = true, -- U+2744 ❄ snowflake

~~This table is used to hold ISO 639~~-~~1 two~~-~~character and ISO 639~~-~~3 three~~-~~character~~

[10084] = true, -- U+2764 ❤ heavy black heart

~~language codes that apply only to |script~~-~~title~~= ~~and |script~~-~~chapter~~=

[10145] = true, -- U+27A1 ➡ black rightwards arrow

[11035] = true, -- U+2B1B ⬛ black large square

]]

[127752] = true, -- U+1F308 🌈 rainbow

[127787] = true, -- U+1F32B 🌫 fog

~~local script_lang_codes~~ = {

[127806] = true, -- U+1F33E 🌾 ear of rice

~~'am'~~, ~~'ar'~~, ~~'be'~~, ~~'bg'~~, ~~'bn'~~, ~~'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu'~~,

[127859] = true, -- U+1F373 🍳 cooking

~~'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo'~~,

[127868] = true, -- U+1F37C 🍼 baby bottle

~~'mk', 'ml', 'mn', 'mr', 'my', 'ne', 'or', 'ota', 'ps', 'ru', 'sd', 'si'~~,

[127876] = true, -- U+1F384 🎄 christmas tree

~~'sr'~~, ~~'ta', 'te', 'tg', 'th', 'ti', 'ug', 'uk', 'ur', 'uz', 'yi', 'zh'~~

[127891] = true, -- U+1F393 🎓 graduation cap

};

[127908] = true, -- U+1F3A4 🎤 microphone

[127912] = true, -- U+1F3A8 🎨 artist palette

[127979] = true, -- U+1F3EB 🏫 school

[127981] = true, -- U+1F3ED 🏭 factory

[128048] = true, -- U+1F430 🐰 rabbit face

[128102] = true, -- U+1F466 👦 boy

[128103] = true, -- U+1F467 👧 girl

[128104] = true, -- U+1F468 👨 man

[128105] = true, -- U+1F469 👩 woman

[128139] = true, -- U+1F48B 💋 kiss mark

[128165] = true, -- U+1F4A5 💥 collision symbol

[128168] = true, -- U+1F4A8 💨 dash symbol

[128171] = true, -- U+1F4AB 💫 dizzy symbol

[128187] = true, -- U+1F4BB 💻 personal computer

[128188] = true, -- U+1F4BC 💼 brief case

[128293] = true, -- U+1F525 🔥 fire

[128295] = true, -- U+1F527 🔧 wrench

[128300] = true, -- U+1F52C 🔬 microscope

[128488] = true, -- U+1F5E8 🗨 left speech bubble

[128640] = true, -- U+1F680 🚀 rocket

[128658] = true, -- U+1F692 🚒 fire engine

[129001] = true, -- U+1F7E9 🟩 large green square

[129003] = true, -- U+1F7EB 🟫 large brown square

[129309] = true, -- U+1F91D 🤝 handshake

[129455] = true, -- U+1F9AF 🦯 probing cane

[129456] = true, -- U+1F9B0 🦰 emoji component red hair

[129457] = true, -- U+1F9B1 🦱 emoji component curly hair

[129458] = true, -- U+1F9B2 🦲 emoji component bald

[129459] = true, -- U+1F9B3 🦳 emoji component white hair

[129466] = true, -- U+1F9BA 🦺 safety vest

[129468] = true, -- U+1F9BC 🦼 motorized wheelchair

[129469] = true, -- U+1F9BD 🦽 manual wheelchair

[129489] = true, -- U+1F9D1 🧑 adult

[129490] = true, -- U+1F9D2 🧒 child

[129648] = true, -- U+1FA70 🩰 ballet shoes

[129657] = true, -- U+1FA79 🩹 adhesive bandage

[129775] = true, -- U+1FAEF 🫯 fight cloud

[129778] = true, -- U+1FAF2 🫲 leftwards hand

}

--[[---------------< L A N G U A G E ~~R E M A~~ P P ~~I N G~~ >~~---~~-------------------

--[[----------------------< L A N G U A G E S U P P O R T >-------------------

These tables ~~hold~~ language ~~information that is different (correct) from MediaWiki's definitions~~

These tables and constants support various language-specific functionality.

~~For each ['code'~~] ~~= 'language name' in lang_code_remap{} there must be a matching ['language name'~~] ~~= {'language name', 'code'} in lang_name_remap{}~~

]]

~~lang_code_remap{}~~:

--local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code

~~key is always lowercase ISO 639~~-~~1, -2,~~ -3 language code ~~or a valid lowercase IETF language tag~~

local this_wiki_code = lang_obj:getCode(); -- get this wiki's language code

~~value is properly spelled and capitalized language name associated with key~~

if string.match (mw.site.server, 'wikidata') then

~~only one~~ language ~~name per key;~~

this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead

~~key/value pair must have matching entry in lang_name_remap{}~~

end

lang_name_remap{}:

local mw_languages_by_tag_t = mw.language.fetchLanguageNames (this_wiki_code, 'all'); -- get a table of language tag/name pairs known to Wikimedia; used for interwiki tests

key is always lowercase language name

local mw_languages_by_name_t = {};

value is a table the holds correctly spelled and capitalized language name [1] and associated ~~code~~ [2] (~~code~~ must match a ~~code~~ key in ~~lang_code_remap~~{})

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=

may have multiple keys referring to a common preferred name and ~~code~~; For example:

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

local inter_wiki_map = {}; -- map of interwiki prefixes that are language-code prefixes

for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local)

if mw_languages_by_tag_t[v["prefix"]] then -- if the prefix matches a known language tag

inter_wiki_map[v["prefix"]] = true; -- add it to our local map

end

--[[--------------------< S C R I P T _ L A N G _ C O D E S >-------------------

This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character

language codes that apply only to |script-title= and |script-chapter=

]]

local script_lang_codes = {

'ab', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'ce', 'chr',

'cu', 'dv', 'dz', 'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka',

'kaa', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni',

'mr', 'my', 'ne', 'or', 'ota', 'pa', 'ps', 'ru', 'sd', 'si', 'sr', 'syc',

'ta', 'te', 'tg', 'th', 'ti', 'tkr', 'tt', 'ug', 'uk', 'ur', 'uz', 'yi',

'yue', 'zh', 'zgh'

};

--[[---------------< L A N G U A G E R E M A P P I N G >----------------------

These tables hold language information that is different (correct) from MediaWiki's definitions

For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{}

lang_tag_remap{}:

key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag

value is properly spelled and capitalized language name associated with <tag>

only one language name per <tag>;

key/value pair must have matching entry in lang_name_remap{}

lang_name_remap{}:

key is always lowercase language name

value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{})

may have multiple keys referring to a common preferred name and tag; For example:

['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'

]]

local ~~lang_code_remap~~ = { -- used for |language= and |script-title= / |script-chapter=

local lang_tag_remap = { -- used for |language= and |script-title= / |script-chapter=

['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch

['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org

Line 906:

Line 1,257:

['bn'] = 'Bengali', -- MediaWiki returns Bangla

['ca-valencia'] = 'Valencian', -- IETF variant of Catalan

['~~crh~~'] = '~~Crimean Tatar~~', -- ~~synonymous with Crimean Turkish (return value from {{#language:crh|en}})~~

['fkv'] = 'Kven', -- MediaWiki returns Kvensk

['gsw'] = 'Swiss German',

['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name

['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name

Line 912:

Line 1,264:

['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=

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 922:

Line 1,277:

['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name

['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh

~~['crimean tatar'] = {'Crimean Tatar', 'crh'}, -- MediaWiki uses 'crh' as a subdomain name for Crimean Tatar Wikipedia: crh.wikipedia.org~~

['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

['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-TW'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese

['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'}, -- special case to get correct tag when |language=sr-ec

['serbian (latin script)'] = {'Serbian (Latin script)', 'sr-latn'}, -- special case to get correct tag when |language=sr-el

['swiss german'] = {'Swiss German', 'gsw'},

['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese

['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found

['valencian'] = {'Valencian', 'ca'}, -- variant of Catalan; categorizes as ~~Catalan~~

['valencian'] = {'Valencian', 'ca-valencia'}, -- variant of Catalan; categorizes as Valencian

}

Line 940:

Line 1,299:

local prop_cats = {

['~~foreign_lang_source~~'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code

['foreign-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code

['~~foreign_lang_source_2~~'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key

['foreign-lang-source-2'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key

['~~local_lang_source~~'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false

['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

['location test'] = 'CS1 location test',

['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

['~~script~~'] = 'CS1 ~~uses foreign language script~~', -- ~~when language specified by~~ |~~script-title~~=~~xx: doesn't have its own category~~

['local-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false

['~~script_with_name~~'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ~~ISO639~~-1 ~~code~~

['location-test'] = 'CS1 location test',

['~~jul_greg_uncertainty~~'] = 'CS1: ~~Julian–Gregorian uncertainty~~', -- ~~probably temporary~~ cat ~~to identify scope of template with dates 1 October 1582 – 1 January 1926~~

['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters

['~~long_vol~~'] = 'CS1: ~~long volume value~~', -- ~~probably temporary cat to identify scope of~~ |~~volume~~= ~~values longer than 4 charachters~~

['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is language tag

['~~year_range_abbreviated~~'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form

['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

}

Line 960:

Line 1,322:

local title_types = {

['AV-media-notes'] = 'Media notes',

['document'] = 'Document',

['interview'] = 'Interview',

['mailinglist'] = 'Mailing list',

Line 966:

Line 1,329:

['pressrelease'] = 'Press release',

['report'] = 'Report',

['speech'] = 'Speech',

['techreport'] = 'Technical report',

['thesis'] = 'Thesis',

}

--[[----------------------------

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', '9778', '11131', '11569', '11647',

'11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995',

'17645', '18637', '19080', '19173', '20944', '21037', '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', '53347', '54081', '54947', '55667', '55914', '57009', '58647', '59081',

}) do

registrants_t[v] = true; -- build a k/v table of known free-to-read doi registrants

end

return registrants_t;

end

local extended_registrants_t = { -- known free registrants identifiable by the doi suffix incipit

['1002'] = {'aelm', 'leap'}, -- Advanced Electronic Materials, Learned Publishing

['1016'] = {'j.aace', 'j.aed', 'j.aiopen', 'j.animal', 'j.apsb', 'j.addicn',-- AACE Endocrinology and Diabetes, AACE Endocrinology and Diabetes, AI Open, Animal, Acta Pharmaceutica Sinica B, Addiction Neuroscience

'j.abrep', 'j.gpb', 'j.heliyon', 'j.nlp', 'j.patter', 'j.proche', -- Addictive Behaviors Reports, Genomics, Proteomics & Bioinformatics after 2015, Heliyon, Natural Language Processing, Patterns, Procedia Chemistry

'j.vgie', 'S1672-0229'}, -- VideoGIE, Genomics, Proteomics & Bioinformatics before 2015

['1017'] = {'nlp'}, -- Natural Language Processing Journal

['1046'] = {'j.1365-8711', 'j.1365-246x'}, -- MNRAS, GJI

['1093'] = {'mnras', 'mnrasl', 'gji', 'pnasnexus', 'rasti'}, -- MNRAS, MNRAS Letters, GJI, PNAS Nexus, RASTI

['1098'] = {'rsos'}, -- Royal Society Open Science

['1099'] = {'acmi', 'mic', '00221287', 'mgen'}, -- Access Microbiology, Microbiology, Journal of General Microbiology, Microbial Genomics

['1107'] = {'S20569890', 'S20522525', 'S16005775', 'S24143146'}, -- Acta Crystallographica E, IUCrJ, Journal of Synchrotron Radiation, IUCrData

['1109'] = {'oa', 'oj'}, -- IEEE Open Access..., IEEE Open Journal...

['1111'] = {'j.1365-2966', 'j.1745-3933', 'j.1365-246X'}, -- MNRAS, MNRAS Letters, GJI

['1128'] = {'asmcr', 'jmbe', 'mbio', 'mra', 'spectrum', 'msphere', 'msystems'}, --ASM Case Reports, Journal of Microbiology & Biology Education, mBio, Microbiology Resource Announcements, Microbiology Spectrum, mSphere, mSystems

['1210'] = {'jendso','jcemcr'}, -- Journal of the Endocrine Society, JCEM Case Reports

['4171'] = {'dm','mag'}, -- Documenta Mathematica, EMS Magazine

['11158'] = {'saasp'}, -- Systematic and Applied Acarology Special Publications

['11646'] = {'megataxa', 'mesozoic'}, -- Megataxa, Mesozoic

['14231'] = {'ag'}, -- Algebraic Geometry

['22073'] = {'pja'}, -- Persian Journal of Acarology

['35249'] = {'rche'}, -- Revista Chilena de Entomología

['37520'] = {'fi'}, -- Fossil Imprint

['53562'] = {'ajcb'} -- Asian Journal of Conservation Biology

}

Line 985:

Line 1,405:

['char'] = 'invalid character', -- |isbn=, |sbn=

['check'] = 'checksum', -- |isbn=, |sbn=

empty_str = '(empty string)', -- empty unknown parameter check when cite has |=

['flag'] = 'flag', -- |archive-url=

['form'] = 'invalid form', -- |isbn=, |sbn=

['group'] = 'invalid group id', -- |isbn=

['initials'] = 'initials', -- Vancouver

['invalid language code'] = 'invalid language code', -- |script-<param>=

['journal'] = 'journal', -- |bibcode=

['length'] = 'length', -- |isbn=, |bibcode=, |sbn=

['liveweb'] = 'liveweb', -- |archive-url=

['missing comma'] = 'missing comma', -- Vancouver

['missing prefix'] = 'missing prefix', -- |script-<param>=

['missing title part'] = 'missing title part', -- |script-<param>=

['name'] = 'name', -- Vancouver

['non-Latin char'] = 'non-Latin character', -- Vancouver

Line 1,001:

Line 1,425:

['suffix'] = 'suffix', -- Vancouver

['timestamp'] = 'timestamp', -- |archive-url=

['unknown language code'] = 'unknown language code', -- |script-<param>=

['value'] = 'value', -- |bibcode=

['year'] = 'year', -- |bibcode=

Line 1,035:

Line 1,460:

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>',

Line 1,153:

Line 1,590:

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 1,351:

Line 1,794:

anchor = 'extra_text_volume',

category = 'CS1 errors: extra text: volume',

hidden = ~~true~~,

hidden = false,

},

err_first_missing_last = {

message = '<code class="cs1-code">|$1=</code> missing <code class="cs1-code">|$2=</code>', -- $1 is first alias, $2 is matching last alias

anchor = 'first_missing_last',

category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator

hidden = false

},

Line 1,364:

Line 1,807:

category = 'CS1 errors: format without URL',

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 1,370:

Line 1,819:

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 1,381:

Line 1,836:

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 1,393:

Line 1,854:

anchor = 'missing_periodical',

category = 'CS1 errors: missing periodical',

hidden = ~~true~~

hidden = false

},

err_missing_pipe = {

Line 1,400:

Line 1,861:

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 1,411:

Line 1,884:

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 1,423:

Line 1,902:

anchor = 'parameter_ignored_suggest',

category = 'CS1 errors: unsupported parameter',

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 1,440:

Line 1,925:

message = '<code class="cs1-code">|ssrn=</code> required',

anchor = 'ssrn_missing',

category = 'CS1 errors: SSRN', ~~-- same as bad arxiv~~

category = 'CS1 errors: SSRN',

hidden = false

},

Line 1,481:

Line 1,966:

]]

maint_archived_copy = {

message = nil,

Line 1,487:

Line 1,973:

hidden = true,

},

~~maint_authors~~ = {

maint_bibcode = {

message = nil,

anchor = 'bibcode',

category = 'CS1 maint: bibcode',

hidden = true,

},

maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite

message = nil,

anchor = '~~authors~~',

anchor = 'location_no_publisher',

category = 'CS1 maint: ~~uses authors parameter~~',

category = 'CS1 maint: location missing publisher',

hidden = true,

},

Line 1,497:

Line 1,989:

anchor = 'bot:_unknown',

category = 'CS1 maint: bot: original URL status unknown',

hidden = true,

},

maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki

message = nil,

anchor = 'date_auto_xlated',

category = 'CS1 maint: date auto-translated',

hidden = true,

},

Line 1,509:

Line 2,007:

anchor = 'date_year',

category = 'CS1 maint: date and year',

~~hidden = true,~~

},

~~maint_discouraged = {~~

~~message = nil,~~

~~anchor = 'discouraged',~~

~~category = 'CS1 maint: discouraged parameter',~~

hidden = true,

},

Line 1,533:

Line 2,025:

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 1,541:

Line 2,039:

hidden = true,

},

~~maint_extra_text_names~~ = {

maint_id_limit_load_fail = { -- applies to all cs1|2 templates on a page;

message = nil,

message = nil, -- maint message (category link) never emitted

anchor = '~~extra_text_names~~',

anchor = 'id_limit_load_fail',

category = 'CS1 maint: ~~extra text: $1~~', ~~-- $1 is '<name>s list'; gets value from special_case_translation table~~

category = 'CS1 maint: ID limit load fail',

hidden = true,

},

Line 1,570:

Line 2,068:

category = 'CS1 maint: location',

hidden = true,

},

maint_mr_format = {

maint_missing_class = {

message = nil,

anchor = 'missing_class',

category = 'CS1 maint: missing class',

hidden = true,

},

maint_mr_format = {

message = nil,

anchor = 'mr_format',

category = 'CS1 maint: MR format',

hidden = true,

},

maint_mult_names = {

message = nil,

Line 1,600:

Line 2,104:

category = 'CS1 maint: others in cite AV media (notes)',

hidden = true,

},

maint_overridden_setting = {

message = nil,

anchor = 'overridden',

category = 'CS1 maint: overridden setting',

hidden = true,

},

maint_page_art_num = {

message = nil,

anchor = 'page_art_num',

category = 'CS1 maint: article number as page number',

hidden = true,

},

maint_pmc_embargo = {

message = nil,

Line 1,617:

Line 2,133:

anchor = 'postscript',

category = 'CS1 maint: postscript',

hidden = true,

},

maint_publisher_location = {

message = nil,

anchor = 'publisher_location',

category = 'CS1 maint: publisher location',

hidden = true,

},

Line 1,625:

Line 2,147:

hidden = true,

},

~~maint_ref_harv = {~~

~~message = nil,~~

~~anchor = 'ref_harv',~~

~~category = 'CS1 maint: ref=harv',~~

~~hidden = true,~~

},

~~maint_unfit = {~~

~~message = nil,~~

~~anchor = 'unfit',~~

~~category = 'CS1 maint: unfit URL',~~

~~hidden = true,~~

},

maint_unknown_lang = {

message = nil,

Line 1,649:

Line 2,159:

hidden = true,

},

~~maint_zbl~~ = {

maint_url_status = {

message = nil,

anchor = 'url_status',

category = 'CS1 maint: url-status',

hidden = true,

},

maint_work_isbn = {

message = nil,

anchor = '~~zbl~~',

anchor = 'work_isbn',

category = 'CS1 maint: ~~Zbl~~',

category = 'CS1 maint: work parameter with ISBN',

hidden = true,

},

}

maint_year= {

message = nil,

anchor = 'year',

category = 'CS1 maint: year',

hidden = true,

},

maint_zbl = {

message = nil,

anchor = 'zbl',

category = 'CS1 maint: Zbl',

hidden = true,

},

}

--[[------------------------------------------------------------------------

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'); -- attempt to load the tabular data from commons into <tab_data_t>

if false == tab_data_t then -- undocumented 'feature': mw.ext.data.get() sometimes returns false

id_limits_data_load_fail = true; -- set the flag so that Module:Citation/CS1 can create an unannotated maint category

else

for _, limit_t in ipairs (tab_data_t.data) do -- overwrite default <load_fail_limit> values from the data table in the tabular data

id_limits_data_t[limit_t[1]] = limit_t[2]; -- <limit[1]> is identifier; <limit[2]> is upper limit for that identifier

end

--[[----------------------------------------------------------------------------------

Line 1,668:

Line 2,232:

redirect: a local redirect to a local Wikipedia article name; at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'

q: Wikidata q number for the identifier

label: the label ~~preceeding~~ the identifier; label is linked to a Wikipedia article (in this order):

label: the label preceding the identifier; label is linked to a Wikipedia article (in this order):

redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true

Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q

Line 1,687:

Line 2,251:

custom_access: to enable custom access level for an identifier, set this parameter

to the parameter that should control it (normally 'id-access')

]]

Line 1,696:

Line 2,261:

q = 'Q118398',

label = 'arXiv',

prefix = '//arxiv.org/abs/', ~~-- protocol-relative tested 2013-09-04~~

prefix = 'https://arxiv.org/abs/',

encode = false,

COinS = 'info:arxiv',

Line 1,708:

Line 2,273:

q = 'Q1753278',

label = 'ASIN',

prefix = '//www.amazon.',

prefix = 'https://www.amazon.',

COinS = 'url',

separator = ' ',

Line 1,731:

Line 2,296:

q = 'Q19835482',

label = 'bioRxiv',

prefix = '//doi.org/',

prefix = 'https://doi.org/',

COinS = 'pre', -- use prefix value

access = 'free', -- free to read

Line 1,743:

Line 2,308:

q = 'Q2715061',

label = 'CiteSeerX',

prefix = '//citeseerx.ist.psu.edu/viewdoc/summary?doi=',

prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=',

COinS = 'pre', -- use prefix value

access = 'free', -- free to read

Line 1,755:

Line 2,320:

q = 'Q25670',

label = 'doi',

prefix = '//doi.org/',

prefix = 'https://doi.org/',

COinS = 'info:doi',

separator = ':',

Line 1,767:

Line 2,332:

q = 'Q46339674',

label = 'eISSN',

prefix = '//~~www~~.worldcat.org/issn/',

prefix = 'https://search.worldcat.org/issn/',

COinS = 'rft.eissn',

encode = false,

Line 1,778:

Line 2,343:

q = 'Q3126718',

label = 'hdl',

prefix = '//hdl.handle.net/',

prefix = 'https://hdl.handle.net/',

COinS = 'info:hdl',

separator = ':',

Line 1,785:

Line 2,350:

},

['ISBN'] = { -- Used by InternetArchiveBot

parameters = {'isbn', 'ISBN~~', 'isbn13', 'ISBN13~~'},

parameters = {'isbn', 'ISBN'},

link = 'International Standard Book Number',

redirect = 'ISBN (identifier)',

Line 1,807:

Line 2,372:

parameters = {'issn', 'ISSN'},

link = 'International Standard Serial Number',

redirect = '',

redirect = 'ISSN (identifier)',

q = 'Q131276',

label = 'ISSN',

prefix = '//~~www~~.worldcat.org/issn/',

prefix = 'https://search.worldcat.org/issn/',

COinS = 'rft.issn',

encode = false,

Line 1,821:

Line 2,386:

q = '',

label = 'JFM',

prefix = '//zbmath.org/?format=complete&q=an:',

prefix = 'https://zbmath.org/?format=complete&q=an:',

COinS = 'pre', -- use prefix value

encode = true,

Line 1,832:

Line 2,397:

q = 'Q1420342',

label = 'JSTOR',

prefix = '//www.jstor.org/stable/', ~~-- protocol-relative tested 2013-09-04~~

prefix = 'https://www.jstor.org/stable/',

COinS = 'pre', -- use prefix value

encode = false,

Line 1,844:

Line 2,409:

q = 'Q620946',

label = 'LCCN',

prefix = '//lccn.loc.gov/', ~~-- protocol-relative tested 2015-12-28~~

prefix = 'https://lccn.loc.gov/',

COinS = 'info:lccn',

encode = false,

separator = ' ',

},

['MR'] = {

['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 = ' ',

},

['MR'] = {

parameters = {'mr', 'MR'},

link = 'Mathematical Reviews',

Line 1,855:

Line 2,432:

q = 'Q211172',

label = 'MR',

prefix = '//~~www~~.ams.org/mathscinet-getitem?mr=', ~~-- protocol-relative tested 2013-09-04~~

prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=',

COinS = 'pre', -- use prefix value

encode = true,

Line 1,866:

Line 2,443:

q = 'Q190593',

label = 'OCLC',

prefix = '//~~www~~.worldcat.org/oclc/',

prefix = 'https://search.worldcat.org/oclc/',

COinS = 'info:oclcnum',

encode = true,

separator = ' ',

id_limit = ~~9999999999~~, ~~-- 10-digits~~

id_limit = id_limits_data_t.OCLC or 0,

},

['OL'] = {

Line 1,878:

Line 2,455:

q = 'Q1201876',

label = 'OL',

prefix = '//openlibrary.org/',

prefix = 'https://openlibrary.org/',

COinS = 'url',

separator = ' ',

Line 1,890:

Line 2,467:

q = 'Q2015776',

label = 'OSTI',

prefix = '//www.osti.gov/biblio/', ~~-- protocol-relative tested 2018-09-12~~

prefix = 'https://www.osti.gov/biblio/',

COinS = 'pre', -- use prefix value

encode = true,

separator = ' ',

id_limit = ~~23000000~~,

id_limit = id_limits_data_t.OSTI or 0,

custom_access = 'osti-access',

},

Line 1,903:

Line 2,480:

q = 'Q229883',

label = 'PMC',

prefix = '//www.ncbi.nlm.nih.gov/pmc/articles/PMC',

prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC',

suffix = '',

COinS = 'pre', -- use prefix value

encode = true,

separator = ' ',

id_limit = ~~8300000~~,

id_limit = id_limits_data_t.PMC or 0,

access = 'free', -- free to read

},

Line 1,917:

Line 2,494:

q = 'Q2082879',

label = 'PMID',

prefix = '//pubmed.ncbi.nlm.nih.gov/',

prefix = 'https://pubmed.ncbi.nlm.nih.gov/',

COinS = 'info:pmid',

encode = false,

separator = ' ',

id_limit = ~~34400000~~,

id_limit = id_limits_data_t.PMID or 0,

},

['RFC'] = {

Line 1,929:

Line 2,506:

q = 'Q212971',

label = 'RFC',

prefix = '//tools.ietf.org/html/rfc',

prefix = 'https://tools.ietf.org/html/rfc',

COinS = 'pre', -- use prefix value

encode = false,

separator = ' ',

id_limit = ~~9000~~,

id_limit = id_limits_data_t.RFC or 0,

access = 'free', -- free to read

},

Line 1,951:

Line 2,528:

q = 'Q7550801',

label = 'SSRN',

prefix = '//ssrn.com/~~abstract~~=', ~~-- protocol-relative tested 2013-09-04~~

prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=',

COinS = 'pre', -- use prefix value

encode = true,

separator = ' ',

id_limit = ~~4000000~~,

id_limit = id_limits_data_t.SSRN or 0,

~~access~~ = '~~free~~', ~~-- always free to read~~

custom_access = 'ssrn-access',

},

['S2CID'] = {

Line 1,968:

Line 2,545:

encode = false,

separator = ' ',

id_limit = ~~235000000~~,

id_limit = id_limits_data_t.S2CID or 0,

custom_access = 's2cid-access',

},

Line 1,988:

Line 2,565:

q = 'Q190269',

label = 'Zbl',

prefix = '//zbmath.org/?format=complete&q=an:',

prefix = 'https://zbmath.org/?format=complete&q=an:',

COinS = 'pre', -- use prefix value

encode = true,

Line 1,999:

Line 2,576:

]]

return {

use_identifier_redirects = ~~true~~, -- when true ~~use redirect name for~~ identifier ~~label links~~

use_identifier_redirects = use_identifier_redirects, -- booleans defined in the settings at the top of this module

local_lang_cat_enable = local_lang_cat_enable,

date_name_auto_xlate_enable = date_name_auto_xlate_enable,

date_digit_auto_xlate_enable = date_digit_auto_xlate_enable,

enable_sort_keys = enable_sort_keys,

-- 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,

date_names = date_names,

err_msg_supl = err_msg_supl,

error_conditions = error_conditions,

editor_markup_patterns = editor_markup_patterns,

et_al_patterns = et_al_patterns,

extended_registrants_t = extended_registrants_t,

id_handlers = id_handlers,

keywords_lists = keywords_lists,

keywords_xlate = keywords_xlate,

stripmarkers = stripmarkers,

invisible_chars = invisible_chars,

invisible_defs = invisible_defs,

indic_script = indic_script,

emoji_t = emoji_t,

maint_cats = maint_cats,

messages = messages,

presentation = presentation,

prop_cats = prop_cats,

script_lang_codes = script_lang_codes,

lang_tag_remap = lang_tag_remap,

lang_name_remap = lang_name_remap,

this_wiki_code = this_wiki_code,

title_types = title_types,

uncategorized_namespaces = uncategorized_namespaces_t,

uncategorized_subpages = uncategorized_subpages,

templates_using_volume = templates_using_volume,

templates_using_issue = templates_using_issue,

templates_not_using_page = templates_not_using_page,

vol_iss_pg_patterns = vol_iss_pg_patterns,

single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t,

url_access_map_t = url_access_map_t,

inter_wiki_map = inter_wiki_map,

mw_languages_by_tag_t = mw_languages_by_tag_t,

mw_languages_by_name_t = mw_languages_by_name_t,

citation_class_map_t = citation_class_map_t,

~~aliases~~ = ~~aliases~~,

citation_issue_t = citation_issue_t,

~~special_case_translation~~ = ~~special_case_translation,~~

citation_no_volume_t = citation_no_volume_t,

~~date_names = date_names,~~

~~err_msg_supl = err_msg_supl,~~

~~error_conditions = error_conditions,~~

~~editor_markup_patterns = editor_markup_patterns,~~

~~et_al_patterns = et_al_patterns,~~

~~global_df = global_df,~~

~~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 = emoji,~~

~~local_lang_cat_enable = local_lang_cat_enable,~~

~~maint_cats = maint_cats,~~

~~messages = messages,~~

~~presentation = presentation,~~

~~prop_cats = prop_cats,~~

~~punct_skip = punct_skip,~~

~~script_lang_codes = script_lang_codes,~~

~~lang_code_remap = lang_code_remap,~~

~~lang_name_remap = lang_name_remap,~~

~~this_wiki_code = this_wiki_code,~~

~~title_types = title_types,~~

~~uncategorized_namespaces = 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,~~

~~inter_wiki_map = inter_wiki_map,~~

~~languages = languages~~,

}

@@ Line 1: / 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 that should not be included in citation error categories.
+List of namespaces identifiers for namespaces that will not be included in citation error categories.
 Same as setting notracking = true by default.
-Note: Namespace names should use underscores instead of spaces.
+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 = { 'User', 'Talk', 'User_talk', 'Wikipedia_talk',
+local uncategorized_namespaces_t = {[2]=true};										-- init with user namespace id
-	'File_talk', 'Template_talk', 'Help_talk', 'Category_talk', 'Portal_talk',
+for k, _ in pairs (mw.site.talkNamespaces) do									-- add all talk namespace ids
-	'Book_talk', 'Draft_talk', 'Education_Program_talk', 'Module_talk', 'MediaWiki_talk' };
+	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 29: / Line 69: @@
 	['archived-dead'] = 'Archived from $1 on $2',
 	['archived-live'] = '$1 from the original on $2',
-	['archived-missing'] = 'Archived from the original$1 on $2',
+	['archived-unfit'] = 'Archived from the original on $1',
-	['archived-unfit'] = 'Archived from the original on ',
 	['archived'] = 'Archived',
 	['by'] = 'By',																-- contributions to authored works: introduction, foreword, afterword
@@ Line 40: / Line 79: @@
 	['et al'] = 'et&nbsp;al.',
 	['in'] = 'In',																-- edited works
-	['inactive'] = 'inactive',
+	['inactive'] = ' (inactive $1)',											-- $1 is date which the doi was found to be broken in
 	['inset'] = '$1 inset',
 	['interview'] = 'Interviewed by $1',
-	['lay summary'] = 'Lay summary',
+	invisible_1 = '$1 $2',														-- $1 stripmarker name; $2 is text from <invisible_chars[1]>
+	invisible_2 = '$1 character',												-- $1 character name from <invisible_chars[1]>
 	['mismatch'] = '<code class="cs1-code">&#124;$1=</code> / <code class="cs1-code">&#124;$2=</code> mismatch',	-- $1 is year param name; $2 is date param name
 	['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]:&nbsp;$1',
@@ Line 58: / Line 98: @@
 	['translated'] = 'Translated by $1',
 	['type'] = ' ($1)',															-- for titletype
+	wikidata = 'Wikidata',														-- these used for interwikilinked author/editor/... names
+	wikipedia = 'Wikipedia',
+	wikisource = 'Wikisource',
 	['written'] = 'Written at $1',
 	['vol'] = '$1 Vol.&nbsp;$2',												-- $1 is sepc; bold journal style volume is in presentation{}
-	['vol-no'] = '$1 Vol.&nbsp;$2 no.&nbsp;$3',									-- sepc, volume, issue
+	['vol-no'] = '$1 Vol.&nbsp;$2, no.&nbsp;$3',								-- sepc, volume, issue (alternatively insert $1 after $2, but then we'd also have to change capitalization)
 	['issue'] = '$1 No.&nbsp;$2',												-- $1 is sepc
+	['art'] = '$1 Art.&nbsp;$2',												-- $1 is sepc; for {{cite conference}} only
+	['vol-art'] = '$1 Vol.&nbsp;$2, art.&nbsp;$3',								-- sepc, volume, article-number; for {{cite conference}} only
 	['j-vol'] = '$1 $2',														-- sepc, volume; bold journal volume is in presentation{}
 	['j-issue'] = ' ($1)',
+	['j-article-num'] = ' $1',													-- TODO: any punctuation here? static text?
 	['nopp'] = '$1 $2';															-- page(s) without prefix; $1 is sepc
@@ Line 81: / Line 130: @@
 	['via'] = " &ndash; via $1",
 	['event'] = 'Event occurs at',
-	['minutes'] = 'minutes in',
+	['minutes'] = ' $1 minutes in',												-- $1 is the number of minutes
 	-- Determines the location of the help page
@@ Line 89: / Line 138: @@
 	-- categories
 	['cat wikilink'] = '[[Category:$1]]',										-- $1 is the category name
+	['cat wikilink sk'] = '[[Category:$1|$2]]',									-- $1 is the category name; $2 is namespace sort key
 	[':cat wikilink'] = '[[:Category:$1|link]]',								-- category name as maintenance message wikilink; $1 is the category name
 	-- Internal errors (should only occur if configuration is bad)
 	['undefined_error'] = 'Called with an undefined error condition',
-	['unknown_ID_key'] = 'Unrecognized ID key',									-- an ID key in id_handlers not found in ~/Identifiers func_map{}
+	['unknown_ID_key'] = 'Unrecognized ID key: ',								-- an ID key in id_handlers not found in ~/Identifiers func_map{}
+	['unknown_ID_access'] = 'Unrecognized ID access keyword: ',					-- an ID access keyword in id_handlers not found in keywords_lists['id-access']{}
 	['unknown_argument_map'] = 'Argument map not defined for this variable',
 	['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty',
+	['warning_msg_e'] = '<span style="color:#d33"><code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code>: this [[#$2|reference]] has errors</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).';	-- $1 is template link; $2 is anchor ID
+	['warning_msg_m'] = '<span style="color:#085"><code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code>: this [[#$2|reference]] has maintenance messages</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).';	-- $1 is template link; $2 is anchor ID
 	}
+--[[--------------------------< C I T A T I O N _ C L A S S _ M A P >------------------------------------------
+this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when
+the value assigned to |CitationClass= is different from the canonical template name.  |CitationClass= values are
+used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while
+the canonical template name may.  These names are used in warning_msg_e and warning_msg_m to create links to the
+template's documentation when an article is displayed in preview mode.
+]]
+	local citation_class_map_t = {												-- TODO: in Module:Cite/config write a function to use this table
+		arxiv = 'cite arXiv',													-- as the source for known_templates_t and citation_classes_t
+		['audio-visual'] = 'cite AV media',
+		['AV-media-notes'] = 'cite AV media notes',
+		biorxiv = 'cite bioRxiv',
+		book = 'cite book',
+		citation = 'citation',
+		citeseerx = 'cite CiteSeerX',
+		conference = 'cite conference',
+		document = 'cite document',
+		encyclopaedia = 'cite encyclopedia',
+		episode = 'cite episode',
+		interview = 'cite interview',
+		journal = 'cite journal',
+		magazine = 'cite magazine',
+		mailinglist = 'cite mailing list',
+		map = 'cite map',
+		medrxiv = 'cite medRxiv',
+		news = 'cite news',
+		newsgroup = 'cite newsgroup',
+		podcast = 'cite podcast',
+		pressrelease = 'cite press release',
+		report = 'cite report',
+		serial = 'cite serial',
+		sign = 'cite sign',
+		speech = 'cite speech',
+		ssrn = 'cite SSRN',
+		techreport = 'cite tech report',
+		thesis = 'cite thesis',
+		web = 'cite web',
+		}
@@ Line 107: / Line 204: @@
 local et_al_patterns = {
-	"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$",						-- variations on the 'et al' theme
+	"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$",						-- variations on the 'et al' theme
-	"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.\"']*$",				-- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)
+	"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.;,\"']*$",		-- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)
 	"[;,]? *%f[%a]and [Oo]thers",												-- an alternative to et al.
 	"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]",										-- a wikilinked form
-	"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)",									-- a double-bracketed form (to counter partial removal of ((...)) syntax)
+	"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)",										-- a double-bracketed form (to counter partial removal of ((...)) syntax)
 	"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]",									-- a bracketed form
 	}
---[[--------------------------< E D I T O R _ M A R K U P _ P A T T E R N S >----------------------------------
+--[[--------------------------< P R E S E N T A T I O N >------------------------
-This table provides Lua patterns for the phrase "ed" and variants in name text
+Fixed presentation markup.  Originally part of citation_config.messages it has
-(author, editor, etc.). The main module uses these to identify and emit the
+been moved into its own, more semantically correct place.
-'extra_text_names' message. (It is not the only series of patterns for this message.)
 ]]
-local editor_markup_patterns = {												-- these patterns match annotations at end of name
-	'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$',								-- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'
-	'[,%.%s]%f[e]eds?%.?$',														-- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)
-	'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$',				-- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'
-	'[,%.%s]%f[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$',								-- editor or editors: without '('or ')'; case insensitive
-																				-- these patterns match annotations at beginning of name
-	'^eds?[%.,;]',																-- ed. or eds.: lower case only, optional 's', requires '.'
-	'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]',										-- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'
-	'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A',								-- (editor or (editors: also square brackets, case insensitive, optional brackets, 's'
-	'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A',									-- (edited: also square brackets, case insensitive, optional brackets
-																				-- these patterns match annotations that are the 'name'
+local presentation =
-	'^[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$',										-- editor or editors; case insensitive
-	}
---[[--------------------------< P R E S E N T A T I O N >------------------------
-Fixed presentation markup.  Originally part of citation_config.messages it has
-been moved into its own, more semantically correct place.
-]]
-local presentation =
 	{
-	-- Error output
-	-- .error class is specified at https://git.wikimedia.org/blob/mediawiki%2Fcore.git/9553bd02a5595da05c184f7521721fb1b79b3935/skins%2Fcommon%2Fshared.css#L538
 	-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display
-	['hidden-error'] = '<span class="cs1-hidden-error error citation-comment">$1</span>',
+	['hidden-error'] = '<span class="cs1-hidden-error citation-comment">$1</span>',
-	['visible-error'] = '<span class="cs1-visible-error error citation-comment">$1</span>',
+	['visible-error'] = '<span class="cs1-visible-error citation-comment">$1</span>',
 	['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>',
@@ Line 160: / Line 231: @@
 	['bdi'] = '<bdi$1>$2</bdi>',												-- bidirectional isolation used with |script-title= and the like
-	['cite'] = '<cite class="$1">$2</cite>';									-- |ref= not set so no id="..." attribute
+	['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 |ref= is set
+	['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=, ...
@@ Line 169: / Line 242: @@
 	['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>',		-- external link with appropriate lock icon
-		['free'] = {class='cs1-lock-free', title='Freely accessible'},			-- classes defined in Module:Citation/CS1/styles.css
+		['free'] = {class='id-lock-free', title='Freely accessible'},			-- classes defined in Module:Citation/CS1/styles.css
-		['registration'] = {class='cs1-lock-registration', title='Free registration required'},
+		['registration'] = {class='id-lock-registration', title='Free registration required'},
-		['limited'] = {class='cs1-lock-limited', title='Free access subject to limited trial, subscription normally required'},
+		['limited'] = {class='id-lock-limited', title='Free access subject to limited trial, subscription normally required'},
-		['subscription'] = {class='cs1-lock-subscription', title='Paid subscription required'},
+		['subscription'] = {class='id-lock-subscription', title='Paid subscription required'},
 	['interwiki-icon'] = '<span class="$1" title="$2">$3</span>',
@@ Line 179: / Line 252: @@
 	['italic-title'] = "''$1''",
-	['kern-left'] = '<span class="cs1-kern-left">$1</span>$2',					-- spacing to use when title contains leading single or double quote mark
+	['kern-left'] = '<span class="cs1-kern-left"></span>$1',					-- spacing to use when title contains leading single or double quote mark
-	['kern-right'] = '$1<span class="cs1-kern-right">$2</span>',				-- spacing to use when title contains trailing single or double quote mark
+	['kern-right'] = '$1<span class="cs1-kern-right"></span>',					-- spacing to use when title contains trailing single or double quote mark
-																				-- these for simple wikilinked titles [["text]], [[text"]] and [["text"]]
-																				-- span wraps entire wikilink
-	['kern-wl-left'] = '<span class="cs1-kern-wl-left">$1</span>',				-- when title contains leading single or double quote mark
-	['kern-wl-right'] = '<span class="cs1-kern-wl-left">$1</span>',				-- when title contains trailing single or double quote mark
-	['kern-wl-both'] = '<span class="cs1-kern-wl-left cs1-kern-wl-right">$1</span>',	-- when title contains leading and trailing single or double quote marks
 	['nowrap1'] = '<span class="nowrap">$1</span>',								-- for nowrapping an item: <span ...>yyyy-mm-dd</span>
@@ Line 194: / Line 261: @@
 	['parameter'] = '<code class="cs1-code">&#124;$1=</code>',
 	['ps_cs1'] = '.';															-- CS1 style postscript (terminal) character
 	['ps_cs2'] = '';															-- CS2 style postscript (terminal) character (empty string)
 	['quoted-text'] = '<q>$1</q>',												-- for wrapping |quote= content
-	['quoted-title'] = '\'$1\'',
+	['quoted-title'] = '"$1"',
 	['sep_cs1'] = '.',															-- CS1 element separator
@@ Line 206: / Line 273: @@
 	['sep_nl_and'] = ' and ',													-- used as last nl sep when |name-list-style=and and list has 2 items
 	['sep_nl_end'] = '; and ',													-- used as last nl sep when |name-list-style=and and list has 3+ names
-	['sep_name'] = ' ',														-- CS1|2 style last/first separator is <comma><space>
+	['sep_name'] = ', ',														-- CS1|2 style last/first separator is <comma><space>
 	['sep_nl_vanc'] = ',',														-- Vancouver style name-list separator between authors is a comma
 	['sep_name_vanc'] = ' ',													-- Vancouver style last/first separator is a space
@@ Line 235: / Line 302: @@
 	['ArchiveFormat'] = 'archive-format',
 	['ArchiveURL'] = {'archive-url', 'archiveurl'},								-- Used by InternetArchiveBot
+	['ArticleNumber'] = 'article-number',
 	['ASINTLD'] = 'asin-tld',
 	['At'] = 'at',																-- Used by InternetArchiveBot
-	['Authors'] = {'authors', 'people', 'credits'},
+	['Authors'] = {'people', 'credits'},
 	['BookTitle'] = {'book-title', 'booktitle'},
 	['Cartography'] = 'cartography',
 	['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'},
-	['ChapterWikilink'] = {'chapter-wikilink'},
 	['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format',
 		'article-format', 'section-format'};
-	['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url',
+	['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url'},	-- Used by InternetArchiveBot
-		'section-url', 'chapterurl'},											-- Used by InternetArchiveBot
 	['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access',
 		'entry-url-access', 'article-url-access', 'section-url-access'},		-- Used by InternetArchiveBot
-	['Class'] = 'class',														-- cite arxiv and arxiv identifiers
+	['Class'] = 'class',														-- cite arxiv and arxiv identifier
 	['Collaboration'] = 'collaboration',
 	['Conference'] = {'conference', 'event'},
@@ Line 272: / Line 338: @@
 	['Issue'] = {'issue', 'number'},
 	['Language'] = {'language', 'lang'},
-	['LayDate'] = 'lay-date',
-	['LayFormat'] = 'lay-format',
-	['LaySource'] = 'lay-source',
-	['LayURL'] = 'lay-url',
 	['MailingList'] = {'mailing-list', 'mailinglist'},							-- cite mailing list only
 	['Map'] = 'map',															-- cite map only
@@ Line 306: / Line 368: @@
 	['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',
@@ Line 323: / Line 386: @@
 	['Title'] = 'title',														-- Used by InternetArchiveBot
 	['TitleLink'] = {'title-link', 'episode-link', 'episodelink'},				-- Used by InternetArchiveBot
-	['TitleNote'] = 'department',
+	['TitleNote'] = {'title-note', 'department'},
 	['TitleType'] = {'type', 'medium'},
 	['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution',
@@ Line 329: / Line 392: @@
 	['Transcript'] = 'transcript',
 	['TranscriptFormat'] = 'transcript-format',
-	['TranscriptURL'] = {'transcript-url', 'transcripturl'},					-- Used by InternetArchiveBot
+	['TranscriptURL'] = 'transcript-url',										-- Used by InternetArchiveBot
+	['TransEncyclopedia'] = {'trans-encyclopedia', 'trans-encyclopaedia'},		-- cite encyclopedia only
 	['TransMap'] = 'trans-map',													-- cite map only
 	['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper',
@@ Line 344: / Line 408: @@
 	['Year'] = 'year',
-	['AuthorList-First'] = {"first#", "author-first#", "author#-first", "given#",
+	['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given",
-		"author-given#", "author#-given"},
+		"subject-first#", "subject#-first", "subject-given#", "subject#-given",
-	['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "surname#",
+		"given#"},
-		"author-surname#", "author#-surname", "author#", "subject#", 'host#'},
+	['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname",
+		"subject-last#", "subject#-last", "subject-surname#", "subject#-surname",
+		"author#", 'host#', "subject#", "surname#"},
 	['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#",
 		"subject#-link", "authorlink#", "author#link"},
@@ Line 387: / Line 453: @@
 ]]
-local punct_skip = {};
+local punct_meta_params = {														-- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
-local meta_params = {															-- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
 	'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap',	'TransTitle',	-- title-holding parameters
 	'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask',	-- name-list mask may have name separators
-	'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref',																		-- miscellaneous
+	'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref',											-- miscellaneous
-	'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'LayURL', 'MapURL', 'TranscriptURL', 'URL',			-- URL-holding parameters
+	'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'MapURL', 'TranscriptURL', 'URL',						-- URL-holding parameters
+	}
+local url_meta_params = {														-- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
+	'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL',		-- parameters allowed to hold urls
+	'Page', 'Pages', 'At', 'QuotePage', 'QuotePages',							-- insource locators allowed to hold urls
 	}
+local function build_skip_table (skip_t, meta_params)
 	for _, meta_param in ipairs (meta_params) do								-- for each meta parameter key
 		local params = aliases[meta_param];										-- get the parameter or the table of parameters associated with the meta parameter name
 		if 'string' == type (params) then
-			punct_skip[params] = 1;												-- just a single parameter
+			skip_t[params] = 1;													-- just a single parameter
 		else
 			for _, param in ipairs (params) do									-- get the parameter name
-				punct_skip[param] = 1;											-- add the parameter name to the skip table
+				skip_t[param] = 1;												-- add the parameter name to the skip table
 				local count;
 				param, count = param:gsub ('#', '');							-- remove enumerator marker from enumerated parameters
 				if 0 ~= count then												-- if removed
-					punct_skip[param] = 1;										-- add param name without enumerator marker
+					skip_t[param] = 1;											-- add param name without enumerator marker
 				end
 			end
 		end
 	end
+	return skip_t;
+end
+local punct_skip = {};
+local url_skip = {};
+--[[--------------------------< U R L _ A C C E S S _ M A P >--------------------------------------------------
+this table used by the wikipedia library url test, has_twl_url(), which automatically sets a url-access parameter
+to 'subscription' when it discovers a wikipedia library url in any of the url-holding paramters used as keys in
+this table.
---[[-----------< S P E C I A L   C A S E   T R A N S L A T I O N S >------------
+translators:  if your wiki uses parameter names for these url-holding parameters and their matching -access parameters,
+add your wiki's parameters to this list.  Leave the English parameters in place.
-This table is primarily here to support internationalization.  Translations in
+TODO: is there a better way to do this?
-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 special_case_translation = {
+local url_access_map_t = {
+	['chapter-url'] = 'chapter-url-access',
+	['contribution-url'] = 'contribution-url-access',
+	['entry-url'] = 'entry-url-access',
+	['article-url'] = 'article-url-access',
+	['section-url'] = 'section-url-access',
+	['map-url'] = 'map-url-access',
+	['mapurl'] = 'map-url-access',
+	['url'] = 'url-access',
+	['URL'] = 'url-access'
+	}
+--[[--------------------------< S I N G L E - L E T T E R   S E C O N D - L E V E L   D O M A I N S >----------
+this is a list of tlds that are known to have single-letter second-level domain names.  This list does not include
+ccTLDs which are accepted in is_domain_name().
+]]
+local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'media', 'org', 'today'};
+--[[-----------< S P E C I A L   C A S E   T R A N S L A T I O N S >------------
+This table is primarily here to support internationalization.  Translations in
+this table are used, for example, when an error message, category name, etc.,
+is extracted from the English alias key.  There may be other cases where
+this translation table may be useful.
+]]
+local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191';
+local special_case_translation = {
+	author = 'author',
+	editor = 'editor',
+	name_list_params = '$1-name-list parameters',								-- $1 is 'author' or 'editor'; used with err_redundant_parameters
 	['AuthorList'] = 'authors list',											-- used to assemble maintenance category names
-	['ContributorList'] = 'contributors list',									-- translation of these names plus translation of the base mainenance category names in maint_cats{} table below
+	['ContributorList'] = 'contributors list',									-- translation of these names plus translation of the base maintenance category names in maint_cats{} table below
 	['EditorList'] = 'editors list',											-- must match the names of the actual categories
 	['InterviewerList'] = 'interviewers list',									-- this group or translations used by name_has_ed_markup() and name_has_mult_names()
@@ Line 437: / Line 552: @@
 																				-- Lua patterns to match generic titles; usually created by bots or reference filling tools
 																				-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
-	['generic_titles'] = {
+		-- generic titles and patterns in this table should be lowercase only
-		-- patterns in this table should be lowercase only
 		-- leave ['local'] nil except when there is a matching generic title in your language
-		-- generic titles must be lowercase
 		-- boolean 'true' for plain-text searches; 'false' for pattern searches
-		{['en'] = {'^wayback%s+machine$', false},				['local'] = nil},
-		{['en'] = {'are you a robot', true},					['local'] = nil},
+	['generic_titles'] = {
-		{['en'] = {'hugedomains.com', true},					['local'] = nil},
+		['accept'] = {
-		{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false},		['local'] = nil},
+			},
-		{['en'] = {'page not found', true},						['local'] = nil},
+		['reject'] = {
-		{['en'] = {'subscribe to read', true},					['local'] = nil},
+			{['en'] = {'^wayback%s+machine$', false},				['local'] = nil},
-		{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false},		['local'] = nil},
+			{['en'] = {'are you a robot', true},					['local'] = nil},
-		{['en'] = {'website is for sale', true},				['local'] = nil},
+			{['en'] = {'hugedomains', true},						['local'] = nil},
-		{['en'] = {'^404', true},								['local'] = nil},
+			{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false},		['local'] = nil},
-		{['en'] = {'internet archive wayback machine', true},	['local'] = nil},
+			{['en'] = {'page not found', true},						['local'] = nil},
-		{['en'] = {'log into facebook', true},					['local'] = nil},
+			{['en'] = {'subscribe to read', true},					['local'] = nil},
-		{['en'] = {'redirecting...', true},						['local'] = nil},
+			{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false},		['local'] = nil},
-		{['en'] = {'webcite query result', true},				['local'] = nil},
+			{['en'] = {'website is for sale', true},				['local'] = nil},
-		{['en'] = {'wikiwix\'s cache', true},					['local'] = nil},
+			{['en'] = {'^404', false},								['local'] = nil},
+			{['en'] = {'error[ %-]404', false},						['local'] = nil},
+			{['en'] = {'internet archive wayback machine', true},	['local'] = nil},
+			{['en'] = {'log into facebook', true},					['local'] = nil},
+			{['en'] = {'login • instagram', true},					['local'] = nil},
+			{['en'] = {'redirecting...', true},						['local'] = nil},
+			{['en'] = {'usurped title', true},						['local'] = nil},	-- added by a GreenC bot
+			{['en'] = {'webcite query result', true},				['local'] = nil},
+			{['en'] = {'wikiwix\'s cache', true},					['local'] = nil},
+			{['en'] = {'bot verification', true},					['local'] = nil},
+			}
+		},
+		-- boolean 'true' for plain-text searches, search string must be lowercase only
+		-- boolean 'false' for pattern searches
+		-- leave ['local'] nil except when there is a matching generic name in your language
+	['generic_names'] = {
+		['accept'] = {
+			{['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false},				['local'] = nil},
+			},
+		['reject'] = {
+			{['en'] = {'about us', true},										['local'] = nil},
+			{['en'] = {'%f[%a][Aa]dvisor%f[%A]', false},						['local'] = nil},
+			{['en'] = {'allmusic', true},										['local'] = nil},
+			{['en'] = {'%f[%a][Aa]uthor%f[%A]', false},							['local'] = nil},
+			{['en'] = {'^[Bb]ureau$', false},									['local'] = nil},
+			{['en'] = {'business', true},										['local'] = nil},
+			{['en'] = {'cnn', true},											['local'] = nil},
+			{['en'] = {'collaborator', true},									['local'] = nil},
+			{['en'] = {'^[Cc]ompany$', false},									['local'] = nil},
+			{['en'] = {'contributor', true},									['local'] = nil},
+			{['en'] = {'contact us', true},										['local'] = nil},
+			{['en'] = {'correspondent', true},									['local'] = nil},
+			{['en'] = {'^[Dd]esk$', false},										['local'] = nil},
+			{['en'] = {'directory', true},										['local'] = nil},
+			{['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false},			['local'] = nil},
+			{['en'] = {'[,%.%s]%f[e]eds?%.?$', false},							['local'] = nil},
+			{['en'] = {'^eds?[%.,;]', false},									['local'] = nil},
+			{['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false},			['local'] = nil},
+			{['en'] = {'%f[%a][Ee]dited%f[%A]', false},							['local'] = nil},
+			{['en'] = {'%f[%a][Ee]ditors?%f[%A]', false},						['local'] = nil},
+			{['en'] = {'%f[%a][Ee]mail%f[%A]', false},							['local'] = nil},
+			{['en'] = {'facebook', true},										['local'] = nil},
+			{['en'] = {'google', true},											['local'] = nil},
+			{['en'] = {'^[Gg]roup$', false},									['local'] = nil},
+			{['en'] = {'home page', true},										['local'] = nil},
+			{['en'] = {'^[Ii]nc%.?$', false},									['local'] = nil},
+			{['en'] = {'instagram', true},										['local'] = nil},
+			{['en'] = {'interviewer', true},									['local'] = nil},
+			{['en'] = {'^[Ll]imited$', false},									['local'] = nil},
+			{['en'] = {'linkedIn', true},										['local'] = nil},
+			{['en'] = {'^[Nn]ews$', false},										['local'] = nil},
+			{['en'] = {'[Nn]ews[ %-]?[Rr]oom', false},							['local'] = nil},
+			{['en'] = {'pinterest', true},										['local'] = nil},
+			{['en'] = {'policy', true},											['local'] = nil},
+			{['en'] = {'privacy', true},										['local'] = nil},
+			{['en'] = {'reuters', true},										['local'] = nil},
+			{['en'] = {'translator', true},										['local'] = nil},
+			{['en'] = {'tumblr', true},											['local'] = nil},
+			{['en'] = {'twitter', true},										['local'] = nil},
+			{['en'] = {'site name', true},										['local'] = nil},
+			{['en'] = {'statement', true},										['local'] = nil},
+			{['en'] = {'submitted', true},										['local'] = nil},
+			{['en'] = {'super.?user', false},									['local'] = nil},
+			{['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false},	['local'] = nil},
+			{['en'] = {'updated', true},										['local'] = nil},
+			{['en'] = {'verfasser', true},										['local'] = nil},
+			}
 		}
 	}
@@ Line 481: / Line 662: @@
 Easter and Christmas are defined here as 98 and 99, which should be out of the
 ISO 8601 (EDTF) range of uses for a while.
+local_date_names_from_mediawiki is a boolean.  When set to:
+	true – module will fetch local month names from MediaWiki for both date_names['local']['long'] and date_names['local']['short']; this will unconditionally overwrite manual translations
+	false – module will *not* fetch local month names from MediaWiki
+Caveat lector:  There is no guarantee that MediaWiki will provide short month names.  At your wiki you can test
+the results of the MediaWiki fetch in the debug console with this command (the result is alpha sorted):
+	=mw.dumpObject (p.date_names['local'])
+While the module can fetch month names from MediaWiki, it cannot fetch the quarter, season, and named date names
+from MediaWiki.  Those must be translated manually.
 ]]
+local local_date_names_from_mediawiki = true;									-- when false, manual translation required for date_names['local']['long'] and date_names['local']['short']; overwrites manual translations
+																				-- when true, module fetches long and short month names from MediaWiki
 local date_names = {
 	['en'] = {																	-- English
@@ Line 492: / Line 686: @@
 		['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 499: / Line 694: @@
 		['named']	= {['Easter'] = 98, ['Christmas'] = 99},
 		},
-	['inv_local_l'] = {},														-- used in date reformatting; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.
+	['inv_local_long'] = {},													-- used in date reformatting & translation; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.
-	['inv_local_s'] = {},														-- used in date reformatting; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.
+	['inv_local_short'] = {},													-- used in date reformatting & translation; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.
+	['inv_local_quarter'] = {},													-- used in date translation; copy of date_names['local'].quarter where k/v are inverted: [1]='<local name>' etc.
+	['inv_local_season'] = {},													-- used in date translation; copy of date_names['local'].season where k/v are inverted: [1]='<local name>' etc.
+	['inv_local_named'] = {},													-- used in date translation; copy of date_names['local'].named where k/v are inverted: [1]='<local name>' etc.
 	['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'},	-- used to convert local language digits to Western 0-9
 	['xlate_digits'] = {},
 	}
-for name, i in pairs (date_names['local'].long) do								-- this table is ['name'] = i
+if local_date_names_from_mediawiki then											-- if fetching local month names from MediaWiki is enabled
-	date_names['inv_local_l'][i] = name;										-- invert to get [i] = 'name' for conversions from ymd
+	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
-for name, i in pairs (date_names['local'].short) do								-- this table is ['name'] = i
+if local_digits_from_mediawiki then												-- if fetching local digits from MediaWiki is enabled
-	date_names['inv_local_s'][i] = name;										-- invert to get [i] = 'name' for conversions from ymd
+	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 532: / Line 749: @@
 	'{{ *([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 ()
-	local content = mw.title.getCurrentTitle():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
+	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
-			content = content:match ('%b{}', start);							-- get the whole template
+			local use_dates_template = content:match ('%b{}', start);			-- get the whole template
-			if content:match ('| *cs1%-dates *= *[lsy][sy]?') then				-- look for |cs1-dates=publication date length access-/archive-date length
+			if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then	-- look for |cs1-dates=publication date length access-/archive-date length
-				return match:lower() .. '-' .. content:match ('| *cs1%-dates *= *([lsy][sy]?)');
+				return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)');
 			else
 				return match:lower() .. '-all';									-- no |cs1-dates= k/v pair; return value appropriate for use in |df=
@@ Line 548: / Line 773: @@
 end
-local global_df = get_date_format ();
+local global_df;																-- TODO: add this to <global_cs1_config_t>?
@@ Line 563: / Line 788: @@
 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',
+	}
 --[[
@@ Line 574: / Line 815: @@
 	bad_ppatterns = {															-- patterns for |page= and |pages=
 		'^[Pp][PpGg]?%.?[ %d]',
+		'^[Pp][Pp]?%.&nbsp;',													-- from {{p.}} and {{pp.}} templates
 		'^[Pp]ages?',
 		'^[Pp]gs.?',
 		},
-	vpatterns = {																-- patterns for |volume=
+	vi_patterns_t = {															-- combined to catch volume-like text in |issue= and issue-like text in |volume=
-		'^volumes?',
+		'^volumes?',															-- volume-like text
-		'^vols?[%.:=]?'
+		'^vols?[%.:=]?',
-		},
-	ipatterns = {																-- patterns for |issue=
+		'^issues?',																--issue-like text
-		'^issues?',
 		'^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[%.:= ]',															-- 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)
+		},
 	}
@@ Line 619: / Line 862: @@
 	['cs1'] = {'cs1'},															-- |mode=
 	['cs2'] = {'cs2'},															-- |mode=
-	['dead'] = {'dead'},														-- |url-status= -- Used by InternetArchiveBot
+	['dead'] = {'dead', 'deviated'},											-- |url-status= -- Used by InternetArchiveBot
 	['dmy'] = {'dmy'},															-- |df=
 	['dmy-all'] = {'dmy-all'},													-- |df=
 	['foreword'] = {'foreword'},												-- |contribution=
-	['free'] = {'free'},														-- |url-access= -- Used by InternetArchiveBot
+	['free'] = {'free'},														-- |<id>-access= -- Used by InternetArchiveBot
+	['harv'] = {'harv'},														-- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true
 	['introduction'] = {'introduction'},										-- |contribution=
 	['limited'] = {'limited'},													-- |url-access= -- Used by InternetArchiveBot
@@ Line 715: / Line 959: @@
 	['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 721: / Line 966: @@
---[[---------------------< S T R I P M A R K E R S >----------------------------
+--[[--------------------------< C S 1 _ C O N F I G _ G E T >--------------------------------------------------
+fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t>
+no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked.
-Common pattern definition location for stripmarkers so that we don't have to go
+Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors,
-hunting for them if (when) MediaWiki changes their form.
+DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode.  The DisplayWhatever metaparameters
+accept numeric values only (|display-authors=etal and the like is not supported).
 ]]
-local stripmarkers = {
+local global_cs1_config_t = {};													-- TODO: add value returned from get_date_format() to this table?
-	['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127',			-- capture returns name of stripmarker
-	['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127'			-- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()
+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
---[[------------< I N V I S I B L E _ C H A R A C T E R S >---------------------
+		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
-This table holds non-printing or invisible characters indexed either by name or
+		local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'};
-by Unicode group. Values are decimal representations of UTF-8 codes.  The table
+		local meta_param_map_t = {};											-- list of accepted parameter names usable in {{cs1 config}} goes here
-is organized as a table of tables because the Lua pairs keyword returns table
-data in an arbitrary order.  Here, we want to process the table from top to bottom
+		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
-because the entries at the top of the table are also found in the ranges specified
+			if 'table' == type (aliases[meta_param]) then						-- if <meta_param> is a sequence,
-by the entries at the bottom of the table.
+				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
-Also here is a pattern that recognizes stripmarkers that begin and end with the
+get_cs1_config ();																-- fill <global_cs1_config_t>
-delete characters.  The nowiki stripmarker is not an error but some others are
-because the parameter values that include them become part of the template's
-metadata before stripmarker replacement.
-]]
-local invisible_defs = {
+--[[---------------------< S T R I P M A R K E R S >----------------------------
-	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 = {
+Common pattern definition location for stripmarkers so that we don't have to go
-	{'replacement', '\239\191\189'},											-- U+FFFD, EF BF BD
+hunting for them if (when) MediaWiki changes their form.
-	{'zero width joiner', '('.. invisible_defs.zwj .. ')'},						-- U+200D, E2 80 8D; capture because zwj may be allowed
-	{'zero width space', '\226\128\139'},										-- U+200B, E2 80 8B
+]]
-	{'hair space', '\226\128\138'},												-- U+200A, E2 80 8A
-	{'soft hyphen', '\194\173'},												-- U+00AD, C2 AD
+local stripmarkers = {
-	{'horizontal tab', '\009'},													-- U+0009 (HT), 09
+	['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127',			-- capture returns name of stripmarker
-	{'line feed', '\010'},														-- U+000A (LF), 0A
+	['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127'			-- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()
-	{'no-break space', '\194\160'},												-- U+00A0 (NBSP), C2 A0
-	{'carriage return', '\013'},												-- U+000D (CR), 0D
-	{'stripmarker', stripmarkers.any},											-- stripmarker; may or may not be an error; capture returns the stripmaker type
-	{'delete', '('.. invisible_defs.del .. ')'},								-- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker
-	{'C0 control', '[\000-\008\011\012\014-\031]'},								-- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
-	{'C1 control', '[\194\128-\194\159]'},										-- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-	--	{'Specials', '[\239\191\185-\239\191\191]'},								-- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-	--	{'Private use area', '[\238\128\128-\239\163\191]'},						-- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-	--	{'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'},	-- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD
-	--	{'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'},	-- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD
 	}
---[[
-Indic script makes use of zero width joiner as a character modifier so zwj
+--[[------------< I N V I S I B L E _ C H A R A C T E R S >---------------------
-characters must be left in.  This pattern covers all of the unicode characters
-for these languages:
+This table holds non-printing or invisible characters indexed either by name or
-	Devanagari					0900–097F – https://unicode.org/charts/PDF/U0900.pdf
+by Unicode group. Values are decimal representations of UTF-8 codes.  The table
-		Devanagari extended		A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
+is organized as a table of tables because the Lua pairs keyword returns table
-	Bengali						0980–09FF – https://unicode.org/charts/PDF/U0980.pdf
+data in an arbitrary order.  Here, we want to process the table from top to bottom
-	Gurmukhi					0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf
+because the entries at the top of the table are also found in the ranges specified
-	Gujarati					0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf
+by the entries at the bottom of the table.
-	Oriya						0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf
-	Tamil						0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf
+Also here is a pattern that recognizes stripmarkers that begin and end with the
-	Telugu						0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf
+delete characters.  The nowiki stripmarker is not an error but some others are
-	Kannada						0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf
+because the parameter values that include them become part of the template's
-	Malayalam					0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf
+metadata before stripmarker replacement.
-plus the not-necessarily Indic scripts for Sinhala and Burmese:
-	Sinhala						0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf
-	Myanmar						1000-109F - https://unicode.org/charts/PDF/U1000.pdf
-		Myanmar extended A		AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf
-		Myanmar extended B		A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
-the pattern is used by has_invisible_chars() and coins_cleanup()
 ]]
-local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]';
+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
+	}
--- list of emoji that use zwj character (U+200D) to combine with another emoji
+local invisible_chars = {
-local emoji = {																	-- indexes are decimal forms of the hex values in U+xxxx
+	{'replacement', '\239\191\189'},											-- U+FFFD, EF BF BD
-	[127752] = true,															-- U+1F308 🌈 rainbow
+	{'zero width joiner', '('.. invisible_defs.zwj .. ')'},						-- U+200D, E2 80 8D; capture because zwj may be allowed
-	[127806] = true,															-- U+1F33E 🌾 ear of rice
+	{'zero width space', '\226\128\139'},										-- U+200B, E2 80 8B
-	[127859] = true,															-- U+1F373 🍳 cooking
+	{'hair space', '\226\128\138'},												-- U+200A, E2 80 8A
-	[127891] = true,															-- U+1F393 🎓 graduation cap
+	{'soft hyphen', '\194\173'},												-- U+00AD, C2 AD
-	[127908] = true,															-- U+1F3A4 🎤 microphone
+	{'horizontal tab', '\009'},													-- U+0009 (HT), 09
-	[127912] = true,															-- U+1F3A8 🎨 artist palette
+	{'line feed', '\010'},														-- U+000A (LF), 0A
-	[127979] = true,															-- U+1F3EB 🏫 school
+	{'no-break space', '\194\160'},												-- U+00A0 (NBSP), C2 A0
-	[127981] = true,															-- U+1F3ED 🏭 factory
+	{'carriage return', '\013'},												-- U+000D (CR), 0D
-	[128102] = true,															-- U+1F466 👦 boy
+	{'stripmarker', stripmarkers.any},											-- stripmarker; may or may not be an error; capture returns the stripmaker type
-	[128103] = true,															-- U+1F467 👧 girl
+	{'delete', '('.. invisible_defs.del .. ')'},								-- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker
-	[128104] = true,															-- U+1F468 👨 man
+	{'C0 control', '[\000-\008\011\012\014-\031]'},								-- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
-	[128105] = true,															-- U+1F469 👩 woman
+	{'C1 control', '[\194\128-\194\159]'},										-- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-	[128139] = true,															-- U+1F48B 💋 kiss mark
+	--	{'Specials', '[\239\191\185-\239\191\191]'},								-- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-	[128187] = true,															-- U+1F4BB 💻 personal computer
+	--	{'Private use area', '[\238\128\128-\239\163\191]'},						-- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-	[128188] = true,															-- U+1F4BC 💼 brief case
+	--	{'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
-	[128295] = true,															-- U+1F527 🔧 wrench
+	--	{'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
-	[128300] = true,															-- U+1F52C 🔬 microscope
-	[128488] = true,															-- U+1F5E8 🗨 left speech bubble
-	[128640] = true,															-- U+1F680 🚀 rocket
-	[128658] = true,															-- U+1F692 🚒 fire engine
-	[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
-	[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
-	[9992] = true,																-- U+2708 ✈ airplane
-	[10084] = true,																-- U+2764 ❤ heavy black heart
 	}
+--[[
---[[----------------------< L A N G U A G E   S U P P O R T >-------------------
+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
-These tables and constants support various language-specific functionality.
+for these languages:
+	Devanagari					0900–097F – https://unicode.org/charts/PDF/U0900.pdf
+		Devanagari extended		A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
+	Bengali						0980–09FF – https://unicode.org/charts/PDF/U0980.pdf
+	Gurmukhi					0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf
+	Gujarati					0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf
+	Oriya						0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf
+	Tamil						0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf
+	Telugu						0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf
+	Kannada						0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf
+	Malayalam					0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf
+plus the not-necessarily Indic scripts for Sinhala and Burmese:
+	Sinhala						0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf
+	Myanmar						1000-109F - https://unicode.org/charts/PDF/U1000.pdf
+		Myanmar extended A		AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf
+		Myanmar extended B		A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
+the pattern is used by has_invisible_chars() and coins_cleanup()
 ]]
-local this_wiki_code = mw.getContentLanguage():getCode();						-- get this wiki's language code
+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]';
-	if string.match (mw.site.server, 'wikidata') then
-		this_wiki_code = mw.getCurrentFrame():preprocess('{{int:lang}}');		-- on Wikidata so use interface language setting instead
-	end
-local languages = mw.language.fetchLanguageNames (this_wiki_code, 'all');		-- get a list of language names known to Wikimedia; used for |language= and interwiki tests
+-- list of emoji that use a zwj character (U+200D) to combine with another emoji
+-- from: https://unicode.org/Public/emoji/17.0/emoji-zwj-sequences.txt; version: 17.0; 2025-01-08
-local inter_wiki_map = {};														-- map of interwiki prefixes that are language-code prefixes
+-- table created by: [[:en:Module:Make emoji zwj table]]
-	for k, v in pairs (mw.site.interwikiMap ('local')) do						-- spin through the base interwiki map (limited to local)
+local emoji_t = {																-- indexes are decimal forms of the hex values in U+xxxx
-		if languages[v["prefix"]] then											-- if the prefix matches a known language code
+	[8596] = true,																-- U+2194 ↔ left right arrow
-			inter_wiki_map[v["prefix"]] = true;									-- add it to our local map
+	[8597] = true,																-- U+2195 ↕ up down arrow
-		end
+	[9760] = true,																-- U+2620 ☠ skull and crossbones
-	end
+	[9792] = true,																-- U+2640 ♀ female sign
+	[9794] = true,																-- U+2642 ♂ male sign
-local local_lang_cat_enable = false;											-- set to true to categorize pages where |language=<local wiki's language>
+	[9877] = true,																-- U+2695 ⚕ staff of aesculapius
+	[9878] = true,																-- U+2696 ⚖ scales
+	[9895] = true,																-- U+26A7 ⚧ male with stroke and male and female sign
---[[--------------------< S C R I P T _ L A N G _ C O D E S >-------------------
+	[9992] = true,																-- U+2708 ✈ airplane
+	[10052] = true,																-- U+2744 ❄ snowflake
-This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character
+	[10084] = true,																-- U+2764 ❤ heavy black heart
-language codes that apply only to |script-title= and |script-chapter=
+	[10145] = true,																-- U+27A1 ➡ black rightwards arrow
+	[11035] = true,																-- U+2B1B ⬛ black large square
-]]
+	[127752] = true,															-- U+1F308 🌈 rainbow
+	[127787] = true,															-- U+1F32B 🌫 fog
-local script_lang_codes = {
+	[127806] = true,															-- U+1F33E 🌾 ear of rice
-	'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu',
+	[127859] = true,															-- U+1F373 🍳 cooking
-	'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo',
+	[127868] = true,															-- U+1F37C 🍼 baby bottle
-	'mk', 'ml', 'mn', 'mr', 'my', 'ne', 'or', 'ota', 'ps', 'ru', 'sd', 'si',
+	[127876] = true,															-- U+1F384 🎄 christmas tree
-	'sr', 'ta', 'te', 'tg', 'th', 'ti', 'ug', 'uk', 'ur', 'uz', 'yi', 'zh'
+	[127891] = true,															-- U+1F393 🎓 graduation cap
-	};
+	[127908] = true,															-- U+1F3A4 🎤 microphone
+	[127912] = true,															-- U+1F3A8 🎨 artist palette
+	[127979] = true,															-- U+1F3EB 🏫 school
+	[127981] = true,															-- U+1F3ED 🏭 factory
+	[128048] = true,															-- U+1F430 🐰 rabbit face
+	[128102] = true,															-- U+1F466 👦 boy
+	[128103] = true,															-- U+1F467 👧 girl
+	[128104] = true,															-- U+1F468 👨 man
+	[128105] = true,															-- U+1F469 👩 woman
+	[128139] = true,															-- U+1F48B 💋 kiss mark
+	[128165] = true,															-- U+1F4A5 💥 collision symbol
+	[128168] = true,															-- U+1F4A8 💨 dash symbol
+	[128171] = true,															-- U+1F4AB 💫 dizzy symbol
+	[128187] = true,															-- U+1F4BB 💻 personal computer
+	[128188] = true,															-- U+1F4BC 💼 brief case
+	[128293] = true,															-- U+1F525 🔥 fire
+	[128295] = true,															-- U+1F527 🔧 wrench
+	[128300] = true,															-- U+1F52C 🔬 microscope
+	[128488] = true,															-- U+1F5E8 🗨 left speech bubble
+	[128640] = true,															-- U+1F680 🚀 rocket
+	[128658] = true,															-- U+1F692 🚒 fire engine
+	[129001] = true,															-- U+1F7E9 🟩 large green square
+	[129003] = true,															-- U+1F7EB 🟫 large brown square
+	[129309] = true,															-- U+1F91D 🤝 handshake
+	[129455] = true,															-- U+1F9AF 🦯 probing cane
+	[129456] = true,															-- U+1F9B0 🦰 emoji component red hair
+	[129457] = true,															-- U+1F9B1 🦱 emoji component curly hair
+	[129458] = true,															-- U+1F9B2 🦲 emoji component bald
+	[129459] = true,															-- U+1F9B3 🦳 emoji component white hair
+	[129466] = true,															-- U+1F9BA 🦺 safety vest
+	[129468] = true,															-- U+1F9BC 🦼 motorized wheelchair
+	[129469] = true,															-- U+1F9BD 🦽 manual wheelchair
+	[129489] = true,															-- U+1F9D1 🧑 adult
+	[129490] = true,															-- U+1F9D2 🧒 child
+	[129648] = true,															-- U+1FA70 🩰 ballet shoes
+	[129657] = true,															-- U+1FA79 🩹 adhesive bandage
+	[129775] = true,															-- U+1FAEF 🫯 fight cloud
+	[129778] = true,															-- U+1FAF2 🫲 leftwards hand
+	}
---[[---------------< L A N G U A G E   R E M A P P I N G >----------------------
+--[[----------------------< L A N G U A G E   S U P P O R T >-------------------
-These tables hold language information that is different (correct) from MediaWiki's definitions
+These tables and constants support various language-specific functionality.
-For each ['code'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', 'code'} in lang_name_remap{}
+]]
-lang_code_remap{}:
+--local this_wiki_code = mw.getContentLanguage():getCode();						-- get this wiki's language code
-	key is always lowercase ISO 639-1, -2, -3 language code or a valid lowercase IETF language tag
+local this_wiki_code = lang_obj:getCode();										-- get this wiki's language code
-	value is properly spelled and capitalized language name associated with key
+if string.match (mw.site.server, 'wikidata') then
-	only one language name per key;
+		this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead
-	key/value pair must have matching entry in lang_name_remap{}
+	end
-lang_name_remap{}:
+local mw_languages_by_tag_t = mw.language.fetchLanguageNames (this_wiki_code, 'all');	-- get a table of language tag/name pairs known to Wikimedia; used for interwiki tests
-	key is always lowercase language name
+local mw_languages_by_name_t = {};
-	value is a table the holds correctly spelled and capitalized language name [1] and associated code [2] (code must match a code key in lang_code_remap{})
+	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=
-	may have multiple keys referring to a common preferred name and code; For example:
+		v = mw.ustring.lower (v);												-- lowercase for tag fetch; get name's proper case from mw_languages_by_tag_t[<tag>]
+		if mw_languages_by_name_t[v] then										-- when name already in the table
+			if 2 == #k or 3 == #k then											-- if tag does not have subtags
+				mw_languages_by_name_t[v] = k;									-- prefer the shortest tag for this name
+			end
+		else																	-- here when name not in the table
+			mw_languages_by_name_t[v] = k;										-- so add name and matching tag
+		end
+	end
+local inter_wiki_map = {};														-- map of interwiki prefixes that are language-code prefixes
+	for k, v in pairs (mw.site.interwikiMap ('local')) do						-- spin through the base interwiki map (limited to local)
+		if mw_languages_by_tag_t[v["prefix"]] then								-- if the prefix matches a known language tag
+			inter_wiki_map[v["prefix"]] = true;									-- add it to our local map
+		end
+	end
+--[[--------------------< S C R I P T _ L A N G _ C O D E S >-------------------
+This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character
+language codes that apply only to |script-title= and |script-chapter=
+]]
+local script_lang_codes = {
+	'ab', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'ce', 'chr',
+	'cu', 'dv', 'dz', 'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka',
+	'kaa', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni',
+	'mr', 'my', 'ne', 'or', 'ota', 'pa', 'ps', 'ru', 'sd', 'si', 'sr', 'syc',
+	'ta', 'te', 'tg', 'th', 'ti', 'tkr', 'tt', 'ug', 'uk', 'ur', 'uz', 'yi',
+	'yue', 'zh', 'zgh'
+	};
+--[[---------------< L A N G U A G E   R E M A P P I N G >----------------------
+These tables hold language information that is different (correct) from MediaWiki's definitions
+For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{}
+lang_tag_remap{}:
+	key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag
+	value is properly spelled and capitalized language name associated with <tag>
+	only one language name per <tag>;
+	key/value pair must have matching entry in lang_name_remap{}
+lang_name_remap{}:
+	key is always lowercase language name
+	value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{})
+	may have multiple keys referring to a common preferred name and tag; For example:
 		['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'
 ]]
-local lang_code_remap = {														-- used for |language= and |script-title= / |script-chapter=
+local lang_tag_remap = {														-- used for |language= and |script-title= / |script-chapter=
 	['als'] = 'Tosk Albanian',													-- MediaWiki returns Alemannisch
 	['bh'] = 'Bihari',															-- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
@@ Line 906: / Line 1,257: @@
 	['bn'] = 'Bengali',															-- MediaWiki returns Bangla
 	['ca-valencia'] = 'Valencian',												-- IETF variant of Catalan
-	['crh'] = 'Crimean Tatar',													-- synonymous with Crimean Turkish (return value from {{#language:crh|en}})
+	['fkv'] = 'Kven',															-- MediaWiki returns Kvensk
+	['gsw'] = 'Swiss German',
 	['ilo'] = 'Ilocano',														-- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
 	['ksh'] = 'Kölsch',															-- MediaWiki: Colognian; use IANA/ISO 639 preferred name
@@ Line 912: / Line 1,264: @@
 	['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=
+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 922: / Line 1,277: @@
 	['blackfoot'] = {'Blackfoot', 'bla'},										-- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
 	['colognian'] = {'Colognian', 'ksh-x-colog'},								-- MediaWiki preferred name for ksh
-	['crimean tatar'] = {'Crimean Tatar', 'crh'},								-- MediaWiki uses 'crh' as a subdomain name for Crimean Tatar Wikipedia: crh.wikipedia.org
 	['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
-	['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-TW'},					-- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
+	['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'},	-- special case to get correct tag when |language=sr-ec
+	['serbian (latin script)'] = {'Serbian (Latin script)', 'sr-latn'},			-- special case to get correct tag when |language=sr-el
+	['swiss german'] = {'Swiss German', 'gsw'},
+	['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'},					-- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
 	['tosk albanian'] = {'Tosk Albanian', 'als'},								-- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
-	['valencian'] = {'Valencian', 'ca'},										-- variant of Catalan; categorizes as Catalan
+	['valencian'] = {'Valencian', 'ca-valencia'},								-- variant of Catalan; categorizes as Valencian
 	}
@@ Line 940: / Line 1,299: @@
 local prop_cats = {
-	['foreign_lang_source'] = 'CS1 $1-language sources ($2)',					-- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code
+	['foreign-lang-source'] = 'CS1 $1-language sources ($2)',					-- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code
-	['foreign_lang_source_2'] = 'CS1 foreign language sources (ISO 639-2)|$1',	-- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key
+	['foreign-lang-source-2'] = 'CS1 foreign language sources (ISO 639-2)|$1',	-- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key
-	['local_lang_source'] = 'CS1 $1-language sources ($2)',						-- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false
+	['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
-	['location test'] = 'CS1 location test',
+	['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
-	['script'] = 'CS1 uses foreign language script',							-- when language specified by |script-title=xx: doesn't have its own category
+	['local-lang-source'] = 'CS1 $1-language sources ($2)',						-- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false
-	['script_with_name'] = 'CS1 uses $1-language script ($2)',					-- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code
+	['location-test'] = 'CS1 location test',
-	['jul_greg_uncertainty'] = 'CS1: Julian–Gregorian uncertainty',				-- probably temporary cat to identify scope of template with dates 1 October 1582 – 1 January 1926
+	['long-vol'] = 'CS1: long volume value',									-- probably temporary cat to identify scope of |volume= values longer than 4 characters
-	['long_vol'] = 'CS1: long volume value',									-- probably temporary cat to identify scope of |volume= values longer than 4 charachters
+	['script'] = 'CS1 uses $1-language script ($2)',							-- |script-title=xx: has matching category; $1 is language name, $2 is language tag
-	['year_range_abbreviated'] = 'CS1: abbreviated year range',					-- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form
+	['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
 	}
@@ Line 960: / Line 1,322: @@
 local title_types = {
 	['AV-media-notes'] = 'Media notes',
+	['document'] = 'Document',
 	['interview'] = 'Interview',
 	['mailinglist'] = 'Mailing list',
@@ Line 966: / Line 1,329: @@
 	['pressrelease'] = 'Press release',
 	['report'] = 'Report',
+	['speech'] = 'Speech',
 	['techreport'] = 'Technical report',
 	['thesis'] = 'Thesis',
+	}
+--[[--------------------------< B U I L D _ K N O W N _ F R E E _ D O I _ R E G I S T R A N T S _ T A B L E >--
+build a table of doi registrants known to be free-to-read  In a doi, the registrant ID is the series of digits
+between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID
+see §3.2.2 DOI prefix of the Doi Handbook p. 43
+https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43
+]]
+local function build_free_doi_registrants_table()
+	local registrants_t = {};
+	for _, v in ipairs ({
+		'1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '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', '9778', '11131', '11569', '11647',
+		'11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995',
+		'17645', '18637', '19080', '19173', '20944', '21037', '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', '53347', '54081', '54947', '55667', '55914', '57009', '58647', '59081',
+		}) do
+			registrants_t[v] = true;											-- build a k/v table of known free-to-read doi registrants
+	end
+	return registrants_t;
+end
+local extended_registrants_t = {												-- known free registrants identifiable by the doi suffix incipit
+	['1002'] = {'aelm', 'leap'},												-- Advanced Electronic Materials, Learned Publishing
+	['1016'] = {'j.aace', 'j.aed', 'j.aiopen', 'j.animal', 'j.apsb', 'j.addicn',-- AACE Endocrinology and Diabetes, AACE Endocrinology and Diabetes, AI Open, Animal, Acta Pharmaceutica Sinica B, Addiction Neuroscience
+				'j.abrep', 'j.gpb', 'j.heliyon', 'j.nlp', 'j.patter', 'j.proche', -- Addictive Behaviors Reports, Genomics, Proteomics & Bioinformatics after 2015, Heliyon, Natural Language Processing, Patterns, Procedia Chemistry
+				'j.vgie', 'S1672-0229'},		                                -- VideoGIE, Genomics, Proteomics & Bioinformatics before 2015
+	['1017'] = {'nlp'},															-- Natural Language Processing Journal
+	['1046'] = {'j.1365-8711', 'j.1365-246x'},									-- MNRAS, GJI
+	['1093'] = {'mnras', 'mnrasl', 'gji', 'pnasnexus', 'rasti'},				-- MNRAS, MNRAS Letters, GJI, PNAS Nexus, RASTI
+	['1098'] = {'rsos'},                                                        -- Royal Society Open Science
+	['1099'] = {'acmi', 'mic', '00221287', 'mgen'},                             -- Access Microbiology, Microbiology, Journal of General Microbiology, Microbial Genomics
+	['1107'] = {'S20569890', 'S20522525', 'S16005775', 'S24143146'},            -- Acta Crystallographica E, IUCrJ, Journal of Synchrotron Radiation, IUCrData
+	['1109'] = {'oa', 'oj'},                                                    -- IEEE Open Access..., IEEE Open Journal...
+	['1111'] = {'j.1365-2966', 'j.1745-3933', 'j.1365-246X'},					-- MNRAS, MNRAS Letters, GJI
+	['1128'] = {'asmcr', 'jmbe', 'mbio', 'mra', 'spectrum', 'msphere', 'msystems'}, --ASM Case Reports, Journal of Microbiology & Biology Education, mBio, Microbiology Resource Announcements, Microbiology Spectrum, mSphere, mSystems
+	['1210'] = {'jendso','jcemcr'},												-- Journal of the Endocrine Society, JCEM Case Reports
+	['4171'] = {'dm','mag'},												    -- Documenta Mathematica, EMS Magazine
+	['11158'] = {'saasp'},                                                      -- Systematic and Applied Acarology Special Publications
+	['11646'] = {'megataxa', 'mesozoic'},                                       -- Megataxa, Mesozoic
+	['14231'] = {'ag'},															-- Algebraic Geometry
+	['22073'] = {'pja'},                                                        -- Persian Journal of Acarology
+	['35249'] = {'rche'},                                                       -- Revista Chilena de Entomología
+	['37520'] = {'fi'},                                                         -- Fossil Imprint
+	['53562'] = {'ajcb'}                                                        -- Asian Journal of Conservation Biology
 	}
@@ Line 985: / Line 1,405: @@
 	['char'] = 'invalid character',												-- |isbn=, |sbn=
 	['check'] = 'checksum',														-- |isbn=, |sbn=
+	empty_str = '(empty string)',												-- empty unknown parameter check when cite has |=
 	['flag'] = 'flag',															-- |archive-url=
 	['form'] = 'invalid form',													-- |isbn=, |sbn=
 	['group'] = 'invalid group id',												-- |isbn=
 	['initials'] = 'initials',													-- Vancouver
+	['invalid language code'] = 'invalid language code',						-- |script-<param>=
 	['journal'] = 'journal',													-- |bibcode=
 	['length'] = 'length',														-- |isbn=, |bibcode=, |sbn=
 	['liveweb'] = 'liveweb',													-- |archive-url=
 	['missing comma'] = 'missing comma',										-- Vancouver
+	['missing prefix'] = 'missing prefix',										-- |script-<param>=
+	['missing title part'] = 'missing title part',								-- |script-<param>=
 	['name'] = 'name',															-- Vancouver
 	['non-Latin char'] = 'non-Latin character',									-- Vancouver
@@ Line 1,001: / Line 1,425: @@
 	['suffix'] = 'suffix',														-- Vancouver
 	['timestamp'] = 'timestamp',												-- |archive-url=
+	['unknown language code'] = 'unknown language code',						-- |script-<param>=
 	['value'] = 'value',														-- |bibcode=
 	['year'] = 'year',															-- |bibcode=
@@ Line 1,035: / Line 1,460: @@
 		hidden = false
   		},
+	err_archive_date_missing_url = {
+		message = '<code class="cs1-code">&#124;archive-date=</code> requires <code class="cs1-code">&#124;archive-url=</code>',
+		anchor = 'archive_date_missing_url',
+		category = 'CS1 errors: archive-url',
+		hidden = false
+		},
+	err_archive_date_url_ts_mismatch = {
+		message = '<code class="cs1-code">&#124;archive-date=</code> / <code class="cs1-code">&#124;archive-url=</code> timestamp mismatch; $1 suggested',
+		anchor = 'archive_date_url_ts_mismatch',
+		category = 'CS1 errors: archive-url',
+		hidden = false
+		},
 	err_archive_missing_date = {
 		message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;archive-date=</code>',
@@ Line 1,153: / Line 1,590: @@
 		anchor = 'bad_lccn',
 		category = 'CS1 errors: LCCN',
+		hidden = false
+		},
+	err_bad_medrxiv = {
+		message = 'Check <code class="cs1-code">&#124;medrxiv=</code> value',
+		anchor = 'bad_medrxiv',
+		category = 'CS1 errors: medRxiv',
 		hidden = false
 		},
@@ Line 1,351: / Line 1,794: @@
 		anchor = 'extra_text_volume',
 		category = 'CS1 errors: extra text: volume',
-		hidden = true,
+		hidden = false,
 		},
 	err_first_missing_last = {
 		message = '<code class="cs1-code">&#124;$1=</code> missing <code class="cs1-code">&#124;$2=</code>',	-- $1 is first alias, $2 is matching last alias
 		anchor = 'first_missing_last',
-		category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
+		category = 'CS1 errors: missing name',									-- author, contributor, editor, interviewer, translator
 		hidden = false
 		},
@@ Line 1,364: / Line 1,807: @@
 		category = 'CS1 errors: format without URL',
 		hidden = false
+		},
+	err_generic_name = {
+		message = '<code class="cs1-code">&#124;$1=</code> has generic name',	-- $1 is parameter name
+		anchor = 'generic_name',
+		category = 'CS1 errors: generic name',
+		hidden = false,
 		},
 	err_generic_title = {
@@ Line 1,370: / Line 1,819: @@
 		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 1,381: / Line 1,836: @@
 		anchor = 'invisible_char',
 		category = 'CS1 errors: invisible characters',
+		hidden = false
+		},
+	err_medrxiv_missing = {
+		message = '<code class="cs1-code">&#124;medrxiv=</code> required',
+		anchor = 'medrxiv_missing',
+		category = 'CS1 errors: medRxiv',										-- same as bad medRxiv
 		hidden = false
 		},
@@ Line 1,393: / Line 1,854: @@
 		anchor = 'missing_periodical',
 		category = 'CS1 errors: missing periodical',
-		hidden = true
+		hidden = false
 		},
 	err_missing_pipe = {
@@ Line 1,400: / Line 1,861: @@
 		category = 'CS1 errors: missing pipe',
 		hidden = false
+		},
+	err_missing_publisher = {
+		message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>',	-- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1
+		anchor = 'missing_publisher',
+		category = 'CS1 errors: missing publisher',
+		hidden = false
+		},
+	err_numeric_names = {
+		message = '<code class="cs1-code">&#124;$1=</code> has numeric name',	-- $1 is parameter name',
+		anchor = 'numeric_names',
+		category = 'CS1 errors: numeric name',
+		hidden = false,
 		},
 	err_param_access_requires_param = {
@@ Line 1,411: / Line 1,884: @@
 		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 1,423: / Line 1,902: @@
 		anchor = 'parameter_ignored_suggest',
 		category = 'CS1 errors: unsupported parameter',
+		hidden = false
+		},
+	err_periodical_ignored = {
+		message = '<code class="cs1-code">&#124;$1=</code> ignored',			-- $1 is parameter name
+		anchor = 'periodical_ignored',
+		category = 'CS1 errors: periodical ignored',
 		hidden = false
 		},
@@ Line 1,440: / Line 1,925: @@
 		message = '<code class="cs1-code">&#124;ssrn=</code> required',
 		anchor = 'ssrn_missing',
-		category = 'CS1 errors: SSRN',											-- same as bad arxiv
+		category = 'CS1 errors: SSRN',
 		hidden = false
 		},
@@ Line 1,481: / Line 1,966: @@
 ]]
 	maint_archived_copy = {
 		message = nil,
@@ Line 1,487: / Line 1,973: @@
 		hidden = true,
 		},
-	maint_authors = {
+	maint_bibcode = {
+		message = nil,
+		anchor = 'bibcode',
+		category = 'CS1 maint: bibcode',
+		hidden = true,
+		},
+	maint_location_no_publisher = {												-- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite
 		message = nil,
-		anchor = 'authors',
+		anchor = 'location_no_publisher',
-		category = 'CS1 maint: uses authors parameter',
+		category = 'CS1 maint: location missing publisher',
 		hidden = true,
 		},
@@ Line 1,497: / Line 1,989: @@
 		anchor = 'bot:_unknown',
 		category = 'CS1 maint: bot: original URL status unknown',
+		hidden = true,
+		},
+	maint_date_auto_xlated = {													-- date auto-translation not supported by en.wiki
+		message = nil,
+		anchor = 'date_auto_xlated',
+		category = 'CS1 maint: date auto-translated',
 		hidden = true,
 		},
@@ Line 1,509: / Line 2,007: @@
 		anchor = 'date_year',
 		category = 'CS1 maint: date and year',
-		hidden = true,
-		},
-	maint_discouraged = {
-		message = nil,
-		anchor = 'discouraged',
-		category = 'CS1 maint: discouraged parameter',
 		hidden = true,
 		},
@@ Line 1,533: / Line 2,025: @@
 		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 1,541: / Line 2,039: @@
 		hidden = true,
 		},
-	maint_extra_text_names = {
+	maint_id_limit_load_fail = {												-- applies to all cs1|2 templates on a page;
-		message = nil,
+		message = nil,															-- maint message (category link) never emitted
-		anchor = 'extra_text_names',
+		anchor = 'id_limit_load_fail',
-		category = 'CS1 maint: extra text: $1',									-- $1 is '<name>s list'; gets value from special_case_translation table
+		category = 'CS1 maint: ID limit load fail',
 		hidden = true,
 		},
@@ Line 1,570: / Line 2,068: @@
 		category = 'CS1 maint: location',
 		hidden = true,
-	},
+		},
-	maint_mr_format = {
+	maint_missing_class = {
+		message = nil,
+		anchor = 'missing_class',
+		category = 'CS1 maint: missing class',
+		hidden = true,
+		},
+	maint_mr_format = {
 		message = nil,
 		anchor = 'mr_format',
 		category = 'CS1 maint: MR format',
 		hidden = true,
-	},
+		},
 	maint_mult_names = {
 		message = nil,
@@ Line 1,600: / Line 2,104: @@
 		category = 'CS1 maint: others in cite AV media (notes)',
 		hidden = true,
-	},
+		},
+	maint_overridden_setting = {
+		message = nil,
+		anchor = 'overridden',
+		category = 'CS1 maint: overridden setting',
+		hidden = true,
+		},
+	maint_page_art_num = {
+		message = nil,
+		anchor = 'page_art_num',
+		category = 'CS1 maint: article number as page number',
+		hidden = true,
+		},
 	maint_pmc_embargo = {
 		message = nil,
@@ Line 1,617: / Line 2,133: @@
 		anchor = 'postscript',
 		category = 'CS1 maint: postscript',
+		hidden = true,
+	},
+	maint_publisher_location = {
+		message = nil,
+		anchor = 'publisher_location',
+		category = 'CS1 maint: publisher location',
 		hidden = true,
 	},
@@ Line 1,625: / Line 2,147: @@
 		hidden = true,
 	},
-	maint_ref_harv = {
-		message = nil,
-		anchor = 'ref_harv',
-		category = 'CS1 maint: ref=harv',
-		hidden = true,
-		},
-	maint_unfit = {
-		message = nil,
-		anchor = 'unfit',
-		category = 'CS1 maint: unfit URL',
-		hidden = true,
-		},
 	maint_unknown_lang = {
 		message = nil,
@@ Line 1,649: / Line 2,159: @@
 		hidden = true,
 		},
-	maint_zbl = {
+	maint_url_status = {
+		message = nil,
+		anchor = 'url_status',
+		category = 'CS1 maint: url-status',
+		hidden = true,
+		},
+	maint_work_isbn = {
 		message = nil,
-		anchor = 'zbl',
+		anchor = 'work_isbn',
-		category = 'CS1 maint: Zbl',
+		category = 'CS1 maint: work parameter with ISBN',
 		hidden = true,
 		},
-	}
+	maint_year= {
+		message = nil,
+		anchor = 'year',
+		category = 'CS1 maint: year',
+		hidden = true,
+		},
+	maint_zbl = {
+		message = nil,
+		anchor = 'zbl',
+		category = 'CS1 maint: Zbl',
+		hidden = true,
+		},
+	}
+--[[--------------------------< I D _ L I M I T S _ D A T A _ T >----------------------------------------------
+fetch id limits for certain identifiers from c:Data:CS1/Identifier limits.tab.  This source is a json tabular
+data file maintained at wikipedia commons.  Convert the json format to a table of k/v pairs.
+The values from <id_limits_data_t> are used to set handle.id_limit.
+From 2025-02-21, MediaWiki is broken.  Use this link to edit the tablular data file:
+	https://commons.wikimedia.org/w/index.php?title=Data:CS1/Identifier_limits.tab&action=edit
+See Phab:T389105
+]]
+local id_limits_data_t = {};
+local use_commons_data = true;													-- set to false if your wiki does not have access to mediawiki commons; then,
+if false == use_commons_data then												-- update this table from https://commons.wikimedia.org/wiki/Data:CS1/Identifier_limits.tab; last update: 2025-02-21
+	id_limits_data_t = {['OCLC'] = 10450000000, ['OSTI'] = 23010000, ['PMC'] = 11900000, ['PMID'] = 40400000, ['RFC'] = 9300, ['SSRN'] = 5200000, ['S2CID'] = 276000000};	-- this table must be maintained locally
+else																			-- here for wikis that do have access to mediawiki commons
+	local load_fail_limit = 99999999999;										-- very high number to avoid error messages on load failure
+	id_limits_data_t = {['OCLC'] = load_fail_limit, ['OSTI'] = load_fail_limit, ['PMC'] = load_fail_limit, ['PMID'] = load_fail_limit, ['RFC'] = load_fail_limit, ['SSRN'] = load_fail_limit, ['S2CID'] = load_fail_limit};
+	local id_limits_data_load_fail = false;										-- flag; assume that we will be successful when loading json id limit tabular data
+	local tab_data_t = mw.ext.data.get ('CS1/Identifier limits.tab');			-- attempt to load the tabular data from commons into <tab_data_t>
+	if false == tab_data_t then													-- undocumented 'feature': mw.ext.data.get() sometimes returns false
+		id_limits_data_load_fail = true;										-- set the flag so that Module:Citation/CS1 can create an unannotated maint category
+	else
+		for _, limit_t in ipairs (tab_data_t.data) do							-- overwrite default <load_fail_limit> values from the data table in the tabular data
+			id_limits_data_t[limit_t[1]] = limit_t[2];							-- <limit[1]> is identifier; <limit[2]> is upper limit for that identifier
+		end
+	end
+end
 --[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
@@ Line 1,668: / Line 2,232: @@
 	redirect: a local redirect to a local Wikipedia article name;  at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'
 	q: Wikidata q number for the identifier
-	label: the label preceeding the identifier; label is linked to a Wikipedia article (in this order):
+	label: the label preceding the identifier; label is linked to a Wikipedia article (in this order):
 		redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true
 		Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q
@@ Line 1,687: / Line 2,251: @@
 	custom_access: to enable custom access level for an identifier, set this parameter
 		to the parameter that should control it (normally 'id-access')
 ]]
@@ Line 1,696: / Line 2,261: @@
 		q = 'Q118398',
 		label = 'arXiv',
-		prefix = '//arxiv.org/abs/', 											-- protocol-relative tested 2013-09-04
+		prefix = 'https://arxiv.org/abs/',
 		encode = false,
 		COinS = 'info:arxiv',
@@ Line 1,708: / Line 2,273: @@
 		q = 'Q1753278',
 		label = 'ASIN',
-		prefix = '//www.amazon.',
+		prefix = 'https://www.amazon.',
 		COinS = 'url',
 		separator = '&nbsp;',
@@ Line 1,731: / Line 2,296: @@
 		q = 'Q19835482',
 		label = 'bioRxiv',
-		prefix = '//doi.org/',
+		prefix = 'https://doi.org/',
 		COinS = 'pre',															-- use prefix value
 		access = 'free',														-- free to read
@@ Line 1,743: / Line 2,308: @@
 		q = 'Q2715061',
 		label = 'CiteSeerX',
-		prefix = '//citeseerx.ist.psu.edu/viewdoc/summary?doi=',
+		prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=',
 		COinS =  'pre',															-- use prefix value
 		access = 'free',														-- free to read
@@ Line 1,755: / Line 2,320: @@
 		q = 'Q25670',
 		label = 'doi',
-		prefix = '//doi.org/',
+		prefix = 'https://doi.org/',
 		COinS = 'info:doi',
 		separator = ':',
@@ Line 1,767: / Line 2,332: @@
 		q = 'Q46339674',
 		label = 'eISSN',
-		prefix = '//www.worldcat.org/issn/',
+		prefix = 'https://search.worldcat.org/issn/',
 		COinS = 'rft.eissn',
 		encode = false,
@@ Line 1,778: / Line 2,343: @@
 		q = 'Q3126718',
 		label = 'hdl',
-		prefix = '//hdl.handle.net/',
+		prefix = 'https://hdl.handle.net/',
 		COinS = 'info:hdl',
 		separator = ':',
@@ Line 1,785: / Line 2,350: @@
 		},
 	['ISBN'] = {																-- Used by InternetArchiveBot
-		parameters = {'isbn', 'ISBN', 'isbn13', 'ISBN13'},
+		parameters = {'isbn', 'ISBN'},
 		link = 'International Standard Book Number',
 		redirect = 'ISBN (identifier)',
@@ Line 1,807: / Line 2,372: @@
 		parameters = {'issn', 'ISSN'},
 		link = 'International Standard Serial Number',
-		redirect = '',
+		redirect = 'ISSN (identifier)',
 		q = 'Q131276',
 		label = 'ISSN',
-		prefix = '//www.worldcat.org/issn/',
+		prefix = 'https://search.worldcat.org/issn/',
 		COinS = 'rft.issn',
 		encode = false,
@@ Line 1,821: / Line 2,386: @@
 		q = '',
 		label = 'JFM',
-		prefix = '//zbmath.org/?format=complete&q=an:',
+		prefix = 'https://zbmath.org/?format=complete&q=an:',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
@@ Line 1,832: / Line 2,397: @@
 		q = 'Q1420342',
 		label = 'JSTOR',
-		prefix = '//www.jstor.org/stable/', 									-- protocol-relative tested 2013-09-04
+		prefix = 'https://www.jstor.org/stable/',
 		COinS = 'pre',															-- use prefix value
 		encode = false,
@@ Line 1,844: / Line 2,409: @@
 		q = 'Q620946',
 		label = 'LCCN',
-		prefix = '//lccn.loc.gov/', 											-- protocol-relative tested 2015-12-28
+		prefix = 'https://lccn.loc.gov/',
 		COinS = 'info:lccn',
 		encode = false,
 		separator = '&nbsp;',
 		},
-	['MR'] = {
+	['MEDRXIV'] = {
+		parameters = {'medrxiv'},
+		link = 'medRxiv',
+		redirect = 'medRxiv (identifier)',
+		q = 'Q58465838',
+		label = 'medRxiv',
+		prefix = 'https://www.medrxiv.org/content/',
+		COinS = 'pre',															-- use prefix value
+		access = 'free',														-- free to read
+		encode = false,
+		separator = '&nbsp;',
+		},
+	['MR'] = {
 		parameters = {'mr', 'MR'},
 		link = 'Mathematical Reviews',
@@ Line 1,855: / Line 2,432: @@
 		q = 'Q211172',
 		label = 'MR',
-		prefix = '//www.ams.org/mathscinet-getitem?mr=', 						-- protocol-relative tested 2013-09-04
+		prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
@@ Line 1,866: / Line 2,443: @@
 		q = 'Q190593',
 		label = 'OCLC',
-		prefix = '//www.worldcat.org/oclc/',
+		prefix = 'https://search.worldcat.org/oclc/',
 		COinS = 'info:oclcnum',
 		encode = true,
 		separator = '&nbsp;',
-		id_limit = 9999999999,													-- 10-digits
+		id_limit = id_limits_data_t.OCLC or 0,
 		},
 	['OL'] = {
@@ Line 1,878: / Line 2,455: @@
 		q = 'Q1201876',
 		label = 'OL',
-		prefix = '//openlibrary.org/',
+		prefix = 'https://openlibrary.org/',
 		COinS = 'url',
 		separator = '&nbsp;',
@@ Line 1,890: / Line 2,467: @@
 		q = 'Q2015776',
 		label = 'OSTI',
-		prefix = '//www.osti.gov/biblio/',										-- protocol-relative tested 2018-09-12
+		prefix = 'https://www.osti.gov/biblio/',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
 		separator = '&nbsp;',
-		id_limit = 23000000,
+		id_limit = id_limits_data_t.OSTI or 0,
 		custom_access = 'osti-access',
 		},
@@ Line 1,903: / Line 2,480: @@
 		q = 'Q229883',
 		label = 'PMC',
-		prefix = '//www.ncbi.nlm.nih.gov/pmc/articles/PMC',
+		prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC',
 		suffix = '',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
 		separator = '&nbsp;',
-		id_limit = 8300000,
+		id_limit = id_limits_data_t.PMC or 0,
 		access = 'free',														-- free to read
 		},
@@ Line 1,917: / Line 2,494: @@
 		q = 'Q2082879',
 		label = 'PMID',
-		prefix = '//pubmed.ncbi.nlm.nih.gov/',
+		prefix = 'https://pubmed.ncbi.nlm.nih.gov/',
 		COinS = 'info:pmid',
 		encode = false,
 		separator = '&nbsp;',
-		id_limit = 34400000,
+		id_limit = id_limits_data_t.PMID or 0,
 		},
 	['RFC'] = {
@@ Line 1,929: / Line 2,506: @@
 		q = 'Q212971',
 		label = 'RFC',
-		prefix = '//tools.ietf.org/html/rfc',
+		prefix = 'https://tools.ietf.org/html/rfc',
 		COinS = 'pre',															-- use prefix value
 		encode = false,
 		separator = '&nbsp;',
-		id_limit = 9000,
+		id_limit = id_limits_data_t.RFC or 0,
 		access = 'free',														-- free to read
 		},
@@ Line 1,951: / Line 2,528: @@
 		q = 'Q7550801',
 		label = 'SSRN',
-		prefix = '//ssrn.com/abstract=', 										-- protocol-relative tested 2013-09-04
+		prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
 		separator = '&nbsp;',
-		id_limit = 4000000,
+		id_limit = id_limits_data_t.SSRN or 0,
-		access = 'free',														-- always free to read
+		custom_access = 'ssrn-access',
 		},
 	['S2CID'] = {
@@ Line 1,968: / Line 2,545: @@
 		encode = false,
 		separator = '&nbsp;',
-		id_limit = 235000000,
+		id_limit = id_limits_data_t.S2CID or 0,
 		custom_access = 's2cid-access',
 		},
@@ Line 1,988: / Line 2,565: @@
 		q = 'Q190269',
 		label = 'Zbl',
-		prefix = '//zbmath.org/?format=complete&q=an:',
+		prefix = 'https://zbmath.org/?format=complete&q=an:',
 		COinS = 'pre',															-- use prefix value
 		encode = true,
@@ Line 1,999: / Line 2,576: @@
 ]]
 return 	{
-	use_identifier_redirects = true,											-- when true use redirect name for identifier label links
+	use_identifier_redirects = use_identifier_redirects,						-- booleans defined in the settings at the top of this module
+	local_lang_cat_enable = local_lang_cat_enable,
+	date_name_auto_xlate_enable = date_name_auto_xlate_enable,
+	date_digit_auto_xlate_enable = date_digit_auto_xlate_enable,
+	enable_sort_keys = enable_sort_keys,
+																				-- 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,
+	date_names = date_names,
+	err_msg_supl = err_msg_supl,
+	error_conditions = error_conditions,
+	editor_markup_patterns = editor_markup_patterns,
+	et_al_patterns = et_al_patterns,
+	extended_registrants_t = extended_registrants_t,
+	id_handlers = id_handlers,
+	keywords_lists = keywords_lists,
+	keywords_xlate = keywords_xlate,
+	stripmarkers = stripmarkers,
+	invisible_chars = invisible_chars,
+	invisible_defs = invisible_defs,
+	indic_script = indic_script,
+	emoji_t = emoji_t,
+	maint_cats = maint_cats,
+	messages = messages,
+	presentation = presentation,
+	prop_cats = prop_cats,
+	script_lang_codes = script_lang_codes,
+	lang_tag_remap = lang_tag_remap,
+	lang_name_remap = lang_name_remap,
+	this_wiki_code = this_wiki_code,
+	title_types = title_types,
+	uncategorized_namespaces = uncategorized_namespaces_t,
+	uncategorized_subpages = uncategorized_subpages,
+	templates_using_volume = templates_using_volume,
+	templates_using_issue = templates_using_issue,
+	templates_not_using_page = templates_not_using_page,
+	vol_iss_pg_patterns = vol_iss_pg_patterns,
+	single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t,
+	url_access_map_t = url_access_map_t,
+	inter_wiki_map = inter_wiki_map,
+	mw_languages_by_tag_t = mw_languages_by_tag_t,
+	mw_languages_by_name_t = mw_languages_by_name_t,
+	citation_class_map_t = citation_class_map_t,
-	aliases = aliases,
+	citation_issue_t = citation_issue_t,
-	special_case_translation = special_case_translation,
+	citation_no_volume_t = citation_no_volume_t,
-	date_names = date_names,
-	err_msg_supl = err_msg_supl,
-	error_conditions = error_conditions,
-	editor_markup_patterns = editor_markup_patterns,
-	et_al_patterns = et_al_patterns,
-	global_df = global_df,
-	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 = emoji,
-	local_lang_cat_enable = local_lang_cat_enable,
-	maint_cats = maint_cats,
-	messages = messages,
-	presentation = presentation,
-	prop_cats = prop_cats,
-	punct_skip = punct_skip,
-	script_lang_codes = script_lang_codes,
-	lang_code_remap = lang_code_remap,
-	lang_name_remap = lang_name_remap,
-	this_wiki_code = this_wiki_code,
-	title_types = title_types,
-	uncategorized_namespaces = 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,
-	inter_wiki_map = inter_wiki_map,
-	languages = languages,
 	}