Wikigama

Module:Citation/CS1/Configuration: Difference between revisions

← Older edit

PS (talk | contribs)

7 user groups
456 edits
PS (talk | contribs)
automoderated, Bureaucrats, checkuser, Interface administrators, moderator, Suppressors, Administrators
456 edits
m 1 revision imported
PS (talk | contribs)
automoderated, Bureaucrats, checkuser, Interface administrators, moderator, Suppressors, Administrators
456 edits
No edit summary
 
Line 1: Line 1:
local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates
local z = {
error_cats_t = {}; -- for categorizing citations that contain errors
error_ids_t = {}; -- list of error identifiers; used to prevent duplication of certain errors; local to this module
error_msgs_t = {}; -- sequence table of error messages
maint_cats_t = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
prop_cats_t = {}; -- for categorizing citations based on certain properties, language of source for instance
prop_keys_t = {}; -- for adding classes to the citation's <cite> tag
};




--[[--------------------------< S E T T I N G S >--------------------------------------------------------------
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
 
boolean settings used to control various things.  these setting located here to make them easy to find
 
]]
]]
-- these settings local to this module only
local local_digits_from_mediawiki = false; -- for i18n; when true, module fills date_names['local_digits'] from MediaWiki; manual fill required else; always false at en.wiki
local local_date_names_from_mediawiki = false; -- for i18n; when true, module fills date_names['local']['long'] and date_names['local']['short'] from MediaWiki;
-- manual translation required else; ; always false at en.wiki
-- these settings exported to other modules
local use_identifier_redirects = true; -- when true use redirect name for identifier label links; always true at en.wiki
local local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki
local date_name_auto_xlate_enable = false; -- when true translates English month-names to the local-wiki's language month names; always false at en.wiki
local date_digit_auto_xlate_enable = false; -- when true translates Western date digit to the local-wiki's language digits (date_names['local_digits']); always false at en.wiki
local enable_sort_keys = true; -- when true module adds namespace sort keys to error and maintenance category links


local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration


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


List of namespaces identifiers for namespaces that will not be included in citation error categories.
--[[--------------------------< I S _ S E T >------------------------------------------------------------------
Same as setting notracking = true by default.


For wikis that have a current version of Module:cs1 documentation support, this #invoke will return an unordered
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
list of namespace names and their associated identifiers:
{{#invoke:cs1 documentation support|uncategorized_namespace_lister|all=<anything>}}


]]
]]


local uncategorized_namespaces_t = {[2]=true}; -- init with user namespace id
local function is_set (var)
for k, _ in pairs (mw.site.talkNamespaces) do -- add all talk namespace ids
return not (var == nil or var == '');
uncategorized_namespaces_t[k] = true;
end
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


--[[
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
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
Whether needle is in haystack
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:
local function in_array (needle, haystack)
[4] = 'ω', -- wikipedia; omega
if needle == nil then
[10] = 'τ', -- template; tau
return false;
[118] = 'Δ', -- draft; delta
end
['other'] = 'ο', -- all other non-talk namespaces except main (article); omicron
for n, v in ipairs (haystack) do
}
if v == needle then
return n;
end
end
return false;
end


--[[--------------------------< M E S S A G E S >--------------------------------------------------------------


Translation table
--[[--------------------------< H A S _ A C C E P T _ A S _ W R I T T E N >------------------------------------


The following contains fixed text that may be output as part of a citation.
When <str> is wholly wrapped in accept-as-written markup, return <str> without markup and true; return <str> and false else
This is separated from the main body to aid in future translations of this
 
module.
with allow_empty = false, <str> must have at least one character inside the markup
with allow_empty = true, <str> the markup frame can be empty like (()) to distinguish an empty template parameter from the specific condition "has no applicable value" in citation-context.
 
After further evaluation the two cases might be merged at a later stage, but should be kept separated for now.


]]
]]


local messages = {
local function has_accept_as_written (str, allow_empty)
['agency'] = '$1 $2', -- $1 is sepc, $2 is agency
if not is_set (str) then
['archived-dead'] = 'Archived from $1 on $2',
return str, false;
['archived-live'] = '$1 from the original on $2',
end
['archived-unfit'] = 'Archived from the original on ',
['archived'] = 'Archived',
['by'] = 'By', -- contributions to authored works: introduction, foreword, afterword
['cartography'] = 'Cartography by $1',
['editor'] = 'ed.',
['editors'] = 'eds.',
['edition'] = '($1&nbsp;ed.)',
['episode'] = 'Episode $1',
['et al'] = 'et&nbsp;al.',
['in'] = 'In', -- edited works
['inactive'] = 'inactive',
['inset'] = '$1 inset',
['interview'] = 'Interviewed by $1',
['mismatch'] = '<code class="cs1-code">&#124;$1=</code> / <code class="cs1-code">&#124;$2=</code> mismatch', -- $1 is year param name; $2 is date param name
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]:&nbsp;$1',
['notitle'] = 'No title', -- for |title=(()) and (in the future) |title=none
['original'] = 'the original',
['origdate'] = ' [$1]',
['published'] = ' (published $1)',
['retrieved'] = 'Retrieved $1',
['season'] = 'Season $1',
['section'] = '§&nbsp;$1',
['sections'] = '§§&nbsp;$1',
['series'] = '$1 $2', -- $1 is sepc, $2 is series
['seriesnum'] = 'Series $1',
['translated'] = 'Translated by $1',
['type'] = ' ($1)', -- for titletype
['written'] = 'Written at $1',


['vol'] = '$1 Vol.&nbsp;$2', -- $1 is sepc; bold journal style volume is in presentation{}
local count;
['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
if true == allow_empty then
['vol-art'] = '$1 Vol.&nbsp;$2, art.&nbsp;$3', -- sepc, volume, article-number; for {{cite conference}} only
str, count = str:gsub ('^%(%((.*)%)%)$', '%1'); -- allows (()) to be an empty set
else
str, count = str:gsub ('^%(%((.+)%)%)$', '%1');
end
return str, 0 ~= count;
end


['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
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------


['p-prefix'] = "$1 p.&nbsp;$2", -- $1 is sepc
Populates numbered arguments in a message string using an argument table. <args> may be a single string or a
['pp-prefix'] = "$1 pp.&nbsp;$2", -- $1 is sepc
sequence table of multiple strings.
['j-page(s)'] = ': $1', -- same for page and pages


['sheet'] = '$1 Sheet&nbsp;$2', -- $1 is sepc
]]
['sheets'] = '$1 Sheets&nbsp;$2', -- $1 is sepc
['j-sheet'] = ': Sheet&nbsp;$1',
['j-sheets'] = ': Sheets&nbsp;$1',
['language'] = '(in $1)',
['via'] = " &ndash; via $1",
['event'] = 'Event occurs at',
['minutes'] = 'minutes in',
-- Determines the location of the help page
['help page link'] = 'Help:CS1 errors',
['help page label'] = 'help',
-- categories
['cat wikilink'] = '[[Category:$1]]', -- $1 is the category name
['cat wikilink sk'] = '[[Category:$1|$2]]', -- $1 is the category name; $2 is namespace sort key
[':cat wikilink'] = '[[:Category:$1|link]]', -- category name as maintenance message wikilink; $1 is the category name


-- Internal errors (should only occur if configuration is bad)
local function substitute (msg, args)
['undefined_error'] = 'Called with an undefined error condition',
return args and mw.message.newRawMessage (msg, args):plain() or msg;
['unknown_ID_key'] = 'Unrecognized ID key: ', -- an ID key in id_handlers not found in ~/Identifiers func_map{}
end
['unknown_ID_access'] = 'Unrecognized ID access keyword: ', -- an ID access keyword in id_handlers not found in keywords_lists['id-access']{}
['unknown_argument_map'] = 'Argument map not defined for this variable',
['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty',
['warning_msg_e'] = '<span style="color:#d33">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code> templates have errors</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link
['warning_msg_m'] = '<span style="color:#3a3">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">&#123;{$1}}</code> templates have maintenance messages</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link
}




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


this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when
Wraps error messages with CSS markup according to the state of hidden. <content> may be a single string or a
the value assigned to |CitationClass= is different from the canonical template name. |CitationClass= values are
sequence table of multiple strings.
used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while
the canonical template name may.  These names are used in warning_msg_e and warning_msg_m to create links to the
template's documentation when an article is displayed in preview mode.
 
Most cs1|2 template |CitationClass= values at en.wiki match their canonical template names so are not listed here.


]]
]]


local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n
local function error_comment (content, hidden)
['arxiv'] = 'arXiv',
return substitute (hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content);
['audio-visual'] = 'AV media',
end
['AV-media-notes'] = 'AV media notes',
['biorxiv'] = 'bioRxiv',
['citeseerx'] = 'CiteSeerX',
['encyclopaedia'] = 'encyclopedia',
['mailinglist'] = 'mailing list',
['medrxiv'] = 'medRxiv',
['pressrelease'] = 'press release',
['ssrn'] = 'SSRN',
['techreport'] = 'tech report',
}




--[=[-------------------------< E T _ A L _ P A T T E R N S >--------------------------------------------------
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------


This table provides Lua patterns for the phrase "et al" and variants in name text
Converts a hyphen, endash, emdash to endash under certain conditions.  The hyphen/en/em must separate
(author, editor, etc.). The main module uses these to identify and emit the 'etal' message.
like items; unlike items are returned unmodified.  These forms are modified:
letter - letter (A-B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and
digit is supported – a.1-a.5 or a-1-a-5)
digitletter - digitletter (5a-5d) (an optional separator between letter and
digit is supported – 5.a-5.d or 5-a-5-d)


]=]
any other forms are returned unmodified.


local et_al_patterns = {
str may be a comma- or semicolon-separated list of page ranges with/without single pages
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$", -- variations on the 'et al' theme
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.;,\"']*$", -- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)
"[;,]? *%f[%a]and [Oo]thers", -- an alternative to et al.
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form
"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax)
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form
}


]]


--[[--------------------------< P R E S E N T A T I O N >------------------------
local function hyphen_to_dash (str)
if not is_set (str) then
return str;
end


Fixed presentation markup. Originally part of citation_config.messages it has
str = str:gsub ("(%(%(.-%)%))", function(m) return m:gsub(",", "，"):gsub(";", "；") end) -- replace commas and semicolons in accept-as-written markup with similar unicode characters so they'll be ignored during the split
been moved into its own, more semantically correct place.
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split
 
str = str:gsub ('&#45;', '-'); -- replace HTML numeric entity with hyphen character
]]
str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character
 
local presentation =
{
-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display
['hidden-error'] = '<span class="cs1-hidden-error citation-comment">$1</span>',
['visible-error'] = '<span class="cs1-visible-error citation-comment">$1</span>',
['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>',
['accessdate'] = '<span class="reference-accessdate">$1$2</span>', -- to allow editors to hide accessdate using personal CSS
local out = {};
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any


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


['cite'] = '<cite class="$1">$2</cite>'; -- for use when citation does not have a namelist and |ref= not set so no id="..." attribute
for _, item in ipairs (list) do -- for each item in the list
['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when when |ref= is set or when citation has a namelist
item, accept = has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[—–-]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
if mw.ustring.match (item, '^%a+[%.%-]?%d+%s*[—–-]%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
mw.ustring.match (item, '^%d+[%.%-]?%a+%s*[—–-]%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
mw.ustring.match (item, '^%d+[%.%-]%d+%s*[—–-]%s*%d+[%.%-]%d+$') then -- digit separator digit hyphen digit separator digit
item = mw.ustring.gsub (item, '(%w*[%.%-]?%w+)%s*[—–-]%s*(%w*[%.%-]?%w+)', '<span class="nowrap">%1 –</span> <span class="nowrap">%2</span>'); -- replace hyphen/dash, with spaced endash


['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc.
elseif mw.ustring.match (item, '^%d+%s*[—–-]%s*%d+$') or -- digit hyphen digit
['interwiki'] = ' <span class="cs1-format">[in $1]</span>', -- for interwiki-language-linked author, editor, etc
mw.ustring.match (item, '^%a+%s*[—–-]%s*%a+$') then -- letter hyphen letter
['interproj'] = ' <span class="cs1-format">[at $1]</span>', -- for interwiki-project-linked author, editor, etc (:d: and :s: supported; :w: ignored)
item = mw.ustring.gsub (item, '(%w+)%s*[—–-]%s*(%w+)', '<span class="nowrap">%1–</span>%2'); -- replace hyphen/emdash with endash, remove extraneous space characters


-- various access levels, for |access=, |doi-access=, |arxiv=, ...
else
-- narrow no-break space &#8239; may work better than nowrap CSS. Or not? Browser support?
-- item = mw.ustring.gsub (item, '%s*[—–-]%s*', '–'); -- disabled; here when 'unlike' items so return <item> as is
end
end
table.insert (out, item); -- add the (possibly modified) item to the output table
end


['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon
local temp_str = ''; -- concatenate the output table into a comma separated string
['free'] = {class='id-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css
temp_str, accept = has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out
['registration'] = {class='id-lock-registration', title='Free registration required'},
if accept then
['limited'] = {class='id-lock-limited', title='Free access subject to limited trial, subscription normally required'},
temp_str = has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value
['subscription'] = {class='id-lock-subscription', title='Paid subscription required'},
return temp_str:gsub("，", ","):gsub("；", ";");
else
return temp_str:gsub("，", ","):gsub("；", ";"); -- else, return assembled temp_str
end
end


['interwiki-icon'] = '<span class="$1" title="$2">$3</span>',
['class-wikisource'] = 'cs1-ws-icon',


['italic-title'] = "''$1''",
--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------


['kern-left'] = '<span class="cs1-kern-left"></span>$1', -- spacing to use when title contains leading single or double quote mark
Makes a wikilink; when both link and display text is provided, returns a wikilink in the form [[L|D]]; if only
['kern-right'] = '$1<span class="cs1-kern-right"></span>', -- spacing to use when title contains trailing single or double quote mark
link is provided (or link and display are the same), returns a wikilink in the form [[L]]; if neither are
provided or link is omitted, returns an empty string.


['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span>
]=]
['nowrap2'] = '<span class="nowrap">$1</span> $2', -- for nowrapping portions of an item: <span ...>dd mmmm</span> yyyy (note white space)


['ocins'] = '<span title="$1" class="Z3988"></span>',
local function make_wikilink (link, display)
if not is_set (link) then return '' end
['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
if is_set (display) and link ~= display then
['quoted-title'] = '"$1"',
return table.concat ({'[[', link, '|', display, ']]'});
else
return table.concat ({'[[', link, ']]'});
end
end


['sep_cs1'] = '.', -- CS1 element separator
['sep_cs2'] = ',', -- CS2 separator
['sep_nl'] = ';', -- CS1|2 style name-list separator between names is a semicolon
['sep_nl_and'] = ' and ', -- used as last nl sep when |name-list-style=and and list has 2 items
['sep_nl_end'] = '; and ', -- used as last nl sep when |name-list-style=and and list has 3+ names
['sep_name'] = ', ', -- CS1|2 style last/first separator is <comma><space>
['sep_nl_vanc'] = ',', -- Vancouver style name-list separator between authors is a comma
['sep_name_vanc'] = ' ', -- Vancouver style last/first separator is a space


['sep_list'] = ', ', -- used for |language= when list has 3+ items except for last sep which uses sep_list_end
--[[--------------------------< S E T _ M E S S A G E >----------------------------------------------------------
['sep_list_pair'] = ' and ', -- used for |language= when list has 2 items
['sep_list_end'] = ', and ', -- used as last list sep for |language= when list has 3+ items
['trans-italic-title'] = "&#91;''$1''&#93;",
['trans-quoted-title'] = "&#91;$1&#93;", -- for |trans-title= and |trans-quote=
['vol-bold'] = '$1 <b>$2</b>', -- sepc, volume; for bold journal cites; for other cites ['vol'] in messages{}
}


Sets an error message using the ~/Configuration error_conditions{} table along with arguments supplied in the function
--[[--------------------------< A L I A S E S >---------------------------------
call, inserts the resulting message in z.error_msgs_t{} sequence table, and returns the error message.


Aliases table for commonly passed parameters.
<error_id> – key value for appropriate error handler in ~/Configuration error_conditions{} table
<arguments> – may be a single string or a sequence table of multiple strings to be subsititued into error_conditions[error_id].message
<raw> – boolean
true – causes this function to return the error message not wrapped in visible-error, hidden-error span tag;
returns error_conditions[error_id].hidden as a second return value
does not add message to z.error_msgs_t sequence table
false, nil – adds message wrapped in visible-error, hidden-error span tag to z.error_msgs_t
returns the error message wrapped in visible-error, hidden-error span tag; there is no second return value
<prefix> – string to be prepended to <message> -- TODO: remove support for these unused(?) arguments?
<suffix> – string to be appended to <message>


Parameter names on the right side in the assignments in this table must have been
TODO: change z.error_cats_t and z.maint_cats_t to have the form cat_name = true?  this to avoid dups without having to have an extra table
defined in the Whitelist before they will be recognized as valid parameter names


]]
]]


local aliases = {
local added_maint_cats = {} -- list of maintenance categories that have been added to z.maint_cats_t; TODO: figure out how to delete this table
['AccessDate'] = {'access-date', 'accessdate'}, -- Used by InternetArchiveBot
['Agency'] = 'agency',
['ArchiveDate'] = {'archive-date', 'archivedate'}, -- Used by InternetArchiveBot
['ArchiveFormat'] = 'archive-format',
['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot
['ArticleNumber'] = 'article-number',
['ASINTLD'] = 'asin-tld',
['At'] = 'at', -- Used by InternetArchiveBot
['Authors'] = {'people', 'credits'},
['BookTitle'] = {'book-title', 'booktitle'},
['Cartography'] = 'cartography',
['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'},
['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format',
'article-format', 'section-format'};
['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url'}, -- Used by InternetArchiveBot
['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access',
'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot
['Class'] = 'class', -- cite arxiv and arxiv identifier
['Collaboration'] = 'collaboration',
['Conference'] = {'conference', 'event'},
['ConferenceFormat'] = 'conference-format',
['ConferenceURL'] = 'conference-url', -- Used by InternetArchiveBot
['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only
['Degree'] = 'degree',
['DF'] = 'df',
['DisplayAuthors'] = {'display-authors', 'display-subjects'},
['DisplayContributors'] = 'display-contributors',
['DisplayEditors'] = 'display-editors',
['DisplayInterviewers'] = 'display-interviewers',
['DisplayTranslators'] = 'display-translators',
['Docket'] = 'docket',
['DoiBroken'] = 'doi-broken-date',
['Edition'] = 'edition',
['Embargo'] = 'pmc-embargo-date',
['Encyclopedia'] = {'encyclopedia', 'encyclopaedia', 'dictionary'}, -- cite encyclopedia only
['Episode'] = 'episode', -- cite serial only TODO: make available to cite episode?
['Format'] = 'format',
['ID'] = {'id', 'ID'},
['Inset'] = 'inset',
['Issue'] = {'issue', 'number'},
['Language'] = {'language', 'lang'},
['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only
['Map'] = 'map', -- cite map only
['MapFormat'] = 'map-format', -- cite map only
['MapURL'] = {'map-url', 'mapurl'}, -- cite map only -- Used by InternetArchiveBot
['MapUrlAccess'] = 'map-url-access', -- cite map only -- Used by InternetArchiveBot
['Minutes'] = 'minutes',
['Mode'] = 'mode',
['NameListStyle'] = 'name-list-style',
['Network'] = 'network',
['Newsgroup'] = 'newsgroup', -- cite newsgroup only
['NoPP'] = {'no-pp', 'nopp'},
['NoTracking'] = {'no-tracking', 'template-doc-demo'},
['Number'] = 'number', -- this case only for cite techreport
['OrigDate'] = {'orig-date', 'orig-year', 'origyear'},
['Others'] = 'others',
['Page'] = {'page', 'p'}, -- Used by InternetArchiveBot
['Pages'] = {'pages', 'pp'}, -- Used by InternetArchiveBot
['Periodical'] = {'journal', 'magazine', 'newspaper', 'periodical', 'website', 'work'},
['Place'] = {'place', 'location'},
['PostScript'] = 'postscript',
['PublicationDate'] = {'publication-date', 'publicationdate'},
['PublicationPlace'] = {'publication-place', 'publicationplace'},
['PublisherName'] = {'publisher', 'institution'},
['Quote'] = {'quote', 'quotation'},
['QuotePage'] = 'quote-page',
['QuotePages'] = 'quote-pages',
['Ref'] = 'ref',
['Scale'] = 'scale',
['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry',
'script-article', 'script-section'},
['ScriptEncyclopedia'] = {'script-encyclopedia', 'script-encyclopaedia'}, -- cite encyclopedia only
['ScriptMap'] = 'script-map',
['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper',
'script-periodical', 'script-website', 'script-work'},
['ScriptQuote'] = 'script-quote',
['ScriptTitle'] = 'script-title', -- Used by InternetArchiveBot
['Season'] = 'season',
['Sections'] = 'sections', -- cite map only
['Series'] = {'series', 'version'},
['SeriesLink'] = {'series-link', 'serieslink'},
['SeriesNumber'] = {'series-number', 'series-no'},
['Sheet'] = 'sheet', -- cite map only
['Sheets'] = 'sheets', -- cite map only
['Station'] = 'station',
['Time'] = 'time',
['TimeCaption'] = 'time-caption',
['Title'] = 'title', -- Used by InternetArchiveBot
['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot
['TitleNote'] = {'title-note', 'department'},
['TitleType'] = {'type', 'medium'},
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution',
'trans-entry', 'trans-section'},
['Transcript'] = 'transcript',
['TranscriptFormat'] = 'transcript-format',
['TranscriptURL'] = 'transcript-url', -- Used by InternetArchiveBot
['TransEncyclopedia'] = {'trans-encyclopedia', 'trans-encyclopaedia'}, -- cite encyclopedia only
['TransMap'] = 'trans-map', -- cite map only
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper',
'trans-periodical', 'trans-website', 'trans-work'},
['TransQuote'] = 'trans-quote',
['TransTitle'] = 'trans-title', -- Used by InternetArchiveBot
['URL'] = {'url', 'URL'}, -- Used by InternetArchiveBot
['UrlAccess'] = 'url-access', -- Used by InternetArchiveBot
['UrlStatus'] = 'url-status', -- Used by InternetArchiveBot
['Vauthors'] = 'vauthors',
['Veditors'] = 'veditors',
['Via'] = 'via',
['Volume'] = 'volume',
['Year'] = 'year',


['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given",
local function set_message (error_id, arguments, raw, prefix, suffix)
"subject-first#", "subject#-first", "subject-given#", "subject#-given",
local error_state = cfg.error_conditions[error_id];
"given#"},
['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname",
prefix = prefix or '';
"subject-last#", "subject#-last", "subject-surname#", "subject#-surname",
suffix = suffix or '';
"author#", 'host#', "subject#", "surname#"},
['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#",
"subject#-link", "authorlink#", "author#link"},
['AuthorList-Mask'] = {"author-mask#", "author#-mask", "subject-mask#", "subject#-mask"},
 
['ContributorList-First'] = {'contributor-first#', 'contributor#-first',
'contributor-given#', 'contributor#-given'},
['ContributorList-Last'] = {'contributor-last#', 'contributor#-last',
'contributor-surname#', 'contributor#-surname', 'contributor#'},
['ContributorList-Link'] = {'contributor-link#', 'contributor#-link'},
['ContributorList-Mask'] = {'contributor-mask#', 'contributor#-mask'},
 
['EditorList-First'] = {"editor-first#", "editor#-first", "editor-given#", "editor#-given"},
['EditorList-Last'] = {"editor-last#", "editor#-last", "editor-surname#",
"editor#-surname", "editor#"},
['EditorList-Link'] = {"editor-link#", "editor#-link"},
['EditorList-Mask'] = {"editor-mask#", "editor#-mask"},
['InterviewerList-First'] = {'interviewer-first#', 'interviewer#-first',
if error_state == nil then
'interviewer-given#', 'interviewer#-given'},
error (cfg.messages['undefined_error'] .. ': ' .. error_id); -- because missing error handler in Module:Citation/CS1/Configuration
['InterviewerList-Last'] = {'interviewer-last#', 'interviewer#-last',
'interviewer-surname#', 'interviewer#-surname', 'interviewer#'},
['InterviewerList-Link'] = {'interviewer-link#', 'interviewer#-link'},
['InterviewerList-Mask'] = {'interviewer-mask#', 'interviewer#-mask'},
 
['TranslatorList-First'] = {'translator-first#', 'translator#-first',
'translator-given#', 'translator#-given'},
['TranslatorList-Last'] = {'translator-last#', 'translator#-last',
'translator-surname#', 'translator#-surname', 'translator#'},
['TranslatorList-Link'] = {'translator-link#', 'translator#-link'},
['TranslatorList-Mask'] = {'translator-mask#', 'translator#-mask'},
}
 
 
--[[--------------------------< P U N C T _ S K I P >---------------------------
 
builds a table of parameter names that the extraneous terminal punctuation check should not check.
 
]]
 
local punct_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters
}
 
local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls
'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls
}


local function build_skip_table (skip_t, meta_params)
elseif is_set (error_state.category) then
for _, meta_param in ipairs (meta_params) do -- for each meta parameter key
if error_state.message then -- when error_state.message defined, this is an error message
local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name
table.insert (z.error_cats_t, error_state.category);
if 'string' == type (params) then
skip_t[params] = 1; -- just a single parameter
else
else
for _, param in ipairs (params) do -- get the parameter name
if not added_maint_cats[error_id] then
skip_t[param] = 1; -- add the parameter name to the skip table
added_maint_cats[error_id] = true; -- note that we've added this category
local count;
table.insert (z.maint_cats_t, substitute (error_state.category, arguments)); -- make cat name then add to table
param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters
if 0 ~= count then -- if removed
skip_t[param] = 1; -- add param name without enumerator marker
end
end
end
return; -- because no message, nothing more to do
end
end
end
end
return skip_t;
end


local punct_skip = {};
local message = substitute (error_state.message, arguments);
local url_skip = {};


message = table.concat (
{
message,
' (',
make_wikilink (
table.concat (
{
cfg.messages['help page link'],
'#',
error_state.anchor
}),
cfg.messages['help page label']),
')'
});


--[[--------------------------< 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 >----------
z.error_ids_t[error_id] = true;
 
if z.error_ids_t['err_citation_missing_title'] and -- if missing-title error already noted
this is a list of tlds that are known to have single-letter second-level domain names. This list does not include
in_array (error_id, {'err_bare_url_missing_title', 'err_trans_missing_title'}) then -- and this error is one of these
ccTLDs which are accepted in is_domain_name().
return '', false; -- don't bother because one flavor of missing title is sufficient
 
end
]]
 
local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'media', 'org', 'today'};
 
 
--[[-----------< S P E C I A L  C A S E  T R A N S L A T I O N S >------------
 
This table is primarily here to support internationalization.  Translations in
this table are used, for example, when an error message, category name, etc.,
is extracted from the English alias key.  There may be other cases where
this translation table may be useful.
 
]]
local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143\225\184\128-\225\187\191';
local special_case_translation = {
['AuthorList'] = 'authors list', -- used to assemble maintenance category names
['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base maintenance category names in maint_cats{} table below
['EditorList'] = 'editors list', -- must match the names of the actual categories
['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names()
['TranslatorList'] = 'translators list',
-- Lua patterns to match pseudo-titles used by InternetArchiveBot and others as placeholder for unknown |title= value
message = table.concat ({prefix, message, suffix});
['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title
['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki
['local'] = nil, -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
},


-- Lua patterns to match generic titles; usually created by bots or reference filling tools
if true == raw then
-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
return message, error_state.hidden; -- return message not wrapped in visible-error, hidden-error span tag
-- generic titles and patterns in this table should be lowercase only
end
-- leave ['local'] nil except when there is a matching generic title in your language
-- boolean 'true' for plain-text searches; 'false' for pattern searches


['generic_titles'] = {
message = error_comment (message, error_state.hidden); -- wrap message in visible-error, hidden-error span tag
['accept'] = {
table.insert (z.error_msgs_t, message); -- add it to the messages sequence table
},
return message; -- and done; return value generally not used but is used as a flag in various functions of ~/Identifiers
['reject'] = {
end
{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil},
{['en'] = {'are you a robot', true}, ['local'] = nil},
{['en'] = {'hugedomains', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'page not found', true}, ['local'] = nil},
{['en'] = {'subscribe to read', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'website is for sale', true}, ['local'] = nil},
{['en'] = {'^404', false}, ['local'] = nil},
{['en'] = {'error[ %-]404', false}, ['local'] = nil},
{['en'] = {'internet archive wayback machine', true}, ['local'] = nil},
{['en'] = {'log into facebook', true}, ['local'] = nil},
{['en'] = {'login • instagram', true}, ['local'] = nil},
{['en'] = {'redirecting...', true}, ['local'] = nil},
{['en'] = {'usurped title', true}, ['local'] = nil}, -- added by a GreenC bot
{['en'] = {'webcite query result', true}, ['local'] = nil},
{['en'] = {'wikiwix\'s cache', true}, ['local'] = nil},
}
},
 
-- boolean 'true' for plain-text searches, search string must be lowercase only
-- boolean 'false' for pattern searches
-- leave ['local'] nil except when there is a matching generic name in your language
 
['generic_names'] = {
['accept'] = {
{['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false}, ['local'] = nil},
},
['reject'] = {
{['en'] = {'about us', true}, ['local'] = nil},
{['en'] = {'%f[%a][Aa]dvisor%f[%A]', false}, ['local'] = nil},
{['en'] = {'allmusic', true}, ['local'] = nil},
{['en'] = {'%f[%a][Aa]uthor%f[%A]', false}, ['local'] = nil},
{['en'] = {'^[Bb]ureau$', false}, ['local'] = nil},
{['en'] = {'business', true}, ['local'] = nil},
{['en'] = {'cnn', true}, ['local'] = nil},
{['en'] = {'collaborator', true}, ['local'] = nil},
{['en'] = {'^[Cc]ompany$', false}, ['local'] = nil},
{['en'] = {'contributor', true}, ['local'] = nil},
{['en'] = {'contact us', true}, ['local'] = nil},
{['en'] = {'correspondent', true}, ['local'] = nil},
{['en'] = {'^[Dd]esk$', false}, ['local'] = nil},
{['en'] = {'directory', true}, ['local'] = nil},
{['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false}, ['local'] = nil},
{['en'] = {'[,%.%s]%f[e]eds?%.?$', false}, ['local'] = nil},
{['en'] = {'^eds?[%.,;]', false}, ['local'] = nil},
{['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]dited%f[%A]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]ditors?%f[%A]', false}, ['local'] = nil},
{['en'] = {'%f[%a][Ee]mail%f[%A]', false}, ['local'] = nil},
{['en'] = {'facebook', true}, ['local'] = nil},
{['en'] = {'google', true}, ['local'] = nil},
{['en'] = {'^[Gg]roup$', false}, ['local'] = nil},
{['en'] = {'home page', true}, ['local'] = nil},
{['en'] = {'^[Ii]nc%.?$', false}, ['local'] = nil},
{['en'] = {'instagram', true}, ['local'] = nil},
{['en'] = {'interviewer', true}, ['local'] = nil},
{['en'] = {'^[Ll]imited$', false}, ['local'] = nil},
{['en'] = {'linkedIn', true}, ['local'] = nil},
{['en'] = {'^[Nn]ews$', false}, ['local'] = nil},
{['en'] = {'[Nn]ews[ %-]?[Rr]oom', false}, ['local'] = nil},
{['en'] = {'pinterest', true}, ['local'] = nil},
{['en'] = {'policy', true}, ['local'] = nil},
{['en'] = {'privacy', true}, ['local'] = nil},
{['en'] = {'reuters', true}, ['local'] = nil},
{['en'] = {'translator', true}, ['local'] = nil},
{['en'] = {'tumblr', true}, ['local'] = nil},
{['en'] = {'twitter', true}, ['local'] = nil},
{['en'] = {'site name', true}, ['local'] = nil},
{['en'] = {'statement', true}, ['local'] = nil},
{['en'] = {'submitted', true}, ['local'] = nil},
{['en'] = {'super.?user', false}, ['local'] = nil},
{['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false}, ['local'] = nil},
{['en'] = {'verfasser', true}, ['local'] = nil},
}
}
}




--[[--------------------------< D A T E _ N A M E S >----------------------------------------------------------
--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------


This table of tables lists local language date names and fallback English date names.
This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
The code in Date_validation will look first in the local table for valid date names.
provided by the template.
If date names are not found in the local table, the code will look in the English table.


Because citations can be copied to the local wiki from en.wiki, the English is
Input:
required when the date-name translation function date_name_xlate() is used.
args – pointer to the arguments table from calling template
alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration
index – for enumerated parameters, identifies which one
enumerated – true/false flag used to choose how enumerated aliases are examined
value – value associated with an alias that has previously been selected; nil if not yet selected
selected – the alias that has previously been selected; nil if not yet selected
error_list – list of aliases that are duplicates of the alias already selected


In these tables, season numbering is defined by
Returns:
Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/)
value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'. The standard
selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected
defines various divisions using numbers 21-41. CS1|2 only supports generic seasons.
EDTF does support the distinction between north and south hemisphere seasons
but CS1|2 has no way to make that distinction.
 
33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each)
 
The standard does not address 'named' dates so, for the purposes of CS1|2,
Easter and Christmas are defined here as 98 and 99, which should be out of the
ISO 8601 (EDTF) range of uses for a while.
 
local_date_names_from_mediawiki is a boolean.  When set to:
true – module will fetch local month names from MediaWiki for both date_names['local']['long'] and date_names['local']['short']; this will unconditionally overwrite manual translations
false – module will *not* fetch local month names from MediaWiki
 
Caveat lector:  There is no guarantee that MediaWiki will provide short month names.  At your wiki you can test
the results of the MediaWiki fetch in the debug console with this command (the result is alpha sorted):
=mw.dumpObject (p.date_names['local'])
 
While the module can fetch month names from MediaWiki, it cannot fetch the quarter, season, and named date names
from MediaWiki.  Those must be translated manually.


]]
]]


local local_date_names_from_mediawiki = true; -- when false, manual translation required for date_names['local']['long'] and date_names['local']['short']; overwrites manual translations
local function is_alias_used (args, alias, index, enumerated, value, selected, error_list)
-- when true, module fetches long and short month names from MediaWiki
if enumerated then -- is this a test for an enumerated parameters?
local date_names = {
alias = alias:gsub ('#', index); -- replace '#' with the value in index
['en'] = { -- English
else
['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},
alias = alias:gsub ('#', ''); -- remove '#' if it exists
['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12},
['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36},
['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23},
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
},
-- when local_date_names_from_mediawiki = false
['local'] = { -- replace these English date names with the local language equivalents
['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12},
['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12},
['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36},
['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23},
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
},
['inv_local_long'] = {}, -- used in date reformatting & translation; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.
['inv_local_short'] = {}, -- used in date reformatting & translation; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.
['inv_local_quarter'] = {}, -- used in date translation; copy of date_names['local'].quarter where k/v are inverted: [1]='<local name>' etc.
['inv_local_season'] = {}, -- used in date translation; copy of date_names['local'].season where k/v are inverted: [1]='<local name>' etc.
['inv_local_named'] = {}, -- used in date translation; copy of date_names['local'].named where k/v are inverted: [1]='<local name>' etc.
['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9
['xlate_digits'] = {},
}
 
if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled
local long_t = {};
local short_t = {};
for i=1, 12 do -- loop 12x and
local name = lang_obj:formatDate('F', '2022-' .. i .. '-1'); -- get long month name for each i
long_t[name] = i; -- save it
name = lang_obj:formatDate('M', '2022-' .. i .. '-1'); -- get short month name for each i
short_t[name] = i; -- save it
end
end
date_names['local']['long'] = long_t; -- write the long table – overwrites manual translation
date_names['local']['short'] = short_t; -- write the short table – overwrites manual translation
end
-- create inverted date-name tables for reformatting and/or translation
for _, invert_t in pairs {{'long', 'inv_local_long'}, {'short', 'inv_local_short'}, {'quarter', 'inv_local_quarter'}, {'season', 'inv_local_season'}, {'named', 'inv_local_named'}} do
for name, i in pairs (date_names['local'][invert_t[1]]) do -- this table is ['name'] = i
date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd
end
end


if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled
if is_set (args[alias]) then -- alias is in the template's argument list
local digits_t = {};
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
for i=0, 9 do -- loop 10x and  
local skip;
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
for _, v in ipairs (error_list) do -- spin through the error list to see if we've added this alias
end
if v == alias then
date_names['local_digits'] = digits_t;
skip = true;
end
break; -- has been added so stop looking
 
end
for ld, ed in pairs (date_names.local_digits) do -- make a digit translation table for simple date translation from en to local language using local_digits table
end
date_names.xlate_digits [ed] = ld; -- en digit becomes index with local digit as the value
if not skip then -- has not been added so
end
table.insert (error_list, alias); -- add error alias to the error list
 
local df_template_patterns = { -- table of redirects to {{Use dmy dates}} and {{Use mdy dates}}
'{{ *[Uu]se +(dmy) +dates *[|}]', -- 1159k -- sorted by approximate transclusion count
'{{ *[Uu]se +(mdy) +dates *[|}]', -- 212k
'{{ *[Uu]se +(MDY) +dates *[|}]', -- 788
'{{ *[Uu]se +(DMY) +dates *[|}]', -- 343
'{{ *([Mm]dy) *[|}]', -- 176
'{{ *[Uu]se *(dmy) *[|}]', -- 156 + 18
'{{ *[Uu]se *(mdy) *[|}]', -- 149 + 11
'{{ *([Dd]my) *[|}]', -- 56
'{{ *[Uu]se +(MDY) *[|}]', -- 5
'{{ *([Dd]MY) *[|}]', -- 3
'{{ *[Uu]se(mdy)dates *[|}]', -- 1
'{{ *[Uu]se +(DMY) *[|}]', -- 0
'{{ *([Mm]DY) *[|}]', -- 0
}
 
local title_object = mw.title.getCurrentTitle();
local content; -- done this way  so that unused templates appear in unused-template-reports; self-transcluded makes them look like they are used
if 10 ~= title_object.namespace then -- all namespaces except Template
content = title_object:getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625
end
 
local function get_date_format ()
if not content then -- nil content when we're in template
return nil; -- auto-formatting does not work in Template space so don't set global_df
end
for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects
local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format
if match then
local use_dates_template = content:match ('%b{}', start); -- get the whole template
if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length
return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)');
else
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df=
end
end
else
value = args[alias]; -- not yet selected an alias, so select this one
selected = alias;
end
end
end
end
return value, selected; -- return newly selected alias, or previously selected alias
end
end


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


--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------


--[[-----------------< V O L U M E ,  I S S U E ,  P A G E S >------------------
Adds a category to z.maint_cats_t using names from the configuration file with additional text if any.
 
To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maint_cats_t.
These tables hold cite class values (from the template invocation) and identify those templates that support
|volume=, |issue=, and |page(s)= parameters. Cite conference and cite map require further qualification which
is handled in the main module.


]]
]]


local templates_using_volume = {'citation', 'audio-visual', 'book', 'conference', 'encyclopaedia', 'interview', 'journal', 'magazine', 'map', 'news', 'report', 'techreport', 'thesis'}
local function add_maint_cat (key, arguments)
local templates_using_issue = {'citation', 'conference', 'episode', 'interview', 'journal', 'magazine', 'map', 'news', 'podcast'}
if not added_maint_cats [key] then
local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'}
added_maint_cats [key] = true; -- note that we've added this category
 
table.insert (z.maint_cats_t, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
--[[
end
end


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=.


]]
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------


local citation_no_volume_t = { -- {{citation}} does not render |volume= when these parameters are used
Adds a category to z.prop_cats_t using names from the configuration file with additional text if any.
'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',
}


--[[
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages
may be categorized but multiples of the same language are not categorized.


Patterns for finding extra text in |volume=, |issue=, |page=, |pages=
added_prop_cats is a table declared in page scope variables above


]]
]]


local vol_iss_pg_patterns = {
local added_prop_cats = {}; -- list of property categories that have been added to z.prop_cats_t
good_ppattern = '^P[^%.PpGg]', -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123); TODO: this allows 'Pages' which it should not
bad_ppatterns = { -- patterns for |page= and |pages=
'^[Pp][PpGg]?%.?[ %d]',
'^[Pp][Pp]?%.&nbsp;', -- from {{p.}} and {{pp.}} templates
'^[Pp]ages?',
'^[Pp]gs.?',
},
vi_patterns_t = { -- combined to catch volume-like text in |issue= and issue-like text in |volume=
'^volumes?', -- volume-like text
'^vols?[%.:=]?',


'^issues?', --issue-like text
local function add_prop_cat (key, arguments, key_modifier)
'^iss[%.:=]?',
local key_modified = key .. ((key_modifier and key_modifier) or ''); -- modify <key> with <key_modifier> if present and not nil
'^numbers?',
'^nos?%A', -- don't match 'november' or 'nostradamus'
if not added_prop_cats [key_modified] then
'^nr[%.:=]?',
added_prop_cats [key_modified] = true; -- note that we've added this category
'^n[%.:= ]', -- might be a valid issue without separator (space char is sep char here)
table.insert (z.prop_cats_t, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
'^n°', -- 'n' with degree sign (U+00B0)
table.insert (z.prop_keys_t, 'cs1-prop-' .. key); -- convert key to class for use in the citation's <cite> tag
'^№', -- precomposed unicode numero character (U+2116)
end
},
end
}
 
--[[--------------------------< K E Y W O R D S >-------------------------------
 
These tables hold keywords for those parameters that have defined sets of acceptable keywords.
 
]]


--[[-------------------< K E Y W O R D S  T A B L E >--------------------------


this is a list of keywords; each key in the list is associated with a table of
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
synonymous keywords possibly from different languages.


for I18N: add local-language keywords to value table; do not change the key.
Protects a string that will be wrapped in wiki italic markup '' ... ''
For example, adding the German keyword 'ja':
['affirmative'] = {'yes', 'true', 'y', 'ja'},


Because CS1|2 templates from en.wiki articles are often copied to other local wikis,
Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
it is recommended that the English keywords remain in these tables.
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
poorly under Mediawiki's HTML tidy.


]]
]]


local keywords = {
local function safe_for_italics (str)
['amp'] = {'&', 'amp', 'ampersand'}, -- |name-list-style=
if not is_set (str) then return str end
['and'] = {'and', 'serial'}, -- |name-list-style=
['affirmative'] = {'yes', 'true', 'y'}, -- |no-tracking=, |no-pp= -- Used by InternetArchiveBot
['afterword'] = {'afterword'}, -- |contribution=
['bot: unknown'] = {'bot: unknown'}, -- |url-status= -- Used by InternetArchiveBot
['cs1'] = {'cs1'}, -- |mode=
['cs2'] = {'cs2'}, -- |mode=
['dead'] = {'dead', 'deviated'}, -- |url-status= -- Used by InternetArchiveBot
['dmy'] = {'dmy'}, -- |df=
['dmy-all'] = {'dmy-all'}, -- |df=
['foreword'] = {'foreword'}, -- |contribution=
['free'] = {'free'}, -- |<id>-access= -- Used by InternetArchiveBot
['harv'] = {'harv'}, -- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true
['introduction'] = {'introduction'}, -- |contribution=
['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot
['live'] = {'live'}, -- |url-status= -- Used by InternetArchiveBot
['mdy'] = {'mdy'}, -- |df=
['mdy-all'] = {'mdy-all'}, -- |df=
['none'] = {'none'}, -- |postscript=, |ref=, |title=, |type= -- Used by InternetArchiveBot
['off'] = {'off'}, -- |title= (potentially also: |title-link=, |postscript=, |ref=, |type=)
['preface'] = {'preface'}, -- |contribution=
['registration'] = {'registration'}, -- |url-access= -- Used by InternetArchiveBot
['subscription'] = {'subscription'}, -- |url-access= -- Used by InternetArchiveBot
['unfit'] = {'unfit'}, -- |url-status= -- Used by InternetArchiveBot
['usurped'] = {'usurped'}, -- |url-status= -- Used by InternetArchiveBot
['vanc'] = {'vanc'}, -- |name-list-style=
['ymd'] = {'ymd'}, -- |df=
['ymd-all'] = {'ymd-all'}, -- |df=
-- ['yMd'] = {'yMd'}, -- |df=; not supported at en.wiki
-- ['yMd-all'] = {'yMd-all'}, -- |df=; not supported at en.wiki
}


if str:sub (1, 1) == "'" then str = "<span></span>" .. str; end
if str:sub (-1, -1) == "'" then str = str .. "<span></span>"; end
return str:gsub ('\n', ' '); -- Remove newlines as they break italics.
end


--[[------------------------< X L A T E _ K E Y W O R D S >---------------------


this function builds a list, keywords_xlate{}, of the keywords found in keywords{} where the values from keywords{}
--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------
become the keys in keywords_xlate{} and the keys from keywords{} become the values in keywords_xlate{}:
['affirmative'] = {'yes', 'true', 'y'}, -- in keywords{}
becomes
['yes'] = 'affirmative', -- in keywords_xlate{}
['true'] = 'affirmative',
['y'] = 'affirmative',


the purpose of this function is to act as a translator between a non-English keyword and its English equivalent
Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
that may be used in other modules of this suite
argument; protects italic styled parameters.  Additional text taken from citation_config.presentation - the reason
this function is similar to but separate from wrap_msg().


]]
]]


local function xlate_keywords ()
local function wrap_style (key, str)
local out_table = {}; -- output goes here
if not is_set (str) then
for k, keywords_t in pairs (keywords) do -- spin through the keywords table
return "";
for _, keyword in ipairs (keywords_t) do -- for each keyword
elseif in_array (key, {'italic-title', 'trans-italic-title'}) then
out_table[keyword] = k; -- create an entry in the output table where keyword is the key
str = safe_for_italics (str);
end
end
end
 
return out_table;
return substitute (cfg.presentation[key], {str});
end
end


local keywords_xlate = xlate_keywords (); -- the list of translated keywords


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


--[[----------------< M A K E _ K E Y W O R D S _ L I S T >---------------------
make a separated list of items using provided separators.
<sep_list> - typically '<comma><space>'
<sep_list_pair> - typically '<space>and<space>'
<sep_list_end> - typically '<comma><space>and<space>' or '<comma><space>&<space>'


this function assembles, for parameter-value validation, the list of keywords appropriate to that parameter.
defaults to cfg.presentation['sep_list'], cfg.presentation['sep_list_pair'], and cfg.presentation['sep_list_end']
if <sep_list_end> is specified, <sep_list> and <sep_list_pair> must also be supplied


keywords_lists{}, is a table of tables from keywords{}
]]


]]
local function make_sep_list (count, list_seq, sep_list, sep_list_pair, sep_list_end)
local list = '';


local function make_keywords_list (keywords_lists)
if not sep_list then -- set the defaults
local out_table = {}; -- output goes here
sep_list = cfg.presentation['sep_list'];
sep_list_pair = cfg.presentation['sep_list_pair'];
sep_list_end = cfg.presentation['sep_list_end'];
end
for _, keyword_list in ipairs (keywords_lists) do -- spin through keywords_lists{} and get a table of keywords
if 2 >= count then
for _, keyword in ipairs (keyword_list) do -- spin through keyword_list{} and add each keyword, ...
list = table.concat (list_seq, sep_list_pair); -- insert separator between two items; returns list_seq[1] then only one item
table.insert (out_table, keyword); -- ... as plain text, to the output list
elseif 2 < count then
end
list = table.concat (list_seq, sep_list, 1, count - 1); -- concatenate all but last item with plain list separator
list = table.concat ({list, list_seq[count]}, sep_list_end); -- concatenate last item onto end of <list> with final separator
end
end
return out_table;
return list;
end
end




--[[----------------< K E Y W O R D S _ L I S T S >-----------------------------
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------


this is a list of lists of valid keywords for the various parameters in [key].
Chooses one matching parameter from a list of parameters to consider.  The list of parameters to consider is just
Generally the keys in this table are the canonical en.wiki parameter names though
names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified
some are contrived because of use in multiple differently named parameters:
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
['yes_true_y'], ['id-access'].


The function make_keywords_list() extracts the individual keywords from the
Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
appropriate list in keywords{}.


The lists in this table are used to validate the keyword assignment for the
parameters named in this table's keys.


]]
Generates an error if more than one match is present.
 
local keywords_lists = {
['yes_true_y'] = make_keywords_list ({keywords.affirmative}),
['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}),
['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all']}),
-- ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all'], keywords.yMd, keywords['yMd-all']}), -- not supported at en.wiki
['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}),
['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}),
['ref'] = make_keywords_list ({keywords.harv}), -- inverted check; |ref=harv no longer supported
['url-access'] = make_keywords_list ({keywords.subscription, keywords.limited, keywords.registration}),
['url-status'] = make_keywords_list ({keywords.dead, keywords.live, keywords.unfit, keywords.usurped, keywords['bot: unknown']}),
['id-access'] = make_keywords_list ({keywords.free}),
}
 
 
--[[--------------------------< C S 1 _ C O N F I G _ G E T >--------------------------------------------------
 
fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t>
 
no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked.
 
Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors,
DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode.  The DisplayWhatever metaparameters
accept numeric values only (|display-authors=etal and the like is not supported).


]]
]]


local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table?
local function select_one (args, aliases_list, error_condition, index)
 
local value = nil; -- the value assigned to the selected parameter
local function get_cs1_config ()
local selected = ''; -- the name of the parameter we have chosen
if not content then -- nil content when we're in template
local error_list = {};
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 index ~= nil then index = tostring(index); end
if start then
local cs1_config_template = content:match ('%b{}', start); -- get the whole template


if not cs1_config_template then
for _, alias in ipairs (aliases_list) do -- for each alias in the aliases list
return nil;
if alias:match ('#') then -- if this alias can be enumerated
end
if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases
 
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias
local params_t = mw.text.split (cs1_config_template:gsub ('^{{%s*', ''):gsub ('%s*}}$', ''), '%s*|%s*'); -- remove '{{' and '}}'; make a sequence of parameter/value pairs (split on the pipe)
table.remove (params_t, 1); -- remove the template name because it isn't a parameter/value pair
 
local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'};
local meta_param_map_t = {}; -- list of accepted parameter names usable in {{cs1 config}} goes here
for _, meta_param in ipairs (config_meta_params_t) do -- for i18n using <config_meta_params_t>, map template parameter names to their metaparameter equivalents
if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence,
for _, param in ipairs (aliases[meta_param]) do -- extract its contents
meta_param_map_t[param] = meta_param; -- and add to <meta_param_map_t>
end
else
meta_param_map_t[aliases[meta_param]] = meta_param; -- not a sequence so just add the parameter to <meta_param_map_t>
end
end
value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias
else
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- test for non-enumerated alias
end
end
end


local keywords_t = {}; -- map valid keywords to their associate metaparameter; reverse form of <keyword_lists[key] for these metaparameters
if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
for _, metaparam_t in ipairs ({{'NameListStyle', 'name-list-style'}, {'Mode', 'mode'}}) do -- only these metaparameter / keywords_lists key pairs
for i, v in ipairs (error_list) do
for _, keyword in ipairs (keywords_lists[metaparam_t[2]]) do -- spin through the list of keywords
error_list[i] = wrap_style ('parameter', v);
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
table.insert (error_list, wrap_style ('parameter', selected));
set_message (error_condition, {make_sep_list (#error_list, error_list)});
end
end
return value, selected;
end
end


get_cs1_config (); -- fill <global_cs1_config_t>


--[=[-------------------------< R E M O V E _ W I K I _ L I N K >----------------------------------------------


--[[---------------------< S T R I P M A R K E R S >----------------------------
Gets the display text from a wikilink like [[A|B]] or [[B]] gives B


Common pattern definition location for stripmarkers so that we don't have to go
The str:gsub() returns either A|B froma [[A|B]] or B from [[B]] or B from B (no wikilink markup).
hunting for them if (when) MediaWiki changes their form.


]]
In l(), l:gsub() removes the link and pipe (if they exist); the second :gsub() trims whitespace from the label
if str was wrapped in wikilink markup.  Presumably, this is because without wikimarkup in str, there is no match
in the initial gsub, the replacement function l() doesn't get called.


local stripmarkers = {
]=]
['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127', -- capture returns name of stripmarker
['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127' -- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()
}


local function remove_wiki_link (str)
return (str:gsub ("%[%[([^%[%]]*)%]%]", function(l)
return l:gsub ("^[^|]*|(.*)$", "%1" ):gsub ("^%s*(.-)%s*$", "%1");
end));
end


--[[------------< I N V I S I B L E _ C H A R A C T E R S >---------------------


This table holds non-printing or invisible characters indexed either by name or
--[=[-------------------------< I S _ W I K I L I N K >--------------------------------------------------------
by Unicode group. Values are decimal representations of UTF-8 codes.  The table
is organized as a table of tables because the Lua pairs keyword returns table
data in an arbitrary order.  Here, we want to process the table from top to bottom
because the entries at the top of the table are also found in the ranges specified
by the entries at the bottom of the table.


Also here is a pattern that recognizes stripmarkers that begin and end with the
Determines if str is a wikilink, extracts, and returns the wikilink type, link text, and display text parts.
delete characters.  The nowiki stripmarker is not an error but some others are
If str is a complex wikilink ([[L|D]]):
because the parameter values that include them become part of the template's
returns wl_type 2 and D and L from [[L|D]];
metadata before stripmarker replacement.
if str is a simple wikilink ([[D]])
returns wl_type 1 and D from [[D]] and L as empty string;
if not a wikilink:
returns wl_type 0, str as D, and L as empty string.


]]
trims leading and trailing whitespace and pipes from L and D ([[L|]] and [[|D]] are accepted by MediaWiki and
treated like [[D]]; while [[|D|]] is not accepted by MediaWiki, here, we accept it and return D without the pipes).


local invisible_defs = {
]=]
del = '\127', -- used to distinguish between stripmarker and del char
zwj = '\226\128\141', -- used with capture because zwj may be allowed
}


local invisible_chars = {
local function is_wikilink (str)
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD
local D, L
{'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed
local wl_type = 2; -- assume that str is a complex wikilink [[L|D]]
{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A
{'soft hyphen', '\194\173'}, -- U+00AD, C2 AD
{'horizontal tab', '\009'}, -- U+0009 (HT), 09
{'line feed', '\010'}, -- U+000A (LF), 0A
{'no-break space', '\194\160'}, -- U+00A0 (NBSP), C2 A0
{'carriage return', '\013'}, -- U+000D (CR), 0D
{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type
{'delete', '('.. invisible_defs.del .. ')'}, -- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker
{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-- {'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD
-- {'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'}, -- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD
}


--[[
if not str:match ('^%[%[[^%]]+%]%]$') then -- is str some sort of a wikilink (must have some sort of content)
return 0, str, ''; -- not a wikilink; return wl_type as 0, str as D, and empty string as L
end
L, D = str:match ('^%[%[([^|]+)|([^%]]+)%]%]$'); -- get L and D from [[L|D]]


Indic script makes use of zero width joiner as a character modifier so zwj
if not is_set (D) then -- if no separate display
characters must be left in.  This pattern covers all of the unicode characters
D = str:match ('^%[%[([^%]]*)|*%]%]$'); -- get D from [[D]] or [[D|]]
for these languages:
wl_type = 1;
Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf
end
Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
Bengali 0980–09FF – https://unicode.org/charts/PDF/U0980.pdf
D = mw.text.trim (D, '%s|'); -- trim white space and pipe characters
Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf
return wl_type, D, L or '';
Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf
end
Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf
Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf
Telugu 0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf
Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf
Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf
plus the not-necessarily Indic scripts for Sinhala and Burmese:
Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf
Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf
Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf
Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
the pattern is used by has_invisible_chars() and coins_cleanup()
 
]]


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


-- list of emoji that use a zwj character (U+200D) to combine with another emoji
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
-- from: https://unicode.org/Public/emoji/16.0/emoji-zwj-sequences.txt; version: 16.0; 2024-08-14
-- table created by: [[:en:Module:Make emoji zwj table]]
local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx
[8596] = true, -- U+2194 ↔ left right arrow
[8597] = true, -- U+2195 ↕ up down arrow
[9760] = true, -- U+2620 ☠ skull and crossbones
[9792] = true, -- U+2640 ♀ female sign
[9794] = true, -- U+2642 ♂ male sign
[9877] = true, -- U+2695 ⚕ staff of aesculapius
[9878] = true, -- U+2696 ⚖ scales
[9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign
[9992] = true, -- U+2708 ✈ airplane
[10052] = true, -- U+2744 ❄ snowflake
[10084] = true, -- U+2764 ❤ heavy black heart
[10145] = true, -- U+27A1 ➡ black rightwards arrow
[11035] = true, -- U+2B1B ⬛ black large square
[127752] = true, -- U+1F308 🌈 rainbow
[127787] = true, -- U+1F32B 🌫 fog
[127806] = true, -- U+1F33E 🌾 ear of rice
[127859] = true, -- U+1F373 🍳 cooking
[127868] = true, -- U+1F37C 🍼 baby bottle
[127876] = true, -- U+1F384 🎄 christmas tree
[127891] = true, -- U+1F393 🎓 graduation cap
[127908] = true, -- U+1F3A4 🎤 microphone
[127912] = true, -- U+1F3A8 🎨 artist palette
[127979] = true, -- U+1F3EB 🏫 school
[127981] = true, -- U+1F3ED 🏭 factory
[128102] = true, -- U+1F466 👦 boy
[128103] = true, -- U+1F467 👧 girl
[128104] = true, -- U+1F468 👨 man
[128105] = true, -- U+1F469 👩 woman
[128139] = true, -- U+1F48B 💋 kiss mark
[128165] = true, -- U+1F4A5 💥 collision symbol
[128168] = true, -- U+1F4A8 💨 dash symbol
[128171] = true, -- U+1F4AB 💫 dizzy symbol
[128187] = true, -- U+1F4BB 💻 personal computer
[128188] = true, -- U+1F4BC 💼 brief case
[128293] = true, -- U+1F525 🔥 fire
[128295] = true, -- U+1F527 🔧 wrench
[128300] = true, -- U+1F52C 🔬 microscope
[128488] = true, -- U+1F5E8 🗨 left speech bubble
[128640] = true, -- U+1F680 🚀 rocket
[128658] = true, -- U+1F692 🚒 fire engine
[129001] = true, -- U+1F7E9 🟩 large green square
[129003] = true, -- U+1F7EB 🟫 large brown square
[129309] = true, -- U+1F91D 🤝 handshake
[129455] = true, -- U+1F9AF 🦯 probing cane
[129456] = true, -- U+1F9B0 🦰 emoji component red hair
[129457] = true, -- U+1F9B1 🦱 emoji component curly hair
[129458] = true, -- U+1F9B2 🦲 emoji component bald
[129459] = true, -- U+1F9B3 🦳 emoji component white hair
[129466] = true, -- U+1F9BA 🦺 safety vest
[129468] = true, -- U+1F9BC 🦼 motorized wheelchair
[129469] = true, -- U+1F9BD 🦽 manual wheelchair
[129489] = true, -- U+1F9D1 🧑 adult
[129490] = true, -- U+1F9D2 🧒 child
[129657] = true, -- U+1FA79 🩹 adhesive bandage
[129778] = true, -- U+1FAF2 🫲 leftwards hand
}


Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.


--[[----------------------< L A N G U A G E  S U P P O R T >-------------------
Returns the argument without wiki markup and a number; the number is more-or-less meaningless except as a flag
 
to indicate that markup was replaced; do not rely on it as an indicator of how many of any kind of markup was
These tables and constants support various language-specific functionality.
removed; returns the argument and nil when no markup removed


]]
]]


--local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code
local function strip_apostrophe_markup (argument)
local this_wiki_code = lang_obj:getCode(); -- get this wiki's language code
if not is_set (argument) then
if string.match (mw.site.server, 'wikidata') then
return argument, nil; -- no argument, nothing to do
this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead
end
end


local mw_languages_by_tag_t = mw.language.fetchLanguageNames (this_wiki_code, 'all'); -- get a table of language tag/name pairs known to Wikimedia; used for interwiki tests
if nil == argument:find ( "''", 1, true ) then -- Is there at least one double apostrophe?  If not, exit.
local mw_languages_by_name_t = {};
return argument, nil;
for k, v in pairs (mw_languages_by_tag_t) do -- build a 'reversed' table name/tag language pairs know to MediaWiki; used for |language=
v = mw.ustring.lower (v); -- lowercase for tag fetch; get name's proper case from mw_languages_by_tag_t[<tag>]
if mw_languages_by_name_t[v] then -- when name already in the table
if 2 == #k or 3 == #k then -- if tag does not have subtags
mw_languages_by_name_t[v] = k; -- prefer the shortest tag for this name
end
else -- here when name not in the table
mw_languages_by_name_t[v] = k; -- so add name and matching tag
end
end
end


local inter_wiki_map = {}; -- map of interwiki prefixes that are language-code prefixes
local flag;
for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local)
while true do
if mw_languages_by_tag_t[v["prefix"]] then -- if the prefix matches a known language tag
if argument:find ("'''''", 1, true) then -- bold italic (5)
inter_wiki_map[v["prefix"]] = true; -- add it to our local map
argument, flag = argument:gsub ("%'%'%'%'%'", ""); -- remove all instances of it
elseif argument:find ("''''", 1, true) then -- italic start and end without content (4)
argument, flag=argument:gsub ("%'%'%'%'", "");
elseif argument:find ("'''", 1, true) then -- bold (3)
argument, flag=argument:gsub ("%'%'%'", "");
elseif argument:find ("''", 1, true) then -- italic (2)
argument, flag = argument:gsub ("%'%'", "");
else
break;
end
end
end
end


 
return argument, flag; -- done
--[[--------------------< 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', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'ce', 'chr', 'dv', 'dz',
'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko',
'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni', 'mr', 'my', 'ne', 'or', 'ota',
'pa', 'ps', 'ru', 'sd', 'si', 'sr', 'syc', 'ta', 'te', 'tg', 'th', 'ti', 'tt',
'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh', 'zgh'
};
 
 
--[[---------------< L A N G U A G E  R E M A P P I N G >----------------------
 
These tables hold language information that is different (correct) from MediaWiki's definitions
 
For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{}
 
lang_tag_remap{}:
key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag
value is properly spelled and capitalized language name associated with <tag>
only one language name per <tag>;
key/value pair must have matching entry in lang_name_remap{}
 
lang_name_remap{}:
key is always lowercase language name
value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{})
may have multiple keys referring to a common preferred name and tag; For example:
['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'
 
]]
 
local lang_tag_remap = { -- used for |language= and |script-title= / |script-chapter=
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['bn'] = 'Bengali', -- MediaWiki returns Bangla
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan
['fkv'] = 'Kven', -- MediaWiki returns Kvensk
['gsw'] = 'Swiss German',
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name
['ksh-x-colog'] = 'Colognian', -- override MediaWiki ksh; no IANA/ISO 639 code for Colognian; IETF private code created at Module:Lang/data
['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data
['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name
['sr-ec'] = 'Serbian (Cyrillic script)', -- MediaWiki returns српски (ћирилица)
['sr-el'] = 'Serbian (Latin script)', -- MediaWiki returns srpski (latinica)
}
 
local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase
['alemannic'] = {'Swiss German', 'gsw'}, -- ISO 639-2, -3 alternate for Swiss German; MediaWiki mediawiki returns Alemannic for gsw; en.wiki preferred name
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org
['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap
['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code
['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replaces 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found
['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö)
['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name
['kven'] = {'Kven', 'fkv'}, -- Unicode CLDR have decided not to support English language name for these two...
['kvensk'] = {'Kven', 'fkv'}, -- ...they say to refer to IANA registry for English names
['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639
['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'}, -- special case to get correct tag when |language=sr-ec
['serbian (latin script)'] = {'Serbian (Latin script)', 'sr-latn'}, -- special case to get correct tag when |language=sr-el
['swiss german'] = {'Swiss German', 'gsw'},
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
['valencian'] = {'Valencian', 'ca-valencia'}, -- variant of Catalan; categorizes as Valencian
}
 
 
--[[---------------< P R O P E R T I E S _ C A T E G O R I E S >----------------
 
Properties categories. These are used for investigating qualities of citations.
 
]]
 
local prop_cats = {
['foreign-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code
['foreign-lang-source-2'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key
['interproj-linked-name'] = 'CS1 interproject-linked names|$1', -- any author, editor, etc that has an interproject link; $1 is interproject tag used as a sort key
['interwiki-linked-name'] = 'CS1 interwiki-linked names|$1', -- any author, editor, etc that has an interwiki link; $1 is interwiki tag used as a sort key; yeilds to interproject
['local-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false
['location-test'] = 'CS1 location test',
['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters
['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is language tag
['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name
['unfit'] = 'CS1: unfit URL', -- |url-status=unfit or |url-status=usurped; used to be a maint cat
['vanc-accept'] = 'CS1:Vancouver names with accept markup', -- for |vauthors=/|veditors= with accept-as-written markup
['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form
}
 
 
--[[-------------------< T I T L E _ T Y P E S >--------------------------------
 
Here we map a template's CitationClass to TitleType (default values for |type= parameter)
 
]]
 
local title_types = {
['AV-media-notes'] = 'Media notes',
['document'] = 'Document',
['interview'] = 'Interview',
['mailinglist'] = 'Mailing list',
['map'] = 'Map',
['podcast'] = 'Podcast',
['pressrelease'] = 'Press release',
['report'] = 'Report',
['speech'] = 'Speech',
['techreport'] = 'Technical report',
['thesis'] = 'Thesis',
}
 
 
--[[--------------------------< B U I L D _ K N O W N _ F R E E _ D O I _ R E G I S T R A N T S _ T A B L E >--
 
build a table of doi registrants known to be free-to-read  In a doi, the registrant ID is the series of digits
between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID
 
see §3.2.2 DOI prefix of the Doi Handbook p. 43
https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43
 
]]
 
local function build_free_doi_registrants_table()
local registrants_t = {};
for _, v in ipairs ({
'1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '1629', '1989', '1999', '2147', '2196', '3285', '3389', '3390',
'3748', '3814', '3847', '3897', '4061', '4089', '4103', '4172', '4175', '4230', '4236', '4239', '4240', '4249', '4251',
'4252', '4253', '4254', '4291', '4292', '4329', '4330', '4331', '5194', '5210', '5306', '5312', '5313', '5314',
'5315', '5316', '5317', '5318', '5319', '5320', '5321', '5334', '5402', '5409', '5410', '5411', '5412',
'5492', '5493', '5494', '5495', '5496', '5497', '5498', '5499', '5500', '5501', '5527', '5528', '5662',
'6064', '6219', '7167', '7217', '7287', '7482', '7490', '7554', '7717', '7759', '7766', '11131', '11569', '11647',
'11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995',
'17645', '18637', '19080', '19173', '20944', '21037', '21468', '21767', '22261', '22323', '22459', '24105', '24196', '24966',
'26775', '30845', '32545', '35711', '35712', '35713', '35995', '36648', '37126', '37532', '37871', '47128',
'47622', '47959', '52437', '52975', '53288', '54081', '54947', '55667', '55914', '57009', '58647', '59081',
}) do
registrants_t[v] = true; -- build a k/v table of known free-to-read doi registrants
end
 
return registrants_t;
end
end
local extended_registrants_t = { -- known free registrants identifiable by the doi suffix incipit
['1002'] = {'aelm', 'leap'}, -- Advanced Electronic Materials, Learned Publishing
['1016'] = {'j.heliyon', 'j.nlp', 'j.proche'}, -- Heliyon, Natural Language Processing, Procedia Chemistry
['1017'] = {'nlp'}, -- Natural Language Processing Journal
['1046'] = {'j.1365-8711', 'j.1365-246x'}, -- MNRAS, GJI
['1093'] = {'mnras', 'mnrasl', 'gji', 'rasti'}, -- MNRAS, MNRAS Letters, GJI, RASTI
['1099'] = {'acmi', 'mic', '00221287', 'mgen'},                            -- Access Microbiology, Microbiology, Journal of General Microbiology, Microbial Genomics
['1111'] = {'j.1365-2966', 'j.1745-3933', 'j.1365-246X'}, -- MNRAS, MNRAS Letters, GJI
['1210'] = {'jendso','jcemcr'}, -- Journal of the Endocrine Society, JCEM Case Reports
['4171'] = {'dm','mag'},     -- Documenta Mathematica, EMS Magazine
['14231'] = {'ag'}, -- Algebraic Geometry
}
--[[===================<< E R R O R  M E S S A G I N G >>======================
]]
--[[----------< E R R O R  M E S S A G E  S U P P L I M E N T S >-------------
I18N for those messages that are supplemented with additional specific text that
describes the reason for the error
TODO: merge this with special_case_translations{}?
]]
local err_msg_supl = {
['char'] = 'invalid character', -- |isbn=, |sbn=
['check'] = 'checksum', -- |isbn=, |sbn=
['flag'] = 'flag', -- |archive-url=
['form'] = 'invalid form', -- |isbn=, |sbn=
['group'] = 'invalid group id', -- |isbn=
['initials'] = 'initials', -- Vancouver
['invalid language code'] = 'invalid language code', -- |script-<param>=
['journal'] = 'journal', -- |bibcode=
['length'] = 'length', -- |isbn=, |bibcode=, |sbn=
['liveweb'] = 'liveweb', -- |archive-url=
['missing comma'] = 'missing comma', -- Vancouver
['missing prefix'] = 'missing prefix', -- |script-<param>=
['missing title part'] = 'missing title part', -- |script-<param>=
['name'] = 'name', -- Vancouver
['non-Latin char'] = 'non-Latin character', -- Vancouver
['path'] = 'path', -- |archive-url=
['prefix'] = 'invalid prefix', -- |isbn=
['punctuation'] = 'punctuation', -- Vancouver
['save'] = 'save command', -- |archive-url=
['suffix'] = 'suffix', -- Vancouver
['timestamp'] = 'timestamp', -- |archive-url=
['unknown language code'] = 'unknown language code', -- |script-<param>=
['value'] = 'value', -- |bibcode=
['year'] = 'year', -- |bibcode=
}




--[[--------------< E R R O R _ C O N D I T I O N S >---------------------------
--[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >--------------------------------------


Error condition table.  This table has two sections: errors at the top, maintenance
Sets local cfg table to same (live or sandbox) as that used by the other modules.
at the bottom.  Maint 'messaging' does not have a 'message' (message=nil)
 
The following contains a list of IDs for various error conditions defined in the
code.  For each ID, we specify a text message to display, an error category to
include, and whether the error message should be wrapped as a hidden comment.
 
Anchor changes require identical changes to matching anchor in Help:CS1 errors
 
TODO: rename error_conditions{} to something more generic; create separate error
and maint tables inside that?


]]
]]


local error_conditions = {
local function set_selected_modules (cfg_table_ptr)
err_accessdate_missing_url = {
cfg = cfg_table_ptr;
message = '<code class="cs1-code">&#124;access-date=</code> requires <code class="cs1-code">&#124;url=</code>',
anchor = 'accessdate_missing_url',
category = 'CS1 errors: access-date without URL',
hidden = false
},
err_apostrophe_markup = {
message = 'Italic or bold markup not allowed in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'apostrophe_markup',
category = 'CS1 errors: markup',
hidden = false
},
err_archive_date_missing_url = {
message = '<code class="cs1-code">&#124;archive-date=</code> requires <code class="cs1-code">&#124;archive-url=</code>',
anchor = 'archive_date_missing_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_date_url_ts_mismatch = {
message = '<code class="cs1-code">&#124;archive-date=</code> / <code class="cs1-code">&#124;archive-url=</code> timestamp mismatch; $1 suggested',
anchor = 'archive_date_url_ts_mismatch',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_missing_date = {
message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;archive-date=</code>',
anchor = 'archive_missing_date',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_missing_url = {
message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;url=</code>',
anchor = 'archive_missing_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_url = {
message = '<code class="cs1-code">&#124;archive-url=</code> is malformed: $1', -- $1 is error message detail
anchor = 'archive_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_arxiv_missing = {
message = '<code class="cs1-code">&#124;arxiv=</code> required',
anchor = 'arxiv_missing',
category = 'CS1 errors: arXiv', -- same as bad arxiv
hidden = false
},
err_asintld_missing_asin = {
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;asin=</code>', -- $1 is parameter name
anchor = 'asintld_missing_asin',
category = 'CS1 errors: ASIN TLD',
hidden = false
},
err_bad_arxiv = {
message = 'Check <code class="cs1-code">&#124;arxiv=</code> value',
anchor = 'bad_arxiv',
category = 'CS1 errors: arXiv',
hidden = false
},
err_bad_asin = {
message = 'Check <code class="cs1-code">&#124;asin=</code> value',
anchor = 'bad_asin',
category ='CS1 errors: ASIN',
hidden = false
},
err_bad_asin_tld = {
message = 'Check <code class="cs1-code">&#124;asin-tld=</code> value',
anchor = 'bad_asin_tld',
category ='CS1 errors: ASIN TLD',
hidden = false
},
err_bad_bibcode = {
message = 'Check <code class="cs1-code">&#124;bibcode=</code> $1', -- $1 is error message detail
anchor = 'bad_bibcode',
category = 'CS1 errors: bibcode',
hidden = false
},
err_bad_biorxiv = {
message = 'Check <code class="cs1-code">&#124;biorxiv=</code> value',
anchor = 'bad_biorxiv',
category = 'CS1 errors: bioRxiv',
hidden = false
},
err_bad_citeseerx = {
message = 'Check <code class="cs1-code">&#124;citeseerx=</code> value',
anchor = 'bad_citeseerx',
category = 'CS1 errors: citeseerx',
hidden = false
},
err_bad_date = {
message = 'Check date values in: $1', -- $1 is a parameter name list
anchor = 'bad_date',
category = 'CS1 errors: dates',
hidden = false
},
err_bad_doi = {
message = 'Check <code class="cs1-code">&#124;doi=</code> value',
anchor = 'bad_doi',
category = 'CS1 errors: DOI',
hidden = false
},
err_bad_hdl = {
message = 'Check <code class="cs1-code">&#124;hdl=</code> value',
anchor = 'bad_hdl',
category = 'CS1 errors: HDL',
hidden = false
},
err_bad_isbn = {
message = 'Check <code class="cs1-code">&#124;isbn=</code> value: $1', -- $1 is error message detail
anchor = 'bad_isbn',
category = 'CS1 errors: ISBN',
hidden = false
},
err_bad_ismn = {
message = 'Check <code class="cs1-code">&#124;ismn=</code> value',
anchor = 'bad_ismn',
category = 'CS1 errors: ISMN',
hidden = false
},
err_bad_issn = {
message = 'Check <code class="cs1-code">&#124;$1issn=</code> value', -- $1 is 'e' or '' for eissn or issn
anchor = 'bad_issn',
category = 'CS1 errors: ISSN',
hidden = false
},
err_bad_jfm = {
message = 'Check <code class="cs1-code">&#124;jfm=</code> value',
anchor = 'bad_jfm',
category = 'CS1 errors: JFM',
hidden = false
},
err_bad_jstor = {
message = 'Check <code class="cs1-code">&#124;jstor=</code> value',
anchor = 'bad_jstor',
category = 'CS1 errors: JSTOR',
hidden = false
},
err_bad_lccn = {
message = 'Check <code class="cs1-code">&#124;lccn=</code> value',
anchor = 'bad_lccn',
category = 'CS1 errors: LCCN',
hidden = false
},
err_bad_medrxiv = {
message = 'Check <code class="cs1-code">&#124;medrxiv=</code> value',
anchor = 'bad_medrxiv',
category = 'CS1 errors: medRxiv',
hidden = false
},
err_bad_mr = {
message = 'Check <code class="cs1-code">&#124;mr=</code> value',
anchor = 'bad_mr',
category = 'CS1 errors: MR',
hidden = false
},
err_bad_oclc = {
message = 'Check <code class="cs1-code">&#124;oclc=</code> value',
anchor = 'bad_oclc',
category = 'CS1 errors: OCLC',
hidden = false
},
err_bad_ol = {
message = 'Check <code class="cs1-code">&#124;ol=</code> value',
anchor = 'bad_ol',
category = 'CS1 errors: OL',
hidden = false
},
err_bad_osti = {
message = 'Check <code class="cs1-code">&#124;osti=</code> value',
anchor = 'bad_osti',
category = 'CS1 errors: OSTI',
hidden = false
},
err_bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link=
message = 'Check <code class="cs1-code">&#124;$1=</code> value', -- $1 is parameter name
anchor = 'bad_paramlink',
category = 'CS1 errors: parameter link',
hidden = false
},
err_bad_pmc = {
message = 'Check <code class="cs1-code">&#124;pmc=</code> value',
anchor = 'bad_pmc',
category = 'CS1 errors: PMC',
hidden = false
},
err_bad_pmid = {
message = 'Check <code class="cs1-code">&#124;pmid=</code> value',
anchor = 'bad_pmid',
category = 'CS1 errors: PMID',
hidden = false
},
err_bad_rfc = {
message = 'Check <code class="cs1-code">&#124;rfc=</code> value',
anchor = 'bad_rfc',
category = 'CS1 errors: RFC',
hidden = false
},
err_bad_s2cid = {
message = 'Check <code class="cs1-code">&#124;s2cid=</code> value',
anchor = 'bad_s2cid',
category = 'CS1 errors: S2CID',
hidden = false
},
err_bad_sbn = {
message = 'Check <code class="cs1-code">&#124;sbn=</code> value: $1', -- $1 is error message detail
anchor = 'bad_sbn',
category = 'CS1 errors: SBN',
hidden = false
},
err_bad_ssrn = {
message = 'Check <code class="cs1-code">&#124;ssrn=</code> value',
anchor = 'bad_ssrn',
category = 'CS1 errors: SSRN',
hidden = false
},
err_bad_url = {
message = 'Check $1 value', -- $1 is parameter name
anchor = 'bad_url',
category = 'CS1 errors: URL',
hidden = false
},
err_bad_usenet_id = {
message = 'Check <code class="cs1-code">&#124;message-id=</code> value',
anchor = 'bad_message_id',
category = 'CS1 errors: message-id',
hidden = false
},
err_bad_zbl = {
message = 'Check <code class="cs1-code">&#124;zbl=</code> value',
anchor = 'bad_zbl',
category = 'CS1 errors: Zbl',
hidden = false
},
err_bare_url_missing_title = {
message = '$1 missing title', -- $1 is parameter name
anchor = 'bare_url_missing_title',
category = 'CS1 errors: bare URL',
hidden = false
},
err_biorxiv_missing = {
message = '<code class="cs1-code">&#124;biorxiv=</code> required',
anchor = 'biorxiv_missing',
category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv
hidden = false
},
err_chapter_ignored = {
message = '<code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name
anchor = 'chapter_ignored',
category = 'CS1 errors: chapter ignored',
hidden = false
},
err_citation_missing_title = {
message = 'Missing or empty <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'citation_missing_title',
category = 'CS1 errors: missing title',
hidden = false
},
err_citeseerx_missing = {
message = '<code class="cs1-code">&#124;citeseerx=</code> required',
anchor = 'citeseerx_missing',
category = 'CS1 errors: citeseerx', -- same as bad citeseerx
hidden = false
},
err_cite_web_url = { -- this error applies to cite web and to cite podcast
message = 'Missing or empty <code class="cs1-code">&#124;url=</code>',
anchor = 'cite_web_url',
category = 'CS1 errors: requires URL',
hidden = false
},
err_class_ignored = {
message = '<code class="cs1-code">&#124;class=</code> ignored',
anchor = 'class_ignored',
category = 'CS1 errors: class',
hidden = false
},
err_contributor_ignored = {
message = '<code class="cs1-code">&#124;contributor=</code> ignored',
anchor = 'contributor_ignored',
category = 'CS1 errors: contributor',
hidden = false
},
err_contributor_missing_required_param = {
message = '<code class="cs1-code">&#124;contributor=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'contributor_missing_required_param',
category = 'CS1 errors: contributor',
hidden = false
},
err_deprecated_params = {
message = 'Cite uses deprecated parameter <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'deprecated_params',
category = 'CS1 errors: deprecated parameters',
hidden = false
},
err_disp_name = {
message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name; $2 is the assigned value
anchor = 'disp_name',
category = 'CS1 errors: display-names',
hidden = false,
},
err_doibroken_missing_doi = {
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;doi=</code>', -- $1 is parameter name
anchor = 'doibroken_missing_doi',
category = 'CS1 errors: DOI',
hidden = false
},
err_embargo_missing_pmc = {
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;pmc=</code>', -- $1 is parameter name
anchor = 'embargo_missing_pmc',
category = 'CS1 errors: PMC embargo',
hidden = false
},
err_empty_citation = {
message = 'Empty citation',
anchor = 'empty_citation',
category = 'CS1 errors: empty citation',
hidden = false
},
err_etal = {
message = 'Explicit use of et al. in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'explicit_et_al',
category = 'CS1 errors: explicit use of et al.',
hidden = false
},
err_extra_text_edition = {
message = '<code class="cs1-code">&#124;edition=</code> has extra text',
anchor = 'extra_text_edition',
category = 'CS1 errors: extra text: edition',
hidden = false,
},
err_extra_text_issue = {
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_issue',
category = 'CS1 errors: extra text: issue',
hidden = false,
},
err_extra_text_pages = {
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_pages',
category = 'CS1 errors: extra text: pages',
hidden = false,
},
err_extra_text_volume = {
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
anchor = 'extra_text_volume',
category = 'CS1 errors: extra text: volume',
hidden = false,
},
err_first_missing_last = {
message = '<code class="cs1-code">&#124;$1=</code> missing <code class="cs1-code">&#124;$2=</code>', -- $1 is first alias, $2 is matching last alias
anchor = 'first_missing_last',
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
hidden = false
},
err_format_missing_url = {
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;$2=</code>', -- $1 is format parameter $2 is url parameter
anchor = 'format_missing_url',
category = 'CS1 errors: format without URL',
hidden = false
},
err_generic_name = {
message = '<code class="cs1-code">&#124;$1=</code> has generic name', -- $1 is parameter name
anchor = 'generic_name',
category = 'CS1 errors: generic name',
hidden = false,
},
err_generic_title = {
message = 'Cite uses generic title',
anchor = 'generic_title',
category = 'CS1 errors: generic title',
hidden = false,
},
err_invalid_isbn_date = {
message = 'ISBN / Date incompatibility',
anchor = 'invalid_isbn_date',
category = 'CS1 errors: ISBN date',
hidden = true
},
err_invalid_param_val = {
message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name $2 is parameter value
anchor = 'invalid_param_val',
category = 'CS1 errors: invalid parameter value',
hidden = false
},
err_invisible_char = {
message = '$1 in $2 at position $3', -- $1 is invisible char $2 is parameter name $3 is position number
anchor = 'invisible_char',
category = 'CS1 errors: invisible characters',
hidden = false
},
err_medrxiv_missing = {
message = '<code class="cs1-code">&#124;medrxiv=</code> required',
anchor = 'medrxiv_missing',
category = 'CS1 errors: medRxiv', -- same as bad medRxiv
hidden = false
},
err_missing_name = {
message = 'Missing <code class="cs1-code">&#124;$1$2=</code>', -- $1 is modified NameList; $2 is enumerator
anchor = 'missing_name',
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
hidden = false
},
err_missing_periodical = {
message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>', -- $1 is cs1 template name; $2 is canonical periodical parameter name for cite $1
anchor = 'missing_periodical',
category = 'CS1 errors: missing periodical',
hidden = false
},
err_missing_pipe = {
message = 'Missing pipe in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'missing_pipe',
category = 'CS1 errors: missing pipe',
hidden = false
},
err_missing_publisher = {
message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>', -- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1
anchor = 'missing_publisher',
category = 'CS1 errors: missing publisher',
hidden = false
},
err_numeric_names = {
message = '<code class="cs1-code">&#124;$1=</code> has numeric name', -- $1 is parameter name',
anchor = 'numeric_names',
category = 'CS1 errors: numeric name',
hidden = false,
},
err_param_access_requires_param = {
message = '<code class="cs1-code">&#124;$1-access=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'param_access_requires_param',
category = 'CS1 errors: param-access',
hidden = false
},
err_param_has_ext_link = {
message = 'External link in <code class="cs1-code">$1</code>', -- $1 is parameter name
anchor = 'param_has_ext_link',
category = 'CS1 errors: external links',
hidden = false
},
err_param_has_twl_url = {
message = 'Wikipedia Library link in <code class="cs1-code">$1</code>', -- $1 is parameter name
anchor = 'param_has_twl_url',
category = 'CS1 errors: URL',
hidden = false
},
err_parameter_ignored = {
message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name
anchor = 'parameter_ignored',
category = 'CS1 errors: unsupported parameter',
hidden = false
},
err_parameter_ignored_suggest = {
message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored (<code class="cs1-code">&#124;$2=</code> suggested)', -- $1 is unknown parameter $2 is suggested parameter name
anchor = 'parameter_ignored_suggest',
category = 'CS1 errors: unsupported parameter',
hidden = false
},
err_periodical_ignored = {
message = '<code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name
anchor = 'periodical_ignored',
category = 'CS1 errors: periodical ignored',
hidden = false
},
err_redundant_parameters = {
message = 'More than one of $1 specified', -- $1 is error message detail
anchor = 'redundant_parameters',
category = 'CS1 errors: redundant parameter',
hidden = false
},
err_script_parameter = {
message = 'Invalid <code class="cs1-code">&#124;$1=</code>: $2', -- $1 is parameter name $2 is script language code or error detail
anchor = 'script_parameter',
category = 'CS1 errors: script parameters',
hidden = false
},
err_ssrn_missing = {
message = '<code class="cs1-code">&#124;ssrn=</code> required',
anchor = 'ssrn_missing',
category = 'CS1 errors: SSRN',
hidden = false
},
err_text_ignored = {
message = 'Text "$1" ignored', -- $1 is ignored text
anchor = 'text_ignored',
category = 'CS1 errors: unrecognized parameter',
hidden = false
},
err_trans_missing_title = {
message = '<code class="cs1-code">&#124;trans-$1=</code> requires <code class="cs1-code">&#124;$1=</code> or <code class="cs1-code">&#124;script-$1=</code>', -- $1 is base parameter name
anchor = 'trans_missing_title',
category = 'CS1 errors: translated title',
hidden = false
},
err_param_unknown_empty = {
message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is emty unknown param list
anchor = 'param_unknown_empty',
category = 'CS1 errors: empty unknown parameters',
hidden = false
},
err_vancouver = {
message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name
anchor = 'vancouver',
category = 'CS1 errors: Vancouver style',
hidden = false
},
err_wikilink_in_url = {
message = 'URL–wikilink conflict', -- uses ndash
anchor = 'wikilink_in_url',
category = 'CS1 errors: URL–wikilink conflict', -- uses ndash
hidden = false
},
 
 
--[[--------------------------< M A I N T >-------------------------------------
 
maint messages do not have a message (message = nil); otherwise the structure
is the same as error messages
 
]]
 
maint_archived_copy = {
message = nil,
anchor = 'archived_copy',
category = 'CS1 maint: archived copy as title',
hidden = true,
},
maint_bibcode = {
message = nil,
anchor = 'bibcode',
category = 'CS1 maint: bibcode',
hidden = true,
},
maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite
message = nil,
anchor = 'location_no_publisher',
category = 'CS1 maint: location missing publisher',
hidden = true,
},
maint_bot_unknown = {
message = nil,
anchor = 'bot:_unknown',
category = 'CS1 maint: bot: original URL status unknown',
hidden = true,
},
maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki
message = nil,
anchor = 'date_auto_xlated',
category = 'CS1 maint: date auto-translated',
hidden = true,
},
maint_date_format = {
message = nil,
anchor = 'date_format',
category = 'CS1 maint: date format',
hidden = true,
},
maint_date_year = {
message = nil,
anchor = 'date_year',
category = 'CS1 maint: date and year',
hidden = true,
},
maint_doi_ignore = {
message = nil,
anchor = 'doi_ignore',
category = 'CS1 maint: ignored DOI errors',
hidden = true,
},
maint_doi_inactive = {
message = nil,
anchor = 'doi_inactive',
category = 'CS1 maint: DOI inactive',
hidden = true,
},
maint_doi_inactive_dated = {
message = nil,
anchor = 'doi_inactive_dated',
category = 'CS1 maint: DOI inactive as of $2$3$1', -- $1 is year, $2 is month-name or empty string, $3 is space or empty string
hidden = true,
},
maint_doi_unflagged_free = {
message = nil,
anchor = 'doi_unflagged_free',
category = 'CS1 maint: unflagged free DOI',
hidden = true,
},
maint_extra_punct = {
message = nil,
anchor = 'extra_punct',
category = 'CS1 maint: extra punctuation',
hidden = true,
},
maint_id_limit_load_fail = { -- applies to all cs1|2 templates on a page;
message = nil, -- maint message (category link) never emitted
anchor = 'id_limit_load_fail',
category = 'CS1 maint: ID limit load fail',
hidden = true,
},
maint_isbn_ignore = {
message = nil,
anchor = 'ignore_isbn_err',
category = 'CS1 maint: ignored ISBN errors',
hidden = true,
},
maint_issn_ignore = {
message = nil,
anchor = 'ignore_issn',
category = 'CS1 maint: ignored ISSN errors',
hidden = true,
},
maint_jfm_format = {
message = nil,
anchor = 'jfm_format',
category = 'CS1 maint: JFM format',
hidden = true,
},
maint_location = {
message = nil,
anchor = 'location',
category = 'CS1 maint: location',
hidden = true,
},
maint_mr_format = {
message = nil,
anchor = 'mr_format',
category = 'CS1 maint: MR format',
hidden = true,
},
maint_mult_names = {
message = nil,
anchor = 'mult_names',
category = 'CS1 maint: multiple names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_numeric_names = {
message = nil,
anchor = 'numeric_names',
category = 'CS1 maint: numeric names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_others = {
message = nil,
anchor = 'others',
category = 'CS1 maint: others',
hidden = true,
},
maint_others_avm = {
message = nil,
anchor = 'others_avm',
category = 'CS1 maint: others in cite AV media (notes)',
hidden = true,
},
maint_overridden_setting = {
message = nil,
anchor = 'overridden',
category = 'CS1 maint: overridden setting',
hidden = true,
},
maint_pmc_embargo = {
message = nil,
anchor = 'embargo',
category = 'CS1 maint: PMC embargo expired',
hidden = true,
},
maint_pmc_format = {
message = nil,
anchor = 'pmc_format',
category = 'CS1 maint: PMC format',
hidden = true,
},
maint_postscript = {
message = nil,
anchor = 'postscript',
category = 'CS1 maint: postscript',
hidden = true,
},
maint_publisher_location = {
message = nil,
anchor = 'publisher_location',
category = 'CS1 maint: publisher location',
hidden = true,
},
maint_ref_duplicates_default = {
message = nil,
anchor = 'ref_default',
category = 'CS1 maint: ref duplicates default',
hidden = true,
},
maint_unknown_lang = {
message = nil,
anchor = 'unknown_lang',
category = 'CS1 maint: unrecognized language',
hidden = true,
},
maint_untitled = {
message = nil,
anchor = 'untitled',
category = 'CS1 maint: untitled periodical',
hidden = true,
},
maint_url_status = {
message = nil,
anchor = 'url_status',
category = 'CS1 maint: url-status',
hidden = true,
},
maint_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').data; -- attempt to load the json limit data from commons into <tab_data_t>
if false == tab_data_t then -- undocumented 'feature': mw.ext.data.get() sometimes returns false
id_limits_data_load_fail = true; -- set the flag so that Module:Citation/CS1 can create an unannotated maint category
else
for _, limit_t in ipairs (tab_data_t) do -- overwrite default <load_fail_limit> values
id_limits_data_t[limit_t[1]] = limit_t[2]; -- <limit[1]> is identifier; <limit[2]> is upper limit for that identifier
end
end
end
end




--[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
--[[--------------------------< E X P O R T S >----------------------------------------------------------------
 
The following contains a list of values for various defined identifiers.  For each
identifier we specify a variety of information necessary to properly render the
identifier in the citation.
 
parameters: a list of parameter aliases for this identifier; first in the list is the canonical form
link: Wikipedia article name
redirect: a local redirect to a local Wikipedia article name;  at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'
q: Wikidata q number for the identifier
label: the label preceding the identifier; label is linked to a Wikipedia article (in this order):
redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true
Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q
local article name from id_handlers['<id>'].link
prefix: the first part of a URL that will be concatenated with a second part which usually contains the identifier
suffix: optional third part to be added after the identifier
encode: true if URI should be percent-encoded; otherwise false
COinS: identifier link or keyword for use in COinS:
for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn
for |asin= and |ol=, which require assembly, use the keyword: url
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here)
set to nil to leave the identifier out of the COinS
separator: character or text between label and the identifier in the rendered citation
id_limit: for those identifiers with established limits, this property holds the upper limit
access: use this parameter to set the access level for all instances of this identifier.
the value must be a valid access level for an identifier (see ['id-access'] in this file).
custom_access: to enable custom access level for an identifier, set this parameter
to the parameter that should control it (normally 'id-access')
]]
 
local id_handlers = {
['ARXIV'] = {
parameters = {'arxiv', 'eprint'},
link = 'arXiv',
redirect = 'arXiv (identifier)',
q = 'Q118398',
label = 'arXiv',
prefix = 'https://arxiv.org/abs/',
encode = false,
COinS = 'info:arxiv',
separator = ':',
access = 'free', -- free to read
},
['ASIN'] = {
parameters = { 'asin', 'ASIN' },
link = 'Amazon Standard Identification Number',
redirect = 'ASIN (identifier)',
q = 'Q1753278',
label = 'ASIN',
prefix = 'https://www.amazon.',
COinS = 'url',
separator = '&nbsp;',
encode = false;
},
['BIBCODE'] = {
parameters = {'bibcode'},
link = 'Bibcode',
redirect = 'Bibcode (identifier)',
q = 'Q25754',
label = 'Bibcode',
prefix = 'https://ui.adsabs.harvard.edu/abs/',
encode = false,
COinS = 'info:bibcode',
separator = ':',
custom_access = 'bibcode-access',
},
['BIORXIV'] = {
parameters = {'biorxiv'},
link = 'bioRxiv',
redirect = 'bioRxiv (identifier)',
q = 'Q19835482',
label = 'bioRxiv',
prefix = 'https://doi.org/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = '&nbsp;',
},
['CITESEERX'] = {
parameters = {'citeseerx'},
link = 'CiteSeerX',
redirect = 'CiteSeerX (identifier)',
q = 'Q2715061',
label = 'CiteSeerX',
prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=',
COinS =  'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = '&nbsp;',
},
['DOI'] = { -- Used by InternetArchiveBot
parameters = { 'doi', 'DOI'},
link = 'Digital object identifier',
redirect = 'doi (identifier)',
q = 'Q25670',
label = 'doi',
prefix = 'https://doi.org/',
COinS = 'info:doi',
separator = ':',
encode = true,
custom_access = 'doi-access',
},
['EISSN'] = {
parameters = {'eissn', 'EISSN'},
link = 'International Standard Serial Number#Electronic ISSN',
redirect = 'eISSN (identifier)',
q = 'Q46339674',
label = 'eISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.eissn',
encode = false,
separator = '&nbsp;',
},
['HDL'] = {
parameters = { 'hdl', 'HDL' },
link = 'Handle System',
redirect = 'hdl (identifier)',
q = 'Q3126718',
label = 'hdl',
prefix = 'https://hdl.handle.net/',
COinS = 'info:hdl',
separator = ':',
encode = true,
custom_access = 'hdl-access',
},
['ISBN'] = { -- Used by InternetArchiveBot
parameters = {'isbn', 'ISBN'},
link = 'International Standard Book Number',
redirect = 'ISBN (identifier)',
q = 'Q33057',
label = 'ISBN',
prefix = 'Special:BookSources/',
COinS = 'rft.isbn',
separator = '&nbsp;',
},
['ISMN'] = {
parameters = {'ismn', 'ISMN'},
link = 'International Standard Music Number',
redirect = 'ISMN (identifier)',
q = 'Q1666938',
label = 'ISMN',
prefix = '', -- not currently used;
COinS = nil, -- nil because we can't use pre or rft or info:
separator = '&nbsp;',
},
['ISSN'] = {
parameters = {'issn', 'ISSN'},
link = 'International Standard Serial Number',
redirect = 'ISSN (identifier)',
q = 'Q131276',
label = 'ISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.issn',
encode = false,
separator = '&nbsp;',
},
['JFM'] = {
parameters = {'jfm', 'JFM'},
link = 'Jahrbuch über die Fortschritte der Mathematik',
redirect = 'JFM (identifier)',
q = '',
label = 'JFM',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
['JSTOR'] = {
parameters = {'jstor', 'JSTOR'},
link = 'JSTOR',
redirect = 'JSTOR (identifier)',
q = 'Q1420342',
label = 'JSTOR',
prefix = 'https://www.jstor.org/stable/',
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
custom_access = 'jstor-access',
},
['LCCN'] = {
parameters = {'lccn', 'LCCN'},
link = 'Library of Congress Control Number',
redirect = 'LCCN (identifier)',
q = 'Q620946',
label = 'LCCN',
prefix = 'https://lccn.loc.gov/',
COinS = 'info:lccn',
encode = false,
separator = '&nbsp;',
},
['MEDRXIV'] = {
parameters = {'medrxiv'},
link = 'medRxiv',
redirect = 'medRxiv (identifier)',
q = 'Q58465838',
label = 'medRxiv',
prefix = 'https://www.medrxiv.org/content/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = false,
separator = '&nbsp;',
},
['MR'] = {
parameters = {'mr', 'MR'},
link = 'Mathematical Reviews',
redirect = 'MR (identifier)',
q = 'Q211172',
label = 'MR',
prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
['OCLC'] = {
parameters = {'oclc', 'OCLC'},
link = 'OCLC',
redirect = 'OCLC (identifier)',
q = 'Q190593',
label = 'OCLC',
prefix = 'https://search.worldcat.org/oclc/',
COinS = 'info:oclcnum',
encode = true,
separator = '&nbsp;',
id_limit = id_limits_data_t.OCLC or 0,
},
['OL'] = {
parameters = { 'ol', 'OL' },
link = 'Open Library',
redirect = 'OL (identifier)',
q = 'Q1201876',
label = 'OL',
prefix = 'https://openlibrary.org/',
COinS = 'url',
separator = '&nbsp;',
encode = true,
custom_access = 'ol-access',
},
['OSTI'] = {
parameters = {'osti', 'OSTI'},
link = 'Office of Scientific and Technical Information',
redirect = 'OSTI (identifier)',
q = 'Q2015776',
label = 'OSTI',
prefix = 'https://www.osti.gov/biblio/',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = id_limits_data_t.OSTI or 0,
custom_access = 'osti-access',
},
['PMC'] = {
parameters = {'pmc', 'PMC'},
link = 'PubMed Central',
redirect = 'PMC (identifier)',
q = 'Q229883',
label = 'PMC',
prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC',
suffix = '',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = id_limits_data_t.PMC or 0,
access = 'free', -- free to read
},
['PMID'] = {
parameters = {'pmid', 'PMID'},
link = 'PubMed Identifier',
redirect = 'PMID (identifier)',
q = 'Q2082879',
label = 'PMID',
prefix = 'https://pubmed.ncbi.nlm.nih.gov/',
COinS = 'info:pmid',
encode = false,
separator = '&nbsp;',
id_limit = id_limits_data_t.PMID or 0,
},
['RFC'] = {
parameters = {'rfc', 'RFC'},
link = 'Request for Comments',
redirect = 'RFC (identifier)',
q = 'Q212971',
label = 'RFC',
prefix = 'https://tools.ietf.org/html/rfc',
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
id_limit = id_limits_data_t.RFC or 0,
access = 'free', -- free to read
},
['SBN'] = {
parameters = {'sbn', 'SBN'},
link = 'Standard Book Number', -- redirect to International_Standard_Book_Number#History
redirect = 'SBN (identifier)',
label = 'SBN',
prefix = 'Special:BookSources/0-', -- prefix has leading zero necessary to make 9-digit sbn a 10-digit isbn
COinS = nil, -- nil because we can't use pre or rft or info:
separator = '&nbsp;',
},
['SSRN'] = {
parameters = {'ssrn', 'SSRN'},
link = 'Social Science Research Network',
redirect = 'SSRN (identifier)',
q = 'Q7550801',
label = 'SSRN',
prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = id_limits_data_t.SSRN or 0,
custom_access = 'ssrn-access',
},
['S2CID'] = {
parameters = {'s2cid', 'S2CID'},
link = 'Semantic Scholar',
redirect = 'S2CID (identifier)',
q = 'Q22908627',
label = 'S2CID',
prefix = 'https://api.semanticscholar.org/CorpusID:',
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
id_limit = id_limits_data_t.S2CID or 0,
custom_access = 's2cid-access',
},
['USENETID'] = {
parameters = {'message-id'},
link = 'Usenet',
redirect = 'Usenet (identifier)',
q = 'Q193162',
label = 'Usenet:',
prefix = 'news:',
encode = false,
COinS = 'pre', -- use prefix value
separator = '&nbsp;',
},
['ZBL'] = {
parameters = {'zbl', 'ZBL' },
link = 'Zentralblatt MATH',
redirect = 'Zbl (identifier)',
q = 'Q190269',
label = 'Zbl',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
}
 
 
--[[--------------------------< E X P O R T S >---------------------------------
]]
]]


return {
return {
use_identifier_redirects = use_identifier_redirects, -- booleans defined in the settings at the top of this module
add_maint_cat = add_maint_cat, -- exported functions
local_lang_cat_enable = local_lang_cat_enable,
add_prop_cat = add_prop_cat,
date_name_auto_xlate_enable = date_name_auto_xlate_enable,
error_comment = error_comment,
date_digit_auto_xlate_enable = date_digit_auto_xlate_enable,
has_accept_as_written = has_accept_as_written,
enable_sort_keys = enable_sort_keys,
hyphen_to_dash = hyphen_to_dash,
in_array = in_array,
-- tables and variables created when this module is loaded
is_set = is_set,
global_df = get_date_format (), -- this line can be replaced with "global_df = 'dmy-all'," to have all dates auto translated to dmy format.
is_wikilink = is_wikilink,
global_cs1_config_t = global_cs1_config_t, -- global settings from {{cs1 config}}
make_sep_list = make_sep_list,
punct_skip = build_skip_table (punct_skip, punct_meta_params),
make_wikilink = make_wikilink,
url_skip = build_skip_table (url_skip, url_meta_params),
remove_wiki_link = remove_wiki_link,
known_free_doi_registrants_t = build_free_doi_registrants_table(),
safe_for_italics = safe_for_italics,
id_limits_data_load_fail = id_limits_data_load_fail, -- true when commons tabular identifier-limit data fails to load
select_one = select_one,
 
set_message = set_message,
name_space_sort_keys = name_space_sort_keys,
set_selected_modules = set_selected_modules,
aliases = aliases,
strip_apostrophe_markup = strip_apostrophe_markup,
special_case_translation = special_case_translation,
substitute = substitute,
date_names = date_names,
wrap_style = wrap_style,
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,
inter_wiki_map = inter_wiki_map,
mw_languages_by_tag_t = mw_languages_by_tag_t,
mw_languages_by_name_t = mw_languages_by_name_t,
citation_class_map_t = citation_class_map_t,


citation_issue_t = citation_issue_t,
z = z, -- exported table
citation_no_volume_t = citation_no_volume_t,
}
}
Retrieved from "https://wikigama.org/wiki/Module:Citation/CS1/Configuration"