Module:Citation/CS1/Configuration: Difference between revisions
< Module:Citation | CS1
Jump to navigation
Jump to search
(sync from sandbox;) |
m (1 revision imported from wikipedia:Module:Citation/CS1/Configuration) |
Latest revision as of 12:29, 29 March 2020
Documentation for this module may be created at Module:Citation/CS1/Configuration/doc
--[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------
List of namespaces that should not be included in citation error categories. Same as setting notracking = true by default
Note: Namespace names should use underscores instead of spaces.
]]
local uncategorized_namespaces = { 'User', 'Talk', 'User_talk', 'Wikipedia_talk', 'File_talk', 'Template_talk', 'Help_talk', 'Category_talk', 'Portal_talk', 'Book_talk', 'Draft_talk', 'Education_Program_talk', 'Module_talk', 'MediaWiki_talk' };
local uncategorized_subpages = {'/[Ss]andbox', '/[Tt]estcases'}; -- list of Lua patterns found in page names of pages we should not categorize
--[[--------------------------< M E S S A G E S >--------------------------------------------------------------
Translation table
The following contains fixed text that may be output as part of a citation.
This is separated from the main body to aid in future translations of this
module.
]]
local messages = {
['agency'] = '$1 $2', -- $1 is sepc, $2 is agency
['archived-dead'] = 'Archived from $1 on $2',
['archived-live'] = '$1 from the original on $2',
['archived-missing'] = 'Archived from the original$1 on $2',
['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 ed.)',
['episode'] = 'Episode $1',
['et al'] = 'et al.',
['in'] = 'In', -- edited works
['inactive'] = 'inactive',
['inset'] = '$1 inset',
['interview'] = 'Interviewed by $1',
['lay summary'] = 'Lay summary',
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1',
['original'] = 'the original',
['origyear'] = ' [$1]',
['published'] = ' (published $1)',
['retrieved'] = 'Retrieved $1',
['season'] = 'Season $1',
['section'] = '§ $1',
['sections'] = '§§ $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. $2', -- $1 is sepc; bold journal style volume is in presentation{}
['vol-no'] = '$1 Vol. $2 no. $3', -- sepc, volume, issue
['issue'] = '$1 No. $2', -- $1 is sepc
['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{}
['j-issue'] = ' ($1)',
['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc
['p-prefix'] = "$1 p. $2", -- $1 is sepc
['pp-prefix'] = "$1 pp. $2", -- $1 is sepc
['j-page(s)'] = ': $1', -- same for page and pages
['sheet'] = '$1 Sheet $2', -- $1 is sepc
['sheets'] = '$1 Sheets $2', -- $1 is sepc
['j-sheet'] = ': Sheet $1',
['j-sheets'] = ': Sheets $1',
['language'] = '(in $1)',
['via'] = " – via $1",
['event'] = 'Event occurs at',
['minutes'] = 'minutes in',
['parameter-separator'] = ', ',
['parameter-final-separator'] = ', and ',
['parameter-pair-separator'] = ' and ',
-- Determines the location of the help page
['help page link'] = 'Help:CS1 errors',
['help page label'] = 'help',
-- Internal errors (should only occur if configuration is bad)
['undefined_error'] = 'Called with an undefined error condition',
['unknown_manual_ID'] = 'Unrecognized manual ID mode',
['unknown_ID_mode'] = 'Unrecognized ID mode',
['unknown_argument_map'] = 'Argument map not defined for this variable',
['bare_url_no_origin'] = 'Bare url found but origin indicator is nil or empty',
}
--[=[-------------------------< E T _ A L _ P A T T E R N S >--------------------------------------------------
This table provides Lua patterns for the phrase "et al" and variants in name text
(author, editor, etc.). The main module uses these to identify and emit the 'etal' message.
]=]
local et_al_patterns = {
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$", -- variations on the 'et al' theme
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][Aa][%.\"']*$", -- variations on the 'et alia' theme
"[;,]? *%f[%a]and [Oo]thers", -- and alternate to et al.
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form
}
--[[--------------------------< E D I T O R _ M A R K U P _ P A T T E R N S >----------------------------------
This table provides Lua patterns for the phrase "ed" and variants in name text
(author, editor, etc.). The main module uses these to identify and emit the
'extra_text_names' message. (It is not the only series of patterns for this message.)
]]
local editor_markup_patterns = { -- these patterns match annotations at end of name
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'
'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)
'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'
'[,%.%s]%f[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive
-- these patterns match annotations at beginning of name
'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.'
'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's'
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets
-- these patterns match annotations that are the 'name'
'^[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors; case insensitive
}
--[[--------------------------< P R E S E N T A T I O N >------------------------------------------------------
Fixed presentation markup. Originally part of citation_config.messages it has been moved into its own, more semantically
correct place.
]]
local presentation =
{
-- Error output
-- .error class is specified at https://git.wikimedia.org/blob/mediawiki%2Fcore.git/9553bd02a5595da05c184f7521721fb1b79b3935/skins%2Fcommon%2Fshared.css#L538
-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display
['hidden-error'] = '<span class="cs1-hidden-error error citation-comment">$1</span>',
['visible-error'] = '<span class="cs1-visible-error error citation-comment">$1</span>',
['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>',
['accessdate'] = '<span class="reference-accessdate">$1$2</span>', -- to allow editors to hide accessdate using personal css
['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like
['cite'] = '<cite class="$1">$2</cite>'; -- |ref= not set so no id="..." attribute
['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when |ref= is set
['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc
-- various access levels, for |access=, |doi-access=, |arxiv=, ...
-- narrow no-break space   may work better than nowrap css. Or not? browser support?
['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon
['free'] = {class='cs1-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css
['registration'] = {class='cs1-lock-registration', title='Free registration required'},
['limited'] = {class='cs1-lock-limited', title='Free access subject to limited trial, subscription normally required'},
['subscription'] = {class='cs1-lock-subscription', title='Paid subscription required'},
['interwiki-icon'] = '<span class="$1" title="$2">$3</span>',
['class-wikisource'] = 'cs1-ws-icon',
['italic-title'] = "''$1''",
['kern-left'] = '<span class="cs1-kern-left">$1</span>$2', -- spacing to use when title contains leading single or double quote mark
['kern-right'] = '$1<span class="cs1-kern-right">$2</span>', -- spacing to use when title contains trailing single or double quote mark
-- these for simple wikilinked titles [["text]], [[text"]] and [["text"]]
-- span wraps entire wikilink
['kern-wl-left'] = '<span class="cs1-kern-wl-left">$1</span>', -- when title contains leading single or double quote mark
['kern-wl-right'] = '<span class="cs1-kern-wl-left">$1</span>', -- when title contains trailing single or double quote mark
['kern-wl-both'] = '<span class="cs1-kern-wl-left cs1-kern-wl-right">$1</span>', -- when title contains leading and trailing single or double quote marks
['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span>
['nowrap2'] = '<span class="nowrap">$1</span> $2', -- for nowrapping portions of an item: <span ...>dd mmmm</span> yyyy (note white space)
['ocins'] = '<span title="$1" class="Z3988"></span>',
['parameter'] = '<code class="cs1-code">|$1=</code>',
['ps_cs1'] = '.'; -- cs1 style postscript (terminal) character
['ps_cs2'] = ''; -- cs2 style postscript (terminal) character (empty string)
['quoted-text'] = '<q>$1</q>', -- for wrapping |quote= content
['quoted-title'] = '"$1"',
['sep_cs1'] = '.', -- cs1 element separator
['sep_cs2'] = ',', -- cs2 separator
['sep_nl'] = ';', -- cs1|2 style name-list separator between authors is a semicolon
['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
['trans-italic-title'] = "[''$1'']",
['trans-quoted-title'] = "[$1]",
['vol-bold'] = '$1 <b>$2</b>', -- sepc, volume; for bold journal cites; for other cites ['vol'] in messages{}
}
--[[--------------------------< A L I A S E S >----------------------------------------------------------------
Aliases table for commonly passed parameters
]]
local aliases = {
['AccessDate'] = {'access-date', 'accessdate'}, -- (Used by InternetArchiveBot)
['Agency'] = 'agency',
['AirDate'] = {'air-date', 'airdate'},
['ArchiveDate'] = {'archive-date', 'archivedate'}, -- (Used by InternetArchiveBot)
['ArchiveFormat'] = 'archive-format',
['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- (Used by InternetArchiveBot)
['ASINTLD'] = 'asin-tld',
['At'] = 'at', -- (Used by InternetArchiveBot)
['Authors'] = {'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', 'chapterurl', 'contribution-url', 'contributionurl', 'entry-url', 'article-url', 'section-url', 'sectionurl'}, -- (Used by InternetArchiveBot)
['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access', 'entry-url-access', 'article-url-access', 'section-url-access'}, -- (Used by InternetArchiveBot)
['Class'] = 'class', -- cite arxiv and arxiv identifiers
['Collaboration'] = 'collaboration',
['Conference'] = {'conference', 'event'},
['ConferenceFormat'] = {'conference-format', 'event-format'},
['ConferenceURL'] = {'conference-url', 'conferenceurl', 'event-url', 'eventurl'}, -- (Used by InternetArchiveBot)
['Contribution'] = 'contribution', -- introduction, foreword, afterword, etc; required when |contributor= set
['Date'] = 'date',
['Degree'] = 'degree',
['DF'] = 'df',
['DisplayAuthors'] = {'display-authors', 'displayauthors'},
['DisplayContributors'] = 'display-contributors',
['DisplayEditors'] = {'display-editors', 'displayeditors'},
['DisplayInterviewers'] = 'display-interviewers',
['DisplayTranslators'] = 'display-translators',
['Docket'] = 'docket',
['DoiBroken'] = {'doi-broken', 'doi-broken-date', 'doi-inactive-date'},
['Edition'] = 'edition',
['Editors'] = 'editors',
['Embargo'] = 'embargo',
['Encyclopedia'] = {'encyclopedia', 'encyclopaedia'}, -- this one only used by citation
['Episode'] = 'episode', -- cite serial only TODO: make available to cite episode?
['Format'] = 'format',
['ID'] = {'id', 'ID'},
['IgnoreISBN'] = {'ignore-isbn-error', 'ignoreisbnerror'},
['Inset'] = 'inset',
['Issue'] = {'issue', 'number'},
['Language'] = {'language', 'lang'},
['LastAuthorAmp'] = {'last-author-amp', 'lastauthoramp'},
['LayDate'] = {'lay-date', 'laydate'},
['LayFormat'] = 'lay-format',
['LaySource'] = {'lay-source', 'laysource'},
['LayURL'] = {'lay-url', 'layurl'}, -- (Used by InternetArchiveBot)
['MailingList'] = {'mailinglist', 'mailing-list'}, -- cite mailing list only
['Map'] = 'map', -- cite map only
['MapFormat'] = 'map-format', -- cite map only
['MapURL'] = {'mapurl', 'map-url'}, -- cite map only -- (Used by InternetArchiveBot)
['MapUrlAccess'] = 'map-url-access', -- cite map only -- (Used by InternetArchiveBot)
['MessageID'] = 'message-id',
['Minutes'] = 'minutes',
['Mode'] = 'mode',
['NameListFormat'] = 'name-list-format',
['Network'] = 'network',
['NoPP'] = {'no-pp', 'nopp'},
['NoTracking'] = {'template-doc-demo', 'no-cat', 'nocat',
'no-tracking', 'notracking'},
['Number'] = 'number', -- this case only for cite techreport
['OrigYear'] = {'orig-year', 'origyear'},
['Others'] = 'others',
['Page'] = {'p', 'page'}, -- (Used by InternetArchiveBot)
['Pages'] = {'pp', 'pages'}, -- (Used by InternetArchiveBot)
['Periodical'] = {'journal', 'magazine', 'newspaper', 'periodical', 'website', 'work',
'encyclopedia', 'encyclopaedia', 'dictionary', 'mailinglist'}, -- these masquerade as periodicals but aren't TODO: find a better way to handle these?
['Place'] = {'place', 'location'},
['PostScript'] = 'postscript',
['PublicationDate'] = {'publicationdate', 'publication-date'},
['PublicationPlace'] = {'publication-place', 'publicationplace'},
['PublisherName'] = {'publisher', 'institution', 'newsgroup'},
['Quote'] = {'quote', 'quotation'},
['Ref'] = 'ref',
['Scale'] = 'scale',
['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry', 'script-article', 'script-section'},
['ScriptMap'] = 'script-map',
['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-website', 'script-work'},
['ScriptTitle'] = 'script-title', -- (Used by InternetArchiveBot)
['Section'] = 'section',
['Season'] = 'season',
['Sections'] = 'sections', -- cite map only
['Series'] = {'series', 'version'},
['SeriesSeparator'] = 'series-separator',
['SeriesLink'] = {'series-link', 'serieslink'},
['SeriesNumber'] = {'series-number', 'series-no', 'seriesnumber', 'seriesno'},
['Sheet'] = 'sheet', -- cite map only
['Sheets'] = 'sheets', -- cite map only
['Station'] = 'station',
['Time'] = 'time',
['TimeCaption'] = {'time-caption', 'timecaption'},
['Title'] = 'title', -- (Used by InternetArchiveBot)
['TitleLink'] = {'title-link', 'episode-link', 'titlelink', 'episodelink'}, -- (Used by InternetArchiveBot)
['TitleNote'] = 'department',
['TitleType'] = {'type', 'medium'},
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', 'trans-entry', 'trans-section'},
['Transcript'] = 'transcript',
['TranscriptFormat'] = 'transcript-format',
['TranscriptURL'] = {'transcript-url', 'transcripturl'}, -- (Used by InternetArchiveBot)
['TransMap'] = 'trans-map', -- cite map only
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', 'trans-periodical', 'trans-website', 'trans-work'},
['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#", "given#", "author-first#", "author#-first"},
['AuthorList-Last'] = {"last#", "author#", "surname#", "author-last#", "author#-last", "subject#", 'host#'},
['AuthorList-Link'] = {"authorlink#", "author-link#", "author#-link", "subjectlink#", "author#link", "subject-link#", "subject#-link", "subject#link"},
['AuthorList-Mask'] = {"author-mask#", "authormask#", "author#mask", "author#-mask"},
['ContributorList-First'] = {'contributor-first#', 'contributor#-first', 'contributor-given#', 'contributor#-given'},
['ContributorList-Last'] = {'contributor#', 'contributor-last#', 'contributor#-last', 'contributor-surname#', 'contributor#-surname'},
['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#", "editor-last#", "editor#-last", "editor-surname#", "editor#-surname"},
['EditorList-Link'] = {"editor-link#", "editor#-link", "editorlink#", "editor#link"},
['EditorList-Mask'] = {"editor-mask#", "editor#-mask", "editormask#", "editor#mask"},
['InterviewerList-First'] = {'interviewer-first#', 'interviewer#-first'},
['InterviewerList-Last'] = {'interviewer#', 'interviewer-last#', 'interviewer#-last'},
['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#', 'translator-last#', 'translator#-last', 'translator-surname#', 'translator#-surname'},
['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_skip = {};
local meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters
'PostScript', 'Quote', -- miscellaneous
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'LayURL', 'MapURL', 'TranscriptURL', 'URL', -- url-holding parameters
}
for _, meta_param in ipairs (meta_params) do -- for each meta parameter key
local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name
if 'string' == type (params) then
punct_skip[params] = 1; -- just a single parameter
else
for _, param in ipairs (params) do -- get the parameter name
punct_skip[param] = 1; -- add the parameter name to the skip table
end
end
end
--[[--------------------------< 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 special_case_translation = {
['AuthorList'] = 'authors list', -- these for multiple names maint categories
['ContributorList'] = 'contributors list',
['EditorList'] = 'editors list',
['InterviewerList'] = 'interviewers list',
['TranslatorList'] = 'translators list',
['authors'] = 'authors', -- used in get_display_names()
['contributors'] = 'contributors',
['editors'] = 'editors',
['interviewers'] = 'interviewers',
['translators'] = 'translators',
['archived_copy'] = '^archived?%s+copy$', -- lua pattern to match pseudo title used by Internet Archive bot and others as place holder for unknown |title= value
-- used with CS1 maint: Archived copy as title
}
--[[--------------------------< D E F A U L T S >--------------------------------------------------------------
Default parameter values
TODO: keep this? Only one default?
]]
local defaults = {
['UrlStatus'] = 'dead', -- (Used by InternetArchiveBot)
}
--[[--------------------------< D A T E _ N A M E S >----------------------------------------------------------
This table of tables lists local language date names and fallback English date names. The code in Date_validation
will look first in the local table for valid date names. If date names are not found in the local table, the code
will look in the English table.
Because citations can be copied to the local wiki from en.wiki, the English is required when the date-name translation
function date_name_xlate() is used.
In these tables, season numbering is defined by ISO DIS 8601:2016 part 2 §4.7 'Divisions of a year'. The standard
defines various divisions using numbers 21-41. cs1|2 only supports generic seasons. ISO DIS 8601:2016 does support
the distinction between north and south hemispere seasons but cs1|2 has no way to make that distinction.
The standard does not address 'named' dates so, for the purposes of cs1|2, Christmas is defined here as 99, which
should be out of the ISO DIS 8601:2016 range of uses for a while.
]]
local date_names = {
['en'] = { -- English
['long'] = {['January']=1, ['February']=2, ['March']=3, ['April']=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12},
['short'] = {['Jan']=1, ['Feb']=2, ['Mar']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12},
['season'] = {['Winter']=24, ['Spring']=21, ['Summer']=22, ['Fall']=23, ['Autumn']=23},
['named'] = {['Christmas']=99},
},
['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},
['season'] = {['Winter']=24, ['Spring']=21, ['Summer']=22, ['Fall']=23, ['Autumn']=23},
['named'] = {['Christmas']=99},
},
['inv_local_l'] = {}, -- used in date reformatting; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc
['inv_local_s'] = {}, -- used in date reformatting; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc
['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9
['xlate_digits'] = {},
}
for name, i in pairs (date_names['local'].long) do -- this table is ['name'] = i
date_names['inv_local_l'][i] = name; -- invert to get [i] = 'name' for conversions from ymd
end
for name, i in pairs (date_names['local'].short) do -- this table is ['name'] = i
date_names['inv_local_s'][i] = name; -- invert to get [i] = 'name' for conversions from ymd
end
for ld, ed in pairs (date_names.local_digits) do -- make a digit translation table for simple date translation from en to local language using local_digits table
date_names.xlate_digits [ed] = ld; -- en digit becomes index with local digit as the value
end
local df_template_patterns = { -- table of redirects to {{Use dmy dates}} and {{Use mdy dates}}
'{{ *[Uu]se (dmy) dates *[|}]', -- 915k -- sorted by approximate transclusion count
'{{ *[Uu]se *(mdy) *dates *[|}]', -- 161k
'{{ *[Uu]se (DMY) dates *[|}]', -- 2929
'{{ *[Uu]se *(dmy) *[|}]', -- 250 + 34
'{{ *([Dd]my) *[|}]', -- 272
'{{ *[Uu]se (MDY) dates *[|}]', -- 173
'{{ *[Uu]se *(mdy) *[|}]', -- 59 + 12
'{{ *([Mm]dy) *[|}]', -- 9
'{{ *[Uu]se (MDY) *[|}]', -- 3
'{{ *([Dd]MY) *[|}]', -- 2
'{{ *([Mm]DY) *[|}]', -- 0
-- '{{ *[Uu]se(mdy) *[|}]',
-- '{{ *[Uu]se(mdy)dates *[|}]',
-- '{{ *[Uu]se(dmy) *[|}]',
}
local function get_date_format ()
local content = mw.title.getCurrentTitle():getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625
for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects
local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format
if match then
content = content:match ('%b{}', start); -- get the whole template
if content:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length
return match:lower() .. '-' .. content:match ('| *cs1%-dates *= *([lsy][sy]?)');
else
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df=
end
end
end
end
local global_df = get_date_format ();
--[[--------------------------< V O L U M E , I S S U E , P A G E S >----------------------------------------
These tables hold cite class values (from the template invocation) and identify those templates that support
|volume=, |issue=, and |page(s)= parameters. Cite conference and cite map require further qualification which
is handled in the main module.
]]
local templates_using_volume = {'citation', 'audio-visual', 'book', 'conference', 'encyclopaedia', 'interview', 'journal', 'magazine', 'map', 'news', 'report', 'techreport', 'thesis'}
local templates_using_issue = {'citation', 'conference', 'episode', 'interview', 'journal', 'magazine', 'map', 'news', 'podcast'}
local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'}
--[[--------------------------< K E Y W O R D S >--------------------------------------------------------------
These tables hold keywords for those parameters that have defined sets of acceptible keywords.
]]
--[[--------------------------< M A K E _ K E Y W O R D S _ L I S T >------------------------------------------
this function assembles, for parameter-value validation, the list of keywords appropriate to that parameter.
keywords_lists{}, is a table of tables from keywords{}
]]
local function make_keywords_list (keywords_lists)
local out_table = {}; -- output goes here
for _, keyword_list in ipairs (keywords_lists) do -- spin through keywords_lists{} and get a table of keywords
for _, keyword in ipairs (keyword_list) do -- spin through keyword_list{} and add each keyword, ...
table.insert (out_table, keyword); -- ... as plain text, to the output list
end
end
return out_table;
end
--[[--------------------------< K E Y W O R D S T A B L E >--------------------------------------------------
this is a list of keywords; each key in the list is associated with a table of synonymous keywords possibly from
different languages.
for i18n: add local-language keywords to value table; do not change the key. For example, adding the German keyword 'ja':
['affirmative'] = {'yes', 'true', 'y', 'ja'},
Because cs1|2 templates from en.wiki articles are often copied to other local wikis, it is recommended that the English
keywords remain in these tables.
]]
local keywords = {
['affirmative'] = {'yes', 'true', 'y'}, -- ignore-isbn-error, last-author-amp, no-tracking, nopp -- (Used by InternetArchiveBot)
['afterword'] = {'afterword'}, -- contribution
['bot: unknown'] = {'bot: unknown'}, -- url-status -- (Used by InternetArchiveBot)
['cs1'] = {'cs1'}, -- mode
['cs2'] = {'cs2'}, -- mode
['dead'] = {'dead'}, -- url-status -- (Used by InternetArchiveBot)
['dmy'] = {'dmy'}, -- df
['dmy-all'] = {'dmy-all'}, -- df
['foreword'] = {'foreword'}, -- contribution
['free'] = {'free'}, -- url-access -- (Used by InternetArchiveBot)
['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
['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-format
['ymd'] = {'ymd'}, -- df
['ymd-all'] = {'ymd-all'}, -- df
-- ['yMd'] = {'yMd'}, -- df; not supported at en.wiki
-- ['yMd-all'] = {'yMd-all'}, -- df; not supported at en.wiki
}
--[[--------------------------< X L A T E _ K E Y W O R D S >--------------------------------------------------
this function builds a list, keywords_xlate{}, of the keywords found in keywords{} where the values from keywords{}
become the keys in keywords_xlate{} and the keys from keywords{} become the values in keywords_xlate{}:
['affirmative'] = {'yes', 'true', 'y'}, -- in keywords{}
becomes
['yes'] = 'affirmative', -- in keywords_xlate{}
['true'] = 'affirmative',
['y'] = 'affirmative',
the purpose of this function is to act as a translator between a non-English keyword and its English equivalent
that may be used in other modules of this suite
]]
local function xlate_keywords ()
local out_table = {}; -- output goes here
for k, keywords_t in pairs (keywords) do -- spin through the keywords table
for _, keyword in ipairs (keywords_t) do -- for each keyword
out_table[keyword] = k; -- create an entry in the output table where keyword is the key
end
end
return out_table;
end
local keywords_xlate = xlate_keywords (); -- the list of translated keywords
--[[--------------------------< K E Y W O R D S _ L I S T S >--------------------------------------------------
this is a list of lists of valid keywords for the various parameters in [key]. Generally the keys in this table
are the canonical en.wiki parameter names though some are contrived because of use in multiple differently named
parameters: ['yes_true_y'], ['id-access'].
The function make_keywords_list() extracts the individual keywords from the appropriate list in keywords{}.
The lists in this table are used to validate the keyword assignment for the parameters named in this table's keys.
]]
local keywords_lists = {
['yes_true_y'] = make_keywords_list ({keywords.affirmative}),
['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}),
['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all']}),
-- ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all'], keywords.yMd, keywords['yMd-all']}), -- not supported at en.wiki
['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}),
['name-list-format'] = make_keywords_list ({keywords.vanc}),
['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}),
}
--[[--------------------------< S T R I P M A R K E R S >------------------------------------------------------
Common pattern definition location for stripmarkers so that we don't have to go hunting for them if (when)
MediaWiki changes their form.
]]
local stripmarkers = {
['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127', -- capture returns name of stripmarker
['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127' -- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()
}
--[[--------------------------< I N V I S I B L E _ C H A R A C T E R S >--------------------------------------
This table holds non-printing or invisible characters indexed either by name or by Unicode group. Values are decimal
representations of UTF-8 codes. The table is organized as a table of tables because the lua pairs keyword returns
table data in an arbitrary order. Here, we want to process the table from top to bottom because the entries at
the top of the table are also found in the ranges specified by the entries at the bottom of the table.
Also here is a pattern that recognizes stripmarkers that begin and end with the delete characters. The nowiki
stripmarker is not an error but some others are because the parameter values that include them become part of the
template's metadata before stripmarker replacement.
]]
local invisible_chars = {
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD
{'zero width joiner', '\226\128\141'}, -- U+200D, E2 80 8D
{'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
{'carriage return', '\013'}, -- U+000D (CR), 0D
{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type
{'delete', '\127'}, -- U+007F (DEL), 7F; must be done after stripmarker test
{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-- {'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD
-- {'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'}, -- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD
}
--[[
Indic script makes use of zero width joiner as a character modifier so zwj characters must be left in. This
pattern covers all of the unicode characters for these languages:
Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf
Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
Bengali 0980–09FF – https://unicode.org/charts/PDF/U0980.pdf
Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf
Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf
Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf
Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf
Telugu 0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf
Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf
Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf
plus the not-necessarily Indic scripts for Sinhala and Burmese:
Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf
Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf
Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf
Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
the pattern is used by has_invisible_chars() and coins_cleanup()
TODO: find a better place for this?
]]
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]';
--[[--------------------------< L A N G U A G E S U P P O R T >----------------------------------------------
These tables and constants support various language-specific functionality.
]]
local this_wiki_code = mw.getContentLanguage():getCode() -- get this wiki's language code
local local_lang_cat_enable = false; -- set to true to categorize pages where |language=<local wiki's language>
--[[--------------------------< 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 language codes that apply only to |script-title= and |script-chapter=
]]
local script_lang_codes = {
'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', -- ISO 639-1 codes only for |script-title= and |script-chapter=
'gu', 'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku',
'mk', 'ml', 'mn', 'mr', 'my', 'ne', 'ota', 'ps', 'ru', 'sd', 'si',
'sr', 'ta', 'tg', 'th', 'ug', 'uk', 'ur', 'uz', 'yi', 'zh'
};
--[[--------------------------< 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
]]
local lang_code_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 wWikipedia: 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
['crh'] = 'Crimean Tatar', -- synonymous with Crimean Turkish (return value from {{#language:crh|en}})
['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
}
local lang_name_remap = { -- used for |language=
['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
['crimean tatar'] = {'Crimean Tatar', 'crh'}, -- MediaWiki uses 'crh' as a subdomain name for Crimean Tatar Wikipedia: crh.wikipedia.org
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use o instead of ö)
['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name
['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639
-- ['siksika'] = {'Siksika', 'bla'}, -- MediaWiki/IANA/ISO 639 preferred name: Siksika
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-TW'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
['valencian'] = {'Valencian', 'ca'}, -- variant of Catalan; categorizes as Catalan
}
--[[--------------------------< M A I N T E N A N C E _ C A T E G O R I E S >----------------------------------
Here we name maintenance categories to be used in maintenance messages.
]]
local maint_cats = {
['ASIN'] = 'CS1 maint: ASIN uses ISBN',
['archived_copy'] = 'CS1 maint: archived copy as title',
['authors'] = 'CS1 maint: uses authors parameter',
['bot:_unknown'] = 'CS1 maint: BOT: original-url status unknown',
['date_format'] = 'CS1 maint: date format',
['date_year'] = 'CS1 maint: date and year',
['disp_name'] = 'CS1 maint: display-$1', -- $1 is authors, contributors, editors, interviewers, translators; gets value from special_case_translation table
['editors'] = 'CS1 maint: uses editors parameter',
['embargo'] = 'CS1 maint: PMC embargo expired',
['extra_punct'] = 'CS1 maint: extra punctuation',
['extra_text'] = 'CS1 maint: extra text',
['extra_text_names'] = 'CS1 maint: extra text: $1', -- $1 is <name>s list; gets value from special_case_translation table
['ignore_isbn_err'] = 'CS1 maint: ignored ISBN errors',
['location'] = 'CS1 maint: location',
['mult_names'] = 'CS1 maint: multiple names: $1', -- $1 is <name>s list; gets value from special_case_translation table
['others'] = 'CS1 maint: others',
['pmc_format'] = 'CS1 maint: PMC format',
['unfit'] = 'CS1 maint: unfit url',
['unknown_lang'] = 'CS1 maint: unrecognized language',
['untitled'] = 'CS1 maint: untitled periodical',
['zbl'] = 'CS1 maint: ZBL',
}
--[[--------------------------< P R O P E R T I E S _ C A T E G O R I E S >------------------------------------
Here we name properties categories
]]
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
['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',
['script'] = 'CS1 uses foreign language script', -- when language specified by |script-title=xx: doesn't have its own category
['script_with_name'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code
['jul_greg_uncertainty'] = 'CS1: Julian–Gregorian uncertainty', -- probably temporary cat to identify scope of template with dates 1 October 1582 – 1 January 1926
['long_vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 charachters
}
--[[--------------------------< 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',
['interview'] = 'Interview',
['mailinglist'] = 'Mailing list',
['map'] = 'Map',
['podcast'] = 'Podcast',
['pressrelease'] = 'Press release',
['report'] = 'Report',
['techreport'] = 'Technical report',
['thesis'] = 'Thesis',
}
--[[--------------------------< E R R O R _ C O N D I T I O N S >----------------------------------------------
Error condition table
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
]]
local error_conditions = {
accessdate_missing_url = {
message = '<code class="cs1-code">|access-date=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'accessdate_missing_url',
category = 'Pages using citations with accessdate and no URL',
hidden = false
},
apostrophe_markup = {
message = 'Italic or bold markup not allowed in: <code class="cs1-code">|$1=</code>',
anchor = 'apostrophe_markup',
category = 'CS1 errors: markup',
hidden = false
},
archive_missing_date = {
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|archive-date=</code>',
anchor = 'archive_missing_date',
category = 'Pages with archiveurl citation errors',
hidden = false
},
archive_missing_url = {
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'archive_missing_url',
category = 'Pages with archiveurl citation errors',
hidden = false
},
archive_url = {
message = '<code class="cs1-code">|archive-url=</code> is malformed: $1',
anchor = 'archive_url',
category = 'Pages with archiveurl citation errors',
hidden = false
},
arxiv_missing = {
message = '<code class="cs1-code">|arxiv=</code> required',
anchor = 'arxiv_missing',
category = 'CS1 errors: arXiv', -- same as bad arxiv
hidden = false
},
arxiv_params_not_supported = {
message = 'Unsupported parameter(s) in cite arXiv',
anchor = 'arxiv_params_not_supported',
category = 'CS1 errors: arXiv', -- same as bad arxiv
hidden = false
},
bad_arxiv = {
message = 'Check <code class="cs1-code">|arxiv=</code> value',
anchor = 'bad_arxiv',
category = 'CS1 errors: arXiv',
hidden = false
},
bad_asin = {
message = 'Check <code class="cs1-code">|asin=</code> value',
anchor = 'bad_asin',
category ='CS1 errors: ASIN',
hidden = false
},
bad_bibcode = {
message = 'Check <code class="cs1-code">|bibcode=</code> $1',
anchor = 'bad_bibcode',
category = 'CS1 errors: bibcode',
hidden = false
},
bad_biorxiv = {
message = 'Check <code class="cs1-code">|biorxiv=</code> value',
anchor = 'bad_biorxiv',
category = 'CS1 errors: bioRxiv',
hidden = false
},
bad_citeseerx = {
message = 'Check <code class="cs1-code">|citeseerx=</code> value',
anchor = 'bad_citeseerx',
category = 'CS1 errors: citeseerx',
hidden = false
},
bad_date = {
message = 'Check date values in: <code class="cs1-code">$1</code>',
anchor = 'bad_date',
category = 'CS1 errors: dates',
hidden = false
},
bad_doi = {
message = 'Check <code class="cs1-code">|doi=</code> value',
anchor = 'bad_doi',
category = 'CS1 errors: DOI',
hidden = false
},
bad_hdl = {
message = 'Check <code class="cs1-code">|hdl=</code> value',
anchor = 'bad_hdl',
category = 'CS1 errors: HDL',
hidden = false
},
bad_isbn = {
message = 'Check <code class="cs1-code">|isbn=</code> value: $1',
anchor = 'bad_isbn',
category = 'CS1 errors: ISBN',
hidden = false
},
bad_ismn = {
message = 'Check <code class="cs1-code">|ismn=</code> value',
anchor = 'bad_ismn',
category = 'CS1 errors: ISMN',
hidden = false
},
bad_issn = {
message = 'Check <code class="cs1-code">|$1issn=</code> value',
anchor = 'bad_issn',
category = 'CS1 errors: ISSN',
hidden = false
},
bad_jfm = {
message = 'Check <code class="cs1-code">|jfm=</code> value',
anchor = 'bad_jfm',
category = 'CS1 errors: JFM',
hidden = false
},
bad_lccn = {
message = 'Check <code class="cs1-code">|lccn=</code> value',
anchor = 'bad_lccn',
category = 'CS1 errors: LCCN',
hidden = false
},
bad_usenet_id = {
message = 'Check <code class="cs1-code">|message-id=</code> value',
anchor = 'bad_message_id',
category = 'CS1 errors: message-id',
hidden = false
},
bad_mr = {
message = 'Check <code class="cs1-code">|mr=</code> value',
anchor = 'bad_mr',
category = 'CS1 errors: MR',
hidden = false
},
bad_ol = {
message = 'Check <code class="cs1-code">|ol=</code> value',
anchor = 'bad_ol',
category = 'CS1 errors: OL',
hidden = false
},
bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link=
message = 'Check <code class="cs1-code">|$1=</code> value',
anchor = 'bad_paramlink',
category = 'CS1 errors: parameter link',
hidden = false
},
bad_pmc = {
message = 'Check <code class="cs1-code">|pmc=</code> value',
anchor = 'bad_pmc',
category = 'CS1 errors: PMC',
hidden = false
},
bad_pmid = {
message = 'Check <code class="cs1-code">|pmid=</code> value',
anchor = 'bad_pmid',
category = 'CS1 errors: PMID',
hidden = false
},
bad_oclc = {
message = 'Check <code class="cs1-code">|oclc=</code> value',
anchor = 'bad_oclc',
category = 'CS1 errors: OCLC',
hidden = false
},
bad_ssrn = {
message = 'Check <code class="cs1-code">|ssrn=</code> value',
anchor = 'bad_ssrn',
category = 'CS1 errors: SSRN',
hidden = false
},
bad_url = {
message = 'Check $1 value',
anchor = 'bad_url',
category = 'Pages with URL errors',
hidden = false
},
bad_zbl = {
message = 'Check <code class="cs1-code">|zbl=</code> value',
anchor = 'bad_zbl',
category = 'CS1 errors: ZBL',
hidden = false
},
bare_url_missing_title = {
message = '$1 missing title',
anchor = 'bare_url_missing_title',
category = 'Pages with citations having bare URLs',
hidden = false
},
biorxiv_missing = {
message = '<code class="cs1-code">|biorxiv=</code> required',
anchor = 'biorxiv_missing',
category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv
hidden = false
},
chapter_ignored = {
message = '<code class="cs1-code">|$1=</code> ignored',
anchor = 'chapter_ignored',
category = 'CS1 errors: chapter ignored',
hidden = false
},
citation_missing_title = {
message = 'Missing or empty <code class="cs1-code">|$1=</code>',
anchor = 'citation_missing_title',
category = 'Pages with citations lacking titles',
hidden = false
},
citeseerx_missing = {
message = '<code class="cs1-code">|citeseerx=</code> required',
anchor = 'citeseerx_missing',
category = 'CS1 errors: citeseerx', -- same as bad citeseerx
hidden = false
},
cite_web_url = { -- this error applies to cite web and to cite podcast
message = 'Missing or empty <code class="cs1-code">|url=</code>',
anchor = 'cite_web_url',
category = 'Pages using web citations with no URL',
hidden = false
},
class_ignored = {
message = '<code class="cs1-code">|class=</code> ignored',
anchor = 'class_ignored',
category = 'CS1 errors: class',
hidden = false
},
contributor_ignored = {
message = '<code class="cs1-code">|contributor=</code> ignored',
anchor = 'contributor_ignored',
category = 'CS1 errors: contributor',
hidden = false
},
contributor_missing_required_param = {
message = '<code class="cs1-code">|contributor=</code> requires <code class="cs1-code">|$1=</code>',
anchor = 'contributor_missing_required_param',
category = 'CS1 errors: contributor',
hidden = false
},
deprecated_params = {
message = 'Cite uses deprecated parameter <code class="cs1-code">|$1=</code>',
anchor = 'deprecated_params',
category = 'CS1 errors: deprecated parameters',
hidden = false
},
doibroken_missing_doi = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|doi=</code>',
anchor = 'doibroken_missing_doi',
category = 'CS1 errors: DOI',
hidden = false
},
empty_citation = {
message = 'Empty citation',
anchor = 'empty_citation',
category = 'Pages with empty citations',
hidden = false
},
etal = {
message = 'Explicit use of et al. in: <code class="cs1-code">|$1=</code>',
anchor = 'explicit_et_al',
category = 'CS1 errors: explicit use of et al.',
hidden = false
},
first_missing_last = {
message = '<code class="cs1-code">|$1=</code> missing <code class="cs1-code">|$2=</code>', -- $1 is first alias, $2 is matching last alias
anchor = 'first_missing_last',
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
hidden = false
},
format_missing_url = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|$2=</code>',
anchor = 'format_missing_url',
category = 'Pages using citations with format and no URL',
hidden = false
},
invalid_param_val = {
message = 'Invalid <code class="cs1-code">|$1=$2</code>',
anchor = 'invalid_param_val',
category = 'CS1 errors: invalid parameter value',
hidden = false
},
invisible_char = {
message = '$1 in $2 at position $3',
anchor = 'invisible_char',
category = 'CS1 errors: invisible characters',
hidden = false
},
missing_name = {
message = 'Missing <code class="cs1-code">|$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
},
missing_periodical = {
message = 'Cite $1 requires <code class="cs1-code">|$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 = true
},
missing_pipe = {
message = 'Missing pipe in: <code class="cs1-code">|$1=</code>',
anchor = 'missing_pipe',
category = 'CS1 errors: missing pipe',
hidden = false
},
param_access_requires_param = {
message = '<code class="cs1-code">|$1-access=</code> requires <code class="cs1-code">|$1=</code>',
anchor = 'param_access_requires_param',
category = 'CS1 errors: param-access',
hidden = false
},
param_has_ext_link = {
message = 'External link in <code class="cs1-code">$1</code>',
anchor = 'param_has_ext_link',
category = 'CS1 errors: external links',
hidden = false
},
parameter_ignored = {
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored',
anchor = 'parameter_ignored',
category = 'Pages with citations using unsupported parameters',
hidden = false
},
parameter_ignored_suggest = {
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored (<code class="cs1-code">|$2=</code> suggested)',
anchor = 'parameter_ignored_suggest',
category = 'Pages with citations using unsupported parameters',
hidden = false
},
redundant_parameters = {
message = 'More than one of $1 specified',
anchor = 'redundant_parameters',
category = 'Pages with citations having redundant parameters',
hidden = false
},
script_parameter = {
message = 'Invalid <code class="cs1-code">|$1=</code>: $2',
anchor = 'script_parameter',
category = 'CS1 errors: script parameters',
hidden = false
},
ssrn_missing = {
message = '<code class="cs1-code">|ssrn=</code> required',
anchor = 'ssrn_missing',
category = 'CS1 errors: ssrn', -- same as bad arxiv
hidden = false
},
text_ignored = {
message = 'Text "$1" ignored',
anchor = 'text_ignored',
category = 'Pages with citations using unnamed parameters',
hidden = false
},
trans_missing_title = {
message = '<code class="cs1-code">|trans-$1=</code> requires <code class="cs1-code">|$1=</code>',
anchor = 'trans_missing_title',
category = 'CS1 errors: translated title',
hidden = false
},
vancouver = {
message = 'Vancouver style error: $1',
anchor = 'vancouver',
category = 'CS1 errors: Vancouver style',
hidden = false
},
wikilink_in_url = {
message = 'URL–wikilink conflict', -- uses ndash
anchor = 'wikilink_in_url',
category = 'CS1 errors: URL–wikilink conflict', -- uses ndash
hidden = false
},
}
--[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
The following contains a list of values for various defined identifiers. For each identifier we specify a
variety of information necessary to properly render the identifier in the citation.
parameters: a list of parameter aliases for this identifier
link: Wikipedia article name
q: wikidata q number for the identifier
label: the alternate name to apply to link
mode: 'manual' when there is a specific function in the code to handle the identifier;
'external' for identifiers that link outside of Wikipedia;
prefix: the first part of a url that will be concatenated with a second part which usually contains 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:....
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn
for others make a url using the value in prefix, use the keyword: pre (not checked; any text other than 'info' or 'rft' 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
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',
q = 'Q118398',
label = 'arXiv',
mode = 'manual',
prefix = '//arxiv.org/abs/', -- protocol relative tested 2013-09-04
encode = false,
COinS = 'info:arxiv',
separator = ':',
access = 'free', -- free to read
},
['ASIN'] = {
parameters = { 'asin', 'ASIN' },
link = 'Amazon Standard Identification Number',
q = 'Q1753278',
label = 'ASIN',
mode = 'manual',
prefix = '//www.amazon.',
COinS = nil, -- no COinS for this id (needs thinking on implementation because |asin-tld=)
separator = ' ',
encode = false;
},
['BIBCODE'] = {
parameters = {'bibcode'},
link = 'Bibcode',
q = 'Q25754',
label = 'Bibcode',
mode = 'manual',
prefix = 'https://ui.adsabs.harvard.edu/abs/',
encode = false,
COinS = 'info:bibcode',
separator = ':',
custom_access = 'bibcode-access',
},
['BIORXIV'] = {
parameters = {'biorxiv'},
link = 'bioRxiv',
q = 'Q19835482',
label = 'bioRxiv',
mode = 'manual',
prefix = '//doi.org/10.1101/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = ' ',
},
['CITESEERX'] = {
parameters = {'citeseerx'},
link = 'CiteSeerX',
q = 'Q2715061',
label = 'CiteSeerX',
mode = 'manual', -- manual for custom validation of the "doi"
prefix = '//citeseerx.ist.psu.edu/viewdoc/summary?doi=',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = ' ',
},
['DOI'] = { -- (Used by InternetArchiveBot)
parameters = { 'doi', 'DOI' },
link = 'Digital object identifier',
q = 'Q25670',
label = 'doi',
mode = 'manual',
prefix = '//doi.org/',
COinS = 'info:doi',
separator = ':',
encode = true,
custom_access = 'doi-access',
},
['EISSN'] = {
parameters = {'eissn', 'EISSN'},
link = 'International_Standard_Serial_Number#Electronic_ISSN',
q = 'Q46339674',
label = 'eISSN',
mode = 'manual',
prefix = '//www.worldcat.org/issn/',
COinS = 'rft.eissn',
encode = false,
separator = ' ',
},
['HDL'] = {
parameters = { 'hdl', 'HDL' },
link = 'Handle System',
q = 'Q3126718',
label = 'hdl',
mode = 'manual',
prefix = '//hdl.handle.net/',
COinS = 'info:hdl',
separator = ':',
encode = true,
custom_access = 'hdl-access',
},
['ISBN'] = { -- (Used by InternetArchiveBot)
parameters = {'isbn', 'ISBN', 'isbn13', 'ISBN13'},
link = 'International Standard Book Number',
q = 'Q33057',
label = 'ISBN',
mode = 'manual',
prefix = 'Special:BookSources/',
COinS = 'rft.isbn',
separator = ' ',
},
['ISMN'] = {
parameters = {'ismn', 'ISMN'},
link = 'International Standard Music Number',
q = 'Q1666938',
label = 'ISMN',
mode = 'manual',
prefix = '', -- not currently used;
COinS = 'nil', -- nil because we can't use pre or rft or info:
separator = ' ',
},
['ISSN'] = {
parameters = {'issn', 'ISSN'},
link = 'International Standard Serial Number',
q = 'Q131276',
label = 'ISSN',
mode = 'manual',
prefix = '//www.worldcat.org/issn/',
COinS = 'rft.issn',
encode = false,
separator = ' ',
},
['JFM'] = {
parameters = {'jfm', 'JFM'},
link = 'Jahrbuch über die Fortschritte der Mathematik',
q = '',
label = 'JFM',
mode = 'manual',
prefix = '//zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
['JSTOR'] = {
parameters = {'jstor', 'JSTOR'},
link = 'JSTOR',
q = 'Q1420342',
label = 'JSTOR',
mode = 'external',
prefix = '//www.jstor.org/stable/', -- protocol relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
custom_access = 'jstor-access',
},
['LCCN'] = {
parameters = {'LCCN', 'lccn'},
link = 'Library of Congress Control Number',
q = 'Q620946',
label = 'LCCN',
mode = 'manual',
prefix = '//lccn.loc.gov/', -- protocol relative tested 2015-12-28
COinS = 'info:lccn', -- use prefix value
encode = false,
separator = ' ',
},
['MR'] = {
parameters = {'MR', 'mr'},
link = 'Mathematical Reviews',
q = 'Q211172',
label = 'MR',
mode = 'manual',
prefix = '//www.ams.org/mathscinet-getitem?mr=', -- protocol relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
['OCLC'] = {
parameters = {'OCLC', 'oclc'},
link = 'OCLC',
q = 'Q190593',
label = 'OCLC',
mode = 'manual',
prefix = '//www.worldcat.org/oclc/',
COinS = 'info:oclcnum',
encode = true,
separator = ' ',
},
['OL'] = {
parameters = { 'ol', 'OL' },
link = 'Open Library',
q = 'Q1201876',
label = 'OL',
mode = 'manual',
prefix = '//openlibrary.org/',
COinS = nil, -- no COinS for this id (needs thinking on implementation because /authors/books/works/OL)
separator = ' ',
encode = true,
custom_access = 'ol-access',
},
['OSTI'] = {
parameters = {'OSTI', 'osti'},
link = 'Office of Scientific and Technical Information',
q = 'Q2015776',
label = 'OSTI',
mode = 'external',
prefix = '//www.osti.gov/biblio/', -- protocol relative tested 2018-09-12
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
custom_access = 'osti-access',
},
['PMC'] = {
parameters = {'PMC', 'pmc'},
link = 'PubMed Central',
q = 'Q229883',
label = 'PMC',
mode = 'manual',
prefix = '//www.ncbi.nlm.nih.gov/pmc/articles/PMC',
suffix = " ",
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
access = 'free', -- free to read
},
['PMID'] = {
parameters = {'PMID', 'pmid'},
link = 'PubMed Identifier',
q = '',
label = 'PMID',
mode = 'manual',
-- prefix = '//www.ncbi.nlm.nih.gov/pubmed/',
prefix = '//pubmed.ncbi.nlm.nih.gov/', -- new for 2020
COinS = 'info:pmid',
encode = false,
separator = ' ',
},
['RFC'] = {
parameters = {'RFC', 'rfc'},
link = 'Request for Comments',
q = 'Q212971',
label = 'RFC',
mode = 'external',
prefix = '//tools.ietf.org/html/rfc',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
access = 'free', -- free to read
},
['SSRN'] = {
parameters = {'SSRN', 'ssrn'},
link = 'Social Science Research Network',
q = 'Q7550801',
label = 'SSRN',
mode = 'manual',
prefix = '//ssrn.com/abstract=', -- protocol relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
access = 'free', -- always free to read
},
['USENETID'] = {
parameters = {'message-id'},
link = 'Usenet',
q = 'Q193162',
label = 'Usenet:',
mode = 'manual',
prefix = 'news:',
encode = false,
COinS = 'pre', -- use prefix value
separator = ' ',
},
['ZBL'] = {
parameters = {'ZBL', 'zbl'},
link = 'Zentralblatt MATH',
q = 'Q190269',
label = 'Zbl',
mode = 'manual',
prefix = '//zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
}
--[[--------------------------< E X P O R T E D T A B L E S >------------------------------------------------
]]
return {
aliases = aliases,
special_case_translation = special_case_translation,
defaults = defaults,
date_names = date_names,
error_conditions = error_conditions,
editor_markup_patterns = editor_markup_patterns,
et_al_patterns = et_al_patterns,
global_df = global_df,
id_handlers = id_handlers,
keywords_lists = keywords_lists,
keywords_xlate = keywords_xlate,
stripmarkers=stripmarkers,
invisible_chars = invisible_chars,
indic_script = indic_script,
local_lang_cat_enable = local_lang_cat_enable,
maint_cats = maint_cats,
messages = messages,
presentation = presentation,
prop_cats = prop_cats,
punct_skip = punct_skip,
script_lang_codes = script_lang_codes,
lang_code_remap = lang_code_remap,
lang_name_remap = lang_name_remap,
this_wiki_code = this_wiki_code,
title_types = title_types,
uncategorized_namespaces = uncategorized_namespaces,
uncategorized_subpages = uncategorized_subpages,
templates_using_volume = templates_using_volume,
templates_using_issue = templates_using_issue,
templates_not_using_page = templates_not_using_page,
}