Module:Citation/CS1/Configuration: Difference between revisions

Revision as of 17:18, 15 December 2023

Latest revision as of 11:34, 19 April 2025

(8 intermediate revisions by one other user not shown)

Line 31:

]]

local 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;

Line 219:

['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon

['free'] = {class='cs1id-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css

['registration'] = {class='cs1id-lock-registration', title='Free registration required'},

['limited'] = {class='cs1id-lock-limited', title='Free access subject to limited trial, subscription normally required'},

['subscription'] = {class='cs1id-lock-subscription', title='Paid subscription required'},

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

Line 345:

['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry',

'script-article', 'script-section'},

['ScriptEncyclopedia'] = {'script-encyclopedia', 'script-encyclopaedia'}, -- cite encyclopedia only

['ScriptMap'] = 'script-map',

['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper',

Line 369 ⟶ 370:

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

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

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

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

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

Line 481 ⟶ 483:

]]

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

local special_case_translation = {

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

Line 507 ⟶ 509:

{['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},

Line 514 ⟶ 516:

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

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

{['en'] = {'error[ %-]404', false}, ['local'] = nil},

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

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

Line 537 ⟶ 540:

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

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

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

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

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

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

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

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

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

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

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

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

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

Line 549 ⟶ 556:

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Line 599 ⟶ 609:

local_date_names_from_mediawiki is a boolean. When set to:

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

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

Line 611 ⟶ 621:

]]

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

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

local date_names = {

Line 754 ⟶ 764:

'^[Pp]gs.?',

},

vpatternsvi_patterns_t = { -- patternscombined to catch volume-like text in |issue= and issue-like text forin |volume=

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

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

},

ipatterns = { '^issues?', --issue-like patterns for |issue=text

'^issues?',

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

'^numbers?',

'^nos?%A', -- don't match 'november' or 'nostradamus'

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

'^n[%.:= ]' , -- might be a valid issue without separator (space char is sep char here)

'^n°', -- 'n' with degree sign (U+00B0)

}

'^№', -- precomposed unicode numero character (U+2116)

},

}

Line 1,051 ⟶ 1,062:

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

-- from: https://unicode.org/Public/emoji/1516.10/emoji-zwj-sequences.txt; version: 1516.10; 20232024-0608-0514

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

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

Line 1,153 ⟶ 1,164:

local script_lang_codes = {

'ab', 'am', 'ar', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'dvce', 'dzchr', 'eldv', 'fa', 'gu', 'hedz',

'hiel', 'hyfa', 'jagrc', 'kagu', 'kkhe', 'kmhi', 'knhy', 'koja', 'kuka', 'kykk', 'lokm', 'mk', 'mlkn', 'mnko',

'mniku', 'mrky', 'mylo', 'nemk', 'orml', 'otamn', 'pamni', 'psmr', 'rumy', 'sdne', 'sior', 'sr', 'syc', 'taota',

'tepa', 'tgps', 'thru', 'tisd', 'ttsi', 'ugsr', 'uksyc', 'urta', 'uzte', 'yitg', 'yueth', 'zhti', 'tt',

'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh', 'zgh'

};

Line 1,230 ⟶ 1,242:

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

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

['interproj-linked-name'] = 'CS1 interproject-linked names|$1', -- any author, editor, etc that has an interproject link; $1 is interproject tag used as a sort key

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

['interwiki-linked-name'] = 'CS1 interwiki-linked names|$1', -- any author, editor, etc that has an interwiki link; $1 is interwiki tag used as a sort key; yeilds to interproject

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

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

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

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

['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name

['unfit'] = 'CS1: unfit URL', -- |url-status=unfit or |url-status=usurped; used to be a maint cat

['vanc-accept'] = 'CS1:Vancouver names with accept markup', -- for |vauthors=/|veditors= with accept-as-written markup

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

}

Line 1,265 ⟶ 1,280:

build a table of doi registrants known to be free-to-read In a doi, the registrant ID is the series of digits

between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID

see §3.2.2 DOI prefix of the Doi Handbook p. 43

https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43

]]

Line 1,271 ⟶ 1,289:

local registrants_t = {};

for _, v in ipairs ({

'1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '1629', '1989', '1999', '2147', '2196', '3285', '3389', '3390', '3410',

'3748', '3814', '3847', '3897', '4061', '4089', '4103', '4172', '4175', '4230', '4236', '4239', '4240', '4249', '4251',

'4252', '4253', '4254', '4291', '4292', '4329', '4330', '4331', '5194', '5210', '5306', '5312', '5313', '5314',

'5315', '5316', '5317', '5318', '5319', '5320', '5321', '5334', '5402', '5409', '5410', '5411', '5412',

'5492', '5493', '5494', '5495', '5496', '5497', '5498', '5499', '5500', '5501', '5527', '5528', '5662',

'6064', '6219', '7167', '7217', '7287', '7482', '7490', '7554', '7717', '7759', '7766', '11131', '11569', '11647',

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

'17645', '18637', '19080', '19173', '20944', '21037', '21468', '21767', '22261', '22323', '22459', '24105', '24196', '24966',

'26775', '30845', '32545', '35711', '35712', '35713', '35995', '36648', '37126', '37532', '37871', '47128',

'47622', '47959', '52437', '52975', '53288', '54081', '54947', '55667', '55914', '57009', '58647', '59081',

Line 1,287 ⟶ 1,305:

return registrants_t;

end

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

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

['1016'] = {'j.heliyon', 'j.nlp', 'j.proche'}, -- Heliyon, Natural Language Processing, Procedia Chemistry

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

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

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

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

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

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

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

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

}

Line 1,716 ⟶ 1,747:

category = 'CS1 errors: generic title',

hidden = false,

},

err_invalid_isbn_date = {

message = 'ISBN / Date incompatibility',

anchor = 'invalid_isbn_date',

category = 'CS1 errors: ISBN date',

hidden = true

},

err_invalid_param_val = {

Line 1,775 ⟶ 1,812:

anchor = 'param_has_ext_link',

category = 'CS1 errors: external links',

hidden = false

},

err_param_has_twl_url = {

message = 'Wikipedia Library link in <code class="cs1-code">$1</code>', -- $1 is parameter name

anchor = 'param_has_twl_url',

category = 'CS1 errors: URL',

hidden = false

},

Line 1,922 ⟶ 1,965:

anchor = 'extra_punct',

category = 'CS1 maint: extra punctuation',

hidden = true,

},

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

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

anchor = 'id_limit_load_fail',

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

hidden = true,

},

Line 2,000 ⟶ 2,049:

anchor = 'postscript',

category = 'CS1 maint: postscript',

hidden = true,

},

maint_publisher_location = {

message = nil,

anchor = 'publisher_location',

category = 'CS1 maint: publisher ___location',

hidden = true,

},

Line 2,008 ⟶ 2,063:

hidden = true,

},

maint_unfit = {

message = nil,

anchor = 'unfit',

category = 'CS1 maint: unfit URL',

hidden = true,

},

maint_unknown_lang = {

message = nil,

Line 2,030 ⟶ 2,079:

anchor = 'url_status',

category = 'CS1 maint: url-status',

hidden = true,

},

maint_year= {

message = nil,

anchor = 'year',

category = 'CS1 maint: year',

hidden = true,

},

Line 2,039 ⟶ 2,094:

},

}

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

fetch id limits for certain identifiers from c:Data:CS1/Identifier limits.tab. This source is a json tabular

data file maintained at wikipedia commons. Convert the json format to a table of k/v pairs.

The values from <id_limits_data_t> are used to set handle.id_limit.

From 2025-02-21, MediaWiki is broken. Use this link to edit the tablular data file:

https://commons.wikimedia.org/w/index.php?title=Data:CS1/Identifier_limits.tab&action=edit

See Phab:T389105

]]

local id_limits_data_t = {};

local use_commons_data = true; -- set to false if your wiki does not have access to mediawiki commons; then,

if false == use_commons_data then -- update this table from https://commons.wikimedia.org/wiki/Data:CS1/Identifier_limits.tab; last update: 2025-02-21

id_limits_data_t = {['OCLC'] = 10450000000, ['OSTI'] = 23010000, ['PMC'] = 11900000, ['PMID'] = 40400000, ['RFC'] = 9300, ['SSRN'] = 5200000, ['S2CID'] = 276000000}; -- this table must be maintained locally

else -- here for wikis that do have access to mediawiki commons

local load_fail_limit = 99999999999; -- very high number to avoid error messages on load failure

id_limits_data_t = {['OCLC'] = load_fail_limit, ['OSTI'] = load_fail_limit, ['PMC'] = load_fail_limit, ['PMID'] = load_fail_limit, ['RFC'] = load_fail_limit, ['SSRN'] = load_fail_limit, ['S2CID'] = load_fail_limit};

local id_limits_data_load_fail = false; -- flag; assume that we will be successful when loading json id limit tabular data

local tab_data_t = mw.ext.data.get ('CS1/Identifier limits.tab').data; -- attempt to load the json limit data from commons into <tab_data_t>

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

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

else

for _, limit_t in ipairs (tab_data_t) do -- overwrite default <load_fail_limit> values

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

end

end

end

Line 2,151 ⟶ 2,242:

q = 'Q46339674',

label = 'eISSN',

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

COinS = 'rft.eissn',

encode = false,

Line 2,194 ⟶ 2,285:

q = 'Q131276',

label = 'ISSN',

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

COinS = 'rft.issn',

encode = false,

Line 2,262 ⟶ 2,353:

q = 'Q190593',

label = 'OCLC',

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

COinS = 'info:oclcnum',

encode = true,

separator = '&nbsp;',

id_limit = 10100000000id_limits_data_t.OCLC or 0,

},

['OL'] = {

Line 2,290 ⟶ 2,381:

encode = true,

separator = '&nbsp;',

id_limit = 23010000id_limits_data_t.OSTI or 0,

custom_access = 'osti-access',

},

Line 2,304 ⟶ 2,395:

encode = true,

separator = '&nbsp;',

id_limit = 10900000id_limits_data_t.PMC or 0,

access = 'free', -- free to read

},

Line 2,317 ⟶ 2,408:

encode = false,

separator = '&nbsp;',

id_limit = 38400000id_limits_data_t.PMID or 0,

},

['RFC'] = {

Line 2,329 ⟶ 2,420:

encode = false,

separator = '&nbsp;',

id_limit = 9300id_limits_data_t.RFC or 0,

access = 'free', -- free to read

},

Line 2,351 ⟶ 2,442:

encode = true,

separator = '&nbsp;',

id_limit = 4700000id_limits_data_t.SSRN or 0,

custom_access = 'ssrn-access',

},

Line 2,364 ⟶ 2,455:

encode = false,

separator = '&nbsp;',

id_limit = 268000000id_limits_data_t.S2CID or 0,

custom_access = 's2cid-access',

},

Line 2,408 ⟶ 2,499:

url_skip = build_skip_table (url_skip, url_meta_params),

known_free_doi_registrants_t = build_free_doi_registrants_table(),

id_limits_data_load_fail = id_limits_data_load_fail, -- true when commons tabular identifier-limit data fails to load

name_space_sort_keys = name_space_sort_keys,

Line 2,417 ⟶ 2,509:

editor_markup_patterns = editor_markup_patterns,

et_al_patterns = et_al_patterns,

extended_registrants_t = extended_registrants_t,

id_handlers = id_handlers,

keywords_lists = keywords_lists,