Module:Citation/CS1/Configuration: Difference between revisions
m
1 revision imported
Johnrdorazio (talk | contribs) m (1 revision imported) |
Johnrdorazio (talk | contribs) m (1 revision imported) |
||
(5 intermediate revisions by 2 users not shown) | |||
Line 1: | Line 1: | ||
local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates | |||
--[[--------------------------< 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 29: | Line 34: | ||
['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-missing'] = 'Archived from the original$1 on $2', | ['archived-missing'] = 'Archived from the original $1 on $2', | ||
['archived-unfit'] = 'Archived from the original on ', | ['archived-unfit'] = 'Archived from the original on ', | ||
['archived'] = 'Archived', | ['archived'] = 'Archived', | ||
Line 44: | Line 49: | ||
['interview'] = 'Interviewed by $1', | ['interview'] = 'Interviewed by $1', | ||
['lay summary'] = 'Lay summary', | ['lay summary'] = 'Lay summary', | ||
['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', | ||
['notitle'] = 'No title', -- for |title=(()) and (in the future) |title=none | |||
['notitle'] = 'No title', -- for |title=(()) and (in the future) |title=none | |||
['original'] = 'the original', | ['original'] = 'the original', | ||
['origdate'] = ' [$1]', | ['origdate'] = ' [$1]', | ||
Line 61: | Line 66: | ||
['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 93: | Line 102: | ||
-- Internal errors (should only occur if configuration is bad) | -- Internal errors (should only occur if configuration is bad) | ||
['undefined_error'] = 'Called with an undefined error condition', | ['undefined_error'] = 'Called with an undefined error condition', | ||
['unknown_ID_key'] = 'Unrecognized ID key', | ['unknown_ID_key'] = 'Unrecognized ID key: ', -- an ID key in id_handlers not found in ~/Identifiers func_map{} | ||
['unknown_ID_access'] = 'Unrecognized ID access keyword: ', -- an ID access keyword in id_handlers not found in keywords_lists['id-access']{} | |||
['unknown_argument_map'] = 'Argument map not defined for this variable', | ['unknown_argument_map'] = 'Argument map not defined for this variable', | ||
['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty', | ['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty', | ||
['warning_msg_e'] = '<span style="color:#d33">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code> templates have errors</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link | |||
['warning_msg_m'] = '<span style="color:#3a3">One or more <code style="color: inherit; background: inherit; border: none; padding: inherit;">{{$1}}</code> templates have maintenance messages</span>; messages may be hidden ([[Help:CS1_errors#Controlling_error_message_display|help]]).'; -- $1 is template link | |||
} | } | ||
--[[--------------------------< C I T A T I O N _ C L A S S _ M A P >------------------------------------------ | |||
this table maps the value assigned to |CitationClass= in the cs1|2 templates to the canonical template name when | |||
the value assigned to |CitationClass= is different from the canonical template name. |CitationClass= values are | |||
used as class attributes in the <cite> tag that encloses the citation so these names may not contain spaces while | |||
the canonical template name may. These names are used in warning_msg_e and warning_msg_m to create links to the | |||
template's documentation when an article is displayed in preview mode. | |||
Most cs1|2 template |CitationClass= values at en.wiki match their canonical template names so are not listed here. | |||
]] | |||
local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n | |||
['audio-visual'] = 'AV media', | |||
['AV-media-notes'] = 'AV media notes', | |||
['encyclopaedia'] = 'encyclopedia', | |||
['mailinglist'] = 'mailing list', | |||
['pressrelease'] = 'press release' | |||
} | |||
Line 107: | Line 141: | ||
local et_al_patterns = { | local et_al_patterns = { | ||
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$", -- 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 149: | Line 159: | ||
local presentation = | local presentation = | ||
{ | { | ||
-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display | -- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display | ||
['hidden-error'] = '<span class="cs1-hidden- | ['hidden-error'] = '<span class="cs1-hidden-error citation-comment">$1</span>', | ||
['visible-error'] = '<span class="cs1-visible- | ['visible-error'] = '<span class="cs1-visible-error citation-comment">$1</span>', | ||
['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>', | ['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>', | ||
Line 160: | Line 168: | ||
['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like | ['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like | ||
['cite'] = '<cite class="$1">$2</cite>'; -- |ref= not set so no id="..." attribute | ['cite'] = '<cite class="$1">$2</cite>'; -- for use when citation does not have a namelist and |ref= not set so no id="..." attribute | ||
['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when |ref= is set | ['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when when |ref= is set or when citation has a namelist | ||
['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc. | ['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 179: | Line 189: | ||
['italic-title'] = "''$1''", | ['italic-title'] = "''$1''", | ||
['kern-left'] = '<span class="cs1-kern-left"> | ['kern-left'] = '<span class="cs1-kern-left"></span>$1', -- spacing to use when title contains leading single or double quote mark | ||
['kern-right'] = '$1<span class="cs1-kern-right"> | ['kern-right'] = '$1<span class="cs1-kern-right"></span>', -- spacing to use when title contains trailing single or double quote mark | ||
['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span> | ['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span> | ||
Line 194: | Line 198: | ||
['parameter'] = '<code class="cs1-code">|$1=</code>', | ['parameter'] = '<code class="cs1-code">|$1=</code>', | ||
['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character | ['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character | ||
['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string) | ['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string) | ||
Line 235: | Line 239: | ||
['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 243: | Line 248: | ||
['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format', | ['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format', | ||
'article-format', 'section-format'}; | 'article-format', 'section-format'}; | ||
['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', | ['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url', 'section-url', 'chapterurl'}, -- Used by InternetArchiveBot | ||
['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access', | ['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access', | ||
'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot | 'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot | ||
['Class'] = 'class', -- cite arxiv and arxiv | ['Class'] = 'class', -- cite arxiv and arxiv identifier | ||
['Collaboration'] = 'collaboration', | ['Collaboration'] = 'collaboration', | ||
['Conference'] = {'conference', 'event'}, | ['Conference'] = {'conference', 'event'}, | ||
['ConferenceFormat'] = 'conference-format', | ['ConferenceFormat'] = 'conference-format', | ||
['ConferenceURL'] = | ['ConferenceURL'] = 'conference-url', -- Used by InternetArchiveBot | ||
['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only | ['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only | ||
['Degree'] = 'degree', | ['Degree'] = 'degree', | ||
Line 271: | Line 275: | ||
['Issue'] = {'issue', 'number'}, | ['Issue'] = {'issue', 'number'}, | ||
['Language'] = {'language', 'lang'}, | ['Language'] = {'language', 'lang'}, | ||
['LayDate'] = | ['LayDate'] = 'lay-date', | ||
['LayFormat'] = 'lay-format', | ['LayFormat'] = 'lay-format', | ||
['LaySource'] = | ['LaySource'] = 'lay-source', | ||
['LayURL'] = | ['LayURL'] = 'lay-url', | ||
['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 282: | Line 286: | ||
['Minutes'] = 'minutes', | ['Minutes'] = 'minutes', | ||
['Mode'] = 'mode', | ['Mode'] = 'mode', | ||
['NameListStyle'] = | ['NameListStyle'] = 'name-list-style', | ||
['Network'] = 'network', | ['Network'] = 'network', | ||
['Newsgroup'] = 'newsgroup', -- cite newsgroup only | ['Newsgroup'] = 'newsgroup', -- cite newsgroup only | ||
Line 314: | Line 318: | ||
['Series'] = {'series', 'version'}, | ['Series'] = {'series', 'version'}, | ||
['SeriesLink'] = {'series-link', 'serieslink'}, | ['SeriesLink'] = {'series-link', 'serieslink'}, | ||
['SeriesNumber'] = {'series-number', 'series-no | ['SeriesNumber'] = {'series-number', 'series-no'}, | ||
['Sheet'] = 'sheet', -- cite map only | ['Sheet'] = 'sheet', -- cite map only | ||
['Sheets'] = 'sheets', -- cite map only | ['Sheets'] = 'sheets', -- cite map only | ||
['Station'] = 'station', | ['Station'] = 'station', | ||
['Time'] = 'time', | ['Time'] = 'time', | ||
['TimeCaption'] = | ['TimeCaption'] = 'time-caption', | ||
['Title'] = 'title', -- Used by InternetArchiveBot | ['Title'] = 'title', -- Used by InternetArchiveBot | ||
['TitleLink'] = {'title-link', 'episode-link | ['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot | ||
['TitleNote'] = 'department', | ['TitleNote'] = 'department', | ||
['TitleType'] = {'type', 'medium'}, | ['TitleType'] = {'type', 'medium'}, | ||
Line 386: | Line 390: | ||
]] | ]] | ||
local | local punct_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value | ||
'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters | 'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters | ||
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | 'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | ||
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', | 'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous | ||
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'LayURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters | 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'LayURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters | ||
} | } | ||
local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value | |||
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'LayURL', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls | |||
'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls | |||
} | |||
local function build_skip_table (skip_t, meta_params) | |||
for _, meta_param in ipairs (meta_params) do -- for each meta parameter key | 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 | local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name | ||
if 'string' == type (params) then | if 'string' == type (params) then | ||
skip_t[params] = 1; -- just a single parameter | |||
else | else | ||
for _, param in ipairs (params) do -- get the parameter name | for _, param in ipairs (params) do -- get the parameter name | ||
skip_t[param] = 1; -- add the parameter name to the skip table | |||
local count; | local count; | ||
param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters | param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters | ||
if 0 ~= count then -- if removed | if 0 ~= count then -- if removed | ||
skip_t[param] = 1; -- add param name without enumerator marker | |||
end | end | ||
end | end | ||
end | end | ||
end | end | ||
return skip_t; | |||
end | |||
local punct_skip = {}; | |||
local url_skip = {}; | |||
--[[--------------------------< S I N G L E - L E T T E R S E C O N D - L E V E L D O M A I N S >---------- | |||
this is a list of tlds that are known to have single-letter second-level domain names. This list does not include | |||
ccTLDs which are accepted in is_domain_name(). | |||
]] | |||
local single_letter_2nd_lvl_domains_t = {'cash', 'company', 'foundation', 'org', 'today'}; | |||
--[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------ | --[[-----------< S P E C I A L C A S E T R A N S L A T I O N S >------------ | ||
Line 419: | Line 443: | ||
]] | ]] | ||
local is_Latn = 'A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143'; | |||
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() | ||
['TranslatorList'] = 'translators list', | ['TranslatorList'] = 'translators list', | ||
-- Lua patterns to match pseudo-titles used by InternetArchiveBot and others as placeholder for unknown |title= value | |||
-- Lua patterns to match pseudo-titles used by | |||
['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title | ['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title | ||
['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki | ['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki | ||
Line 439: | Line 457: | ||
}, | }, | ||
-- Lua patterns to match generic titles; usually created by bots | -- Lua patterns to match generic titles; usually created by bots or reference filling tools | ||
-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language | -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language | ||
-- generic titles and patterns in this table should be lowercase only | |||
-- leave ['local'] nil except when there is a matching generic title in your language | |||
-- boolean 'true' for plain-text searches; 'false' for pattern searches | |||
['generic_titles'] = { | ['generic_titles'] = { | ||
['accept'] = { | |||
}, | |||
['reject'] = { | |||
{['en'] = {'^wayback%s+machine$', 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'] = {' | {['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'] = { | |||
['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 470: | Line 551: | ||
which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard | which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard | ||
defines various divisions using numbers 21-41. CS1|2 only supports generic seasons. | defines various divisions using numbers 21-41. CS1|2 only supports generic seasons. | ||
EDTF does support the distinction between north and south | EDTF does support the distinction between north and south hemisphere seasons | ||
but CS1|2 has no way to make that distinction. | but CS1|2 has no way to make that distinction. | ||
Line 478: | Line 559: | ||
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 489: | Line 583: | ||
['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 496: | Line 591: | ||
['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 | if local_date_names_from_mediawiki then -- if fetching local month names from MediaWiki is enabled | ||
date_names[' | 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 | end | ||
-- create inverted date-name tables for reformatting and/or translation | |||
for name, i in pairs (date_names['local'] | 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 | ||
Line 531: | Line 640: | ||
local function get_date_format () | local function get_date_format () | ||
local | local title_object = mw.title.getCurrentTitle(); | ||
if title_object.namespace == 10 then -- not in template space so that unused templates appear in unused-template-reports; | |||
return nil; -- auto-formatting does not work in Template space so don't set global_df | |||
end | |||
local 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 | |||
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 | ||
Line 545: | Line 658: | ||
end | end | ||
local global_df | local global_df; | ||
Line 560: | Line 673: | ||
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'} | ||
--[[ | |||
--[[--------------------------< K E Y W O R D S >------------------------------- | These tables control when it is appropriate for {{citation}} to render |volume= and/or |issue=. The parameter | ||
names in the tables constrain {{citation}} so that its renderings match the renderings of the equivalent cs1 | |||
templates. For example, {{cite web}} does not support |volume= so the equivalent {{citation |website=...}} must | |||
not support |volume=. | |||
]] | |||
local citation_no_volume_t = { -- {{citation}} does not render |volume= when these parameters are used | |||
'website', 'mailinglist', 'script-website', | |||
} | |||
local citation_issue_t = { -- {{citation}} may render |issue= when these parameters are used | |||
'journal', 'magazine', 'newspaper', 'periodical', 'work', | |||
'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work', | |||
} | |||
--[[ | |||
Patterns for finding extra text in |volume=, |issue=, |page=, |pages= | |||
]] | |||
local vol_iss_pg_patterns = { | |||
good_ppattern = '^P[^%.PpGg]', -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123); TODO: this allows 'Pages' which it should not | |||
bad_ppatterns = { -- patterns for |page= and |pages= | |||
'^[Pp][PpGg]?%.?[ %d]', | |||
'^[Pp][Pp]?%. ', -- from {{p.}} and {{pp.}} templates | |||
'^[Pp]ages?', | |||
'^[Pp]gs.?', | |||
}, | |||
vpatterns = { -- patterns for |volume= | |||
'^volumes?', | |||
'^vols?[%.:=]?' | |||
}, | |||
ipatterns = { -- patterns for |issue= | |||
'^issues?', | |||
'^iss[%.:=]?', | |||
'^numbers?', | |||
'^nos?%A', -- don't match 'november' or 'nostradamus' | |||
'^nr[%.:=]?', | |||
'^n[%.:= ]' -- might be a valid issue without separator (space char is sep char here) | |||
} | |||
} | |||
--[[--------------------------< K E Y W O R D S >------------------------------- | |||
These tables hold keywords for those parameters that have defined sets of acceptable keywords. | These tables hold keywords for those parameters that have defined sets of acceptable keywords. | ||
Line 589: | Line 746: | ||
['cs1'] = {'cs1'}, -- |mode= | ['cs1'] = {'cs1'}, -- |mode= | ||
['cs2'] = {'cs2'}, -- |mode= | ['cs2'] = {'cs2'}, -- |mode= | ||
['dead'] = {'dead'}, | ['dead'] = {'dead', 'deviated'}, -- |url-status= -- Used by InternetArchiveBot | ||
['dmy'] = {'dmy'}, -- |df= | ['dmy'] = {'dmy'}, -- |df= | ||
['dmy-all'] = {'dmy-all'}, -- |df= | ['dmy-all'] = {'dmy-all'}, -- |df= | ||
['foreword'] = {'foreword'}, -- |contribution= | ['foreword'] = {'foreword'}, -- |contribution= | ||
['free'] = {'free'}, -- | | ['free'] = {'free'}, -- |<id>-access= -- Used by InternetArchiveBot | ||
['harv'] = {'harv'}, -- |ref=; this no longer supported; is_valid_parameter_value() called with <invert> = true | |||
['introduction'] = {'introduction'}, -- |contribution= | ['introduction'] = {'introduction'}, -- |contribution= | ||
['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot | ['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot | ||
Line 609: | Line 767: | ||
['ymd'] = {'ymd'}, -- |df= | ['ymd'] = {'ymd'}, -- |df= | ||
['ymd-all'] = {'ymd-all'}, -- |df= | ['ymd-all'] = {'ymd-all'}, -- |df= | ||
-- ['yMd'] = {'yMd'}, | -- ['yMd'] = {'yMd'}, -- |df=; not supported at en.wiki | ||
-- ['yMd-all'] = {'yMd-all'}, | -- ['yMd-all'] = {'yMd-all'}, -- |df=; not supported at en.wiki | ||
} | } | ||
Line 682: | Line 840: | ||
['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}), | ['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']}), | ||
-- ['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 | -- ['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}), | ['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}), | ||
['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}), | ['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}), | ||
['ref'] = make_keywords_list ({keywords.harv}), -- inverted check; |ref=harv no longer supported | |||
['url-access'] = make_keywords_list ({keywords.subscription, keywords.limited, keywords.registration}), | ['url-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']}), | ['url-status'] = make_keywords_list ({keywords.dead, keywords.live, keywords.unfit, keywords.usurped, keywords['bot: unknown']}), | ||
Line 719: | Line 878: | ||
]] | ]] | ||
local invisible_defs = { | |||
del = '\127', -- used to distinguish between stripmarker and del char | |||
zwj = '\226\128\141', -- used with capture because zwj may be allowed | |||
} | |||
local invisible_chars = { | local invisible_chars = { | ||
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD | {'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD | ||
{'zero width joiner', ' | {'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 | {'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B | ||
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A | {'hair space', '\226\128\138'}, -- U+200A, E2 80 8A | ||
Line 731: | Line 895: | ||
{'carriage return', '\013'}, -- U+000D (CR), 0D | {'carriage return', '\013'}, -- U+000D (CR), 0D | ||
{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type | {'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type | ||
{'delete', ' | {'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)) | {'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 | {'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 | -- {'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 | -- {'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-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 | -- {'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 | 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 | characters must be left in. This pattern covers all of the unicode characters | ||
Line 760: | Line 925: | ||
Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf | Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf | ||
the pattern is used by has_invisible_chars() and coins_cleanup() | the pattern is used by has_invisible_chars() and coins_cleanup() | ||
]] | ]] | ||
local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]'; | local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]'; | ||
-- list of emoji that use a zwj character (U+200D) to combine with another emoji | |||
-- from: https://unicode.org/Public/emoji/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 | |||
} | |||
Line 774: | Line 991: | ||
]] | ]] | ||
local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code | --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():preprocess('{{int:lang}}'); -- on Wikidata so use interface language setting instead | this_wiki_code = mw.getCurrentFrame():preprocess('{{int:lang}}'); -- on Wikidata so use interface language setting instead | ||
end | end | ||
local | 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 | 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) | for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local) | ||
if | 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 | inter_wiki_map[v["prefix"]] = true; -- add it to our local map | ||
end | end | ||
end | end | ||
Line 799: | Line 1,026: | ||
local script_lang_codes = { | local script_lang_codes = { | ||
'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu', | 'ab', 'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu', | ||
'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo', | 'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo', 'mk', | ||
'ml', 'mn', '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' | ||
}; | }; | ||
Line 832: | Line 1,059: | ||
['bn'] = 'Bengali', -- MediaWiki returns Bangla | ['bn'] = 'Bengali', -- MediaWiki returns Bangla | ||
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan | ['ca-valencia'] = 'Valencian', -- IETF variant of Catalan | ||
['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 840: | Line 1,066: | ||
} | } | ||
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 848: | Line 1,074: | ||
['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name | ['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name | ||
['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh | ['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh | ||
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name | ['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name | ||
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö) | ['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 | ||
['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-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese | |||
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan- | |||
['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 867: | Line 1,091: | ||
local prop_cats = { | 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 | ||
[' | ['jul-greg-uncertainty'] = 'CS1: Julian–Gregorian uncertainty', -- probably temporary cat to identify scope of template with dates 1 October 1582 – 1 January 1926 | ||
['location test'] = 'CS1 location test', | ['local-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false | ||
[' | ['location-test'] = 'CS1 location test', | ||
[' | ['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters | ||
[' | ['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code | ||
[' | ['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name | ||
['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form | |||
} | } | ||
Line 893: | Line 1,117: | ||
['pressrelease'] = 'Press release', | ['pressrelease'] = 'Press release', | ||
['report'] = 'Report', | ['report'] = 'Report', | ||
['speech'] = 'Speech', | |||
['techreport'] = 'Technical report', | ['techreport'] = 'Technical report', | ||
['thesis'] = 'Thesis', | ['thesis'] = 'Thesis', | ||
Line 916: | Line 1,141: | ||
['group'] = 'invalid group id', -- |isbn= | ['group'] = 'invalid group id', -- |isbn= | ||
['initials'] = 'initials', -- Vancouver | ['initials'] = 'initials', -- Vancouver | ||
['invalid language code'] = 'invalid language code', -- |script-<param>= | |||
['journal'] = 'journal', -- |bibcode= | ['journal'] = 'journal', -- |bibcode= | ||
['length'] = 'length', -- |isbn=, |bibcode=, |sbn= | ['length'] = 'length', -- |isbn=, |bibcode=, |sbn= | ||
['liveweb'] = 'liveweb', -- |archive-url= | ['liveweb'] = 'liveweb', -- |archive-url= | ||
['missing comma'] = 'missing comma', -- Vancouver | ['missing comma'] = 'missing comma', -- Vancouver | ||
['missing prefix'] = 'missing prefix', -- |script-<param>= | |||
['missing title part'] = 'missing title part', -- |script-<param>= | |||
['name'] = 'name', -- Vancouver | ['name'] = 'name', -- Vancouver | ||
['non-Latin char'] = 'non-Latin character', -- Vancouver | ['non-Latin char'] = 'non-Latin character', -- Vancouver | ||
Line 928: | Line 1,156: | ||
['suffix'] = 'suffix', -- Vancouver | ['suffix'] = 'suffix', -- Vancouver | ||
['timestamp'] = 'timestamp', -- |archive-url= | ['timestamp'] = 'timestamp', -- |archive-url= | ||
['unknown language code'] = 'unknown language code', -- |script-<param>= | |||
['value'] = 'value', -- |bibcode= | ['value'] = 'value', -- |bibcode= | ||
['year'] = 'year', -- |bibcode= | ['year'] = 'year', -- |bibcode= | ||
Line 984: | Line 1,213: | ||
anchor = 'arxiv_missing', | anchor = 'arxiv_missing', | ||
category = 'CS1 errors: arXiv', -- same as bad arxiv | category = 'CS1 errors: arXiv', -- same as bad arxiv | ||
hidden = false | |||
}, | |||
err_asintld_missing_asin = { | |||
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|asin=</code>', -- $1 is parameter name | |||
anchor = 'asintld_missing_asin', | |||
category = 'CS1 errors: ASIN TLD', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 996: | Line 1,231: | ||
anchor = 'bad_asin', | anchor = 'bad_asin', | ||
category ='CS1 errors: ASIN', | category ='CS1 errors: ASIN', | ||
hidden = false | |||
}, | |||
err_bad_asin_tld = { | |||
message = 'Check <code class="cs1-code">|asin-tld=</code> value', | |||
anchor = 'bad_asin_tld', | |||
category ='CS1 errors: ASIN TLD', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,215: | Line 1,456: | ||
}, | }, | ||
err_disp_name = { | err_disp_name = { | ||
message = 'Invalid <code class="cs1-code">| | message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name; $2 is the assigned value | ||
anchor = 'disp_name', | anchor = 'disp_name', | ||
category = 'CS1 errors: display-names', | category = 'CS1 errors: display-names', | ||
Line 1,224: | Line 1,465: | ||
anchor = 'doibroken_missing_doi', | anchor = 'doibroken_missing_doi', | ||
category = 'CS1 errors: DOI', | category = 'CS1 errors: DOI', | ||
hidden = false | |||
}, | |||
err_embargo_missing_pmc = { | |||
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|pmc=</code>', -- $1 is parameter name | |||
anchor = 'embargo_missing_pmc', | |||
category = 'CS1 errors: PMC embargo', | |||
hidden = false | hidden = false | ||
}, | }, | ||
Line 1,244: | Line 1,491: | ||
hidden = false, | hidden = false, | ||
}, | }, | ||
err_extra_text_issue = { | |||
message = '<code class="cs1-code">| | message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name | ||
anchor = 'extra_text_issue', | |||
category = 'CS1 errors: extra text: issue', | |||
hidden = false, | |||
}, | |||
err_extra_text_pages = { | |||
message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name | |||
anchor = 'extra_text_pages', | anchor = 'extra_text_pages', | ||
category = 'CS1 errors: extra text: pages', | category = 'CS1 errors: extra text: pages', | ||
hidden = false, | hidden = false, | ||
}, | |||
err_extra_text_volume = { | |||
message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name | |||
anchor = 'extra_text_volume', | |||
category = 'CS1 errors: extra text: volume', | |||
hidden = true, | |||
}, | }, | ||
err_first_missing_last = { | err_first_missing_last = { | ||
message = '<code class="cs1-code">|$1=</code> missing <code class="cs1-code">|$2=</code>', -- $1 is first alias, $2 is matching last alias | 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 1,261: | Line 1,520: | ||
category = 'CS1 errors: format without URL', | category = 'CS1 errors: format without URL', | ||
hidden = false | hidden = false | ||
}, | |||
err_generic_name = { | |||
message = '<code class="cs1-code">|$1=</code> has generic name', -- $1 is parameter name | |||
anchor = 'generic_name', | |||
category = 'CS1 errors: generic name', | |||
hidden = false, | |||
}, | }, | ||
err_generic_title = { | err_generic_title = { | ||
Line 1,347: | Line 1,612: | ||
}, | }, | ||
err_trans_missing_title = { | err_trans_missing_title = { | ||
message = '<code class="cs1-code">|trans-$1=</code> requires <code class="cs1-code">|$1=</code> or | message = '<code class="cs1-code">|trans-$1=</code> requires <code class="cs1-code">|$1=</code> or <code class="cs1-code">|script-$1=</code>', -- $1 is base parameter name | ||
anchor = 'trans_missing_title', | anchor = 'trans_missing_title', | ||
category = 'CS1 errors: translated title', | category = 'CS1 errors: translated title', | ||
Line 1,353: | Line 1,618: | ||
}, | }, | ||
err_param_unknown_empty = { | err_param_unknown_empty = { | ||
message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is | message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is empty unknown param list | ||
anchor = 'param_unknown_empty', | anchor = 'param_unknown_empty', | ||
category = 'CS1 errors: empty unknown parameters', | category = 'CS1 errors: empty unknown parameters', | ||
Line 1,359: | Line 1,624: | ||
}, | }, | ||
err_vancouver = { | err_vancouver = { | ||
message = 'Vancouver style error: $1', | message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name | ||
anchor = 'vancouver', | anchor = 'vancouver', | ||
category = 'CS1 errors: Vancouver style', | category = 'CS1 errors: Vancouver style', | ||
Line 1,378: | Line 1,643: | ||
]] | ]] | ||
maint_archived_copy = { | maint_archived_copy = { | ||
message = nil, | message = nil, | ||
Line 1,400: | Line 1,660: | ||
anchor = 'bot:_unknown', | anchor = 'bot:_unknown', | ||
category = 'CS1 maint: bot: original URL status unknown', | category = 'CS1 maint: bot: original URL status unknown', | ||
hidden = true, | |||
}, | |||
maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki | |||
message = nil, | |||
anchor = 'date_auto_xlated', | |||
category = 'CS1 maint: date auto-translated', | |||
hidden = true, | hidden = true, | ||
}, | }, | ||
Line 1,436: | Line 1,702: | ||
anchor = 'extra_punct', | anchor = 'extra_punct', | ||
category = 'CS1 maint: extra punctuation', | category = 'CS1 maint: extra punctuation', | ||
hidden = true, | hidden = true, | ||
}, | }, | ||
Line 1,490: | Line 1,750: | ||
anchor = 'others', | anchor = 'others', | ||
category = 'CS1 maint: others', | category = 'CS1 maint: others', | ||
hidden = true, | |||
}, | |||
maint_others_avm = { | |||
message = nil, | |||
anchor = 'others_avm', | |||
category = 'CS1 maint: others in cite AV media (notes)', | |||
hidden = true, | hidden = true, | ||
}, | }, | ||
Line 1,504: | Line 1,770: | ||
hidden = true, | hidden = true, | ||
}, | }, | ||
maint_postscript = { | |||
message = nil, | |||
anchor = 'postscript', | |||
category = 'CS1 maint: postscript', | |||
hidden = true, | |||
}, | |||
maint_ref_duplicates_default = { | |||
message = nil, | message = nil, | ||
anchor = ' | anchor = 'ref_default', | ||
category = 'CS1 maint: ref | category = 'CS1 maint: ref duplicates default', | ||
hidden = true, | hidden = true, | ||
}, | |||
maint_unfit = { | maint_unfit = { | ||
message = nil, | message = nil, | ||
Line 1,526: | Line 1,798: | ||
anchor = 'untitled', | anchor = 'untitled', | ||
category = 'CS1 maint: untitled periodical', | category = 'CS1 maint: untitled periodical', | ||
hidden = true, | |||
}, | |||
maint_url_status = { | |||
message = nil, | |||
anchor = 'url_status', | |||
category = 'CS1 maint: url-status', | |||
hidden = true, | hidden = true, | ||
}, | }, | ||
Line 1,547: | Line 1,825: | ||
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 1,555: | Line 1,833: | ||
encode: true if URI should be percent-encoded; otherwise false | encode: true if URI should be percent-encoded; otherwise false | ||
COinS: identifier link or keyword for use in COinS: | COinS: identifier link or keyword for use in COinS: | ||
for identifiers registered at info-uri.info use: info:.... | for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label | ||
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn | for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn | ||
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info' or ' | for |asin= and |ol=, which require assembly, use the keyword: url | ||
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here) | |||
set to nil to leave the identifier out of the COinS | set to nil to leave the identifier out of the COinS | ||
separator: character or text between label and the identifier in the rendered citation | separator: character or text between label and the identifier in the rendered citation | ||
Line 1,565: | Line 1,844: | ||
custom_access: to enable custom access level for an identifier, set this parameter | custom_access: to enable custom access level for an identifier, set this parameter | ||
to the parameter that should control it (normally 'id-access') | to the parameter that should control it (normally 'id-access') | ||
]] | ]] | ||
Line 1,574: | Line 1,854: | ||
q = 'Q118398', | q = 'Q118398', | ||
label = 'arXiv', | label = 'arXiv', | ||
prefix = '//arxiv.org/abs/', -- protocol-relative tested 2013-09-04 | prefix = 'https://arxiv.org/abs/', -- protocol-relative tested 2013-09-04 | ||
encode = false, | encode = false, | ||
COinS = 'info:arxiv', | COinS = 'info:arxiv', | ||
Line 1,586: | Line 1,866: | ||
q = 'Q1753278', | q = 'Q1753278', | ||
label = 'ASIN', | label = 'ASIN', | ||
prefix = '//www.amazon.', | prefix = 'https://www.amazon.', | ||
COinS = | COinS = 'url', | ||
separator = ' ', | separator = ' ', | ||
encode = false; | encode = false; | ||
Line 1,609: | Line 1,889: | ||
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 1,621: | Line 1,901: | ||
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 1,633: | Line 1,913: | ||
q = 'Q25670', | q = 'Q25670', | ||
label = 'doi', | label = 'doi', | ||
prefix = '//doi.org/', | prefix = 'https://doi.org/', | ||
COinS = 'info:doi', | COinS = 'info:doi', | ||
separator = ':', | separator = ':', | ||
Line 1,645: | Line 1,925: | ||
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 1,656: | Line 1,936: | ||
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 1,663: | Line 1,943: | ||
}, | }, | ||
['ISBN'] = { -- Used by InternetArchiveBot | ['ISBN'] = { -- Used by InternetArchiveBot | ||
parameters = {'isbn', 'ISBN | parameters = {'isbn', 'ISBN'}, | ||
link = 'International Standard Book Number', | link = 'International Standard Book Number', | ||
redirect = 'ISBN (identifier)', | redirect = 'ISBN (identifier)', | ||
Line 1,679: | Line 1,959: | ||
label = 'ISMN', | label = 'ISMN', | ||
prefix = '', -- not currently used; | prefix = '', -- not currently used; | ||
COinS = | COinS = nil, -- nil because we can't use pre or rft or info: | ||
separator = ' ', | separator = ' ', | ||
}, | }, | ||
Line 1,688: | Line 1,968: | ||
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 1,699: | Line 1,979: | ||
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 1,710: | Line 1,990: | ||
q = 'Q1420342', | q = 'Q1420342', | ||
label = 'JSTOR', | label = 'JSTOR', | ||
prefix = '//www.jstor.org/stable/', -- protocol-relative tested 2013-09-04 | prefix = 'https://www.jstor.org/stable/', -- protocol-relative tested 2013-09-04 | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = false, | encode = false, | ||
Line 1,722: | Line 2,002: | ||
q = 'Q620946', | q = 'Q620946', | ||
label = 'LCCN', | label = 'LCCN', | ||
prefix = '//lccn.loc.gov/', -- protocol-relative tested 2015-12-28 | prefix = 'https://lccn.loc.gov/', -- protocol-relative tested 2015-12-28 | ||
COinS = 'info:lccn', | COinS = 'info:lccn', | ||
encode = false, | encode = false, | ||
Line 1,733: | Line 2,013: | ||
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 1,744: | Line 2,024: | ||
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 = 9999999999, -- 10-digits | id_limit = 9999999999, -- 10-digits | ||
}, | }, | ||
['OL'] = { | ['OL'] = { | ||
Line 1,756: | Line 2,036: | ||
q = 'Q1201876', | q = 'Q1201876', | ||
label = 'OL', | label = 'OL', | ||
prefix = '//openlibrary.org/', | prefix = 'https://openlibrary.org/', | ||
COinS = | COinS = 'url', | ||
separator = ' ', | separator = ' ', | ||
encode = true, | encode = true, | ||
Line 1,768: | Line 2,048: | ||
q = 'Q2015776', | q = 'Q2015776', | ||
label = 'OSTI', | label = 'OSTI', | ||
prefix = '//www.osti.gov/biblio/', -- protocol-relative tested 2018-09-12 | prefix = 'https://www.osti.gov/biblio/', -- protocol-relative tested 2018-09-12 | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 23010000, | ||
custom_access = 'osti-access', | custom_access = 'osti-access', | ||
}, | }, | ||
Line 1,781: | Line 2,061: | ||
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 = 10300000, | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
}, | }, | ||
Line 1,795: | Line 2,075: | ||
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 = 37400000, | ||
}, | }, | ||
['RFC'] = { | ['RFC'] = { | ||
Line 1,807: | Line 2,087: | ||
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, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 9300, | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
}, | }, | ||
Line 1,829: | Line 2,109: | ||
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 = 4500000, | ||
custom_access = 'ssrn-access', | |||
}, | }, | ||
['S2CID'] = { | ['S2CID'] = { | ||
Line 1,846: | Line 2,126: | ||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 260000000, | ||
custom_access = 's2cid-access', | custom_access = 's2cid-access', | ||
}, | }, | ||
Line 1,866: | Line 2,146: | ||
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 1,878: | Line 2,158: | ||
return { | return { | ||
use_identifier_redirects = true, -- when true use redirect name for identifier label links | use_identifier_redirects = true, -- when true use redirect name for identifier label links; always true at en.wiki | ||
local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki | |||
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 | |||
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 | |||
-- 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. | |||
punct_skip = build_skip_table (punct_skip, punct_meta_params), | |||
url_skip = build_skip_table (url_skip, url_meta_params), | |||
aliases = aliases, | aliases = aliases, | ||
Line 1,887: | Line 2,175: | ||
editor_markup_patterns = editor_markup_patterns, | editor_markup_patterns = editor_markup_patterns, | ||
et_al_patterns = et_al_patterns, | et_al_patterns = et_al_patterns, | ||
id_handlers = id_handlers, | id_handlers = id_handlers, | ||
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, | |||
indic_script = indic_script, | indic_script = indic_script, | ||
emoji_t = emoji_t, | |||
maint_cats = maint_cats, | maint_cats = maint_cats, | ||
messages = messages, | messages = messages, | ||
presentation = presentation, | presentation = presentation, | ||
prop_cats = prop_cats, | prop_cats = prop_cats, | ||
script_lang_codes = script_lang_codes, | script_lang_codes = script_lang_codes, | ||
lang_code_remap = lang_code_remap, | lang_code_remap = lang_code_remap, | ||
Line 1,905: | Line 2,192: | ||
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, | ||
templates_using_issue = templates_using_issue, | templates_using_issue = templates_using_issue, | ||
templates_not_using_page = templates_not_using_page, | templates_not_using_page = templates_not_using_page, | ||
vol_iss_pg_patterns = vol_iss_pg_patterns, | |||
single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t, | |||
inter_wiki_map = inter_wiki_map, | inter_wiki_map = inter_wiki_map, | ||
mw_languages_by_tag_t = mw_languages_by_tag_t, | |||
mw_languages_by_name_t = mw_languages_by_name_t, | |||
citation_class_map_t = citation_class_map_t, | |||
citation_issue_t = citation_issue_t, | |||
citation_no_volume_t = citation_no_volume_t, | |||
} | } |