Module:Citation/CS1/Configuration
From Zoophilia Wiki
< Module:Citation | CS1
 | This Lua module is used on approximately 4,560,000 pages. To avoid major disruption and server load, any changes should be tested in the module's /sandbox or /testcases subpages, or in your own module sandbox. The tested changes can be added to this page in a single edit. Consider discussing changes on the talk page before implementing them. |
 | This module is subject to page protection. It is a highly visible module in use by a very large number of pages, or is substituted very frequently. Because vandalism or mistakes would affect many pages, and even trivial editing might cause substantial load on the servers, it is protected from editing. |
This configuration file contains various data that controls the functioning of Module:Citation/CS1 and hence, the way that Lua-based citations are generated.
It has several sections, among which are:
- Translation tables that contain most of the literal strings that may be included in Lua-based citations.
- A list of error conditions specifying what text to display, categories to include (if any), and what help page section to refer to when errors are detected
- A list of ID handlers specifying the recognized document IDs, such as ISBN, DOI, etc., and how to format them.
These files comprise the module support for CS1 | CS2 citation templates:
-- Make language object for local language; used here for languages and dates.
local lang_obj = mw.language.getContentLanguage()
--[[--------------------------< S E T T I N G S >-------------------------------
Boolean settings used to control various things; these settings are located
here to make them easy to find.
]]
-- These settings are local to this module only.
-- For i18n: When true, fill date_names["local_digits"] from MediaWiki, else
-- manual fill required; always false at Zoophilia Wiki.
local local_digits_from_mediawiki = false
-- For i18n: When true, fill date_names["local"]["long"] and
-- date_names["local"]["short"] from MediaWiki, else manual translation
-- required; always false at Zoophilia Wiki.
local local_date_names_from_mediawiki = false
-- These settings exported to other modules.
-- When true, use redirect name for identifier label links;
-- always true at Zoophilia Wiki.
local use_identifier_redirects = true
-- When true, categorize pages where |language=<local_language>;
-- always false at Zoophilia Wiki.
local local_lang_cat_enable = false
-- When true, translate English month names to local language month names;
-- always false at Zoophilia Wiki.
local date_name_auto_xlate_enable = false
-- When true, translate Western date digits to the local language digits
-- (date_names["local_digits"]); always false at Zoophilia Wiki.
local date_digit_auto_xlate_enable = false
-- When true, add namespace sort keys to error/ maintenance category links.
local enable_sort_keys = true
--[[------------< 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 identifiers for namespaces that will not be included in Citation error
categories. 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=<any>}}
]]
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
end
-- List of Lua patterns found in names of pages we should not categorize.
local uncategorized_subpages = {
"/[Aa]rchive", "/[^/]*[Ll]og", "/[Ss]andbox", "/[Tt]estcases"
}
-- At Zoophilia Wiki, Greek characters are used as sort keys for certain items
-- in a category so that those items are placed at the end of a category page;
-- see Wikipedia:Categorization#Sort_keys. That works well because English is
-- written using the Latin script. It is desireable to place content from
-- certain namespaces at the end of a category listing so the module adds sort
-- keys to error/maintenance category links when rendering a Cs1|2 template on a
-- page in that namespace.
-- i18n: If not working well for your language, set <enable_sort_keys> to false.
local name_space_sort_keys = { -- Sort keys to be used with these namespaces:
[4] = "ω", -- Zoophilia Wiki: omega
[10] = "τ", -- Template: tau
[118] = "Δ", -- Draft: delta
["other"] = "ο" -- All other non-Talk NSs except Main: omicron
}
--[[--------------------------< M E S S A G E S >-------------------------------
The following is a table containing fixed text that may be output as part of a
citation. This is separated from the main body to aid in future translations
of this module.
]]
local messages = {
["agency"] = "$1 $2", -- $1 is separation character, $2 is agency
["archived-dead"] = "Archived from $1 on $2",
["archived-live"] = "$1 from the original on $2",
["archived-unfit"] = "Archived from the original on ",
["archived"] = "Archived",
["by"] = "By", -- Contributions to authored works: intro, foreword, afterword
["cartography"] = "Cartography by $1",
["editor"] = "ed.",
["editors"] = "eds.",
["edition"] = "($1 ed.)",
["episode"] = "Episode $1",
["et al"] = "et al.",
["in"] = "In", -- Edited works
["inactive"] = "inactive",
["inset"] = "$1 inset",
["interview"] = "Interviewed by $1",
-- $1 is year parameter name; $2 is date parameter name
["mismatch"] = '<code class="cs1-code">|$1=</code> / ' ..
'<code class="cs1-code">|$2=</code> mismatch',
["newsgroup"] = "[[wikipedia:Usenet newsgroup|Newsgroup]]: $1",
["notitle"] = "No title", -- For |title=(()) and (in the future) |title=none
["original"] = "the original",
["origdate"] = " [$1]",
["published"] = " (published $1)",
["retrieved"] = "Retrieved $1",
["season"] = "Season $1",
["section"] = "§ $1",
["sections"] = "§§ $1",
["series"] = "$1 $2", -- $1 is separation character, $2 is series
["seriesnum"] = "Series $1",
["translated"] = "Translated by $1",
["type"] = " ($1)", -- For titletype
["written"] = "Written at $1",
["vol"] = "$1 Vol. $2", -- $1 is sepc; bold volume# is in presentation{}
-- sepc, volume, issue (or insert $1 after $2, then change capitalization too)
["vol-no"] = "$1 Vol. $2, no. $3",
["issue"] = "$1 No. $2", -- $1 is separation character
["art"] = "$1 Art. $2", -- $1 is sepc; for Template:Cite_conference only
-- Separation char., volume, article-number; for Template:Cite_conference only
["vol-art"] = "$1 Vol. $2, art. $3",
["j-vol"] = "$1 $2", -- sepc, volume; bold volume# is in presentation{}
["j-issue"] = " ($1)",
["j-article-num"] = " $1", -- TODO: Any punctuation here? Static text?
["nopp"] = "$1 $2", -- Page(s) without prefix; $1 is separation character
["p-prefix"] = "$1 p. $2", -- $1 is separation character
["pp-prefix"] = "$1 pp. $2", -- $1 is separation character
["j-page(s)"] = ": $1", -- Same for page and pages
["sheet"] = "$1 Sheet $2", -- $1 is separation character
["sheets"] = "$1 Sheets $2", -- $1 is separation character
["j-sheet"] = ": Sheet $1",
["j-sheets"] = ": Sheets $1",
["language"] = "(in $1)",
["via"] = " – via $1",
["event"] = "Event occurs at",
["minutes"] = "minutes in",
-- Determines the location of the help page.
["help page link"] = "wikipedia:Help:CS1 errors",
["help page label"] = "help",
-- Categories.
["cat wikilink"] = "[[Category:$1]]", -- $1 is the category name
-- $1 is the category name; $2 is namespace sort key
["cat wikilink sk"] = "[[Category:$1|$2]]",
-- Category name as maintenance message wikilink; $1 is the category name
[":cat wikilink"] = "[[:Category:$1|link]]",
-- Internal errors, should only occur if configuration is bad.
["undefined_error"] = "Called with an undefined error condition",
-- An ID key in id_handlers not found in ~/Identifiers func_map{}
["unknown_ID_key"] = "Unrecognized ID key: ",
-- An ID access keyword in id_handlers not in keywords_lists["id-access"]{}
["unknown_ID_access"] = "Unrecognized ID access keyword: ",
["unknown_argument_map"] = "Argument map not defined for this variable",
["bare_url_no_origin"] = "Bare URL found but origin indicator is nil/empty",
-- $1 is the template link
["warning_msg_e"] = '<span class="cs1-visible-error">One or more ' ..
"<code>{{$1}}</code> templates have errors</span>; " ..
"these messages may be hidden ([[wikipedia:Help:CS1 errors#Controlling " ..
"error message display|help]]).",
-- $1 is the template link
["warning_msg_m"] = '<span class="cs1-warn-maint">One or more ' ..
"<code>{{$1}}</code> templates have maintenance " ..
"messages</span>; these may be hidden ([[wikipedia:Help:CS1 " ..
"errors#Controlling error message display|help]])."
}
--[[--------------< C I T A T I O N _ C L A S S _ M A P >-----------------------
This table maps the value assigned to |CitationClass= in the Cs1|2 templates
to the canonical template name when the value assigned to |CitationClass= is
different from that name. |CitationClass= values are used as class attributes
in the <cite> tag that encloses the citation, so these names may not contain
spaces while the canonical template name may. These names are used in
warning_msg_e and warning_msg_m to create links to the template's
documentation when an article is displayed in preview mode.
Most Cs1|2 template |CitationClass= values at Zoophilia Wiki match their
canonical template names, so are not listed here.
]]
-- TODO: If kept, these and other config.CitationClass names require some i18n.
local citation_class_map_t = {
["AV-media-notes"] = "AV media notes",
["arxiv"] = "arXiv",
["audio-visual"] = "AV media",
["biorxiv"] = "bioRxiv",
["citeseerx"] = "CiteSeerX",
["encyclopaedia"] = "encyclopedia",
["mailinglist"] = "mailing list",
["medrxiv"] = "medRxiv",
["pressrelease"] = "press release",
["ssrn"] = "SSRN",
["techreport"] = "tech report",
}
--[[----------------------< E T _ A L _ P A T T E R N S >-----------------------
This table provides Lua patterns for the phrase "et al." and variants in name
text (author, editor, etc.). The main module uses these to identify and emit
the 'etal' message.
]]
local et_al_patterns = {
-- Variations on 'et al.'
'[;,]? *["\']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.;,"\']*$',
-- Variations on 'et alia', 'et alii' and 'et aliae' ('et aliie' unlikely)
'[;,]? *["\']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.;,"\']*$',
"[;,]? *%f[%a]and [Oo]thers", -- An alternative to et al.
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- A wikilinked form
-- A double-bracketed form (to counter partial removal of ((…)) syntax)
"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)",
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- A bracketed form
}
--[[-----------------------< P R E S E N T A T I O N >--------------------------
Fixed presentation markup; originally part of citation_config.messages, it has
been moved into its own, more semantically correct place.
]]
local presentation = {
-- .citation-comment cls of Help:CS1_errors#Controlling_error_message_display
["hidden-error"] = '<span class="cs1-hidden-error ' ..
'citation-comment">$1</span>',
["visible-error"] = '<span class="cs1-visible-error ' ..
'citation-comment">$1</span>',
["hidden-maint"] = '<span class="cs1-maint citation-comment">$1</span>',
-- To allow editors to hide access-date using personal CSS.
["accessdate"] = '<span class="reference-accessdate">$1$2</span>',
["bdi"] = '<bdi$1>$2</bdi>', -- Bidir. isolation for |script-title= & similar
-- For use when citation has no name list and |ref= unset so no id="…" attrib.
["cite"] = '<cite class="$1">$2</cite>',
-- For use when when |ref= is set or when citation has a name list.
["cite-id"] = '<cite id="$1" class="$2">$3</cite>',
-- For |format=, |chapter-format=, etc.
["format"] = ' <span class="cs1-format">($1)</span>',
-- For interwiki-language-linked author, editor, etc.
["interwiki"] = ' <span class="cs1-format">[in $1]</span>',
-- For interwiki-project-linked author, editor, etc (:d:, :s:, :w: supported)
["interproj"] = ' <span class="cs1-format">[at $1]</span>',
-- Various access levels, for |access=, |doi-access=, |arxiv=,…
-- narrow no-break space   may work better than nowrap CSS. Or not?
-- External link with appropriate lock icon.
["ext-link-access-signal"] = '<span class="$1" title="$2">$3</span>',
-- Classes defined in Module:Citation/CS1/styles.css.
["free"] = {class="id-lock-free", title="Freely accessible"},
["registration"] = {
class="id-lock-registration",
title="Free registration required"
},
["limited"] = {
class="id-lock-limited",
title="Free access subject to limited trial, subscription normally required"
},
["subscription"] = {
class="id-lock-subscription",
title="Paid subscription required"
},
["interwiki-icon"] = '<span class="$1" title="$2">$3</span>',
["class-wikisource"] = "cs1-ws-icon",
["italic-title"] = "''$1''",
-- Spacing to use when titles contain leading single or double quote mark.
["kern-left"] = '<span class="cs1-kern-left"></span>$1',
["kern-right"] = '$1<span class="cs1-kern-right"></span>',
-- For no-wrapping an item: <span …>yyyy-mm-dd</span>
["nowrap1"] = '<span class="nowrap">$1</span>',
-- For no-wrapping item portions, note whitespace: <span …>dd mmmm</span> yyyy
["nowrap2"] = '<span class="nowrap">$1</span> $2',
["ocins"] = '<span title="$1" class="Z3988"></span>',
["parameter"] = '<code class="cs1-code">|$1=</code>',
["ps_cs1"] = ".", -- CS1 style postscript (terminal) character
["ps_cs2"] = "", -- CS2 style postscript (terminal) character (empty string)
["quoted-text"] = "<q>$1</q>", -- For wrapping |quote= content
["quoted-title"] = '"$1"',
["sep_cs1"] = ".", -- CS1 element separator
["sep_cs2"] = ",", -- CS2 separator
["sep_nl"] = ";", -- CS1|2 style name-list separator between names: semicolon
-- Used as last nl separator when |name-list-style=and and list has 2 items
["sep_nl_and"] = " and ",
-- Used as last nl sep when |name-list-style=and and list has 3+ names
["sep_nl_end"] = "; and ",
["sep_name"] = ", ", -- CS1|2 style last/first separator is <comma><space>
-- Vancouver style name-list anchor separator is a comma
["sep_nl_vanc"] = ",",
["sep_name_vanc"] = " ", -- Vancouver style last/first separator is a space
-- Used for |language= when list has 3+ items, except for last is sep_list_end
["sep_list"] = ", ",
["sep_list_pair"] = " and ", -- Used for |language= when list has 2 items
["sep_list_end"] = ", and ", -- Used for |language= last sep when 3+ items
["trans-italic-title"] = "[''$1'']",
-- For |trans-title= / |trans-quote=
["trans-quoted-title"] = "[$1]",
-- sepc, volume; for bold journal cites; for other cites ["vol"] in messages{}
["vol-bold"] = "$1 <b>$2</b>"
}
--[[--------------------------< A L I A S E S >---------------------------------
Aliases table for commonly passed parameters. Parameter names on the right
side in the assignments in this table must have been defined in the Whitelist
before they will be recognized as valid parameter names.
]]
local aliases = {
["AccessDate"] = {"access-date", "accessdate"}, -- Used by InternetArchiveBot
["Agency"] = "agency",
["ArchiveDate"] = {"archive-date", "archivedate"}, -- Used by IAB
["ArchiveFormat"] = "archive-format",
["ArchiveURL"] = {"archive-url", "archiveurl"}, -- Used by InternetArchiveBot
["ArticleNumber"] = "article-number",
["ASINTLD"] = "asin-tld",
["At"] = "at", -- Used by InternetArchiveBot
["Authors"] = {"credits", "people"},
["BookTitle"] = {"book-title", "booktitle"},
["Cartography"] = "cartography",
["Chapter"] = {"article", "chapter", "contribution", "entry", "section"},
["ChapterFormat"] = {
"article-format",
"chapter-format",
"contribution-format",
"entry-format",
"section-format"
},
["ChapterURL"] = { -- Used by InternetArchiveBot
"article-url",
"chapter-url",
"contribution-url",
"entry-url",
"section-url"
},
["ChapterUrlAccess"] = { -- Used by InternetArchiveBot
"article-url-access",
"chapter-url-access",
"contribution-url-access",
"entry-url-access",
"section-url-access"
},
["Class"] = "class", -- Template:Cite_arxiv and arxiv IDs
["Collaboration"] = "collaboration",
["Conference"] = {"conference", "event"},
["ConferenceFormat"] = "conference-format",
["ConferenceURL"] = "conference-url", -- Used by InternetArchiveBot
-- air-date and airdate for Template:Cite_episode & Template:Cite_serial only
["Date"] = {"air-date", "airdate", "date"},
["Degree"] = "degree",
["DF"] = "df",
["DisplayAuthors"] = {"display-authors", "display-subjects"},
["DisplayContributors"] = "display-contributors",
["DisplayEditors"] = "display-editors",
["DisplayInterviewers"] = "display-interviewers",
["DisplayTranslators"] = "display-translators",
["Docket"] = "docket",
["DoiBroken"] = "doi-broken-date",
["Edition"] = "edition",
["Embargo"] = "pmc-embargo-date",
-- Template:Cite_encyclopedia only
["Encyclopedia"] = {"dictionary", "encyclopaedia", "encyclopedia"},
["Episode"] = "episode", -- Template:Cite_serial only (TODO: Cite_episode?)
["Format"] = "format",
["ID"] = {"ID", "id"},
["Inset"] = "inset",
["Issue"] = {"issue", "number"},
["Language"] = {"lang", "language"},
["MailingList"] = {"mailing-list", "mailinglist"}, -- Cite_mailing_list only
["Map"] = "map", -- Template:Cite_map only
["MapFormat"] = "map-format", -- Template:Cite_map only
["MapURL"] = {"map-url", "mapurl"}, -- Template:Cite_map only, used by IAB
["MapUrlAccess"] = "map-url-access", -- Template:Cite map only, used by IAB
["Minutes"] = "minutes",
["Mode"] = "mode",
["NameListStyle"] = "name-list-style",
["Network"] = "network",
["Newsgroup"] = "newsgroup", -- Template:Cite_newsgroup only
["NoPP"] = {"no-pp", "nopp"},
["NoTracking"] = {"no-tracking", "template-doc-demo"},
["Number"] = "number", -- Uppercase only for Cite_Techreport
["OrigDate"] = {"orig-date", "orig-year", "origyear"},
["Others"] = "others",
["Page"] = {"p", "page"}, -- Used by InternetArchiveBot
["Pages"] = {"pages", "pp"}, -- Used by InternetArchiveBot
["Periodical"] = {
"journal",
"magazine",
"newspaper",
"periodical",
"website",
"work"
},
["Place"] = {"location", "place"},
["PostScript"] = "postscript",
["PublicationDate"] = {"publication-date", "publicationdate"},
["PublicationPlace"] = {"publication-place", "publicationplace"},
["PublisherName"] = {"institution", "publisher"},
["Quote"] = {"quotation", "quote"},
["QuotePage"] = "quote-page",
["QuotePages"] = "quote-pages",
["Ref"] = "ref",
["Scale"] = "scale",
["ScriptChapter"] = {
"script-article",
"script-chapter",
"script-contribution",
"script-entry",
"script-section"
},
-- Cite_encyclopedia only
["ScriptEncyclopedia"] = {"script-encyclopaedia", "script-encyclopedia"},
["ScriptMap"] = "script-map",
["ScriptPeriodical"] = {
"script-journal",
"script-magazine",
"script-newspaper",
"script-periodical",
"script-website",
"script-work"
},
["ScriptQuote"] = "script-quote",
["ScriptTitle"] = "script-title", -- Used by InternetArchiveBot
["Season"] = "season",
["Sections"] = "sections", -- Template:Cite_map only
["Series"] = {"series", "version"},
["SeriesLink"] = {"series-link", "serieslink"},
["SeriesNumber"] = {"series-no", "series-number"},
["Sheet"] = "sheet", -- Template:Cite_map only
["Sheets"] = "sheets", -- Template:Cite_map only
["Station"] = "station",
["Time"] = "time",
["TimeCaption"] = "time-caption",
["Title"] = "title", -- Used by InternetArchiveBot
["TitleLink"] = {"episode-link", "episodelink", "title-link"}, -- Used by IAB
["TitleNote"] = {"department", "title-note"},
["TitleType"] = {"medium", "type"},
["TransChapter"] = {
"trans-article",
"trans-chapter",
"trans-contribution",
"trans-entry",
"trans-section"
},
["Transcript"] = "transcript",
["TranscriptFormat"] = "transcript-format",
["TranscriptURL"] = "transcript-url", -- Used by InternetArchiveBot
-- Template:Cite_encyclopedia only
["TransEncyclopedia"] = {"trans-encyclopaedia", "trans-encyclopedia"},
["TransMap"] = "trans-map", -- Template:Cite_map only
["TransPeriodical"] = {
"trans-journal",
"trans-magazine",
"trans-newspaper",
"trans-periodical",
"trans-website",
"trans-work"
},
["TransQuote"] = "trans-quote",
["TransTitle"] = "trans-title", -- Used by InternetArchiveBot
["URL"] = {"url", "URL"}, -- Used by InternetArchiveBot
["UrlAccess"] = "url-access", -- Used by InternetArchiveBot
["UrlStatus"] = "url-status", -- Used by InternetArchiveBot
["Vauthors"] = "vauthors",
["Veditors"] = "veditors",
["Via"] = "via",
["Volume"] = "volume",
["Year"] = "year",
["AuthorList-First"] = {
"author-first#",
"author-given#",
"author#-first",
"author#-given",
"first#",
"given#",
"subject-first#",
"subject-given#",
"subject#-first",
"subject#-given"
},
["AuthorList-Last"] = {
"author-last#",
"author-surname#",
"author#",
"author#-last",
"author#-surname",
"host#",
"last#",
"subject-last#",
"subject-surname#",
"subject#",
"subject#-last",
"subject#-surname",
"surname#"
},
["AuthorList-Link"] = {
"author-link#",
"author#-link",
"author#link",
"authorlink#",
"subject-link#",
"subject#-link"
},
["AuthorList-Mask"] = {
"author-mask#",
"author#-mask",
"subject-mask#",
"subject#-mask"
},
["ContributorList-First"] = {
"contributor-first#",
"contributor-given#",
"contributor#-first",
"contributor#-given"
},
["ContributorList-Last"] = {
"contributor-last#",
"contributor-surname#",
"contributor#",
"contributor#-last",
"contributor#-surname"
},
["ContributorList-Link"] = {"contributor-link#", "contributor#-link"},
["ContributorList-Mask"] = {"contributor-mask#", "contributor#-mask"},
["EditorList-First"] = {
"editor-first#",
"editor-given#",
"editor#-first",
"editor#-given"
},
["EditorList-Last"] = {
"editor-last#",
"editor-surname#",
"editor#",
"editor#-last",
"editor#-surname"
},
["EditorList-Link"] = {"editor-link#", "editor#-link"},
["EditorList-Mask"] = {"editor-mask#", "editor#-mask"},
["InterviewerList-First"] = {
"interviewer-first#",
"interviewer-given#",
"interviewer#-first",
"interviewer#-given"
},
["InterviewerList-Last"] = {
"interviewer-last#",
"interviewer-surname#",
"interviewer#",
"interviewer#-last",
"interviewer#-surname"
},
["InterviewerList-Link"] = {"interviewer-link#", "interviewer#-link"},
["InterviewerList-Mask"] = {"interviewer-mask#", "interviewer#-mask"},
["TranslatorList-First"] = {
"translator-first#",
"translator-given#",
"translator#-first",
"translator#-given"
},
["TranslatorList-Last"] = {
"translator-last#",
"translator-surname#",
"translator#",
"translator#-last",
"translator#-surname"
},
["TranslatorList-Link"] = {"translator-link#", "translator#-link"},
["TranslatorList-Mask"] = {"translator-mask#", "translator#-mask"}
}
--[[-------------------------< P U N C T _ S K I P >----------------------------
Builds a table of parameter names that the extraneous terminal punctuation
check should not inspect.
]]
-- Table of aliases[] keys (meta parameters); each has a table of parameter
-- names for a value.
local punct_meta_params = {
-- URL-holding parameters.
"ArchiveURL",
"ChapterURL",
"ConferenceURL",
"MapURL",
"TranscriptURL",
"URL",
-- Name list masks may have name separators.
"AuthorList-Mask",
"ContributorList-Mask",
"EditorList-Mask",
"InterviewerList-Mask",
"TranslatorList-Mask",
-- Title-holding parameters.
"BookTitle",
"Chapter",
"ScriptChapter",
"ScriptTitle",
"Title",
"TransChapter",
"TransMap",
"TransTitle",
"Transcript",
-- Miscellaneous holding parameters.
"PostScript",
"Quote",
"Ref",
"ScriptQuote",
"TransQuote"
}
-- Table of aliases[] keys (meta parameters); each key has a table of parameter
-- names for a value.
local url_meta_params = {
-- Parameters allowed to hold URLs.
"ArchiveURL",
"ChapterURL",
"ConferenceURL",
"ID",
"MapURL",
"TranscriptURL",
"URL",
-- In-source locators are also allowed to hold URLs.
"At",
"Page",
"Pages",
"QuotePage",
"QuotePages"
}
local function build_skip_table(skip_t, meta_params)
for _, meta_param in ipairs(meta_params) do -- For each meta parameter key…
-- …get the parameter or table of them associated with meta parameter name.
local params = aliases[meta_param]
if "string" == type(params) then
skip_t[params] = 1 -- Just a single parameter.
else
for _, param in ipairs(params) do -- Get the parameter name…
skip_t[param] = 1 -- …and add it to the skip table.
local count
-- Remove enumerator marker from enumerated parameters.
param, count = param:gsub("#", "")
if 0 ~= count then -- If removed…
skip_t[param] = 1 -- …add it w/o enumerator marker.
end
end
end
end
return skip_t
end
local punct_skip = {}
local url_skip = {}
--[[----------------------< U R L _ A C C E S S _ M A P >-----------------------
This table is used by the Zoophilia Wiki library URL test, has_twl_url(),
which automatically sets a url-access parameter to 'subscription' when it
discovers a library URL in any of the URL-holding parameters used as keys in
this table.
Translators: If localized parameter names are used for these URL-holding
parameters and their matching -access parameters, add those parameters to this
list but leave the English parameters in place.
TODO: Is there a better way to do this?
]]
local url_access_map_t = {
["URL"] = "url-access",
["article-url"] = "article-url-access",
["chapter-url"] = "chapter-url-access",
["contribution-url"] = "contribution-url-access",
["entry-url"] = "entry-url-access",
["map-url"] = "map-url-access",
["mapurl"] = "map-url-access",
["section-url"] = "section-url-access",
["url"] = "url-access"
}
--[[---< 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 top-level domains 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", "media", "org", "today"
}
--[[----------< S P E C I A L _ C A S E _ T R A N S L A T I O N S >-------------
This table is primarily here to support internationalization. Translations in
this table are used, for example, when an error message, category name, etc.,
is extracted from the English alias key. There may be other cases where this
translation table may be useful.
]]
local is_Latn = "A-Za-z\195\128-\195\150\195\152-\195\182\195\184-" ..
"\198\191\199\132-\201\143\225\184\128-\225\187\191"
local special_case_translation = {
["AuthorList"] = "authors list", -- Assembles maintenance category names.
-- Translation of these names + base maintcat names in maint_cats{} table
["ContributorList"] = "contributors list",
["EditorList"] = "editors list", -- Must match names of the actual categories
-- These translations used by name_has_ed_markup() and name_has_mult_names()
["InterviewerList"] = "interviewers list",
["TranslatorList"] = "translators list",
-- Patterns to match pseudo-titles used by IAB & others as placeholder for
-- unknown |title= value.
["archived_copy"] = { -- Used with CS1 maint: Archive[d] copy as title.
-- For English; translators keep this for imported templates.
["en"] = "^archived?%s+copy$",
-- Translators: Replace ["local"] = nil with lowercase translation only when
-- bots or tools create generic titles in your language.
["local"] = nil
},
-- 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.
-- 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; Set to true for plain-text searches, false for pattern searches.
["generic_titles"] = {
["accept"] = {},
["reject"] = {
{["en"] = {"^404", false}, ["local"] = nil},
{["en"] = {"^[%(%[{<]?no +title[>}%]%)]?$", false}, ["local"] = nil},
{["en"] = {"^[%(%[{<]?unknown[>}%]%)]?$", false}, ["local"] = nil},
{["en"] = {"^wayback%s+machine$", false}, ["local"] = nil},
{["en"] = {"are you a robot", true}, ["local"] = nil},
{["en"] = {"error[ %-]404", false}, ["local"] = nil},
{["en"] = {"hugedomains", true}, ["local"] = nil},
{["en"] = {"internet archive wayback machine", true}, ["local"] = nil},
{["en"] = {"log into facebook", true}, ["local"] = nil},
{["en"] = {"login • instagram", true}, ["local"] = nil},
{["en"] = {"page not found", true}, ["local"] = nil},
{["en"] = {"redirecting…", true}, ["local"] = nil},
{["en"] = {"subscribe to read", true}, ["local"] = nil},
{["en"] = {"website is for sale", true}, ["local"] = nil},
-- Added by a GreenC bot.
{["en"] = {"usurped title", true}, ["local"] = nil},
{["en"] = {"webcite query result", true}, ["local"] = nil},
{["en"] = {"wikiwix's cache", true}, ["local"] = nil}
}
},
-- Set true for plain-text searches (string must be lowercase only), or false
-- for pattern searches. Leave ["local"] nil except when there is a matching
-- generic name in your language.
["generic_names"] = {
["accept"] = {
{["en"] = {"%[%[[^|]*%(author%) *|[^%]]*%]%]", false}, ["local"] = nil}
},
["reject"] = {
{
["en"] = {"%f[" .. is_Latn .. "][Uu]ser%f[^" .. is_Latn .. "]", false},
["local"] = nil
},
{
["en"] = {"%f[%(%[][%(%[]%s*eds?%.?%s*[%)%]]?$", false},
["local"] = nil
},
{["en"] = {"%f[%a][Aa]dvisor%f[%A]", false}, ["local"] = nil},
{["en"] = {"%f[%a][Aa]uthor%f[%A]", 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"] = {"[,%.%s]%f[e]eds?%.?$", false}, ["local"] = nil},
{["en"] = {"[Nn]ews[ %-]?[Rr]oom", false}, ["local"] = nil},
{
["en"] = {"^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]", false},
["local"] = nil
},
{["en"] = {"^[Bb]ureau$", false}, ["local"] = nil},
{["en"] = {"^[Cc]ompany$", false}, ["local"] = nil},
{["en"] = {"^[Dd]esk$", false}, ["local"] = nil},
{["en"] = {"^[Gg]roup$", false}, ["local"] = nil},
{["en"] = {"^[Ii]nc%.?$", false}, ["local"] = nil},
{["en"] = {"^[Ll]imited$", false}, ["local"] = nil},
{["en"] = {"^[Nn]ews$", false}, ["local"] = nil},
{["en"] = {"^eds?[%.,;]", false}, ["local"] = nil},
{["en"] = {"about us", true}, ["local"] = nil},
{["en"] = {"allmusic", true}, ["local"] = nil},
{["en"] = {"business", true}, ["local"] = nil},
{["en"] = {"cnn", true}, ["local"] = nil},
{["en"] = {"collaborator", true}, ["local"] = nil},
{["en"] = {"contact us", true}, ["local"] = nil},
{["en"] = {"contributor", true}, ["local"] = nil},
{["en"] = {"correspondent", true}, ["local"] = nil},
{["en"] = {"directory", true}, ["local"] = nil},
{["en"] = {"facebook", true}, ["local"] = nil},
{["en"] = {"google", true}, ["local"] = nil},
{["en"] = {"home page", true}, ["local"] = nil},
{["en"] = {"instagram", true}, ["local"] = nil},
{["en"] = {"interviewer", true}, ["local"] = nil},
{["en"] = {"linkedIn", true}, ["local"] = nil},
{["en"] = {"pinterest", true}, ["local"] = nil},
{["en"] = {"policy", true}, ["local"] = nil},
{["en"] = {"privacy", true}, ["local"] = nil},
{["en"] = {"reuters", 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"] = {"translator", true}, ["local"] = nil},
{["en"] = {"tumblr", true}, ["local"] = nil},
{["en"] = {"twitter", true}, ["local"] = nil},
{["en"] = {"updated", true}, ["local"] = nil},
{["en"] = {"verfasser", true}, ["local"] = nil}
}
}
}
--[[--------------------------< D A T E _ N A M E S >---------------------------
This table of tables lists local language date names and fallback English date
names. The code in Date_validation will look first in the local table for
valid date names. If none are found in the local table, the code will look in
the English table, which is required when the date-name translation function
date_name_xlate() is used.
In these tables, season numbering is defined by Extended Date/Time Format
(EDTF) Specification <https://www.loc.gov/standards/datetime/>, 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.
EDTF does support the distinction between north and south hemisphere seasons,
but CS1|2 has no way currently to make those distinctions.
33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each).
The standard does not address "named" dates, so, for the purposes of CS1|2,
Easter and Christmas are defined here as 98 and 99, which should be out of the
ISO 8601 (EDTF) range of uses for a while.
local_date_names_from_mediawiki is a boolean. When set to:
true – fetch local month names from MediaWiki for both
date_names["local"]["long"] and date_names["local"]["short"];
this will unconditionally overwrite manual translations.
false – do *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. Those must be translated manually.
]]
-- When false, manual translation required for date_names["local"]["long"] and
-- date_names["local"]["short"]; overwrites manual translations. When true,
-- fetches long and short month names from MediaWiki.
local local_date_names_from_mediawiki = true
local date_names = {
["en"] = { -- English
["long"] = {
["January"] = 1,
["February"] = 2,
["March"] = 3,
["April"] = 4,
["May"] = 5,
["June"] = 6,
["July"] = 7,
["August"] = 8,
["September"] = 9,
["October"] = 10,
["November"] = 11,
["December"] = 12
},
["short"] = {
["Jan"] = 1,
["Feb"] = 2,
["Mar"] = 3,
["Apr"] = 4,
["May"] = 5,
["Jun"] = 6,
["Jul"] = 7,
["Aug"] = 8,
["Sep"] = 9,
["Oct"] = 10,
["Nov"] = 11,
["Dec"] = 12
},
["quarter"] = {
["First Quarter"] = 33,
["Second Quarter"] = 34,
["Third Quarter"] = 35,
["Fourth Quarter"] = 36
},
["season"] = {
["Spring"] = 21,
["Summer"] = 22,
["Autumn"] = 23,
["Fall"] = 23,
["Winter"] = 24
},
["named"] = {["Easter"] = 98, ["Christmas"] = 99}
},
-- When local_date_names_from_mediawiki = false
["local"] = { -- Replace English date names with local language equivalents.
["long"] = {
["January"] = 1,
["February"] = 2,
["March"] = 3,
["April"] = 4,
["May"] = 5,
["June"] = 6,
["July"] = 7,
["August"] = 8,
["September"] = 9,
["October"] = 10,
["November"] = 11,
["December"] = 12
},
["short"] = {
["Jan"] = 1,
["Feb"] = 2,
["Mar"] = 3,
["Apr"] = 4,
["May"] = 5,
["Jun"] = 6,
["Jul"] = 7,
["Aug"] = 8,
["Sep"] = 9,
["Oct"] = 10,
["Nov"] = 11,
["Dec"] = 12
},
["quarter"] = {
["First Quarter"] = 33,
["Second Quarter"] = 34,
["Third Quarter"] = 35,
["Fourth Quarter"] = 36
},
["season"] = {
["Spring"] = 21,
["Summer"] = 22,
["Autumn"] = 23,
["Fall"] = 23,
["Winter"] = 24
},
["named"] = {["Easter"] = 98, ["Christmas"] = 99}
},
-- Used in date reformatting/translation; copy of date_names["local"].long
-- where key/value pairs are inverted: [1]="<local name>", etc.
["inv_local_long"] = {},
["inv_local_named"] = {}, -- As above, but for date_names["local"].named
["inv_local_quarter"] = {}, -- As above, but for date_names["local"].quarter
["inv_local_season"] = {}, -- As above, but for date_names["local"].season
["inv_local_short"] = {}, -- As above, but for date_names["local"].short
-- Used to convert local language digits to Western (Arabic) numbers 0-9.
["local_digits"] = {
["0"] = "0",
["1"] = "1",
["2"] = "2",
["3"] = "3",
["4"] = "4",
["5"] = "5",
["6"] = "6",
["7"] = "7",
["8"] = "8",
["9"] = "9"
},
["xlate_digits"] = {}
}
if local_date_names_from_mediawiki then -- Fetching local month names from MW.
local long_t = {}
local short_t = {}
for i = 1, 12 do -- Loop through 12 times and…
-- …get long month name for each i…
local name = lang_obj:formatDate("F", "2022-" .. i .. "-1")
long_t[name] = i -- …then store it.
-- Get short month name for each i…
name = lang_obj:formatDate("M", "2022-" .. i .. "-1")
short_t[name] = i -- …and store this, too.
end
-- Write the long table; overwrites manual translation.
date_names["local"]["long"] = long_t
-- Write the short table; overwrites manual translation.
date_names["local"]["short"] = short_t
end
-- Create inverted date-name tables for reformatting and/or translation.
for _, invert_t in pairs {
{"long", "inv_local_long"},
{"named", "inv_local_named"},
{"quarter", "inv_local_quarter"},
{"season", "inv_local_season"},
{"short", "inv_local_short"}
} do
for name, i in pairs(date_names["local"][invert_t[1]]) do -- ["name"] = i
-- Invert to get [i] = "name"
date_names[invert_t[2]][i] = name
end
end
if local_digits_from_mediawiki then -- Fetching local digits from MediaWiki.
local digits_t = {}
for i = 0, 9 do -- Loop through 10 times and…
-- …format loop indexer as localized table index and assign a string value.
digits_t[lang_obj:formatNum(i)] = tostring(i)
end
date_names["local_digits"] = digits_t
end
-- Make a table for simple date digit translation from English to the local
-- language using the local_digits table.
for ld, ed in pairs(date_names.local_digits) do
-- English digit becomes the index with the local digit as the value.
date_names.xlate_digits[ed] = ld
end
local df_template_patterns = {
"{{ *[Uu]se +(dmy) +dates *[|}]",
"{{ *[Uu]se +(mdy) +dates *[|}]"
}
-- This ensures that unused templates appear in unused-template-reports;
-- self-transclusion makes them look like they are used.
local title_object = mw.title.getCurrentTitle()
local content
if 10 ~= title_object.namespace then -- All namespaces, except Template.
-- Get the content of the article or ""; new pages edited by VisualEditor do
-- not have "content" until saved as it does not preview. (phab:T221625)
content = title_object:getContent() or ""
end
local function get_date_format()
if not content then -- Nil content when we're in template.
return nil -- Can't auto-format in Template space, so don't set global_df.
end
-- Look for Template:Use_dmy_dates or Template:Use_mdy_dates.
for _, pattern in ipairs(df_template_patterns) do
-- Match is the three letters indicating the desired date format.
local start, _, match = content:find(pattern)
if match then
-- Get the whole template.
local use_dates_template = content:match("%b{}", start)
-- Look for |cs1-dates=publication date length access-/archive-date length
if use_dates_template:match("| *cs1%-dates *= *[lsy][sy]?") then
return match:lower() .. "-" ..
use_dates_template:match("| *cs1%-dates *= *([lsy][sy]?)")
else
-- No |cs1-dates= k/v pair, so return value appropriate for use in |df=.
return match:lower() .. "-all"
end
end
end
end
local global_df -- TODO: Add this to <global_cs1_config_t>?
--[[-----------------< V O L U M E , I S S U E , P A G E S >------------------
These tables hold cite class values (from the template invocation) and
identify those templates that support |volume=, |issue=, and |page(s)=
parameters. Template:Cite_conference and Template:Cite_map require further
qualification which is handled in the main module.
]]
local templates_using_volume = {
"audio-visual",
"book",
"citation",
"conference",
"encyclopaedia",
"interview",
"journal",
"magazine",
"map",
"news",
"report",
"techreport",
"thesis"
}
local templates_using_issue = {
"citation",
"conference",
"episode",
"interview",
"journal",
"magazine",
"map",
"news",
"podcast"
}
local templates_not_using_page = {
"audio-visual",
"episode",
"mailinglist",
"newsgroup",
"podcast",
"serial",
"sign",
"speech"
}
-- These tables control when it is appropriate for Template:Citation to render
-- |volume= and/or |issue=. The parameter names in the tables constrain its
-- renderings to match the renderings of the equivalenttype-named Cs1 templates.
-- For example, Template:Cite_web does not support |volume=, so the equivalent
-- {{Citation|website=…}} must not support |volume=.
-- Template:Citation does not render |volume= when these parameters are used.
local citation_no_volume_t = {"mailinglist", "script-website", "website"}
-- Template:Citation may render |issue= when these parameters are used.
local citation_issue_t = {
"journal",
"magazine",
"newspaper",
"periodical",
"script-journal",
"script-magazine",
"script-newspaper",
"script-periodical",
"script-work",
"work"
}
-- Patterns for finding extra text in |volume=, |issue=, |page=, |pages=.
local vol_iss_pg_patterns = {
-- Okay to begin with uppercase P: P7 (page 7 of section P), but not p123
-- (page 123). TODO: This allows 'Pages', which it should not.
good_ppattern = "^P[^%.PpGg]",
bad_ppatterns = { -- Patterns for |page= and |pages=
"^[Pp][PpGg]?%.?[ %d]",
"^[Pp][Pp]?%. ", -- From Template:P. and Template:Pp.
"^[Pp]ages?",
"^[Pp]gs.?"
},
-- Combined to catch volume-like text in |issue= and vice versa.
vi_patterns_t = {
"^iss[%.:=]?",
"^issues?", -- Issue-like text.
"^n[%.:= ]", -- Might be valid issue w/o separator character (space).
"^nos?%A", -- Doesn't match "november" or "nostradamus".
"^nr[%.:=]?",
"^numbers?",
"^n°", -- "n" with degree symbol (U+00B0).
"^vols?[%.:=]?",
"^volumes?", -- Volume-like text.
"^№" -- Precomposed Unicode numero character (U+2116).
}
}
--[[--------------------------< K E Y W O R D S >-------------------------------
These tables hold keywords for those parameters that have defined sets of
acceptable keywords ("whitelists").
]]
--[[-------------------< K E Y W O R D S T A B L E >--------------------------
This is a list of keywords; each key in the list is associated with a table of
synonymous keywords possibly from different languages.
For i18n: Add localized keywords to value table, but do not change the key.
For example, adding the German keyword "ja":
["affirmative"] = {"1", "on", "true", "y", "yes", "ja"}
]]
local keywords = {
["amp"] = {"&", "amp", "ampersand"}, -- |name-list-style=
["and"] = {"and", "serial"}, -- |name-list-style=
-- Used with |no-tracking=, |no-pp= and by InternetArchiveBot.
["affirmative"] = {"1", "on", "true", "y", "yes"},
["afterword"] = {"afterword"}, -- |contribution=
["bot: unknown"] = {"bot: unknown"}, -- |url-status= and InternetArchiveBot
["cs1"] = {"cs1"}, -- |mode=
["cs2"] = {"cs2"}, -- |mode=
["dead"] = {"dead", "deviated"}, -- |url-status= and InternetArchiveBot
["dmy"] = {"dmy"}, -- |df=
["dmy-all"] = {"dmy-all"}, -- |df=
["foreword"] = {"foreword"}, -- |contribution=
["free"] = {"free"}, -- |<id>-access= and InternetArchiveBot
-- Support for |ref= removed; is_valid_parameter_value() w/ <invert> = true.
["harv"] = {"harv"},
["introduction"] = {"introduction"}, -- |contribution=
["limited"] = {"limited"}, -- |url-access= and InternetArchiveBot
["live"] = {"live"}, -- |url-status= and InternetArchiveBot
["mdy"] = {"mdy"}, -- |df=
["mdy-all"] = {"mdy-all"}, -- |df=
-- |postscript=, |ref=, |title=, |type= and InternetArchiveBot
["none"] = {"none"},
-- |title=, |title-link=, |postscript=, |ref= and |type=
["off"] = {"off"},
["preface"] = {"preface"}, -- |contribution=
["registration"] = {"registration"}, -- |url-access= and InternetArchiveBot
["subscription"] = {"subscription"}, -- |url-access= and InternetArchiveBot
["unfit"] = {"unfit"}, -- |url-status= and InternetArchiveBot
["usurped"] = {"usurped"}, -- |url-status= and InternetArchiveBot
["vanc"] = {"vanc"}, -- |name-list-style=
["ymd"] = {"ymd"}, -- |df=
["ymd-all"] = {"ymd-all"} -- |df=
}
--[[------------------------< X L A T E _ K E Y W O R D S >---------------------
This function builds keywords_xlate{}, a list of the members of keywords{}
where the values become the keys in keywords_xlate{} and likewise the keys
become the values. For example:
keywords = {["affirmative"] = {"1", "on", "true", "y", "yes"}}
becomes
keywords_xlate = {["1"] = "affirmative", ["on"] = "affirmative", …}
It acts as a translator between a non-English keyword and its English-language
equivalent that may be used in other modules of this suite.
]]
local function xlate_keywords()
local out_table = {}
for k, keywords_t in pairs(keywords) do -- Iterate through keywords table…
for _, keyword in ipairs(keywords_t) do -- …and for each keyword…
-- …output an entry where keyword is the key.
out_table[keyword] = k
end
end
return out_table
end
local keywords_xlate = xlate_keywords() -- The list of translated keywords.
--[[----------------< M A K E _ K E Y W O R D S _ L I S T >---------------------
This function assembles the list of keywords appropriate to a given parameter
for value validation with keywords_lists{}, a table of tables from keywords{}.
]]
local function make_keywords_list(keywords_lists)
local out_table = {}
for _, keyword_list in ipairs(keywords_lists) do
for _, keyword in ipairs(keyword_list) do
table.insert(out_table, keyword)
end
end
return out_table
end
--[[----------------< K E Y W O R D S _ L I S T S >-----------------------------
This is a list of lists of valid keywords for the various parameters in [key].
Generally the keys in this table are the canonical Zoophilia Wiki parameter
names, though some are contrived because of use in multiple differently-named
parameters, such as:
["yes_true_y"], ["id-access"]
The function make_keywords_list() extracts the individual keywords from the
appropriate list in keywords{}, which are then used to validate the keyword
assignments for the parameters named in this table's keys.
]]
local keywords_lists = {
["contribution"] = make_keywords_list({
keywords.afterword,
keywords.foreword,
keywords.introduction,
keywords.preface
}),
["df"] = make_keywords_list({
keywords.dmy,
keywords.mdy,
keywords.ymd,
keywords["dmy-all"],
keywords["mdy-all"],
keywords["ymd-all"]
}),
["id-access"] = make_keywords_list({keywords.free}),
["mode"] = make_keywords_list({keywords.cs1, keywords.cs2}),
["name-list-style"] = make_keywords_list({
keywords.amp, keywords.vanc, keywords["and"]
}),
-- Inverted check; |ref=harv is no longer supported.
["ref"] = make_keywords_list({keywords.harv}),
["url-access"] = make_keywords_list({
keywords.limited, keywords.registration, keywords.subscription
}),
["url-status"] = make_keywords_list({
keywords.dead,
keywords.live,
keywords.unfit,
keywords.usurped,
keywords["bot: unknown"]
}),
["id-access"] = make_keywords_list ({keywords.free})
}
--[[--------------------------< C S 1 _ C O N F I G _ G E T >--------------------------------------------------
fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t>
no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked.
Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors,
DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode. The DisplayWhatever metaparameters
accept numeric values only (|display-authors=etal and the like is not supported).
]]
local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table?
local function get_cs1_config ()
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 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 = {
{'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 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/17.0/emoji-zwj-sequences.txt; version: 17.0; 2025-01-08
-- table created by: [[:en:Module:Make emoji zwj table]]
local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx
[8596] = true, -- U+2194 ↔ left right arrow
[8597] = true, -- U+2195 ↕ up down arrow
[9760] = true, -- U+2620 ☠ skull and crossbones
[9792] = true, -- U+2640 ♀ female sign
[9794] = true, -- U+2642 ♂ male sign
[9877] = true, -- U+2695 ⚕ staff of aesculapius
[9878] = true, -- U+2696 ⚖ scales
[9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign
[9992] = true, -- U+2708 ✈ airplane
[10052] = true, -- U+2744 ❄ snowflake
[10084] = true, -- U+2764 ❤ heavy black heart
[10145] = true, -- U+27A1 ➡ black rightwards arrow
[11035] = true, -- U+2B1B ⬛ black large square
[127752] = true, -- U+1F308 🌈 rainbow
[127787] = true, -- U+1F32B 🌫 fog
[127806] = true, -- U+1F33E 🌾 ear of rice
[127859] = true, -- U+1F373 🍳 cooking
[127868] = true, -- U+1F37C 🍼 baby bottle
[127876] = true, -- U+1F384 🎄 christmas tree
[127891] = true, -- U+1F393 🎓 graduation cap
[127908] = true, -- U+1F3A4 🎤 microphone
[127912] = true, -- U+1F3A8 🎨 artist palette
[127979] = true, -- U+1F3EB 🏫 school
[127981] = true, -- U+1F3ED 🏭 factory
[128048] = true, -- U+1F430 🐰 rabbit face
[128102] = true, -- U+1F466 👦 boy
[128103] = true, -- U+1F467 👧 girl
[128104] = true, -- U+1F468 👨 man
[128105] = true, -- U+1F469 👩 woman
[128139] = true, -- U+1F48B 💋 kiss mark
[128165] = true, -- U+1F4A5 💥 collision symbol
[128168] = true, -- U+1F4A8 💨 dash symbol
[128171] = true, -- U+1F4AB 💫 dizzy symbol
[128187] = true, -- U+1F4BB 💻 personal computer
[128188] = true, -- U+1F4BC 💼 brief case
[128293] = true, -- U+1F525 🔥 fire
[128295] = true, -- U+1F527 🔧 wrench
[128300] = true, -- U+1F52C 🔬 microscope
[128488] = true, -- U+1F5E8 🗨 left speech bubble
[128640] = true, -- U+1F680 🚀 rocket
[128658] = true, -- U+1F692 🚒 fire engine
[129001] = true, -- U+1F7E9 🟩 large green square
[129003] = true, -- U+1F7EB 🟫 large brown square
[129309] = true, -- U+1F91D 🤝 handshake
[129455] = true, -- U+1F9AF 🦯 probing cane
[129456] = true, -- U+1F9B0 🦰 emoji component red hair
[129457] = true, -- U+1F9B1 🦱 emoji component curly hair
[129458] = true, -- U+1F9B2 🦲 emoji component bald
[129459] = true, -- U+1F9B3 🦳 emoji component white hair
[129466] = true, -- U+1F9BA 🦺 safety vest
[129468] = true, -- U+1F9BC 🦼 motorized wheelchair
[129469] = true, -- U+1F9BD 🦽 manual wheelchair
[129489] = true, -- U+1F9D1 🧑 adult
[129490] = true, -- U+1F9D2 🧒 child
[129648] = true, -- U+1FA70 🩰 ballet shoes
[129657] = true, -- U+1FA79 🩹 adhesive bandage
[129775] = true, -- U+1FAEF fight cloud
[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.
]]
--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 script_lang_codes = {
'ab', 'am', 'ar', 'az', 'be', 'bg', 'bn', 'bo', 'bs', 'ce', 'chr', 'cu',
'dv', 'dz', 'el', 'fa', 'grc', 'gu', 'he', 'hi', 'hy', 'ja', 'ka', 'kk',
'km', 'kn', 'ko', 'ku', 'ky', 'lo', 'mk', 'ml', 'mn', 'mni', 'mr', 'my',
'ne', 'or', 'ota', 'pa', 'ps', 'ru', 'sd', 'si', 'sr', 'syc', 'ta', 'te',
'tg', 'th', 'ti', 'tkr', 'tt', 'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh',
'zgh'
};
--[[---------------< L A N G U A G E R E M A P P I N G >----------------------
These tables hold language information that is different (correct) from MediaWiki's definitions
For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{}
lang_tag_remap{}:
key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag
value is properly spelled and capitalized language name associated with <tag>
only one language name per <tag>;
key/value pair must have matching entry in lang_name_remap{}
lang_name_remap{}:
key is always lowercase language name
value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{})
may have multiple keys referring to a common preferred name and tag; For example:
['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'
]]
local lang_tag_remap = { -- used for |language= and |script-title= / |script-chapter=
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['bn'] = 'Bengali', -- MediaWiki returns Bangla
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan
['fkv'] = 'Kven', -- MediaWiki returns Kvensk
['gsw'] = 'Swiss German',
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name
['ksh-x-colog'] = 'Colognian', -- override MediaWiki ksh; no IANA/ISO 639 code for Colognian; IETF private code created at Module:Lang/data
['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data
['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name
['sr-ec'] = 'Serbian (Cyrillic script)', -- MediaWiki returns српски (ћирилица)
['sr-el'] = 'Serbian (Latin script)', -- MediaWiki returns srpski (latinica)
}
local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase
['alemannic'] = {'Swiss German', 'gsw'}, -- ISO 639-2, -3 alternate for Swiss German; MediaWiki mediawiki returns Alemannic for gsw; en.wiki preferred name
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org
['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap
['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code
['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replaces 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found
['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö)
['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name
['kven'] = {'Kven', 'fkv'}, -- Unicode CLDR have decided not to support English language name for these two...
['kvensk'] = {'Kven', 'fkv'}, -- ...they say to refer to IANA registry for English names
['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639
['serbian (cyrillic script)'] = {'Serbian (Cyrillic script)', 'sr-cyrl'}, -- special case to get correct tag when |language=sr-ec
['serbian (latin script)'] = {'Serbian (Latin script)', 'sr-latn'}, -- special case to get correct tag when |language=sr-el
['swiss german'] = {'Swiss German', 'gsw'},
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-tw'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
['valencian'] = {'Valencian', 'ca-valencia'}, -- variant of Catalan; categorizes as Valencian
}
--[[---------------< P R O P E R T I E S _ C A T E G O R I E S >----------------
Properties categories. These are used for investigating qualities of citations.
]]
local prop_cats = {
['foreign-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code
['foreign-lang-source-2'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key
['interproj-linked-name'] = 'CS1 interproject-linked names|$1', -- any author, editor, etc that has an interproject link; $1 is interproject tag used as a sort key
['interwiki-linked-name'] = 'CS1 interwiki-linked names|$1', -- any author, editor, etc that has an interwiki link; $1 is interwiki tag used as a sort key; yeilds to interproject
['local-lang-source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false
['location-test'] = 'CS1 location test',
['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters
['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is language tag
['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name
['unfit'] = 'CS1: unfit URL', -- |url-status=unfit or |url-status=usurped; used to be a maint cat
['vanc-accept'] = 'CS1:Vancouver names with accept markup', -- for |vauthors=/|veditors= with accept-as-written markup
['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form
}
--[[-------------------< T I T L E _ T Y P E S >--------------------------------
Here we map a template's CitationClass to TitleType (default values for |type= parameter)
]]
local title_types = {
['AV-media-notes'] = 'Media notes',
['document'] = 'Document',
['interview'] = 'Interview',
['mailinglist'] = 'Mailing list',
['map'] = 'Map',
['podcast'] = 'Podcast',
['pressrelease'] = 'Press release',
['report'] = 'Report',
['speech'] = 'Speech',
['techreport'] = 'Technical report',
['thesis'] = 'Thesis',
}
--[[--------------------------< B U I L D _ K N O W N _ F R E E _ D O I _ R E G I S T R A N T S _ T A B L E >--
build a table of doi registrants known to be free-to-read In a doi, the registrant ID is the series of digits
between the '10.' and the first '/': in doi 10.1100/sommat, 1100 is the registrant ID
see §3.2.2 DOI prefix of the Doi Handbook p. 43
https://www.doi.org/doi-handbook/DOI_Handbook_Final.pdf#page=43
]]
local function build_free_doi_registrants_table()
local registrants_t = {};
for _, v in ipairs ({
'1045', '1074', '1096', '1100', '1155', '1186', '1194', '1371', '1629', '1989', '1999', '2147', '2196', '3285', '3389', '3390',
'3748', '3814', '3847', '3897', '4061', '4089', '4103', '4172', '4175', '4230', '4236', '4239', '4240', '4249', '4251',
'4252', '4253', '4254', '4291', '4292', '4329', '4330', '4331', '5194', '5210', '5306', '5312', '5313', '5314',
'5315', '5316', '5317', '5318', '5319', '5320', '5321', '5334', '5402', '5409', '5410', '5411', '5412',
'5492', '5493', '5494', '5495', '5496', '5497', '5498', '5499', '5500', '5501', '5527', '5528', '5662',
'6064', '6219', '7167', '7217', '7287', '7482', '7490', '7554', '7717', '7759', '7766', '9778', '11131', '11569', '11647',
'11648', '12688', '12703', '12715', '12942', '12998', '13105', '14256', '14293', '14303', '15215', '15347', '15412', '15560', '16995',
'17645', '18637', '19080', '19173', '20944', '21037', '21468', '21767', '22261', '22323', '22459', '24105', '24196', '24966',
'26775', '30845', '32545', '35711', '35712', '35713', '35995', '36648', '37126', '37532', '37871', '47128',
'47622', '47959', '52437', '52975', '53288', '54081', '54947', '55667', '55914', '57009', '58647', '59081',
}) do
registrants_t[v] = true; -- build a k/v table of known free-to-read doi registrants
end
return registrants_t;
end
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.patter', 'j.proche'}, -- Heliyon, Natural Language Processing, Patterns, 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
['11158'] = {'saasp'}, -- Systematic and Applied Acarology Special Publications
['11646'] = {'megataxa', 'mesozoic'}, -- Megataxa, Mesozoic
['14231'] = {'ag'}, -- Algebraic Geometry
['22073'] = {'pja'}, -- Persian Journal of Acarology
['35249'] = {'rche'}, -- Revista Chilena de Entomología
['37520'] = {'fi'}, -- Fossil Imprint
['53562'] = {'ajcb'} -- Asian Journal of Conservation Biology
}
--[[===================<< E R R O R M E S S A G I N G >>======================
]]
--[[----------< E R R O R M E S S A G E S U P P L I M E N T S >-------------
I18N for those messages that are supplemented with additional specific text that
describes the reason for the error
TODO: merge this with special_case_translations{}?
]]
local err_msg_supl = {
['char'] = 'invalid character', -- |isbn=, |sbn=
['check'] = 'checksum', -- |isbn=, |sbn=
['flag'] = 'flag', -- |archive-url=
['form'] = 'invalid form', -- |isbn=, |sbn=
['group'] = 'invalid group id', -- |isbn=
['initials'] = 'initials', -- Vancouver
['invalid language code'] = 'invalid language code', -- |script-<param>=
['journal'] = 'journal', -- |bibcode=
['length'] = 'length', -- |isbn=, |bibcode=, |sbn=
['liveweb'] = 'liveweb', -- |archive-url=
['missing comma'] = 'missing comma', -- Vancouver
['missing prefix'] = 'missing prefix', -- |script-<param>=
['missing title part'] = 'missing title part', -- |script-<param>=
['name'] = 'name', -- Vancouver
['non-Latin char'] = 'non-Latin character', -- Vancouver
['path'] = 'path', -- |archive-url=
['prefix'] = 'invalid prefix', -- |isbn=
['punctuation'] = 'punctuation', -- Vancouver
['save'] = 'save command', -- |archive-url=
['suffix'] = 'suffix', -- Vancouver
['timestamp'] = 'timestamp', -- |archive-url=
['unknown language code'] = 'unknown language code', -- |script-<param>=
['value'] = 'value', -- |bibcode=
['year'] = 'year', -- |bibcode=
}
--[[--------------< E R R O R _ C O N D I T I O N S >---------------------------
Error condition table. This table has two sections: errors at the top, maintenance
at the bottom. Maint 'messaging' does not have a 'message' (message=nil)
The following contains a list of IDs for various error conditions defined in the
code. For each ID, we specify a text message to display, an error category to
include, and whether the error message should be wrapped as a hidden comment.
Anchor changes require identical changes to matching anchor in Help:CS1 errors
TODO: rename error_conditions{} to something more generic; create separate error
and maint tables inside that?
]]
local error_conditions = {
err_accessdate_missing_url = {
message = '<code class="cs1-code">|access-date=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'accessdate_missing_url',
category = 'CS1 errors: access-date without URL',
hidden = false
},
err_apostrophe_markup = {
message = 'Italic or bold markup not allowed in: <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'apostrophe_markup',
category = 'CS1 errors: markup',
hidden = false
},
err_archive_date_missing_url = {
message = '<code class="cs1-code">|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; $1 suggested',
anchor = 'archive_date_url_ts_mismatch',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_missing_date = {
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|archive-date=</code>',
anchor = 'archive_missing_date',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_missing_url = {
message = '<code class="cs1-code">|archive-url=</code> requires <code class="cs1-code">|url=</code>',
anchor = 'archive_missing_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_archive_url = {
message = '<code class="cs1-code">|archive-url=</code> is malformed: $1', -- $1 is error message detail
anchor = 'archive_url',
category = 'CS1 errors: archive-url',
hidden = false
},
err_arxiv_missing = {
message = '<code class="cs1-code">|arxiv=</code> required',
anchor = 'arxiv_missing',
category = 'CS1 errors: arXiv', -- same as bad arxiv
hidden = false
},
err_asintld_missing_asin = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|asin=</code>', -- $1 is parameter name
anchor = 'asintld_missing_asin',
category = 'CS1 errors: ASIN TLD',
hidden = false
},
err_bad_arxiv = {
message = 'Check <code class="cs1-code">|arxiv=</code> value',
anchor = 'bad_arxiv',
category = 'CS1 errors: arXiv',
hidden = false
},
err_bad_asin = {
message = 'Check <code class="cs1-code">|asin=</code> value',
anchor = 'bad_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
},
err_bad_bibcode = {
message = 'Check <code class="cs1-code">|bibcode=</code> $1', -- $1 is error message detail
anchor = 'bad_bibcode',
category = 'CS1 errors: bibcode',
hidden = false
},
err_bad_biorxiv = {
message = 'Check <code class="cs1-code">|biorxiv=</code> value',
anchor = 'bad_biorxiv',
category = 'CS1 errors: bioRxiv',
hidden = false
},
err_bad_citeseerx = {
message = 'Check <code class="cs1-code">|citeseerx=</code> value',
anchor = 'bad_citeseerx',
category = 'CS1 errors: citeseerx',
hidden = false
},
err_bad_date = {
message = 'Check date values in: $1', -- $1 is a parameter name list
anchor = 'bad_date',
category = 'CS1 errors: dates',
hidden = false
},
err_bad_doi = {
message = 'Check <code class="cs1-code">|doi=</code> value',
anchor = 'bad_doi',
category = 'CS1 errors: DOI',
hidden = false
},
err_bad_hdl = {
message = 'Check <code class="cs1-code">|hdl=</code> value',
anchor = 'bad_hdl',
category = 'CS1 errors: HDL',
hidden = false
},
err_bad_isbn = {
message = 'Check <code class="cs1-code">|isbn=</code> value: $1', -- $1 is error message detail
anchor = 'bad_isbn',
category = 'CS1 errors: ISBN',
hidden = false
},
err_bad_ismn = {
message = 'Check <code class="cs1-code">|ismn=</code> value',
anchor = 'bad_ismn',
category = 'CS1 errors: ISMN',
hidden = false
},
err_bad_issn = {
message = 'Check <code class="cs1-code">|$1issn=</code> value', -- $1 is 'e' or '' for eissn or issn
anchor = 'bad_issn',
category = 'CS1 errors: ISSN',
hidden = false
},
err_bad_jfm = {
message = 'Check <code class="cs1-code">|jfm=</code> value',
anchor = 'bad_jfm',
category = 'CS1 errors: JFM',
hidden = false
},
err_bad_jstor = {
message = 'Check <code class="cs1-code">|jstor=</code> value',
anchor = 'bad_jstor',
category = 'CS1 errors: JSTOR',
hidden = false
},
err_bad_lccn = {
message = 'Check <code class="cs1-code">|lccn=</code> value',
anchor = 'bad_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
},
err_bad_mr = {
message = 'Check <code class="cs1-code">|mr=</code> value',
anchor = 'bad_mr',
category = 'CS1 errors: MR',
hidden = false
},
err_bad_oclc = {
message = 'Check <code class="cs1-code">|oclc=</code> value',
anchor = 'bad_oclc',
category = 'CS1 errors: OCLC',
hidden = false
},
err_bad_ol = {
message = 'Check <code class="cs1-code">|ol=</code> value',
anchor = 'bad_ol',
category = 'CS1 errors: OL',
hidden = false
},
err_bad_osti = {
message = 'Check <code class="cs1-code">|osti=</code> value',
anchor = 'bad_osti',
category = 'CS1 errors: OSTI',
hidden = false
},
err_bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link=
message = 'Check <code class="cs1-code">|$1=</code> value', -- $1 is parameter name
anchor = 'bad_paramlink',
category = 'CS1 errors: parameter link',
hidden = false
},
err_bad_pmc = {
message = 'Check <code class="cs1-code">|pmc=</code> value',
anchor = 'bad_pmc',
category = 'CS1 errors: PMC',
hidden = false
},
err_bad_pmid = {
message = 'Check <code class="cs1-code">|pmid=</code> value',
anchor = 'bad_pmid',
category = 'CS1 errors: PMID',
hidden = false
},
err_bad_rfc = {
message = 'Check <code class="cs1-code">|rfc=</code> value',
anchor = 'bad_rfc',
category = 'CS1 errors: RFC',
hidden = false
},
err_bad_s2cid = {
message = 'Check <code class="cs1-code">|s2cid=</code> value',
anchor = 'bad_s2cid',
category = 'CS1 errors: S2CID',
hidden = false
},
err_bad_sbn = {
message = 'Check <code class="cs1-code">|sbn=</code> value: $1', -- $1 is error message detail
anchor = 'bad_sbn',
category = 'CS1 errors: SBN',
hidden = false
},
err_bad_ssrn = {
message = 'Check <code class="cs1-code">|ssrn=</code> value',
anchor = 'bad_ssrn',
category = 'CS1 errors: SSRN',
hidden = false
},
err_bad_url = {
message = 'Check $1 value', -- $1 is parameter name
anchor = 'bad_url',
category = 'CS1 errors: URL',
hidden = false
},
err_bad_usenet_id = {
message = 'Check <code class="cs1-code">|message-id=</code> value',
anchor = 'bad_message_id',
category = 'CS1 errors: message-id',
hidden = false
},
err_bad_zbl = {
message = 'Check <code class="cs1-code">|zbl=</code> value',
anchor = 'bad_zbl',
category = 'CS1 errors: Zbl',
hidden = false
},
err_bare_url_missing_title = {
message = '$1 missing title', -- $1 is parameter name
anchor = 'bare_url_missing_title',
category = 'CS1 errors: bare URL',
hidden = false
},
err_biorxiv_missing = {
message = '<code class="cs1-code">|biorxiv=</code> required',
anchor = 'biorxiv_missing',
category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv
hidden = false
},
err_chapter_ignored = {
message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name
anchor = 'chapter_ignored',
category = 'CS1 errors: chapter ignored',
hidden = false
},
err_citation_missing_title = {
message = 'Missing or empty <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'citation_missing_title',
category = 'CS1 errors: missing title',
hidden = false
},
err_citeseerx_missing = {
message = '<code class="cs1-code">|citeseerx=</code> required',
anchor = 'citeseerx_missing',
category = 'CS1 errors: citeseerx', -- same as bad citeseerx
hidden = false
},
err_cite_web_url = { -- this error applies to cite web and to cite podcast
message = 'Missing or empty <code class="cs1-code">|url=</code>',
anchor = 'cite_web_url',
category = 'CS1 errors: requires URL',
hidden = false
},
err_class_ignored = {
message = '<code class="cs1-code">|class=</code> ignored',
anchor = 'class_ignored',
category = 'CS1 errors: class',
hidden = false
},
err_contributor_ignored = {
message = '<code class="cs1-code">|contributor=</code> ignored',
anchor = 'contributor_ignored',
category = 'CS1 errors: contributor',
hidden = false
},
err_contributor_missing_required_param = {
message = '<code class="cs1-code">|contributor=</code> requires <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'contributor_missing_required_param',
category = 'CS1 errors: contributor',
hidden = false
},
err_deprecated_params = {
message = 'Cite uses deprecated parameter <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'deprecated_params',
category = 'CS1 errors: deprecated parameters',
hidden = false
},
err_disp_name = {
message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name; $2 is the assigned value
anchor = 'disp_name',
category = 'CS1 errors: display-names',
hidden = false,
},
err_doibroken_missing_doi = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|doi=</code>', -- $1 is parameter name
anchor = 'doibroken_missing_doi',
category = 'CS1 errors: DOI',
hidden = false
},
err_embargo_missing_pmc = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|pmc=</code>', -- $1 is parameter name
anchor = 'embargo_missing_pmc',
category = 'CS1 errors: PMC embargo',
hidden = false
},
err_empty_citation = {
message = 'Empty citation',
anchor = 'empty_citation',
category = 'CS1 errors: empty citation',
hidden = false
},
err_etal = {
message = 'Explicit use of et al. in: <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'explicit_et_al',
category = 'CS1 errors: explicit use of et al.',
hidden = false
},
err_extra_text_edition = {
message = '<code class="cs1-code">|edition=</code> has extra text',
anchor = 'extra_text_edition',
category = 'CS1 errors: extra text: edition',
hidden = false,
},
err_extra_text_issue = {
message = '<code class="cs1-code">|$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',
category = 'CS1 errors: extra text: pages',
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 = false,
},
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
anchor = 'first_missing_last',
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
hidden = false
},
err_format_missing_url = {
message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|$2=</code>', -- $1 is format parameter $2 is url parameter
anchor = 'format_missing_url',
category = 'CS1 errors: format without URL',
hidden = false
},
err_generic_name = {
message = '<code class="cs1-code">|$1=</code> has generic name', -- $1 is parameter name
anchor = 'generic_name',
category = 'CS1 errors: generic name',
hidden = false,
},
err_generic_title = {
message = 'Cite uses generic title',
anchor = 'generic_title',
category = 'CS1 errors: generic title',
hidden = false,
},
err_invalid_isbn_date = {
message = 'ISBN / Date incompatibility',
anchor = 'invalid_isbn_date',
category = 'CS1 errors: ISBN date',
hidden = true
},
err_invalid_param_val = {
message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name $2 is parameter value
anchor = 'invalid_param_val',
category = 'CS1 errors: invalid parameter value',
hidden = false
},
err_invisible_char = {
message = '$1 in $2 at position $3', -- $1 is invisible char $2 is parameter name $3 is position number
anchor = 'invisible_char',
category = 'CS1 errors: invisible characters',
hidden = false
},
err_medrxiv_missing = {
message = '<code class="cs1-code">|medrxiv=</code> required',
anchor = 'medrxiv_missing',
category = 'CS1 errors: medRxiv', -- same as bad medRxiv
hidden = false
},
err_missing_name = {
message = 'Missing <code class="cs1-code">|$1$2=</code>', -- $1 is modified NameList; $2 is enumerator
anchor = 'missing_name',
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
hidden = false
},
err_missing_periodical = {
message = 'Cite $1 requires <code class="cs1-code">|$2=</code>', -- $1 is cs1 template name; $2 is canonical periodical parameter name for cite $1
anchor = 'missing_periodical',
category = 'CS1 errors: missing periodical',
hidden = false
},
err_missing_pipe = {
message = 'Missing pipe in: <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'missing_pipe',
category = 'CS1 errors: missing pipe',
hidden = false
},
err_missing_publisher = {
message = 'Cite $1 requires <code class="cs1-code">|$2=</code>', -- $1 is cs1 template name; $2 is canonical publisher parameter name for cite $1
anchor = 'missing_publisher',
category = 'CS1 errors: missing publisher',
hidden = false
},
err_numeric_names = {
message = '<code class="cs1-code">|$1=</code> has numeric name', -- $1 is parameter name',
anchor = 'numeric_names',
category = 'CS1 errors: numeric name',
hidden = false,
},
err_param_access_requires_param = {
message = '<code class="cs1-code">|$1-access=</code> requires <code class="cs1-code">|$1=</code>', -- $1 is parameter name
anchor = 'param_access_requires_param',
category = 'CS1 errors: param-access',
hidden = false
},
err_param_has_ext_link = {
message = 'External link in <code class="cs1-code">$1</code>', -- $1 is parameter name
anchor = 'param_has_ext_link',
category = 'CS1 errors: external links',
hidden = false
},
err_param_has_twl_url = {
message = 'Wikipedia Library link in <code class="cs1-code">$1</code>', -- $1 is parameter name
anchor = 'param_has_twl_url',
category = 'CS1 errors: URL',
hidden = false
},
err_parameter_ignored = {
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name
anchor = 'parameter_ignored',
category = 'CS1 errors: unsupported parameter',
hidden = false
},
err_parameter_ignored_suggest = {
message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored (<code class="cs1-code">|$2=</code> suggested)', -- $1 is unknown parameter $2 is suggested parameter name
anchor = 'parameter_ignored_suggest',
category = 'CS1 errors: unsupported parameter',
hidden = false
},
err_periodical_ignored = {
message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name
anchor = 'periodical_ignored',
category = 'CS1 errors: periodical ignored',
hidden = false
},
err_redundant_parameters = {
message = 'More than one of $1 specified', -- $1 is error message detail
anchor = 'redundant_parameters',
category = 'CS1 errors: redundant parameter',
hidden = false
},
err_script_parameter = {
message = 'Invalid <code class="cs1-code">|$1=</code>: $2', -- $1 is parameter name $2 is script language code or error detail
anchor = 'script_parameter',
category = 'CS1 errors: script parameters',
hidden = false
},
err_ssrn_missing = {
message = '<code class="cs1-code">|ssrn=</code> required',
anchor = 'ssrn_missing',
category = 'CS1 errors: SSRN',
hidden = false
},
err_text_ignored = {
message = 'Text "$1" ignored', -- $1 is ignored text
anchor = 'text_ignored',
category = 'CS1 errors: unrecognized parameter',
hidden = false
},
err_trans_missing_title = {
message = '<code class="cs1-code">|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',
category = 'CS1 errors: translated title',
hidden = false
},
err_param_unknown_empty = {
message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is emty unknown param list
anchor = 'param_unknown_empty',
category = 'CS1 errors: empty unknown parameters',
hidden = false
},
err_vancouver = {
message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name
anchor = 'vancouver',
category = 'CS1 errors: Vancouver style',
hidden = false
},
err_wikilink_in_url = {
message = 'URL–wikilink conflict', -- uses ndash
anchor = 'wikilink_in_url',
category = 'CS1 errors: URL–wikilink conflict', -- uses ndash
hidden = false
},
--[[--------------------------< M A I N T >-------------------------------------
maint messages do not have a message (message = nil); otherwise the structure
is the same as error messages
]]
maint_archived_copy = {
message = nil,
anchor = 'archived_copy',
category = 'CS1 maint: archived copy as title',
hidden = true,
},
maint_bibcode = {
message = nil,
anchor = 'bibcode',
category = 'CS1 maint: bibcode',
hidden = true,
},
maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite
message = nil,
anchor = 'location_no_publisher',
category = 'CS1 maint: location missing publisher',
hidden = true,
},
maint_bot_unknown = {
message = nil,
anchor = 'bot:_unknown',
category = 'CS1 maint: bot: original URL status unknown',
hidden = true,
},
maint_date_auto_xlated = { -- date auto-translation not supported by en.wiki
message = nil,
anchor = 'date_auto_xlated',
category = 'CS1 maint: date auto-translated',
hidden = true,
},
maint_date_format = {
message = nil,
anchor = 'date_format',
category = 'CS1 maint: date format',
hidden = true,
},
maint_date_year = {
message = nil,
anchor = 'date_year',
category = 'CS1 maint: date and year',
hidden = true,
},
maint_doi_ignore = {
message = nil,
anchor = 'doi_ignore',
category = 'CS1 maint: ignored DOI errors',
hidden = true,
},
maint_doi_inactive = {
message = nil,
anchor = 'doi_inactive',
category = 'CS1 maint: DOI inactive',
hidden = true,
},
maint_doi_inactive_dated = {
message = nil,
anchor = 'doi_inactive_dated',
category = 'CS1 maint: DOI inactive as of $2$3$1', -- $1 is year, $2 is month-name or empty string, $3 is space or empty string
hidden = true,
},
maint_doi_unflagged_free = {
message = nil,
anchor = 'doi_unflagged_free',
category = 'CS1 maint: unflagged free DOI',
hidden = true,
},
maint_extra_punct = {
message = nil,
anchor = 'extra_punct',
category = 'CS1 maint: extra punctuation',
hidden = true,
},
maint_id_limit_load_fail = { -- applies to all cs1|2 templates on a page;
message = nil, -- maint message (category link) never emitted
anchor = 'id_limit_load_fail',
category = 'CS1 maint: ID limit load fail',
hidden = true,
},
maint_isbn_ignore = {
message = nil,
anchor = 'ignore_isbn_err',
category = 'CS1 maint: ignored ISBN errors',
hidden = true,
},
maint_issn_ignore = {
message = nil,
anchor = 'ignore_issn',
category = 'CS1 maint: ignored ISSN errors',
hidden = true,
},
maint_jfm_format = {
message = nil,
anchor = 'jfm_format',
category = 'CS1 maint: JFM format',
hidden = true,
},
maint_location = {
message = nil,
anchor = 'location',
category = 'CS1 maint: location',
hidden = true,
},
maint_missing_class = {
message = nil,
anchor = 'missing_class',
category = 'CS1 maint: missing class',
hidden = true,
},
maint_mr_format = {
message = nil,
anchor = 'mr_format',
category = 'CS1 maint: MR format',
hidden = true,
},
maint_mult_names = {
message = nil,
anchor = 'mult_names',
category = 'CS1 maint: multiple names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_numeric_names = {
message = nil,
anchor = 'numeric_names',
category = 'CS1 maint: numeric names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_others = {
message = nil,
anchor = 'others',
category = 'CS1 maint: others',
hidden = true,
},
maint_others_avm = {
message = nil,
anchor = 'others_avm',
category = 'CS1 maint: others in cite AV media (notes)',
hidden = true,
},
maint_overridden_setting = {
message = nil,
anchor = 'overridden',
category = 'CS1 maint: overridden setting',
hidden = true,
},
maint_page_art_num = {
message = nil,
anchor = 'page_art_num',
category = 'CS1 maint: article number as page number',
hidden = true,
},
maint_pmc_embargo = {
message = nil,
anchor = 'embargo',
category = 'CS1 maint: PMC embargo expired',
hidden = true,
},
maint_pmc_format = {
message = nil,
anchor = 'pmc_format',
category = 'CS1 maint: PMC format',
hidden = true,
},
maint_postscript = {
message = nil,
anchor = 'postscript',
category = 'CS1 maint: postscript',
hidden = true,
},
maint_publisher_location = {
message = nil,
anchor = 'publisher_location',
category = 'CS1 maint: publisher location',
hidden = true,
},
maint_ref_duplicates_default = {
message = nil,
anchor = 'ref_default',
category = 'CS1 maint: ref duplicates default',
hidden = true,
},
maint_unknown_lang = {
message = nil,
anchor = 'unknown_lang',
category = 'CS1 maint: unrecognized language',
hidden = true,
},
maint_untitled = {
message = nil,
anchor = 'untitled',
category = 'CS1 maint: untitled periodical',
hidden = true,
},
maint_url_status = {
message = nil,
anchor = 'url_status',
category = 'CS1 maint: url-status',
hidden = true,
},
maint_year= {
message = nil,
anchor = 'year',
category = 'CS1 maint: year',
hidden = true,
},
maint_zbl = {
message = nil,
anchor = 'zbl',
category = 'CS1 maint: Zbl',
hidden = true,
},
}
--[[--------------------------< I D _ L I M I T S _ D A T A _ T >----------------------------------------------
fetch id limits for certain identifiers from c:Data:CS1/Identifier limits.tab. This source is a json tabular
data file maintained at wikipedia commons. Convert the json format to a table of k/v pairs.
The values from <id_limits_data_t> are used to set handle.id_limit.
From 2025-02-21, MediaWiki is broken. Use this link to edit the tablular data file:
https://commons.wikimedia.org/w/index.php?title=Data:CS1/Identifier_limits.tab&action=edit
See Phab:T389105
]]
local id_limits_data_t = {};
local use_commons_data = true; -- set to false if your wiki does not have access to mediawiki commons; then,
if false == use_commons_data then -- update this table from https://commons.wikimedia.org/wiki/Data:CS1/Identifier_limits.tab; last update: 2025-02-21
id_limits_data_t = {['OCLC'] = 10450000000, ['OSTI'] = 23010000, ['PMC'] = 11900000, ['PMID'] = 40400000, ['RFC'] = 9300, ['SSRN'] = 5200000, ['S2CID'] = 276000000}; -- this table must be maintained locally
else -- here for wikis that do have access to mediawiki commons
local load_fail_limit = 99999999999; -- very high number to avoid error messages on load failure
id_limits_data_t = {['OCLC'] = load_fail_limit, ['OSTI'] = load_fail_limit, ['PMC'] = load_fail_limit, ['PMID'] = load_fail_limit, ['RFC'] = load_fail_limit, ['SSRN'] = load_fail_limit, ['S2CID'] = load_fail_limit};
local id_limits_data_load_fail = false; -- flag; assume that we will be successful when loading json id limit tabular data
local tab_data_t = mw.ext.data.get ('CS1/Identifier limits.tab'); -- attempt to load the tabular 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.data) do -- overwrite default <load_fail_limit> values from the data table in the tabular data
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
--[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
The following contains a list of values for various defined identifiers. For each
identifier we specify a variety of information necessary to properly render the
identifier in the citation.
parameters: a list of parameter aliases for this identifier; first in the list is the canonical form
link: Wikipedia article name
redirect: a local redirect to a local Wikipedia article name; at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'
q: Wikidata q number for the identifier
label: the label preceding the identifier; label is linked to a Wikipedia article (in this order):
redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true
Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q
local article name from id_handlers['<id>'].link
prefix: the first part of a URL that will be concatenated with a second part which usually contains the identifier
suffix: optional third part to be added after the identifier
encode: true if URI should be percent-encoded; otherwise false
COinS: identifier link or keyword for use in COinS:
for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn
for |asin= and |ol=, which require assembly, use the keyword: url
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here)
set to nil to leave the identifier out of the COinS
separator: character or text between label and the identifier in the rendered citation
id_limit: for those identifiers with established limits, this property holds the upper limit
access: use this parameter to set the access level for all instances of this identifier.
the value must be a valid access level for an identifier (see ['id-access'] in this file).
custom_access: to enable custom access level for an identifier, set this parameter
to the parameter that should control it (normally 'id-access')
]]
local id_handlers = {
['ARXIV'] = {
parameters = {'arxiv', 'eprint'},
link = 'arXiv',
redirect = 'wikipedia:ArXiv',
q = 'Q118398',
label = 'arXiv',
prefix = 'https://arxiv.org/abs/',
encode = false,
COinS = 'info:arxiv',
separator = ':',
access = 'free', -- free to read
},
['ASIN'] = {
parameters = { 'asin', 'ASIN' },
link = 'Amazon Standard Identification Number',
redirect = 'wikipedia:Amazon Standard Identification Number',
q = 'Q1753278',
label = 'ASIN',
prefix = 'https://www.amazon.',
COinS = 'url',
separator = ' ',
encode = false;
},
['BIBCODE'] = {
parameters = {'bibcode'},
link = 'Bibcode',
redirect = 'wikipedia:Bibcode',
q = 'Q25754',
label = 'Bibcode',
prefix = 'https://ui.adsabs.harvard.edu/abs/',
encode = false,
COinS = 'info:bibcode',
separator = ':',
custom_access = 'bibcode-access',
},
['BIORXIV'] = {
parameters = {'biorxiv'},
link = 'bioRxiv',
redirect = 'wikipedia:BioRxiv',
q = 'Q19835482',
label = 'bioRxiv',
prefix = 'https://doi.org/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = ' ',
},
['CITESEERX'] = {
parameters = {'citeseerx'},
link = 'CiteSeerX',
redirect = 'wikipedia:CiteSeerX',
q = 'Q2715061',
label = 'CiteSeerX',
prefix = 'https://citeseerx.ist.psu.edu/viewdoc/summary?doi=',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = ' ',
},
['DOI'] = { -- Used by InternetArchiveBot
parameters = { 'doi', 'DOI'},
link = 'Digital object identifier',
redirect = 'wikipedia:Digital object identifier',
q = 'Q25670',
label = 'doi',
prefix = 'https://doi.org/',
COinS = 'info:doi',
separator = ':',
encode = true,
custom_access = 'doi-access',
},
['EISSN'] = {
parameters = {'eissn', 'EISSN'},
link = 'International Standard Serial Number#Electronic ISSN',
redirect = 'wikipedia:ISSN#Electronic ISSN',
q = 'Q46339674',
label = 'eISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.eissn',
encode = false,
separator = ' ',
},
['HDL'] = {
parameters = { 'hdl', 'HDL' },
link = 'Handle System',
redirect = 'wikipedia:Handle System',
q = 'Q3126718',
label = 'hdl',
prefix = 'https://hdl.handle.net/',
COinS = 'info:hdl',
separator = ':',
encode = true,
custom_access = 'hdl-access',
},
['ISBN'] = { -- Used by InternetArchiveBot
parameters = {'isbn', 'ISBN'},
link = 'International Standard Book Number',
redirect = 'wikipedia:ISBN',
q = 'Q33057',
label = 'ISBN',
prefix = 'Special:BookSources/',
COinS = 'rft.isbn',
separator = ' ',
},
['ISMN'] = {
parameters = {'ismn', 'ISMN'},
link = 'International Standard Music Number',
redirect = 'wikipedia:International Standard Music Number',
q = 'Q1666938',
label = 'ISMN',
prefix = '', -- not currently used;
COinS = nil, -- nil because we can't use pre or rft or info:
separator = ' ',
},
['ISSN'] = {
parameters = {'issn', 'ISSN'},
link = 'International Standard Serial Number',
redirect = 'wikipedia:ISSN',
q = 'Q131276',
label = 'ISSN',
prefix = 'https://search.worldcat.org/issn/',
COinS = 'rft.issn',
encode = false,
separator = ' ',
},
['JFM'] = {
parameters = {'jfm', 'JFM'},
link = 'Jahrbuch über die Fortschritte der Mathematik',
redirect = 'wikipedia:ZbMATH Open#Jahrbuch über die Fortschritte der Mathematik',
q = '',
label = 'JFM',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
['JSTOR'] = {
parameters = {'jstor', 'JSTOR'},
link = 'JSTOR',
redirect = 'wikipedia:JSTOR#Content',
q = 'Q1420342',
label = 'JSTOR',
prefix = 'https://www.jstor.org/stable/',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
custom_access = 'jstor-access',
},
['LCCN'] = {
parameters = {'lccn', 'LCCN'},
link = 'Library of Congress Control Number',
redirect = 'wikipedia:Library of Congress Control Number',
q = 'Q620946',
label = 'LCCN',
prefix = 'https://lccn.loc.gov/',
COinS = 'info:lccn',
encode = false,
separator = ' ',
},
['MEDRXIV'] = {
parameters = {'medrxiv'},
link = 'medRxiv',
redirect = 'wikipedia:MedRxiv',
q = 'Q58465838',
label = 'medRxiv',
prefix = 'https://www.medrxiv.org/content/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = false,
separator = ' ',
},
['MR'] = {
parameters = {'mr', 'MR'},
link = 'Mathematical Reviews',
redirect = 'wikipedia:Mathematical Reviews#Online database',
q = 'Q211172',
label = 'MR',
prefix = 'https://mathscinet.ams.org/mathscinet-getitem?mr=',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
['OCLC'] = {
parameters = {'oclc', 'OCLC'},
link = 'OCLC',
redirect = 'wikipedia:OCLC#Identifiers and linked data',
q = 'Q190593',
label = 'OCLC',
prefix = 'https://search.worldcat.org/oclc/',
COinS = 'info:oclcnum',
encode = true,
separator = ' ',
id_limit = id_limits_data_t.OCLC or 0,
},
['OL'] = {
parameters = { 'ol', 'OL' },
link = 'Open Library',
redirect = 'wikipedia:Open Library',
q = 'Q1201876',
label = 'OL',
prefix = 'https://openlibrary.org/',
COinS = 'url',
separator = ' ',
encode = true,
custom_access = 'ol-access',
},
['OSTI'] = {
parameters = {'osti', 'OSTI'},
link = 'Office of Scientific and Technical Information',
redirect = 'wikipedia:Office of Scientific and Technical Information',
q = 'Q2015776',
label = 'OSTI',
prefix = 'https://www.osti.gov/biblio/',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit = id_limits_data_t.OSTI or 0,
custom_access = 'osti-access',
},
['PMC'] = {
parameters = {'pmc', 'PMC'},
link = 'PubMed Central',
redirect = 'wikipedia:PubMed Central#PMCID',
q = 'Q229883',
label = 'PMC',
prefix = 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC',
suffix = '',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit = id_limits_data_t.PMC or 0,
access = 'free', -- free to read
},
['PMID'] = {
parameters = {'pmid', 'PMID'},
link = 'PubMed Identifier',
redirect = 'wikipedia:PubMed#PubMed identifier',
q = 'Q2082879',
label = 'PMID',
prefix = 'https://pubmed.ncbi.nlm.nih.gov/',
COinS = 'info:pmid',
encode = false,
separator = ' ',
id_limit = id_limits_data_t.PMID or 0,
},
['RFC'] = {
parameters = {'rfc', 'RFC'},
link = 'Request for Comments',
redirect = 'wikipedia:Request for Comments',
q = 'Q212971',
label = 'RFC',
prefix = 'https://tools.ietf.org/html/rfc',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
id_limit = id_limits_data_t.RFC or 0,
access = 'free', -- free to read
},
['SBN'] = {
parameters = {'sbn', 'SBN'},
link = 'Standard Book Number', -- redirect to International_Standard_Book_Number#History
redirect = 'wikipedia:ISBN#History',
label = 'SBN',
prefix = 'Special:BookSources/0-', -- prefix has leading zero necessary to make 9-digit sbn a 10-digit isbn
COinS = nil, -- nil because we can't use pre or rft or info:
separator = ' ',
},
['SSRN'] = {
parameters = {'ssrn', 'SSRN'},
link = 'Social Science Research Network',
redirect = 'wikipedia:Social Science Research Network',
q = 'Q7550801',
label = 'SSRN',
prefix = 'https://papers.ssrn.com/sol3/papers.cfm?abstract_id=',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
id_limit = id_limits_data_t.SSRN or 0,
custom_access = 'ssrn-access',
},
['S2CID'] = {
parameters = {'s2cid', 'S2CID'},
link = 'Semantic Scholar',
redirect = 'wikipedia:Semantic Scholar#Article identifier',
q = 'Q22908627',
label = 'S2CID',
prefix = 'https://api.semanticscholar.org/CorpusID:',
COinS = 'pre', -- use prefix value
encode = false,
separator = ' ',
id_limit = id_limits_data_t.S2CID or 0,
custom_access = 's2cid-access',
},
['USENETID'] = {
parameters = {'message-id'},
link = 'Usenet',
redirect = 'wikipedia:Usenet',
q = 'Q193162',
label = 'Usenet:',
prefix = 'news:',
encode = false,
COinS = 'pre', -- use prefix value
separator = ' ',
},
['ZBL'] = {
parameters = {'zbl', 'ZBL' },
link = 'Zentralblatt MATH',
redirect = 'wikipedia:ZbMATH Open',
q = 'Q190269',
label = 'Zbl',
prefix = 'https://zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = ' ',
},
}
--[[--------------------------< E X P O R T S >---------------------------------
]]
return {
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,
date_name_auto_xlate_enable = date_name_auto_xlate_enable,
date_digit_auto_xlate_enable = date_digit_auto_xlate_enable,
enable_sort_keys = enable_sort_keys,
-- 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),
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,
aliases = aliases,
special_case_translation = special_case_translation,
date_names = date_names,
err_msg_supl = err_msg_supl,
error_conditions = error_conditions,
editor_markup_patterns = editor_markup_patterns,
et_al_patterns = et_al_patterns,
extended_registrants_t = extended_registrants_t,
id_handlers = id_handlers,
keywords_lists = keywords_lists,
keywords_xlate = keywords_xlate,
stripmarkers = stripmarkers,
invisible_chars = invisible_chars,
invisible_defs = invisible_defs,
indic_script = indic_script,
emoji_t = emoji_t,
maint_cats = maint_cats,
messages = messages,
presentation = presentation,
prop_cats = prop_cats,
script_lang_codes = script_lang_codes,
lang_tag_remap = lang_tag_remap,
lang_name_remap = lang_name_remap,
this_wiki_code = this_wiki_code,
title_types = title_types,
uncategorized_namespaces = uncategorized_namespaces_t,
uncategorized_subpages = uncategorized_subpages,
templates_using_volume = templates_using_volume,
templates_using_issue = templates_using_issue,
templates_not_using_page = templates_not_using_page,
vol_iss_pg_patterns = vol_iss_pg_patterns,
single_letter_2nd_lvl_domains_t = single_letter_2nd_lvl_domains_t,
url_access_map_t = url_access_map_t,
inter_wiki_map = inter_wiki_map,
mw_languages_by_tag_t = mw_languages_by_tag_t,
mw_languages_by_name_t = mw_languages_by_name_t,
citation_class_map_t = citation_class_map_t,
citation_issue_t = citation_issue_t,
citation_no_volume_t = citation_no_volume_t,
}
