4,507
edits
wp>Trappist the monk (bump ssrn;) |
m (1 revision imported) |
||
(4 intermediate revisions by 3 users not shown) | |||
Line 1: | Line 1: | ||
local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates | local lang_obj = mw.language.getContentLanguage(); -- make a language object for the local language; used here for languages and dates | ||
--[[--------------------------< S E T T I N G S >-------------------------------------------------------------- | |||
boolean settings used to control various things. these setting located here to make them easy to find | |||
]] | |||
-- these settings local to this module only | |||
local local_digits_from_mediawiki = false; -- for i18n; when true, module fills date_names['local_digits'] from MediaWiki; manual fill required else; always false at en.wiki | |||
local local_date_names_from_mediawiki = false; -- for i18n; when true, module fills date_names['local']['long'] and date_names['local']['short'] from MediaWiki; | |||
-- manual translation required else; ; always false at en.wiki | |||
-- these settings exported to other modules | |||
local use_identifier_redirects = true; -- when true use redirect name for identifier label links; always true at en.wiki | |||
local local_lang_cat_enable = false; -- when true categorizes pages where |language=<local wiki's language>; always false at en.wiki | |||
local date_name_auto_xlate_enable = false; -- when true translates English month-names to the local-wiki's language month names; always false at en.wiki | |||
local date_digit_auto_xlate_enable = false; -- when true translates Western date digit to the local-wiki's language digits (date_names['local_digits']); always false at en.wiki | |||
--[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------ | --[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------ | ||
Line 34: | Line 52: | ||
['archived-dead'] = 'Archived from $1 on $2', | ['archived-dead'] = 'Archived from $1 on $2', | ||
['archived-live'] = '$1 from the original on $2', | ['archived-live'] = '$1 from the original on $2', | ||
['archived-unfit'] = 'Archived from the original on ', | ['archived-unfit'] = 'Archived from the original on ', | ||
['archived'] = 'Archived', | ['archived'] = 'Archived', | ||
Line 48: | Line 65: | ||
['inset'] = '$1 inset', | ['inset'] = '$1 inset', | ||
['interview'] = 'Interviewed by $1', | ['interview'] = 'Interviewed by $1', | ||
['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name | ['mismatch'] = '<code class="cs1-code">|$1=</code> / <code class="cs1-code">|$2=</code> mismatch', -- $1 is year param name; $2 is date param name | ||
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1', | ['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]: $1', | ||
Line 125: | Line 141: | ||
local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n | local citation_class_map_t = { -- TODO: if kept, these and all other config.CitationClass 'names' require some sort of i18n | ||
['arxiv'] = 'arXiv', | |||
['audio-visual'] = 'AV media', | ['audio-visual'] = 'AV media', | ||
['AV-media-notes'] = 'AV media notes', | ['AV-media-notes'] = 'AV media notes', | ||
['biorxiv'] = 'bioRxiv', | |||
['citeseerx'] = 'CiteSeerX', | |||
['encyclopaedia'] = 'encyclopedia', | ['encyclopaedia'] = 'encyclopedia', | ||
['mailinglist'] = 'mailing list', | ['mailinglist'] = 'mailing list', | ||
['pressrelease'] = 'press release' | ['medrxiv'] = 'medRxiv', | ||
['pressrelease'] = 'press release', | |||
['ssrn'] = 'SSRN', | |||
['techreport'] = 'tech report', | |||
} | } | ||
Line 275: | Line 297: | ||
['Issue'] = {'issue', 'number'}, | ['Issue'] = {'issue', 'number'}, | ||
['Language'] = {'language', 'lang'}, | ['Language'] = {'language', 'lang'}, | ||
['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only | ['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only | ||
['Map'] = 'map', -- cite map only | ['Map'] = 'map', -- cite map only | ||
Line 326: | Line 344: | ||
['Title'] = 'title', -- Used by InternetArchiveBot | ['Title'] = 'title', -- Used by InternetArchiveBot | ||
['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot | ['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot | ||
['TitleNote'] = 'department', | ['TitleNote'] = {'title-note', 'department'}, | ||
['TitleType'] = {'type', 'medium'}, | ['TitleType'] = {'type', 'medium'}, | ||
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', | ['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution', | ||
Line 332: | Line 350: | ||
['Transcript'] = 'transcript', | ['Transcript'] = 'transcript', | ||
['TranscriptFormat'] = 'transcript-format', | ['TranscriptFormat'] = 'transcript-format', | ||
['TranscriptURL'] = | ['TranscriptURL'] = 'transcript-url', -- Used by InternetArchiveBot | ||
['TransMap'] = 'trans-map', -- cite map only | ['TransMap'] = 'trans-map', -- cite map only | ||
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', | ['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper', | ||
Line 347: | Line 365: | ||
['Year'] = 'year', | ['Year'] = 'year', | ||
['AuthorList-First'] = {"first#", "author-first#", "author#-first", "given#", | ['AuthorList-First'] = {"first#", "author-first#", "author#-first", "author-given#", "author#-given", | ||
" | "subject-first#", "subject#-first", "subject-given#", "subject#-given", | ||
['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "surname#", | "given#"}, | ||
" | ['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "author-surname#", "author#-surname", | ||
"subject-last#", "subject#-last", "subject-surname#", "subject#-surname", | |||
"author#", 'host#', "subject#", "surname#"}, | |||
['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#", | ['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#", | ||
"subject#-link", "authorlink#", "author#link"}, | "subject#-link", "authorlink#", "author#link"}, | ||
Line 394: | Line 414: | ||
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | 'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators | ||
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous | 'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous | ||
'ArchiveURL', 'ChapterURL', 'ConferenceURL | 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters | ||
} | } | ||
local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value | local url_meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value | ||
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID | 'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'ID', 'MapURL', 'TranscriptURL', 'URL', -- parameters allowed to hold urls | ||
'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls | 'Page', 'Pages', 'At', 'QuotePage', 'QuotePages', -- insource locators allowed to hold urls | ||
} | } | ||
Line 617: | Line 637: | ||
date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd | date_names[invert_t[2]][i] = name; -- invert to get [i] = 'name' for conversions from ymd | ||
end | end | ||
end | |||
if local_digits_from_mediawiki then -- if fetching local digits from MediaWiki is enabled | |||
local digits_t = {}; | |||
for i=0, 9 do -- loop 10x and | |||
digits_t [lang_obj:formatNum (i)] = tostring (i); -- format the loop indexer as local lang table index and assign loop indexer (a string) as the value | |||
end | |||
date_names['local_digits'] = digits_t; | |||
end | end | ||
Line 638: | Line 666: | ||
'{{ *([Mm]DY) *[|}]', -- 0 | '{{ *([Mm]DY) *[|}]', -- 0 | ||
} | } | ||
local title_object = mw.title.getCurrentTitle(); | |||
local content; -- done this way so that unused templates appear in unused-template-reports; self-transcluded makes them look like they are used | |||
if 10 ~= title_object.namespace then -- all namespaces except Template | |||
content = title_object:getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625 | |||
end | |||
local function get_date_format () | local function get_date_format () | ||
-- if title_object.namespace == 10 then -- not in template space so that unused templates appear in unused-template-reports; | |||
if not content then -- nil content when we're in template | |||
return nil; -- auto-formatting does not work in Template space so don't set global_df | return nil; -- auto-formatting does not work in Template space so don't set global_df | ||
end | end | ||
for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects | for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects | ||
local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format | local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format | ||
if match then | if match then | ||
local use_dates_template = content:match ('%b{}', start); -- get the whole template | |||
if | if use_dates_template:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length | ||
return match:lower() .. '-' .. | return match:lower() .. '-' .. use_dates_template:match ('| *cs1%-dates *= *([lsy][sy]?)'); | ||
else | else | ||
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df= | return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df= | ||
Line 658: | Line 691: | ||
end | end | ||
local global_df; | local global_df; -- TODO: add this to <global_cs1_config_t>? | ||
Line 850: | Line 883: | ||
--[[---------------------< S | --[[--------------------------< C S 1 _ C O N F I G _ G E T >-------------------------------------------------- | ||
fetch and validate values from {{cs1 config}} template to fill <global_cs1_config_t> | |||
no error messages; when errors are detected, the parameter value from {{cs1 config}} is blanked. | |||
Supports all parameters and aliases associated with the metaparameters: DisplayAuthors, DisplayContributors, | |||
DisplayEditors, DisplayInterviewers, DisplayTranslators, NameListStyle, and Mode. The DisplayWhatever metaparameters | |||
accept numeric values only (|display-authors=etal and the like is not supported). | |||
]] | ]] | ||
local | local global_cs1_config_t = {}; -- TODO: add value returned from get_date_format() to this table? | ||
local function get_cs1_config () | |||
-- if title_object.namespace == 10 then -- not in template space so that unused templates appear in unused-template-reports; | |||
if not content then -- nil content when we're in template | |||
return nil; -- auto-formatting does not work in Template space so don't set global_df | |||
end | |||
local start = content:find('{{ *[Cc][Ss]1 config *[|}]'); -- <start> is offset into <content> when {{cs1 config}} found; nil else | |||
if start then | |||
local cs1_config_template = content:match ('%b{}', start); -- get the whole template | |||
if not cs1_config_template then | |||
return nil; | |||
end | |||
Also here is a pattern that recognizes stripmarkers that begin and end with the | 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) | ||
delete characters. The nowiki stripmarker is not an error but some others are | table.remove (params_t, 1); -- remove the template name because it isn't a parameter/value pair | ||
because the parameter values that include them become part of the template's | |||
metadata before stripmarker replacement. | 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 | |||
local invisible_defs = { | if 'table' == type (aliases[meta_param]) then -- if <meta_param> is a sequence, | ||
del = '\127', -- used to distinguish between stripmarker and del char | for _, param in ipairs (aliases[meta_param]) do -- extract its contents | ||
zwj = '\226\128\141', -- used with capture because zwj may be allowed | meta_param_map_t[param] = meta_param; -- and add to <meta_param_map_t> | ||
} | end | ||
else | |||
local invisible_chars = { | meta_param_map_t[aliases[meta_param]] = meta_param; -- not a sequence so just add the parameter to <meta_param_map_t> | ||
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD | end | ||
{'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed | end | ||
{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B | |||
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A | local keywords_t = {}; -- map valid keywords to their associate metaparameter; reverse form of <keyword_lists[key] for these metaparameters | ||
{'soft hyphen', '\194\173'}, -- U+00AD, C2 AD | for _, metaparam_t in ipairs ({{'NameListStyle', 'name-list-style'}, {'Mode', 'mode'}}) do -- only these metaparameter / keywords_lists key pairs | ||
{'horizontal tab', '\009'}, -- U+0009 (HT), 09 | for _, keyword in ipairs (keywords_lists[metaparam_t[2]]) do -- spin through the list of keywords | ||
{'line feed', '\010'}, -- U+000A (LF), 0A | keywords_t[keyword] = metaparam_t[1]; -- add [keyword] = metaparameter to the map | ||
{'no-break space', '\194\160'}, -- U+00A0 (NBSP), C2 A0 | end | ||
{'carriage return', '\013'}, -- U+000D (CR), 0D | end | ||
{'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 | for _, param in ipairs (params_t) do -- spin through the {{cs1 config}} parameters and fill <global_cs1_config_t> | ||
{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D)) | local k, v = param:match ('([^=]-)%s*=%s*(.+)'); -- <k> is the parameter name; <v> is parameter's assigned value | ||
{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F | if k then | ||
-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF | if k:find ('^display') then -- if <k> is one of the |display-<namelist>= parameters | ||
-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF | if v:match ('%d+') then -- the assigned value must be digits; doesn't accept 'etal' | ||
-- {'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 | global_cs1_config_t[meta_param_map_t[k]]=v; -- add the display param and its value to globals table | ||
-- {'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 | 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/15.0/emoji-zwj-sequences.txt; version: 15.0; 2022-05-06 | |||
-- table created by: [[:en:Module:Make emoji zwj table]] | |||
local emoji_t = { -- indexes are decimal forms of the hex values in U+xxxx | |||
[9760] = true, -- U+2620 ☠ skull and crossbones | |||
[9792] = true, -- U+2640 ♀ female sign | |||
[9794] = true, -- U+2642 ♂ male sign | |||
[9877] = true, -- U+2695 ⚕ staff of aesculapius | |||
[9878] = true, -- U+2696 ⚖ scales | |||
[9895] = true, -- U+26A7 ⚧ male with stroke and male and female sign | |||
[9992] = true, -- U+2708 ✈ airplane | |||
[10052] = true, -- U+2744 ❄ snowflake | |||
[10084] = true, -- U+2764 ❤ heavy black heart | |||
[11035] = true, -- U+2B1B ⬛ black large square | |||
[127752] = true, -- U+1F308 🌈 rainbow | |||
[127787] = true, -- U+1F32B 🌫 fog | |||
[127806] = true, -- U+1F33E 🌾 ear of rice | |||
[127859] = true, -- U+1F373 🍳 cooking | |||
[127868] = true, -- U+1F37C 🍼 baby bottle | |||
[127876] = true, -- U+1F384 🎄 christmas tree | |||
[127891] = true, -- U+1F393 🎓 graduation cap | |||
[127908] = true, -- U+1F3A4 🎤 microphone | |||
[127912] = true, -- U+1F3A8 🎨 artist palette | |||
[127979] = true, -- U+1F3EB 🏫 school | |||
[127981] = true, -- U+1F3ED 🏭 factory | |||
[128102] = true, -- U+1F466 👦 boy | |||
[128103] = true, -- U+1F467 👧 girl | |||
[128104] = true, -- U+1F468 👨 man | |||
[128105] = true, -- U+1F469 👩 woman | |||
[128139] = true, -- U+1F48B 💋 kiss mark | |||
[128168] = true, -- U+1F4A8 💨 dash symbol | |||
[128171] = true, -- U+1F4AB 💫 dizzy symbol | |||
[128187] = true, -- U+1F4BB 💻 personal computer | |||
[128188] = true, -- U+1F4BC 💼 brief case | |||
[128293] = true, -- U+1F525 🔥 fire | |||
[128295] = true, -- U+1F527 🔧 wrench | |||
[128300] = true, -- U+1F52C 🔬 microscope | |||
[128488] = true, -- U+1F5E8 🗨 left speech bubble | |||
[128640] = true, -- U+1F680 🚀 rocket | |||
[128658] = true, -- U+1F692 🚒 fire engine | |||
[129309] = true, -- U+1F91D 🤝 handshake | |||
[129455] = true, -- U+1F9AF 🦯 probing cane | |||
[129456] = true, -- U+1F9B0 🦰 emoji component red hair | |||
[129457] = true, -- U+1F9B1 🦱 emoji component curly hair | |||
[129458] = true, -- U+1F9B2 🦲 emoji component bald | |||
[129459] = true, -- U+1F9B3 🦳 emoji component white hair | |||
[129466] = true, -- U+1F9BA 🦺 safety vest | |||
[129468] = true, -- U+1F9BC 🦼 motorized wheelchair | |||
[129469] = true, -- U+1F9BD 🦽 manual wheelchair | |||
[129489] = true, -- U+1F9D1 🧑 adult | |||
[129657] = true, -- U+1FA79 🩹 adhesive bandage | |||
[129778] = true, -- U+1FAF2 🫲 leftwards hand | |||
} | } | ||
--[[----------------------< L A N G U A G E S U P P O R T >------------------- | |||
These tables and constants support various language-specific functionality. | |||
]] | |||
--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 | 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', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', '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', 'tt', 'ug', 'uk', 'ur', 'uz', 'yi', 'yue', 'zh' | |||
}; | |||
-- | |||
-- | --[[---------------< L A N G U A G E R E M A P P I N G >---------------------- | ||
-- | |||
These tables hold language information that is different (correct) from MediaWiki's definitions | |||
For each ['<tag>'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', '<tag>'} in lang_name_remap{} | |||
lang_tag_remap{}: | |||
key is always lowercase ISO 639-1, -2, -3 language tag or a valid lowercase IETF language tag | |||
value is properly spelled and capitalized language name associated with <tag> | |||
only one language name per <tag>; | |||
key/value pair must have matching entry in lang_name_remap{} | |||
lang_name_remap{}: | |||
key is always lowercase language name | |||
value is a table the holds correctly spelled and capitalized language name [1] and associated tag [2] (tag must match a tag key in lang_tag_remap{}) | |||
may have multiple keys referring to a common preferred name and tag; For example: | |||
['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh' | |||
]] | |||
local lang_tag_remap = { -- used for |language= and |script-title= / |script-chapter= | |||
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch | |||
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org | |||
[ | ['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name | ||
['bn'] = 'Bengali', -- MediaWiki returns Bangla | |||
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan | |||
['fkv'] = 'Kven', -- MediaWiki returns Kvensk | |||
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name | |||
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name | |||
['ksh-x-colog'] = 'Colognian', -- override MediaWiki ksh; no IANA/ISO 639 code for Colognian; IETF private code created at Module:Lang/data | |||
['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data | |||
['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
[ | |||
} | } | ||
local lang_name_remap = { -- used for |language=; names require proper capitalization; tags must be lowercase | |||
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org | |||
['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 | |||
['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 | |||
} | |||
These | --[[---------------< 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 | |||
['jul-greg-uncertainty'] = 'CS1: Julian–Gregorian uncertainty', -- probably temporary cat to identify scope of template with dates 1 October 1582 – 1 January 1926 | |||
['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', | |||
local | ['long-vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 characters | ||
['script'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code | |||
['tracked-param'] = 'CS1 tracked parameter: $1', -- $1 is base (enumerators removed) parameter name | |||
['year-range-abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form | |||
} | |||
--[[-------------------< 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 | 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', | |||
} | |||
--[[ | --[[===================<< 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 | 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 | 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', | |||
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', | |||
message = '<code class="cs1-code">| | |||
anchor = ' | |||
category = 'CS1 errors: | |||
hidden = false | hidden = false | ||
}, | |||
err_bad_date = { | |||
message = ' | message = 'Check date values in: $1', -- $1 is a parameter name list | ||
anchor = ' | anchor = 'bad_date', | ||
category = 'CS1 errors: | category = 'CS1 errors: dates', | ||
hidden = false | hidden = false | ||
}, | |||
err_bad_doi = { | |||
message = '<code class="cs1-code">| | message = 'Check <code class="cs1-code">|doi=</code> value', | ||
anchor = ' | anchor = 'bad_doi', | ||
category = 'CS1 errors: | category = 'CS1 errors: DOI', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_hdl = { | |||
message = '<code class="cs1-code">| | message = 'Check <code class="cs1-code">|hdl=</code> value', | ||
anchor = ' | anchor = 'bad_hdl', | ||
category = 'CS1 errors: | category = 'CS1 errors: HDL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_isbn = { | |||
message = '<code class="cs1-code">| | message = 'Check <code class="cs1-code">|isbn=</code> value: $1', -- $1 is error message detail | ||
anchor = ' | anchor = 'bad_isbn', | ||
category = 'CS1 errors: | category = 'CS1 errors: ISBN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_ismn = { | |||
message = '<code class="cs1-code">| | message = 'Check <code class="cs1-code">|ismn=</code> value', | ||
anchor = ' | anchor = 'bad_ismn', | ||
category = 'CS1 errors: | category = 'CS1 errors: ISMN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_issn = { | |||
message = '<code class="cs1-code">|$ | message = 'Check <code class="cs1-code">|$1issn=</code> value', -- $1 is 'e' or '' for eissn or issn | ||
anchor = ' | anchor = 'bad_issn', | ||
category = 'CS1 errors: | category = 'CS1 errors: ISSN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_jfm = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|jfm=</code> value', | ||
anchor = ' | anchor = 'bad_jfm', | ||
category = 'CS1 errors: | category = 'CS1 errors: JFM', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_jstor = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|jstor=</code> value', | ||
anchor = ' | anchor = 'bad_jstor', | ||
category ='CS1 errors: | category = 'CS1 errors: JSTOR', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_lccn = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|lccn=</code> value', | ||
anchor = ' | anchor = 'bad_lccn', | ||
category ='CS1 errors: | category = 'CS1 errors: LCCN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_medrxiv = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|medrxiv=</code> value', | ||
anchor = ' | anchor = 'bad_medrxiv', | ||
category = 'CS1 errors: | category = 'CS1 errors: medRxiv', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_mr = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|mr=</code> value', | ||
anchor = ' | anchor = 'bad_mr', | ||
category = 'CS1 errors: | category = 'CS1 errors: MR', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_oclc = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|oclc=</code> value', | ||
anchor = ' | anchor = 'bad_oclc', | ||
category = 'CS1 errors: | category = 'CS1 errors: OCLC', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_ol = { | |||
message = 'Check | message = 'Check <code class="cs1-code">|ol=</code> value', | ||
anchor = ' | anchor = 'bad_ol', | ||
category = 'CS1 errors: | category = 'CS1 errors: OL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_osti = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|osti=</code> value', | ||
anchor = ' | anchor = 'bad_osti', | ||
category = 'CS1 errors: | category = 'CS1 errors: OSTI', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link= | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|$1=</code> value', -- $1 is parameter name | ||
anchor = ' | anchor = 'bad_paramlink', | ||
category = 'CS1 errors: | category = 'CS1 errors: parameter link', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_pmc = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|pmc=</code> value', | ||
anchor = ' | anchor = 'bad_pmc', | ||
category = 'CS1 errors: | category = 'CS1 errors: PMC', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_pmid = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|pmid=</code> value', | ||
anchor = ' | anchor = 'bad_pmid', | ||
category = 'CS1 errors: | category = 'CS1 errors: PMID', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_rfc = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|rfc=</code> value', | ||
anchor = ' | anchor = 'bad_rfc', | ||
category = 'CS1 errors: | category = 'CS1 errors: RFC', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_s2cid = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|s2cid=</code> value', | ||
anchor = ' | anchor = 'bad_s2cid', | ||
category = 'CS1 errors: | category = 'CS1 errors: S2CID', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_sbn = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|sbn=</code> value: $1', -- $1 is error message detail | ||
anchor = ' | anchor = 'bad_sbn', | ||
category = 'CS1 errors: | category = 'CS1 errors: SBN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_ssrn = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|ssrn=</code> value', | ||
anchor = ' | anchor = 'bad_ssrn', | ||
category = 'CS1 errors: | category = 'CS1 errors: SSRN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_url = { | |||
message = 'Check | message = 'Check $1 value', -- $1 is parameter name | ||
anchor = ' | anchor = 'bad_url', | ||
category = 'CS1 errors: | category = 'CS1 errors: URL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_usenet_id = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|message-id=</code> value', | ||
anchor = ' | anchor = 'bad_message_id', | ||
category = 'CS1 errors: | category = 'CS1 errors: message-id', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bad_zbl = { | |||
message = 'Check <code class="cs1-code">| | message = 'Check <code class="cs1-code">|zbl=</code> value', | ||
anchor = ' | anchor = 'bad_zbl', | ||
category = 'CS1 errors: | category = 'CS1 errors: Zbl', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_bare_url_missing_title = { | |||
message = ' | message = '$1 missing title', -- $1 is parameter name | ||
anchor = ' | anchor = 'bare_url_missing_title', | ||
category = 'CS1 errors: | category = 'CS1 errors: bare URL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_biorxiv_missing = { | |||
message = ' | message = '<code class="cs1-code">|biorxiv=</code> required', | ||
anchor = ' | anchor = 'biorxiv_missing', | ||
category = 'CS1 errors: | category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_chapter_ignored = { | |||
message = ' | message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name | ||
anchor = ' | anchor = 'chapter_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: chapter ignored', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_citation_missing_title = { | |||
message = ' | message = 'Missing or empty <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'citation_missing_title', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing title', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_citeseerx_missing = { | |||
message = ' | message = '<code class="cs1-code">|citeseerx=</code> required', | ||
anchor = ' | anchor = 'citeseerx_missing', | ||
category = 'CS1 errors: | category = 'CS1 errors: citeseerx', -- same as bad citeseerx | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_cite_web_url = { -- this error applies to cite web and to cite podcast | |||
message = ' | message = 'Missing or empty <code class="cs1-code">|url=</code>', | ||
anchor = ' | anchor = 'cite_web_url', | ||
category = 'CS1 errors: | category = 'CS1 errors: requires URL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_class_ignored = { | |||
message = ' | message = '<code class="cs1-code">|class=</code> ignored', | ||
anchor = ' | anchor = 'class_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: class', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_contributor_ignored = { | |||
message = ' | message = '<code class="cs1-code">|contributor=</code> ignored', | ||
anchor = ' | anchor = 'contributor_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: contributor', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_contributor_missing_required_param = { | |||
message = ' | message = '<code class="cs1-code">|contributor=</code> requires <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'contributor_missing_required_param', | ||
category = 'CS1 errors: | category = 'CS1 errors: contributor', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_deprecated_params = { | |||
message = ' | message = 'Cite uses deprecated parameter <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'deprecated_params', | ||
category = 'CS1 errors: | category = 'CS1 errors: deprecated parameters', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_disp_name = { | |||
message = ' | message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name; $2 is the assigned value | ||
anchor = ' | anchor = 'disp_name', | ||
category = 'CS1 errors: | category = 'CS1 errors: display-names', | ||
hidden = false | hidden = false, | ||
}, | }, | ||
err_doibroken_missing_doi = { | |||
message = '$1 | message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|doi=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'doibroken_missing_doi', | ||
category = 'CS1 errors: | category = 'CS1 errors: DOI', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_embargo_missing_pmc = { | |||
message = '<code class="cs1-code">| | message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|pmc=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'embargo_missing_pmc', | ||
category = 'CS1 errors: | category = 'CS1 errors: PMC embargo', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_empty_citation = { | |||
message = ' | message = 'Empty citation', | ||
anchor = ' | anchor = 'empty_citation', | ||
category = 'CS1 errors: | category = 'CS1 errors: empty citation', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_etal = { | |||
message = ' | message = 'Explicit use of et al. in: <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'explicit_et_al', | ||
category = 'CS1 errors: | category = 'CS1 errors: explicit use of et al.', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_extra_text_edition = { | |||
message = '<code class="cs1-code">| | message = '<code class="cs1-code">|edition=</code> has extra text', | ||
anchor = ' | anchor = 'extra_text_edition', | ||
category = 'CS1 errors: | category = 'CS1 errors: extra text: edition', | ||
hidden = false | 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 = ' | message = '<code class="cs1-code">|$1=</code> has extra text', -- $1 is parameter name | ||
anchor = ' | anchor = 'extra_text_volume', | ||
category = 'CS1 errors: | category = 'CS1 errors: extra text: volume', | ||
hidden = | hidden = true, | ||
}, | }, | ||
err_first_missing_last = { | |||
message = '<code class="cs1-code">|class=</code> | message = '<code class="cs1-code">|$1=</code> missing <code class="cs1-code">|$2=</code>', -- $1 is first alias, $2 is matching last alias | ||
anchor = ' | anchor = 'first_missing_last', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_format_missing_url = { | |||
message = '<code class="cs1-code">| | message = '<code class="cs1-code">|$1=</code> requires <code class="cs1-code">|$2=</code>', -- $1 is format parameter $2 is url parameter | ||
anchor = ' | anchor = 'format_missing_url', | ||
category = 'CS1 errors: | category = 'CS1 errors: format without URL', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_generic_name = { | |||
message = ' | message = '<code class="cs1-code">|$1=</code> has generic name', -- $1 is parameter name | ||
anchor = ' | anchor = 'generic_name', | ||
category = 'CS1 errors: | category = 'CS1 errors: generic name', | ||
hidden = false | hidden = false, | ||
}, | }, | ||
err_generic_title = { | |||
message = 'Cite uses | message = 'Cite uses generic title', | ||
anchor = ' | anchor = 'generic_title', | ||
category = 'CS1 errors: | category = 'CS1 errors: generic title', | ||
hidden = false | hidden = false, | ||
}, | }, | ||
err_invalid_param_val = { | |||
message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name | message = 'Invalid <code class="cs1-code">|$1=$2</code>', -- $1 is parameter name $2 is parameter value | ||
anchor = ' | anchor = 'invalid_param_val', | ||
category = 'CS1 errors: | category = 'CS1 errors: invalid parameter value', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_invisible_char = { | |||
message = ' | message = '$1 in $2 at position $3', -- $1 is invisible char $2 is parameter name $3 is position number | ||
anchor = ' | anchor = 'invisible_char', | ||
category = 'CS1 errors: | category = 'CS1 errors: invisible characters', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_medrxiv_missing = { | |||
message = ' | message = '<code class="cs1-code">|medrxiv=</code> required', | ||
anchor = ' | anchor = 'medrxiv_missing', | ||
category = 'CS1 errors: | category = 'CS1 errors: medRxiv', -- same as bad medRxiv | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_missing_name = { | |||
message = ' | message = 'Missing <code class="cs1-code">|$1$2=</code>', -- $1 is modified NameList; $2 is enumerator | ||
anchor = ' | anchor = 'missing_name', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_missing_periodical = { | |||
message = '<code class="cs1-code">| | 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 = ' | anchor = 'missing_periodical', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing periodical', | ||
hidden = | hidden = true | ||
}, | }, | ||
err_missing_pipe = { | |||
message = '<code class="cs1-code">|$1=</code> | message = 'Missing pipe in: <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'missing_pipe', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing pipe', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_missing_publisher = { | |||
message = '<code class="cs1-code">|$ | 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 = ' | anchor = 'missing_publisher', | ||
category = 'CS1 errors: | category = 'CS1 errors: missing publisher', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_param_access_requires_param = { | |||
message = '<code class="cs1-code">|$1=</code> | message = '<code class="cs1-code">|$1-access=</code> requires <code class="cs1-code">|$1=</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'param_access_requires_param', | ||
category = 'CS1 errors: | category = 'CS1 errors: param-access', | ||
hidden = | hidden = false | ||
}, | }, | ||
err_param_has_ext_link = { | |||
message = '<code class="cs1-code"> | message = 'External link in <code class="cs1-code">$1</code>', -- $1 is parameter name | ||
anchor = ' | anchor = 'param_has_ext_link', | ||
category = 'CS1 errors: | category = 'CS1 errors: external links', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_parameter_ignored = { | |||
message = '<code class="cs1-code">|$1=</code> | message = 'Unknown parameter <code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name | ||
anchor = ' | anchor = 'parameter_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: unsupported parameter', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_parameter_ignored_suggest = { | |||
message = '<code class="cs1-code">|$1=</code> | 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 = ' | anchor = 'parameter_ignored_suggest', | ||
category = 'CS1 errors: | category = 'CS1 errors: unsupported parameter', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_periodical_ignored = { | |||
message = ' | message = '<code class="cs1-code">|$1=</code> ignored', -- $1 is parameter name | ||
anchor = ' | anchor = 'periodical_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: periodical ignored', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_redundant_parameters = { | |||
message = ' | message = 'More than one of $1 specified', -- $1 is error message detail | ||
anchor = ' | anchor = 'redundant_parameters', | ||
category = 'CS1 errors: | category = 'CS1 errors: redundant parameter', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_script_parameter = { | |||
message = '$1 | message = 'Invalid <code class="cs1-code">|$1=</code>: $2', -- $1 is parameter name $2 is script language code or error detail | ||
anchor = ' | anchor = 'script_parameter', | ||
category = 'CS1 errors: | category = 'CS1 errors: script parameters', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_ssrn_missing = { | |||
message = ' | message = '<code class="cs1-code">|ssrn=</code> required', | ||
anchor = ' | anchor = 'ssrn_missing', | ||
category = 'CS1 errors: | category = 'CS1 errors: SSRN', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_text_ignored = { | |||
message = ' | message = 'Text "$1" ignored', -- $1 is ignored text | ||
anchor = ' | anchor = 'text_ignored', | ||
category = 'CS1 errors: | category = 'CS1 errors: unrecognized parameter', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_trans_missing_title = { | |||
message = '<code class="cs1-code">|$1- | 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 = ' | anchor = 'trans_missing_title', | ||
category = 'CS1 errors: | category = 'CS1 errors: translated title', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_param_unknown_empty = { | |||
message = ' | message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is emty unknown param list | ||
anchor = ' | anchor = 'param_unknown_empty', | ||
category = 'CS1 errors: | category = 'CS1 errors: empty unknown parameters', | ||
hidden = false | hidden = false | ||
}, | }, | ||
err_vancouver = { | |||
err_vancouver = { | |||
message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name | message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name | ||
anchor = 'vancouver', | anchor = 'vancouver', | ||
Line 1,654: | Line 1,798: | ||
anchor = 'authors', | anchor = 'authors', | ||
category = 'CS1 maint: uses authors parameter', | category = 'CS1 maint: uses authors parameter', | ||
hidden = true, | |||
}, | |||
maint_bibcode = { | |||
message = nil, | |||
anchor = 'bibcode', | |||
category = 'CS1 maint: bibcode', | |||
hidden = true, | |||
}, | |||
maint_location_no_publisher = { -- cite book, conference, encyclopedia; citation as book cite or encyclopedia cite | |||
message = nil, | |||
anchor = 'location_no_publisher', | |||
category = 'CS1 maint: location missing publisher', | |||
hidden = true, | hidden = true, | ||
}, | }, | ||
Line 1,756: | Line 1,912: | ||
anchor = 'others_avm', | anchor = 'others_avm', | ||
category = 'CS1 maint: others in cite AV media (notes)', | 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, | hidden = true, | ||
}, | }, | ||
Line 1,854: | Line 2,016: | ||
q = 'Q118398', | q = 'Q118398', | ||
label = 'arXiv', | label = 'arXiv', | ||
prefix = 'https://arxiv.org/abs/', | prefix = 'https://arxiv.org/abs/', | ||
encode = false, | encode = false, | ||
COinS = 'info:arxiv', | COinS = 'info:arxiv', | ||
Line 1,990: | Line 2,152: | ||
q = 'Q1420342', | q = 'Q1420342', | ||
label = 'JSTOR', | label = 'JSTOR', | ||
prefix = 'https://www.jstor.org/stable/', | prefix = 'https://www.jstor.org/stable/', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = false, | encode = false, | ||
Line 2,002: | Line 2,164: | ||
q = 'Q620946', | q = 'Q620946', | ||
label = 'LCCN', | label = 'LCCN', | ||
prefix = 'https://lccn.loc.gov/', | prefix = 'https://lccn.loc.gov/', | ||
COinS = 'info:lccn', | COinS = 'info:lccn', | ||
encode = false, | |||
separator = ' ', | |||
}, | |||
['MEDRXIV'] = { | |||
parameters = {'medrxiv'}, | |||
link = 'medRxiv', | |||
redirect = 'medRxiv (identifier)', | |||
q = 'Q58465838', | |||
label = 'medRxiv', | |||
prefix = 'https://www.medrxiv.org/content/', | |||
COinS = 'pre', -- use prefix value | |||
access = 'free', -- free to read | |||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
Line 2,028: | Line 2,202: | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 10030000000, | ||
}, | }, | ||
['OL'] = { | ['OL'] = { | ||
Line 2,048: | Line 2,222: | ||
q = 'Q2015776', | q = 'Q2015776', | ||
label = 'OSTI', | label = 'OSTI', | ||
prefix = 'https://www.osti.gov/biblio/', | prefix = 'https://www.osti.gov/biblio/', | ||
COinS = 'pre', -- use prefix value | COinS = 'pre', -- use prefix value | ||
encode = true, | encode = true, | ||
Line 2,066: | Line 2,240: | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 10700000, | ||
access = 'free', -- free to read | access = 'free', -- free to read | ||
}, | }, | ||
Line 2,079: | Line 2,253: | ||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 37900000, | ||
}, | }, | ||
['RFC'] = { | ['RFC'] = { | ||
Line 2,113: | Line 2,287: | ||
encode = true, | encode = true, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 4600000, | ||
custom_access = 'ssrn-access', | custom_access = 'ssrn-access', | ||
}, | }, | ||
Line 2,126: | Line 2,300: | ||
encode = false, | encode = false, | ||
separator = ' ', | separator = ' ', | ||
id_limit = | id_limit = 264000000, | ||
custom_access = 's2cid-access', | custom_access = 's2cid-access', | ||
}, | }, | ||
Line 2,158: | Line 2,332: | ||
return { | return { | ||
use_identifier_redirects = | use_identifier_redirects = use_identifier_redirects, -- booleans defined in the settings at the top of this module | ||
local_lang_cat_enable = | local_lang_cat_enable = local_lang_cat_enable, | ||
date_name_auto_xlate_enable = | date_name_auto_xlate_enable = date_name_auto_xlate_enable, | ||
date_digit_auto_xlate_enable = | date_digit_auto_xlate_enable = date_digit_auto_xlate_enable, | ||
-- tables and variables created when this module is loaded | -- 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_df = get_date_format (), -- this line can be replaced with "global_df = 'dmy-all'," to have all dates auto translated to dmy format. | ||
global_cs1_config_t = global_cs1_config_t, -- global settings from {{cs1 config}} | |||
punct_skip = build_skip_table (punct_skip, punct_meta_params), | punct_skip = build_skip_table (punct_skip, punct_meta_params), | ||
url_skip = build_skip_table (url_skip, url_meta_params), | url_skip = build_skip_table (url_skip, url_meta_params), | ||
Line 2,188: | Line 2,363: | ||
prop_cats = prop_cats, | prop_cats = prop_cats, | ||
script_lang_codes = script_lang_codes, | script_lang_codes = script_lang_codes, | ||
lang_tag_remap = lang_tag_remap, | |||
lang_name_remap = lang_name_remap, | lang_name_remap = lang_name_remap, | ||
this_wiki_code = this_wiki_code, | this_wiki_code = this_wiki_code, |