Difference between revisions of "Module:Citation/CS1/Configuration"
Jump to navigation
Jump to search
Module:Citation/CS1/Configuration (edit)
Revision as of 02:06, 6 November 2023
, 02:06, 6 November 2023bump s2cid;
m (1 revision imported) |
en>Trappist the monk (bump s2cid;) |
||
Line 1: | Line 1: | ||
local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates | |||
--[[--------------------------< S E T T I N G S >-------------------------------------------------------------- | |||
boolean settings used to control various things. these setting located here to make them easy to find | |||
]] | |||
-- these settings local to this module only | |||
local local_digits_from_mediawiki = false; -- for i18n; when true, module fills date_names['local_digits'] from MediaWiki; manual fill required else; always false at en.wiki | |||
local local_date_names_from_mediawiki = false; -- for i18n; when true, module fills date_names['local']['long'] and date_names['local']['short'] from MediaWiki; | |||
-- manual translation required else; ; always false at en.wiki | |||
-- these settings exported to other modules | |||
local use_identifier_redirects = true; -- when true use redirect name for identifier label links; always true at en.wiki | |||
local local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki | |||
local date_name_auto_xlate_enable = false; -- when true translates English month-names to the local-wiki's language month names; always false at en.wiki | |||
local date_digit_auto_xlate_enable = false; -- when true translates Western date digit to the local-wiki's language digits (date_names['local_digits']); always false at en.wiki | |||
--[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------ | --[[--------------------------< 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 | List of namespaces identifiers for namespaces that will not be included in citation error categories. | ||
Same as setting notracking = true by default. | Same as setting notracking = true by default. | ||
For wikis that have a current version of Module:cs1 documentation support, this #invoke will return an unordered | |||
list of namespace names and their associated identifiers: | |||
{{#invoke:cs1 documentation support|uncategorized_namespace_lister|all=<anything>}} | |||
]] | ]] | ||
uncategorized_namespaces_t = {[2]=true}; -- init with user namespace id | |||
for k, _ in pairs (mw.site.talkNamespaces) do -- add all talk namespace ids | |||
uncategorized_namespaces_t[k] = true; | |||
end | |||
local uncategorized_subpages = {'/[Ss]andbox', '/[Tt]estcases', '/[^/]*[Ll]og', '/[Aa]rchive'}; -- list of Lua patterns found in page names of pages we should not categorize | 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 | ||
Line 28: | Line 52: | ||
['archived-dead'] = 'Archived from $1 on $2', | ['archived-dead'] = 'Archived from $1 on $2', | ||
['archived-live'] = '$1 from the original on $2', | ['archived-live'] = '$1 from the original on $2', | ||
['archived-unfit'] = 'Archived from the original on ', | ['archived-unfit'] = 'Archived from the original on ', | ||
['archived'] = 'Archived', | ['archived'] = 'Archived', | ||
Line 42: | Line 65: | ||
['inset'] = '$1 inset', | ['inset'] = '$1 inset', | ||
['interview'] = 'Interviewed by $1', | ['interview'] = 'Interviewed by $1', | ||
['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name | ['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name | ||
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1', | ['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1', | ||
Line 60: | Line 82: | ||
['vol'] = '$1 Vol. $2', -- $1 is sepc; bold journal style volume is in presentation{} | ['vol'] = '$1 Vol. $2', -- $1 is sepc; bold journal style volume is in presentation{} | ||
['vol-no'] = '$1 Vol. $2, no. $3', | ['vol-no'] = '$1 Vol. $2, no. $3', -- sepc, volume, issue (alternatively insert $1 after $2, but then we'd also have to change capitalization) | ||
['issue'] = '$1 No. $2', -- $1 is sepc | ['issue'] = '$1 No. $2', -- $1 is sepc | ||
['art'] = '$1 Art. $2', -- $1 is sepc; for {{cite conference}} only | |||
['vol-art'] = '$1 Vol. $2, art. $3', -- sepc, volume, article-number; for {{cite conference}} only | |||
['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{} | ['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{} | ||
['j-issue'] = ' ($1)', | ['j-issue'] = ' ($1)', | ||
['j-article-num'] = ' $1', -- TODO: any punctuation here? static text? | |||
['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc | ['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc | ||
Line 108: | Line 134: | ||
used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while | used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while | ||
the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the | the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the | ||
template's documentation when an article is displayed in | template's documentation when an article is displayed in preview mode. | ||
Most cs1|2 template |CitationClass= values at en.wiki match their canonical template names so are not listed here. | Most cs1|2 template |CitationClass= values at en.wiki match their canonical template names so are not listed here. | ||
Line 115: | Line 141: | ||
local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n | local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n | ||
['audio-visual'] = 'AV media', | ['arxiv'] = 'arXiv', | ||
['audio-visual'] = 'AV media', | |||
['AV-media-notes'] = 'AV media notes', | ['AV-media-notes'] = 'AV media notes', | ||
['biorxiv'] = 'bioRxiv', | |||
['citeseerx'] = 'CiteSeerX', | |||
['encyclopaedia'] = 'encyclopedia', | ['encyclopaedia'] = 'encyclopedia', | ||
['mailinglist'] = 'mailing list', | ['mailinglist'] = 'mailing list', | ||
['pressrelease'] = 'press release' | ['medrxiv'] = 'medRxiv', | ||
['pressrelease'] = 'press release', | |||
['ssrn'] = 'SSRN', | |||
['techreport'] = 'tech report', | |||
} | } | ||
Line 131: | Line 163: | ||
local et_al_patterns = { | local et_al_patterns = { | ||
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$", -- variations on the 'et al' theme | "[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,\"']*$", -- variations on the 'et al' theme | ||
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.\"']*$", | "[;,]? *[\"']*%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. | "[;,]? *%f[%a]and [Oo]thers", -- an alternative to et al. | ||
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form | "%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form | ||
"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", | "%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax) | ||
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form | "[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form | ||
} | } | ||
Line 162: | Line 194: | ||
['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc. | ['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc. | ||
['interwiki'] = ' <span class="cs1-format">[in $1]</span>', -- for interwiki-language-linked author, editor, etc | |||
['interproj'] = ' <span class="cs1-format">[at $1]</span>', -- for interwiki-project-linked author, editor, etc (:d: and :s: supported; :w: ignored) | |||
-- various access levels, for |access=, |doi-access=, |arxiv=, ... | -- various access levels, for |access=, |doi-access=, |arxiv=, ... | ||
Line 227: | Line 261: | ||
['ArchiveFormat'] = 'archive-format', | ['ArchiveFormat'] = 'archive-format', | ||
['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot | ['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot | ||
['ArticleNumber'] = 'article-number', | |||
['ASINTLD'] = 'asin-tld', | ['ASINTLD'] = 'asin-tld', | ||
['At'] = 'at', -- Used by InternetArchiveBot | ['At'] = 'at', -- Used by InternetArchiveBot | ||
Line 262: | Line 297: | ||
['Issue'] = {'issue', 'number'}, | ['Issue'] = {'issue', 'number'}, | ||
['Language'] = {'language', 'lang'}, | ['Language'] = {'language', 'lang'}, | ||
['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only | ['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only | ||
['Map'] = 'map', -- cite map only | ['Map'] = 'map', -- cite map only | ||
Line 313: | Line 344: | ||
['Title'] = 'title', -- Used by InternetArchiveBot | ['Title'] = 'title', -- Used by InternetArchiveBot | ||
['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot | ['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot | ||
['TitleNote'] = 'department', | ['TitleNote'] = {'title-note', 'department'}, | ||
['TitleType'] = {'type', 'medium'}, | ['TitleType'] = {'type', 'medium'}, | ||
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', | ['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', | ||
Line 319: | Line 350: | ||
['Transcript'] = 'transcript', | ['Transcript'] = 'transcript', | ||
['TranscriptFormat'] = 'transcript-format', | ['TranscriptFormat'] = 'transcript-format', | ||
['TranscriptURL'] = | ['TranscriptURL'] = 'transcript-url', -- Used by InternetArchiveBot | ||
['TransMap'] = 'trans-map', -- cite map only | ['TransMap'] = 'trans-map', -- cite map only | ||
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', | ['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', | ||
Line 334: | Line 365: | ||
['Year'] = 'year', | ['Year'] = 'year', | ||
['AuthorList-First'] = {"first#", "author-first#", "author#-first", "given#", | ['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given", | ||
" | "subject-first#", "subject#-first", "subject-given#", "subject#-given", | ||
['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "surname#", | "given#"}, | ||
" | ['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname", | ||
"subject-last#", "subject#-last", "subject-surname#", "subject#-surname", | |||
"author#", 'host#', "subject#", "surname#"}, | |||
['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#", | ['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#", | ||
"subject#-link", "authorlink#", "author#link"}, | "subject#-link", "authorlink#", "author#link"}, | ||
Line 381: | Line 414: | ||
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | 'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | ||
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous | 'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous | ||
'ArchiveURL', 'ChapterURL', 'ConferenceURL | '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 | 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 | 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls | ||
'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls | 'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls | ||
} | } | ||
Line 410: | Line 443: | ||
local punct_skip = {}; | local punct_skip = {}; | ||
local url_skip = {}; | local url_skip = {}; | ||
--[[--------------------------< S I N G L E - L E T T E R S E C O N D - L E V E L D O M A I N S >---------- | |||
this is a list of tlds that are known to have single-letter second-level domain names. This list does not include | |||
ccTLDs which are accepted in is_domain_name(). | |||
]] | |||
local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'org', 'today'}; | |||
Line 423: | Line 466: | ||
local special_case_translation = { | local special_case_translation = { | ||
['AuthorList'] = 'authors list', -- used to assemble maintenance category names | ['AuthorList'] = 'authors list', -- used to assemble maintenance category names | ||
['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base | ['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 | ['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() | ['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names() | ||
Line 436: | Line 479: | ||
-- Lua patterns to match generic titles; usually created by bots or reference filling tools | -- Lua patterns to match generic titles; usually created by bots or reference filling tools | ||
-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language | -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language | ||
-- generic titles and patterns in this table should be lowercase only | -- generic titles and patterns in this table should be lowercase only | ||
-- leave ['local'] nil except when there is a matching generic title in your language | -- leave ['local'] nil except when there is a matching generic title in your language | ||
-- boolean 'true' for plain-text searches; 'false' for pattern searches | -- boolean 'true' for plain-text searches; 'false' for pattern searches | ||
{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil}, | |||
['generic_titles'] = { | |||
['accept'] = { | |||
}, | |||
['reject'] = { | |||
{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil}, | |||
{['en'] = {'are you a robot', true}, ['local'] = nil}, | |||
{['en'] = {'hugedomains.com', true}, ['local'] = nil}, | |||
{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil}, | |||
{['en'] = {'page not found', true}, ['local'] = nil}, | |||
{['en'] = {'subscribe to read', true}, ['local'] = nil}, | |||
{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil}, | |||
{['en'] = {'website is for sale', true}, ['local'] = nil}, | |||
{['en'] = {'^404', false}, ['local'] = nil}, | |||
{['en'] = {'internet archive wayback machine', true}, ['local'] = nil}, | |||
{['en'] = {'log into facebook', true}, ['local'] = nil}, | |||
{['en'] = {'login • instagram', true}, ['local'] = nil}, | |||
{['en'] = {'redirecting...', true}, ['local'] = nil}, | |||
{['en'] = {'usurped title', true}, ['local'] = nil}, -- added by a GreenC bot | |||
{['en'] = {'webcite query result', true}, ['local'] = nil}, | |||
{['en'] = {'wikiwix\'s cache', true}, ['local'] = nil}, | |||
} | |||
}, | }, | ||
-- boolean 'true' for plain-text searches, search string must be lowercase only | |||
-- boolean 'false' for pattern searches | |||
-- leave ['local'] nil except when there is a matching generic name in your language | |||
['generic_names'] = { | ['generic_names'] = { | ||
['accept'] = { | |||
{['en'] = {'%[%[[^|]*%(author%) *|[^%]]*%]%]', false}, ['local'] = nil}, | |||
}, | |||
['reject'] = { | |||
{['en'] = {'about us', true}, ['local'] = nil}, | |||
{['en'] = {'%f[%a][Aa]dvisor%f[%A]', false}, ['local'] = nil}, | |||
{['en'] = {'allmusic', true}, ['local'] = nil}, | |||
{['en'] = {'%f[%a][Aa]uthor%f[%A]', false}, ['local'] = nil}, | |||
{['en'] = {'business', true}, ['local'] = nil}, | |||
{['en'] = {'cnn', true}, ['local'] = nil}, | |||
{['en'] = {'collaborator', true}, ['local'] = nil}, | |||
{['en'] = {'contributor', true}, ['local'] = nil}, | |||
{['en'] = {'contact us', true}, ['local'] = nil}, | |||
{['en'] = {'directory', true}, ['local'] = nil}, | |||
{['en'] = {'%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$', false}, ['local'] = nil}, | |||
{['en'] = {'[,%.%s]%f[e]eds?%.?$', false}, ['local'] = nil}, | |||
{['en'] = {'^eds?[%.,;]', false}, ['local'] = nil}, | |||
{['en'] = {'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', false}, ['local'] = nil}, | |||
{['en'] = {'%f[%a][Ee]dited%f[%A]', false}, ['local'] = nil}, | |||
{['en'] = {'%f[%a][Ee]ditors?%f[%A]', false}, ['local'] = nil}, | |||
{['en'] = {'%f[%a]]Ee]mail%f[%A]', false}, ['local'] = nil}, | |||
{['en'] = {'facebook', true}, ['local'] = nil}, | |||
{['en'] = {'google', true}, ['local'] = nil}, | |||
{['en'] = {'home page', true}, ['local'] = nil}, | |||
{['en'] = {'^[Ii]nc%.?$', false}, ['local'] = nil}, | |||
{['en'] = {'instagram', true}, ['local'] = nil}, | |||
{['en'] = {'interviewer', true}, ['local'] = nil}, | |||
{['en'] = {'linkedIn', true}, ['local'] = nil}, | |||
{['en'] = {'^[Nn]ews$', false}, ['local'] = nil}, | |||
{['en'] = {'pinterest', true}, ['local'] = nil}, | |||
{['en'] = {'policy', true}, ['local'] = nil}, | |||
{['en'] = {'privacy', true}, ['local'] = nil}, | |||
{['en'] = {'reuters', true}, ['local'] = nil}, | |||
{['en'] = {'translator', true}, ['local'] = nil}, | |||
{['en'] = {'tumblr', true}, ['local'] = nil}, | |||
{['en'] = {'twitter', true}, ['local'] = nil}, | |||
{['en'] = {'site name', true}, ['local'] = nil}, | |||
{['en'] = {'statement', true}, ['local'] = nil}, | |||
{['en'] = {'submitted', true}, ['local'] = nil}, | |||
{['en'] = {'super.?user', false}, ['local'] = nil}, | |||
{['en'] = {'%f['..is_Latn..'][Uu]ser%f[^'..is_Latn..']', false}, ['local'] = nil}, | |||
{['en'] = {'verfasser', true}, ['local'] = nil}, | |||
} | |||
} | |||
} | } | ||
Line 519: | Line 579: | ||
Easter and Christmas are defined here as 98 and 99, which should be out of the | 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. | 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'] | |||
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'] | |||
-- when true, module fetches long and short month names from MediaWiki | |||
local date_names = { | local date_names = { | ||
['en'] = { -- English | ['en'] = { -- English | ||
Line 530: | Line 603: | ||
['named'] = {['Easter'] = 98, ['Christmas'] = 99}, | ['named'] = {['Easter'] = 98, ['Christmas'] = 99}, | ||
}, | }, | ||
-- when local_date_names_from_mediawiki = false | |||
['local'] = { -- replace these English date names with the local language equivalents | ['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}, | ['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12}, | ||
Line 537: | Line 611: | ||
['named'] = {['Easter'] = 98, ['Christmas'] = 99}, | ['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 | ['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'] = {}, | ['xlate_digits'] = {}, | ||
} | } | ||
for name, i in pairs (date_names['local'] | if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled | ||
local long_t = {}; | |||
local short_t = {}; | |||
for i=1, 12 do -- loop 12x and | |||
local name = lang_obj:formatDate('F', '2022-' .. i .. '-1'); -- get long month name for each i | |||
long_t[name] = i; -- save it | |||
name = lang_obj:formatDate('M', '2022-' .. i .. '-1'); -- get short month name for each i | |||
short_t[name] = i; -- save it | |||
end | |||
date_names['local']['long'] = long_t; -- write the long table – overwrites manual translation | |||
date_names['local']['short'] = short_t; -- write the short table – overwrites manual translation | |||
end | |||
-- create inverted date-name tables for reformatting and/or translation | |||
for _, invert_t in pairs {{'long', 'inv_local_long'}, {'short', 'inv_local_short'}, {'quarter', 'inv_local_quarter'}, {'season', 'inv_local_season'}, {'named', 'inv_local_named'}} do | |||
for name, i in pairs (date_names['local'][invert_t[1]]) do -- this table is ['name'] = i | |||
date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd | |||
end | |||
end | end | ||
for | if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled | ||
date_names[' | local digits_t = {}; | ||
for i=0, 9 do -- loop 10x and | |||
digits_t [lang_obj:formatNum (i)] = tostring (i); -- format the loop indexer as local lang table index and assign loop indexer (a string) as the value | |||
end | |||
date_names['local_digits'] = digits_t; | |||
end | end | ||
Line 570: | Line 666: | ||
'{{ *([Mm]DY) *[|}]', -- 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 () | local function get_date_format () | ||
-- if title_object.namespace == 10 then -- not in template space so that unused templates appear in unused-template-reports; | |||
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 | 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 | local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format | ||
if match then | if match then | ||
local use_dates_template = content:match ('%b{}', start); -- get the whole template | |||
if | if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length | ||
return match:lower() .. '-' .. | return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)'); | ||
else | else | ||
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df= | return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df= | ||
Line 586: | Line 691: | ||
end | end | ||
local global_df; | local global_df; -- TODO: add this to <global_cs1_config_t>? | ||
Line 601: | Line 706: | ||
local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'} | local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'} | ||
--[[ | |||
These tables control when it is appropriate for {{citation}} to render |volume= and/or |issue=. The parameter | |||
names in the tables constrain {{citation}} so that its renderings match the renderings of the equivalent cs1 | |||
templates. For example, {{cite web}} does not support |volume= so the equivalent {{citation |website=...}} must | |||
not support |volume=. | |||
]] | |||
local citation_no_volume_t = { -- {{citation}} does not render |volume= when these parameters are used | |||
'website', 'mailinglist', 'script-website', | |||
} | |||
local citation_issue_t = { -- {{citation}} may render |issue= when these parameters are used | |||
'journal', 'magazine', 'newspaper', 'periodical', 'work', | |||
'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work', | |||
} | |||
--[[ | --[[ | ||
Line 762: | Line 883: | ||
--[[---------------------< S | --[[--------------------------< C S 1 _ C O N F I G _ G E T >-------------------------------------------------- | ||
fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t> | |||
no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked. | |||
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 | local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table? | ||
local function get_cs1_config () | |||
} | -- if title_object.namespace == 10 then -- not in template space so that unused templates appear in unused-template-reports; | ||
if not content then -- nil content when we're in template | |||
return nil; -- auto-formatting does not work in Template space so don't set global_df | |||
end | |||
local start = content:find('{{ *[Cc][Ss]1 config *[|}]'); -- <start> is offset into <content> when {{cs1 config}} found; nil else | |||
if start then | |||
local cs1_config_template = content:match ('%b{}', start); -- get the whole template | |||
if not cs1_config_template then | |||
return nil; | |||
end | |||
-- | local params_t = mw.text.split (cs1_config_template:gsub ('^{{%s*', ''):gsub ('%s*}}$', ''), '%s*|%s*'); -- remove '{{' and '}}'; make a sequence of parameter/value pairs (split on the pipe) | ||
table.remove (params_t, 1); -- remove the template name because it isn't a parameter/value pair | |||
local config_meta_params_t = {'DisplayAuthors', 'DisplayContributors', 'DisplayEditors', 'DisplayInterviewers', 'DisplayTranslators', 'NameListStyle', 'Mode'}; | |||
local meta_param_map_t = {}; -- list of accepted parameter names usable in {{cs1 config}} goes here | |||
for _, meta_param in ipairs (config_meta_params_t) do -- for i18n using <config_meta_params_t>, map template parameter names to their metaparameter equivalents | |||
if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence, | |||
for _, param in ipairs (aliases[meta_param]) do -- extract its contents | |||
meta_param_map_t[param] = meta_param; -- and add to <meta_param_map_t> | |||
end | |||
else | |||
meta_param_map_t[aliases[meta_param]] = meta_param; -- not a sequence so just add the parameter to <meta_param_map_t> | |||
end | |||
end | |||
local keywords_t = {}; -- map valid keywords to their associate metaparameter; reverse form of <keyword_lists[key] for these metaparameters | |||
for _, metaparam_t in ipairs ({{'NameListStyle', 'name-list-style'}, {'Mode', 'mode'}}) do -- only these metaparameter / keywords_lists key pairs | |||
for _, keyword in ipairs (keywords_lists[metaparam_t[2]]) do -- spin through the list of keywords | |||
keywords_t[keyword] = metaparam_t[1]; -- add [keyword] = metaparameter to the map | |||
end | |||
end | |||
for _, param in ipairs (params_t) do -- spin through the {{cs1 config}} parameters and fill <global_cs1_config_t> | |||
local k, v = param:match ('([^=]-)%s*=%s*(.+)'); -- <k> is the parameter name; <v> is parameter's assigned value | |||
if k then | |||
if k:find ('^display') then -- if <k> is one of the |display-<namelist>= parameters | |||
if v:match ('%d+') then -- the assigned value must be digits; doesn't accept 'etal' | |||
global_cs1_config_t[meta_param_map_t[k]]=v; -- add the display param and its value to globals table | |||
end | |||
else | |||
if keywords_t[v] == meta_param_map_t[k] then -- keywords_t[v] returns nil or the metaparam name; these must be the same | |||
global_cs1_config_t[meta_param_map_t[k]]=v; -- add the parameter and its value to globals table | |||
end | |||
end | |||
end | |||
end | |||
end | |||
end | |||
get_cs1_config (); -- fill <global_cs1_config_t> | |||
--[[---------------------< S T R I P M A R K E R S >---------------------------- | |||
Common pattern definition location for stripmarkers so that we don't have to go | |||
hunting for them if (when) MediaWiki changes their form. | |||
]] | |||
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 | 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 | } | ||
local invisible_chars = { | |||
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD | |||
{'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed | |||
{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B | |||
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A | |||
{'soft hyphen', '\194\173'}, -- U+00AD, C2 AD | |||
{'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 | |||
} | } | ||
--[[ | |||
-- | 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() | |||
]] | ]] | ||
local | 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 | |||
local | -- from: https://unicode.org/Public/emoji/15.0/emoji-zwj-sequences.txt; version: 15.0; 2022-05-06 | ||
-- table created by: [[:en:Module:Make emoji zwj table]] | |||
local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx | |||
[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 | |||
[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 | |||
[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 | |||
[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 | |||
[129657] = true, -- U+1FA79 🩹 adhesive bandage | |||
[129778] = true, -- U+1FAF2 🫲 leftwards hand | |||
} | |||
--[[--------------------< | --[[----------------------< L A N G U A G E S U P P O R T >------------------- | ||
These tables and constants support various language-specific functionality. | |||
language | |||
]] | ]] | ||
local | --local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code | ||
local this_wiki_code = lang_obj:getCode(); -- get this wiki's language code | |||
if string.match (mw.site.server, 'wikidata') then | |||
this_wiki_code = mw.getCurrentFrame():callParserFunction('int', {'lang'}); -- on Wikidata so use interface language setting instead | |||
end | |||
local 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 | |||
local mw_languages_by_name_t = {}; | |||
for k, v in pairs (mw_languages_by_tag_t) do -- build a 'reversed' table name/tag language pairs know to MediaWiki; used for |language= | |||
v = mw.ustring.lower (v); -- lowercase for tag fetch; get name's proper case from mw_languages_by_tag_t[<tag>] | |||
if mw_languages_by_name_t[v] then -- when name already in the table | |||
if 2 == #k or 3 == #k then -- if tag does not have subtags | |||
mw_languages_by_name_t[v] = k; -- prefer the shortest tag for this name | |||
end | |||
else -- here when name not in the table | |||
mw_languages_by_name_t[v] = k; -- so add name and matching tag | |||
end | |||
end | |||
-- | local inter_wiki_map = {}; -- map of interwiki prefixes that are language-code prefixes | ||
for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local) | |||
if mw_languages_by_tag_t[v["prefix"]] then -- if the prefix matches a known language tag | |||
inter_wiki_map[v["prefix"]] = true; -- add it to our local map | |||
end | |||
end | |||
--[[--------------------< S C R I P T _ L A N G _ C O D E S >------------------- | |||
This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character | |||
language codes that apply only to |script-title= and |script-chapter= | |||
]] | ]] | ||
local lang_code_remap = { -- used for |language= and |script-title= / |script-chapter= | local script_lang_codes = { | ||
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch | 'ab', 'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu', 'he', | ||
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org | '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' | |||
}; | |||
--[[---------------< 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 | ['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name | ||
['bn'] = 'Bengali', -- MediaWiki returns Bangla | ['bn'] = 'Bengali', -- MediaWiki returns Bangla | ||
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan | ['ca-valencia'] = 'Valencian', -- IETF variant of Catalan | ||
['fkv'] = 'Kven', -- MediaWiki returns Kvensk | |||
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name | ['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name | ||
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name | ['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name | ||
Line 964: | Line 1,171: | ||
} | } | ||
local lang_name_remap = { -- used for |language= | local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase | ||
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org | ['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 | ['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap | ||
Line 975: | Line 1,182: | ||
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö) | ['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 | ['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 | ['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639 | ||
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan- | ['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 | ['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found | ||
['valencian'] = {'Valencian', 'ca'}, | ['valencian'] = {'Valencian', 'ca-valencia'}, -- variant of Catalan; categorizes as Valencian | ||
} | } | ||
Line 994: | Line 1,203: | ||
['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 | ['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', | ['location-test'] = 'CS1 location test', | ||
['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 | ['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 ISO639-1 code | ['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code | ||
['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name | ['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name | ||
Line 1,009: | Line 1,218: | ||
local title_types = { | local title_types = { | ||
['AV-media-notes'] = 'Media notes', | ['AV-media-notes'] = 'Media notes', | ||
['document'] = 'Document', | |||
['interview'] = 'Interview', | ['interview'] = 'Interview', | ||
['mailinglist'] = 'Mailing list', | ['mailinglist'] = 'Mailing list', | ||
Line 1,089: | Line 1,299: | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_archive_date_missing_url = { | |||
message = '<code class="cs1-code">|archive-date=</code> requires <code class="cs1-code">|archive-url=</code>', | |||
anchor = 'archive_date_missing_url', | |||
category = 'CS1 errors: archive-url', | |||
hidden = false | |||
}, | |||
err_archive_date_url_ts_mismatch = { | |||
message = '<code class="cs1-code">|archive-date=</code> / <code class="cs1-code">|archive-url=</code> timestamp mismatch', | |||
anchor = 'archive_date_url_ts_mismatch', | |||
category = 'CS1 errors: archive-url', | |||
hidden = false | |||
}, | |||
err_archive_missing_date = { | err_archive_missing_date = { | ||
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|archive-date=</code>', | message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|archive-date=</code>', | ||
Line 1,207: | Line 1,429: | ||
anchor = 'bad_lccn', | anchor = 'bad_lccn', | ||
category = 'CS1 errors: LCCN', | category = 'CS1 errors: LCCN', | ||
hidden = false | |||
}, | |||
err_bad_medrxiv = { | |||
message = 'Check <code class="cs1-code">|medrxiv=</code> value', | |||
anchor = 'bad_medrxiv', | |||
category = 'CS1 errors: medRxiv', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,410: | Line 1,638: | ||
message = '<code class="cs1-code">|$1=</code> missing <code class="cs1-code">|$2=</code>', -- $1 is first alias, $2 is matching last alias | 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', | anchor = 'first_missing_last', | ||
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator | category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator | ||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,441: | Line 1,669: | ||
anchor = 'invisible_char', | anchor = 'invisible_char', | ||
category = 'CS1 errors: invisible characters', | category = 'CS1 errors: invisible characters', | ||
hidden = false | |||
}, | |||
err_medrxiv_missing = { | |||
message = '<code class="cs1-code">|medrxiv=</code> required', | |||
anchor = 'medrxiv_missing', | |||
category = 'CS1 errors: medRxiv', -- same as bad medRxiv | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,459: | Line 1,693: | ||
anchor = 'missing_pipe', | anchor = 'missing_pipe', | ||
category = 'CS1 errors: missing pipe', | category = 'CS1 errors: missing pipe', | ||
hidden = false | |||
}, | |||
err_missing_publisher = { | |||
message = 'Cite $1 requires <code class="cs1-code">|$2=</code>', -- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1 | |||
anchor = 'missing_publisher', | |||
category = 'CS1 errors: missing publisher', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,483: | Line 1,723: | ||
anchor = 'parameter_ignored_suggest', | anchor = 'parameter_ignored_suggest', | ||
category = 'CS1 errors: unsupported parameter', | category = 'CS1 errors: unsupported parameter', | ||
hidden = false | |||
}, | |||
err_periodical_ignored = { | |||
message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name | |||
anchor = 'periodical_ignored', | |||
category = 'CS1 errors: periodical ignored', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,500: | Line 1,746: | ||
message = '<code class="cs1-code">|ssrn=</code> required', | message = '<code class="cs1-code">|ssrn=</code> required', | ||
anchor = 'ssrn_missing', | anchor = 'ssrn_missing', | ||
category = 'CS1 errors: SSRN', | category = 'CS1 errors: SSRN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,552: | Line 1,798: | ||
anchor = 'authors', | anchor = 'authors', | ||
category = 'CS1 maint: uses authors parameter', | category = 'CS1 maint: uses authors parameter', | ||
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, | hidden = true, | ||
}, | }, | ||
Line 1,625: | Line 1,883: | ||
category = 'CS1 maint: location', | category = 'CS1 maint: location', | ||
hidden = true, | hidden = true, | ||
}, | |||
maint_mr_format = { | maint_mr_format = { | ||
message = nil, | message = nil, | ||
Line 1,631: | Line 1,889: | ||
category = 'CS1 maint: MR format', | category = 'CS1 maint: MR format', | ||
hidden = true, | hidden = true, | ||
}, | |||
maint_mult_names = { | maint_mult_names = { | ||
message = nil, | message = nil, | ||
Line 1,655: | Line 1,913: | ||
category = 'CS1 maint: others in cite AV media (notes)', | category = 'CS1 maint: others in cite AV media (notes)', | ||
hidden = true, | hidden = true, | ||
}, | }, | ||
maint_overridden_setting = { | |||
message = nil, | |||
anchor = 'overridden', | |||
category = 'CS1 maint: overridden setting', | |||
hidden = true, | |||
}, | |||
maint_pmc_embargo = { | maint_pmc_embargo = { | ||
message = nil, | message = nil, | ||
Line 1,723: | Line 1,987: | ||
redirect: a local redirect to a local Wikipedia article name; at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number' | 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 | q: Wikidata q number for the identifier | ||
label: the label | 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 | 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 | Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q | ||
Line 1,752: | Line 2,016: | ||
q = 'Q118398', | q = 'Q118398', | ||
label = 'arXiv', | label = 'arXiv', | ||
prefix = '//arxiv.org/abs/', | prefix = 'https://arxiv.org/abs/', | ||
encode = false, | encode = false, | ||
COinS = 'info:arxiv', | COinS = 'info:arxiv', | ||
Line 1,764: | Line 2,028: | ||
q = 'Q1753278', | q = 'Q1753278', | ||
label = 'ASIN', | label = 'ASIN', | ||
prefix = '//www.amazon.', | prefix = 'https://www.amazon.', | ||
COinS = 'url', | COinS = 'url', | ||
separator = ' ', | separator = ' ', | ||
Line 1,787: | Line 2,051: | ||
q = 'Q19835482', | q = 'Q19835482', | ||
label = 'bioRxiv', | label = 'bioRxiv', | ||
prefix = '//doi.org/', | prefix = 'https://doi.org/', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
Line 1,799: | Line 2,063: | ||
q = 'Q2715061', | q = 'Q2715061', | ||
label = 'CiteSeerX', | label = 'CiteSeerX', | ||
prefix = '//citeseerx.ist.psu.edu/viewdoc/summary?doi=', | prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
Line 1,811: | Line 2,075: | ||
q = 'Q25670', | q = 'Q25670', | ||
label = 'doi', | label = 'doi', | ||
prefix = '//doi.org/', | prefix = 'https://doi.org/', | ||
COinS = 'info:doi', | COinS = 'info:doi', | ||
separator = ':', | separator = ':', | ||
Line 1,823: | Line 2,087: | ||
q = 'Q46339674', | q = 'Q46339674', | ||
label = 'eISSN', | label = 'eISSN', | ||
prefix = '//www.worldcat.org/issn/', | prefix = 'https://www.worldcat.org/issn/', | ||
COinS = 'rft.eissn', | COinS = 'rft.eissn', | ||
encode = false, | encode = false, | ||
Line 1,834: | Line 2,098: | ||
q = 'Q3126718', | q = 'Q3126718', | ||
label = 'hdl', | label = 'hdl', | ||
prefix = '//hdl.handle.net/', | prefix = 'https://hdl.handle.net/', | ||
COinS = 'info:hdl', | COinS = 'info:hdl', | ||
separator = ':', | separator = ':', | ||
Line 1,866: | Line 2,130: | ||
q = 'Q131276', | q = 'Q131276', | ||
label = 'ISSN', | label = 'ISSN', | ||
prefix = '//www.worldcat.org/issn/', | prefix = 'https://www.worldcat.org/issn/', | ||
COinS = 'rft.issn', | COinS = 'rft.issn', | ||
encode = false, | encode = false, | ||
Line 1,877: | Line 2,141: | ||
q = '', | q = '', | ||
label = 'JFM', | label = 'JFM', | ||
prefix = '//zbmath.org/?format=complete&q=an:', | prefix = 'https://zbmath.org/?format=complete&q=an:', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
Line 1,888: | Line 2,152: | ||
q = 'Q1420342', | q = 'Q1420342', | ||
label = 'JSTOR', | label = 'JSTOR', | ||
prefix = '//www.jstor.org/stable/', | prefix = 'https://www.jstor.org/stable/', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = false, | encode = false, | ||
Line 1,900: | Line 2,164: | ||
q = 'Q620946', | q = 'Q620946', | ||
label = 'LCCN', | label = 'LCCN', | ||
prefix = '//lccn.loc.gov/', | prefix = 'https://lccn.loc.gov/', | ||
COinS = 'info:lccn', | COinS = 'info:lccn', | ||
encode = false, | |||
separator = ' ', | |||
}, | |||
['MEDRXIV'] = { | |||
parameters = {'medrxiv'}, | |||
link = 'medRxiv', | |||
redirect = 'medRxiv (identifier)', | |||
q = 'Q58465838', | |||
label = 'medRxiv', | |||
prefix = 'https://www.medrxiv.org/content/', | |||
COinS = 'pre', -- use prefix value | |||
access = 'free', -- free to read | |||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
Line 1,911: | Line 2,187: | ||
q = 'Q211172', | q = 'Q211172', | ||
label = 'MR', | label = 'MR', | ||
prefix = '// | prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
Line 1,922: | Line 2,198: | ||
q = 'Q190593', | q = 'Q190593', | ||
label = 'OCLC', | label = 'OCLC', | ||
prefix = '//www.worldcat.org/oclc/', | prefix = 'https://www.worldcat.org/oclc/', | ||
COinS = 'info:oclcnum', | COinS = 'info:oclcnum', | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 10030000000, | ||
}, | }, | ||
['OL'] = { | ['OL'] = { | ||
Line 1,934: | Line 2,210: | ||
q = 'Q1201876', | q = 'Q1201876', | ||
label = 'OL', | label = 'OL', | ||
prefix = '//openlibrary.org/', | prefix = 'https://openlibrary.org/', | ||
COinS = 'url', | COinS = 'url', | ||
separator = ' ', | separator = ' ', | ||
Line 1,946: | Line 2,222: | ||
q = 'Q2015776', | q = 'Q2015776', | ||
label = 'OSTI', | label = 'OSTI', | ||
prefix = '//www.osti.gov/biblio/', | prefix = 'https://www.osti.gov/biblio/', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
Line 1,959: | Line 2,235: | ||
q = 'Q229883', | q = 'Q229883', | ||
label = 'PMC', | label = 'PMC', | ||
prefix = '//www.ncbi.nlm.nih.gov/pmc/articles/PMC', | prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC', | ||
suffix = '', | suffix = '', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 10700000, | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
}, | }, | ||
Line 1,973: | Line 2,249: | ||
q = 'Q2082879', | q = 'Q2082879', | ||
label = 'PMID', | label = 'PMID', | ||
prefix = '//pubmed.ncbi.nlm.nih.gov/', | prefix = 'https://pubmed.ncbi.nlm.nih.gov/', | ||
COinS = 'info:pmid', | COinS = 'info:pmid', | ||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 38400000, | ||
}, | }, | ||
['RFC'] = { | ['RFC'] = { | ||
Line 1,985: | Line 2,261: | ||
q = 'Q212971', | q = 'Q212971', | ||
label = 'RFC', | label = 'RFC', | ||
prefix = '//tools.ietf.org/html/rfc', | prefix = 'https://tools.ietf.org/html/rfc', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = false, | encode = false, | ||
Line 2,007: | Line 2,283: | ||
q = 'Q7550801', | q = 'Q7550801', | ||
label = 'SSRN', | label = 'SSRN', | ||
prefix = '//ssrn.com/ | prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 4600000, | ||
custom_access = 'ssrn-access', | custom_access = 'ssrn-access', | ||
}, | }, | ||
Line 2,024: | Line 2,300: | ||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 266000000, | ||
custom_access = 's2cid-access', | custom_access = 's2cid-access', | ||
}, | }, | ||
Line 2,044: | Line 2,320: | ||
q = 'Q190269', | q = 'Q190269', | ||
label = 'Zbl', | label = 'Zbl', | ||
prefix = '//zbmath.org/?format=complete&q=an:', | prefix = 'https://zbmath.org/?format=complete&q=an:', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
Line 2,056: | Line 2,332: | ||
return { | return { | ||
use_identifier_redirects = | use_identifier_redirects = use_identifier_redirects, -- booleans defined in the settings at the top of this module | ||
local_lang_cat_enable = | local_lang_cat_enable = local_lang_cat_enable, | ||
date_name_auto_xlate_enable = | date_name_auto_xlate_enable = date_name_auto_xlate_enable, | ||
date_digit_auto_xlate_enable = | date_digit_auto_xlate_enable = date_digit_auto_xlate_enable, | ||
global_df = get_date_format (), -- | -- tables and variables created when this module is loaded | ||
global_df = get_date_format (), -- this line can be replaced with "global_df = 'dmy-all'," to have all dates auto translated to dmy format. | |||
global_cs1_config_t = global_cs1_config_t, -- global settings from {{cs1 config}} | |||
punct_skip = build_skip_table (punct_skip, punct_meta_params), | punct_skip = build_skip_table (punct_skip, punct_meta_params), | ||
url_skip = build_skip_table (url_skip, url_meta_params), | url_skip = build_skip_table (url_skip, url_meta_params), | ||
Line 2,075: | Line 2,353: | ||
keywords_lists = keywords_lists, | keywords_lists = keywords_lists, | ||
keywords_xlate = keywords_xlate, | keywords_xlate = keywords_xlate, | ||
stripmarkers=stripmarkers, | stripmarkers = stripmarkers, | ||
invisible_chars = invisible_chars, | invisible_chars = invisible_chars, | ||
invisible_defs = invisible_defs, | invisible_defs = invisible_defs, | ||
indic_script = indic_script, | indic_script = indic_script, | ||
emoji_t = emoji_t, | |||
maint_cats = maint_cats, | maint_cats = maint_cats, | ||
messages = messages, | messages = messages, | ||
Line 2,086: | Line 2,363: | ||
prop_cats = prop_cats, | prop_cats = prop_cats, | ||
script_lang_codes = script_lang_codes, | script_lang_codes = script_lang_codes, | ||
lang_tag_remap = lang_tag_remap, | |||
lang_name_remap = lang_name_remap, | lang_name_remap = lang_name_remap, | ||
this_wiki_code = this_wiki_code, | this_wiki_code = this_wiki_code, | ||
title_types = title_types, | title_types = title_types, | ||
uncategorized_namespaces = | uncategorized_namespaces = uncategorized_namespaces_t, | ||
uncategorized_subpages = uncategorized_subpages, | uncategorized_subpages = uncategorized_subpages, | ||
templates_using_volume = templates_using_volume, | templates_using_volume = templates_using_volume, | ||
Line 2,096: | Line 2,373: | ||
templates_not_using_page = templates_not_using_page, | templates_not_using_page = templates_not_using_page, | ||
vol_iss_pg_patterns = vol_iss_pg_patterns, | 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, | inter_wiki_map = inter_wiki_map, | ||
Line 2,101: | Line 2,379: | ||
mw_languages_by_name_t = mw_languages_by_name_t, | mw_languages_by_name_t = mw_languages_by_name_t, | ||
citation_class_map_t = citation_class_map_t, | citation_class_map_t = citation_class_map_t, | ||
citation_issue_t = citation_issue_t, | |||
citation_no_volume_t = citation_no_volume_t, | |||
} | } |