Wicipedia

Modiwl:Citation/CS1: Gwahaniaeth rhwng fersiynau

Pori'r hanes yn rhyngweithiol
← Cymharer â'r fersiwn gyntCymharer â'r fersiwn dilynol →
Cynnwys wedi'i ddileu Cynnwys wedi'i ychwanegu
Dadwneud y golygiad 2853641 gan BOT-Twm Crys (Sgwrs | cyfraniadau)
diweddaru
Llinell 1:
 
local cs1 ={};
 
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
 
local dates, year_date_check, reformat_dates , date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation
date_name_xlate
 
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
add_maint_cat, wrap_style, safe_for_italics, remove_wiki_linkis_wikilink, make_wikilink;
 
local z ={}; -- tables in Module:Citation/CS1/Utilities
 
local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
 
local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS
Llinell 18 ⟶ 17:
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
 
 
--[[--------------------------< P A G E S C O P E V A R I A B L E S >--------------------------------------
 
delare variables here that have page-wide scope that are not brought in from other modules; thatare created here
and used here
 
]]
 
local added_deprecated_cat; -- boolean flag so that the category is added only once
local added_prop_cats = {}; -- list of property categories that have been added to z.properties_cats
local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category
 
local Frame; -- holds the module's frame table
 
 
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Llinell 39 ⟶ 53:
end
end
 
 
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
 
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
 
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages
may be categorized but multiples of the same language are not categorized.
 
added_prop_cats is a table declared in page scope variables above
 
]]
 
local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
local function add_prop_cat (key, arguments)
if not added_prop_cats [key] then
added_prop_cats [key] = true; -- note that we've added this category
key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
 
 
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Llinell 58 ⟶ 79:
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 
added_vanc_errs is a boolean declared in page scope variables above
 
]]
 
local function add_vanc_error (source)
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
local function add_vanc_error ()
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } );
end
end
Llinell 109 ⟶ 131:
the first character of the whole domain name including subdomains must be a letter or a digit
internationalized domain name (ascii characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the tld) see https://tools.ietf.org/html/rfc3490
single-letter/digit second-level domains in the .org, TLD.cash, and .today TLDs
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
Llinell 129 ⟶ 151:
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
return false;
end
 
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at wikisource
return false;
end
Llinell 136 ⟶ 162:
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
return true;
elseif domain:match ('%f[%a%d][%a%d]%.orgcash$') then -- one character/digit .orgcash hostname
return true;
elseif domain:match ('%f[%a%d][%a%d]%.today') then -- one character/digit .today hostname
return true;
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/digit .org hostname
return true;
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
Llinell 232 ⟶ 262:
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
 
 
--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
Llinell 359 ⟶ 390:
['\n'] = ' ' } );
end
 
 
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
Llinell 366 ⟶ 398:
]]
 
local function external_link( URL, label, source, access)
local error_str = "";
local domain;
local path;
local base_url;
 
if not is_set( label ) then
label = URL;
Llinell 386 ⟶ 419:
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
URL = table.concat ({domain.., path}); -- and reassemble
end
 
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url
 
if is_set (access) then -- access level (subscription, registration, limited)
base_url = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
end
return table.concat ({ "[", URL, " ", safe_for_url( label ), "]"base_url, error_str });
end
 
Llinell 398 ⟶ 437:
offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated
parameters in the citation.
 
added_deprecated_cat is a boolean declared in page scope variables above
 
]]
 
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local function deprecated_parameter(name)
if not page_in_deprecated_catadded_deprecated_cat then
page_in_deprecated_catadded_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
end
 
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
 
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote
mark contained in a |title= or |chapter= parameter's value.
 
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.
 
Replaces unicode quotemarks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
 
Call this function for chapter titles, for website titles, etc; not for book titles.
 
]=]
 
local function kern_quotes (str)
local cap='';
local cap2='';
local wl_type, label, link;
 
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
cap,if cap21 == str:matchwl_type ("^([\"\'])([^\'].+)");then -- match[[D]] leadingsimple doublewikilink with or singlewithout quote but not double single quotesmarks
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
if is_set (cap) then
str = substitute (cfg.presentation['kern-leftwl-both'], {cap, cap2}str);
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
end
str = substitute (cfg.presentation['kern-wl-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = substitute (cfg.presentation['kern-wl-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
if is_set (cap) then
label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
 
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
label = substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
label = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
return str;
end
 
 
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
Llinell 471 ⟶ 541:
end
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, cfg.script_lang_codes) then
if in_array (lang, {'am', 'ar', 'be', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ml', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
Llinell 489 ⟶ 559:
return script_value;
end
 
 
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Llinell 526 ⟶ 597:
return substitute( cfg.messages[key], str );
end
end
 
 
--[[--------------------------< W I K I S O U R C E _ U R L _ M A K E >----------------------------------------
 
makes a wikisource url from wikisource interwiki link. returns the url and appropriate label; nil else.
 
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
 
]]
 
local function wikisource_url_make (str)
local wl_type, D, L;
local ws_url, ws_label;
 
wl_type, D, L = is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
 
if 0 == wl_type then -- not a wikilink; might be from |title-link=
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_label = D; -- get ws article name from display portion of interwiki link
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
if ws_url then
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable url
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of anchor
end
 
return ws_url, ws_label, L or D; -- return proper url or nil and a label or nil
end
 
Llinell 536 ⟶ 659:
]]
 
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access)
local chapter_error = '';
 
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource url and label from a wikisource interwiki link
if ws_url then
ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters
chapter = ws_label;
end
 
if not is_set (chapter) then
chapter = ''; -- to be safe for concatenation
else
if false == no_quotes then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
chapter = wrap_style ('quoted-title', chapter);
end
Llinell 549 ⟶ 678:
 
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
elseif ws_url then
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
chapter = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
 
if is_set (transchapter) then
Llinell 560 ⟶ 696:
end
 
-- if is_set (chapterurl) then
-- chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
-- end
 
return chapter .. chapter_error;
end
 
 
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
Llinell 576 ⟶ 713:
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)
and identifies them with a slightly different error message. See also coins_cleanup().
 
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
 
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
Llinell 601 ⟶ 736:
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position and (char == 'zero width joiner') then -- if we found a zero width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts
position = nil; -- unset position
end
end
if position then
if 'nowiki' == capture or 'math' == capture then or -- nowiki, and math stripmarkerstripmarkers (not an error condition)
('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
stripmarker = true; -- set a flag
stripmarker = true; -- set a flag
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
position = nil; -- unset
Llinell 671 ⟶ 813:
end,
});
end
 
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.
 
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
 
local function validate( name )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
-- Normal arguments
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- Not supported because not found or name is set to nil
end
 
Llinell 730 ⟶ 839:
return date;
end
 
 
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
Llinell 752 ⟶ 862:
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
 
Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items are
returned unmodified. These forms are modified:
letter - letter (A - B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5)
digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d)
 
any other forms are returned unmodified.
 
str may be a comma- or semicolon-separated list
 
]]
 
local function hyphen_to_dash( str )
if not is_set (str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str
if 0 ~= count then -- non-zero when markup removed; zero else
return str; -- nothing to do, we're done
end
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split
local out = {};
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any
 
for _, item in ipairs (list) do -- for each item in the list
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or -- digitletter hyphen digitletter (optional separator between digit and letter)
item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or -- digit separator digit hyphen digit separator digit
item:match ('%d+%s*%-%s*%d+') or -- digit hyphen digit
item:match ('%a+%s*%-%s*%a+') then -- letter hyphen letter
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space
end
end
item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup
table.insert (out, item); -- add the (possibly modified) item to the output table
end
 
return table.concat (out, ', '); -- concatenate the output table into a comma separated string
end
 
Llinell 771 ⟶ 918:
 
local function safe_join( tbl, duplicate_char )
local f = {}; -- create a function table appropriate to type of 'dupicate character'
--[[
if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions
Note: we use string functions here, rather than ustring functions.
f.gsub=string.gsub
f.match=string.match
This has considerably faster performance and should work correctly as
f.sub=string.sub
long as the duplicate_char is strict ASCII. The strings
else -- for multi-byte characters use the ustring library functions
in tbl may be ASCII or UTF8.
f.gsub=mw.ustring.gsub
]]
f.match=mw.ustring.match
f.sub=mw.ustring.sub
end
 
local str = ''; -- the output string
local comp = ''; -- what does 'comp' mean?
Llinell 795 ⟶ 945:
end
-- typically duplicate_char is sepc
if comp:f.sub(comp, 1,1) == duplicate_char then -- is first charactiercharacter same as duplicate_char? why test first character?
-- Because individual string segments often (always?) begin with terminal punct for ththe
-- preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
end_chr = str:f.sub(str, -1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = str:f.sub(str, 1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if str:f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = str:f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif str: f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif str:f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if str:f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif str:f.sub(str, -23,-1) == duplicate_char .. '"]"' then -- if last twothree chars of str are sepc"] quoted external link
trim = true;
elseif str: f.sub(str, -42,-1) == duplicate_char .. "'']" then -- normalif caselast whentwo |url=somethingchars &of |title=Title.str are sepc] external link
trim = true;
elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if str:f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:f.sub(str, 1,-3); -- remove them both
end
end
Llinell 828 ⟶ 980:
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
if dup2:f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
value = value:f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
Llinell 840 ⟶ 992:
end
return str;
end
 
 
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
 
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
 
]]
 
local function is_suffix (suffix)
if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
return false;
end
 
 
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
Llinell 858 ⟶ 1,025:
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
 
This original test:
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
because the code editor gets confused between character insertion point and cursor position.
was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.
The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary
to use an external editor to maintain this code.
 
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
\195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
\195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
 
]]
 
local function is_good_vanc_name (last, first)
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
 
add_vanc_error ();
if is_set (suffix) then
return false; -- not a string of latin characters; Vancouver required Romanization
if not is_suffix (suffix) then
add_vanc_error ('suffix');
return false; -- not a name with an appropriate suffix
end
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
add_vanc_error ('non-Latin character');
return false; -- not a string of latin characters; Vancouver requires Romanization
end;
return true;
end
 
 
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Llinell 877 ⟶ 1,062:
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
 
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. ThisSee form is nothttp://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
 
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
Llinell 885 ⟶ 1,070:
 
local function reduce_to_initials(first)
iflocal name, suffix = mw.ustring.match(first, "^(%u+) ([%udJS][%drndth]+)$") then return first end; -- when first contains just two upper-case letters, nothing to do
 
local initials = {}
localif inot =name 0; then -- counterif fornot numberinitials ofand initialsa suffix
for name word in= mw.ustring.gmatchmatch(first, "[^(%s%.%-]u+)$") do; -- namesis separated by spaces, hyphens,it orjust periodsintials?
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
i = i + 1; -- bump the counter
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
end
 
if name then -- if first is initials with or without suffix
if 3 > mw.ustring.len (name) then -- if one or two initials
if suffix then -- if there is a suffix
if is_suffix (suffix) then -- is it legitimate?
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
else
return first; -- one or two initials without suffix; nothing to do
end
end
end -- if here then name has 3 or more uppercase letters so treat them as a word
 
 
local initials, names = {}, {}; -- tables to hold name parts and initials
local i = 1; -- counter for number of initials
 
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
 
while names[i] do -- loop through the table
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
if is_suffix (names[i]) then -- if a legitimate suffix
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
break; -- and done because suffix must fall at the end of a name
end -- no error message if not a suffix; possibly because of Romanization
end
if 3 > i then
table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table
end
i = i+1; -- bump the counter
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
 
 
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
Llinell 911 ⟶ 1,130:
 
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = cfg.presentation[',sep_nl_vanc']; -- name-list separator between authors is a comma
namesep = cfg.presentation[' sep_name_vanc']; -- last/first separator is a space
else
sep = cfg.presentation[';sep_nl' ]; -- name-list separator between authors is a semicolon
namesep = cfg.presentation[', sep_name' ]; -- last/first separator is <comma><space>
end
Llinell 940 ⟶ 1,159:
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first ;
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" ..make_wikilink (person.link .. "|" .., one .. "]]"); -- link author/editor if this page is not the author's/editor's page
end
end
Llinell 973 ⟶ 1,192:
return result, count
end
 
 
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
Llinell 999 ⟶ 1,219:
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
 
Evaluates the content of authorname andparameters (author, editor, name parametersetc) for variations on the theme of et al. If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
 
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parametersassociated |display-authors<names>=etal or |display-editors=etalparameter
 
]]
 
local function name_has_etal (name, etal, nocat, param)
 
if is_set (name) then -- name can be nil in which case just return
local patterns = cfg.et_al_patterns; --get patterns from configuration
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
iffor name:match_, pattern in ipairs (etal_patternpatterns) then do -- variantsloop through all onof etthe al.patterns
name =if name:gsubmatch (etal_pattern, ''pattern); then -- if this 'et al' pattern is found, removein name
name = name:gsub (pattern, ''); -- remove the offending text
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if etal not nocat= thentrue; -- noset categorizationflag for(may have been set previously here or by |vauthorsdisplay-<names>=etal)
add_maint_catif ('etal');not nocat then -- andno add a category if notcategorization alreadyfor added|vauthors=
table.insert( z.message_tail, {set_error ('etal', {param})}); -- and set an error if not added
end
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
 
return name, etal; --
end
 
 
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
 
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
 
]]
 
local function name_has_ed_markup (name, list_name)
local _, pattern;
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
 
if is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
end
end
return name; -- and done
end
 
 
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
Llinell 1,041 ⟶ 1,282:
local count, _;
if is_set (name) then
if_, count = name:matchgsub ('^%(%(.*%)%)$[;,]'), then''); -- ifcount wrappedthe innumber doubledof parentheses, ignoreseparator-like characters
name = name:match ('^%(%((.*)%)%)$'); -- strip parens
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable
else
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
if 1 < count then -- param could be |author= or |editor= so one separactor character is acceptable
add_maint_cat ('mult_names', list_name:lower()); -- more than one separator indicates multiple names so add a maint cat for this template
end
end
end
return name; -- and done
end
 
 
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
This function calls various name checking functions used to validate the content of the various name-holding
parameters.
 
]]
 
local function name_checks (last, first, list_name)
if is_set (last) then
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
last = last:match ('^%(%((.*)%)%)$'); -- strip parens
else
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
end
end
if is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
else
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
end
end
return last, first; -- done
end
 
 
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Llinell 1,081 ⟶ 1,345:
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
 
local last_alias, first_alias; -- selected parameter aliases used in error messaging
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
last, last_alias = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first, first_alias = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last, first= name_has_mult_namesname_checks (last, err_msg_list_namefirst, list_name); -- check for multiple names, inextraneous last andannotation, itsetc aliaseschecks
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_namefirst_alias, ifirst_alias:gsub('first', 'last')}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
Llinell 1,105 ⟶ 1,369:
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_namelist_name:match ("(%w+)List"):lower(), i-1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
Llinell 1,114 ⟶ 1,378:
return names, etal; -- all done, return our list of names
end
 
 
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Llinell 1,124 ⟶ 1,389:
return the original language name string.
 
mw.language.fetchLanguageNames(<local wiki language>, 'all') returnreturns a list of languages that in some cases may include
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they
are used as sub-domain names: cbk-zam.wikipedia.org. A list of language names and codes supported by fetchLanguageNames()
can be found at Template:Citation Style documentation/language/doc
 
Names but that are included in the list will be found if that name is provided in the |language= parameter. For example,
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found
and the associated code is not two or three characters, this function returns only the WikimediaWikiMedia language name.
 
Some language names have multiple entries under different codes:
Aromanian has code rup and code roa-rup
When this occurs, this function returns the language name and the 2- or 3-character code
 
Adapted from code taken from Module:Check ISO 639-1.
Llinell 1,137 ⟶ 1,408:
 
local function get_iso639_code (lang, this_wiki_code)
if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
end
 
local ietf_code; -- because some languages have both ietf-like codes and iso 639-like codes
local ietf_name;
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
 
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~== code:len() andor 3 ~== code:len() then -- two- or three-character codes only; extensions not supported
return name, code; -- so return the name but notand the code
end
returnietf_code name,= code; -- foundremember it,that returnwe namefound toan ensureietf-like proper capitalizationcode and thesave theits codename
ietf_name = name; -- but keep looking for a 2- or 3-char code
end
end
return lang; -- notdidn't validfind language;name returnwith language2- inor original3-char casecode; andif nilietf-like forcode thefound codereturn
return ietf_code and ietf_name or lang; -- associated name; return original language text else
end
 
 
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Llinell 1,182 ⟶ 1,463:
 
for _, lang in ipairs (names_table) do -- reuse lang
name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap
 
if lang:match ('^%a%a%-')name then -- stripthere ietfwas languagea tags fromremapped code; TODO: is there a need to support 3-char with tag?so
lang = lang:matchgsub ('^(%a%a%a?)%-.*', '%1') ; -- keepstrip onlyietf 639-1tags code portion to lang; TODO: do something with 3166 alpha 2 countryfrom code?
endelse
if 2 == lang:len() ormatch 3 == lang:len('^%a%a%-') then -- ifstrip two-orietf three-charactertags from code; TODO: is there a need to support 3-char with tag?
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code
end
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName (lang:lower(), this_wiki_code); -- get language name if |language= is a proper code
end
end
 
if is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
Llinell 1,197 ⟶ 1,483:
if is_set (code) then -- only 2- or 3-character codes
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
 
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if 2 == code:len() then -- and is a two-character code
add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it
else -- or is a recognized language (but has a three-character code)
add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
end
end
Llinell 1,214 ⟶ 1,502:
code = #language_list -- reuse code as number of languages in the list
if 2 >= code then
name = table.concat (language_list, cfg.messages[' and parameter-pair-separator']) -- insert '<space>and<space>' between two language names
elseif 2 < code then
language_list[code]name = 'and ' .table.concat (language_list[code], ', '); -- prependand last nameconcatenate with 'and<comma><space>' separators
name = table.concatname:gsub (language_list', ([^,]+)$', cfg.messages['parameter-final-separator'] .. '%1') ; -- andreplace concatenatelast '<comma><space>' separator with '<comma><space>and<space>' separatorsseparator
end
if this_wiki_name == name then
Llinell 1,223 ⟶ 1,511:
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
--[[ TODO: should only return blank or name rather than full list
so we can clean up the bunched parenthetical elements Language, Type, Format
]]
end
 
 
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
 
Set style settings for CS1 citation templates. Returns separator and postscript settings
At en.wiki, for cs1:
ps gets: '.'
sep gets: '.'
 
]]
Llinell 1,233 ⟶ 1,528:
local function set_cs1_style (ps)
if not is_set (ps) then -- unless explicitely set to something
ps = 'cfg.presentation['ps_cs1']; -- terminate the rendered citation with a period
end
return 'cfg.presentation['sep_cs1'], ps; -- element separator is a full stop
end
 
 
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
 
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
At en.wiki, for cs2:
ps gets: '' (empty string - no terminal punctuation)
sep gets: ','
 
]]
Llinell 1,246 ⟶ 1,545:
local function set_cs2_style (ps, ref)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = cfg.presentation['ps_cs2']; -- maketerminate surethe it isn'trendered nilcitation
end
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
return cfg.presentation[',sep_cs2'], ps, ref; -- element separator is a comma
end
 
 
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
Llinell 1,271 ⟶ 1,571:
return sep, ps, ref -- return them all
end
 
 
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
Llinell 1,294 ⟶ 1,595:
return sep, ps, ref
end
 
 
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Llinell 1,300 ⟶ 1,602:
applying the pdf icon to external links.
 
returns true if file extension is one of the recognized extensionextensions, else false
 
]=]
 
local function is_pdf (url)
return url:match ('%.pdf[%?#]?$') or url:match ('%.PDF[%?#]?$'); or
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end
 
 
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
Llinell 1,319 ⟶ 1,624:
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parenthasesparentheses, resize
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
Llinell 1,331 ⟶ 1,636:
end
 
 
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
--[[--------------------------< G E T _ D I S P L A Y _ N A M E S >--------------------------------------------
 
Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag
Llinell 1,354 ⟶ 1,660:
]]
 
local function get_display_authors_editorsget_display_names (max, count, list_name, etal)
if is_set (max) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
Llinell 1,362 ⟶ 1,668:
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cat ('disp_auth_eddisp_name', cfg.special_case_translation [list_name]);
end
else -- not a valid keyword or number
Llinell 1,372 ⟶ 1,678:
return max, etal;
end
 
 
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Llinell 1,385 ⟶ 1,692:
 
local function extra_text_in_page_check (page)
-- local good_pattern = '^P[^%.P%l]';
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
-- local bad_pattern = '^[Pp][Pp]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
 
Llinell 1,393 ⟶ 1,698:
add_maint_cat ('extra_text');
end
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
 
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
 
-- add_maint_cat ('extra_text');
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
-- end
 
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the
rendered citation and in the metadata. Individual author names may be wikilinked
 
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
 
]=]
 
local function get_v_name_table (vparam, output_table, output_link_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local wl_type, label, link; -- wl_type not used here; just a place holder
local i = 1;
while name_table[i] do
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens
local name = name_table[i];
i=i+1; -- bump indexer to next segment
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens
break; -- and done reassembling so
end
i=i+1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
end
i = i+1;
end
return output_table;
end
 
Llinell 1,409 ⟶ 1,754:
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
 
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
 
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
TODO: check for names like Coon V JS (Coon JS 5th at PMID 25205766, John S. Coon V at doi:10.1093/humupd/dmu048)?
 
]]
Llinell 1,418 ⟶ 1,763:
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local v_link_table = {}; -- when name is wikilinked, targets go in this table
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
local corporate = false;
 
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ();
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
 
for i, v_name in ipairs(v_name_table) do
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheseparentheses to supress vanc formatting and error detection
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
corporate = true; -- flag used in list_people()
elseif string.find(v_name, "%s") then
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
add_vanc_error ('punctuation');
end
local lastfirstTable = {}
lastfirstTable = mw.text.split(v_name, "%s")
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
if is_suffix (first) then -- if a valid suffix
last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
suffix = first -- save it as a suffix and
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
first = table.remove(lastfirstTable); -- get what should be the initials from the table
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
end -- no suffix error message here because letter combination may be result of Romanization; check for digits?
last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error ('name'); -- matches a space between two intiials
end
else
Llinell 1,446 ⟶ 1,799:
end
if is_set (first) andthen
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
add_vanc_error ();
end
is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit
if is_set (suffix) then
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
suffix = ''; -- unset so we don't add this suffix to all subsequent names
end
else
if not corporate then
is_good_vanc_name (last, '');
end
end
 
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[i];
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
Llinell 1,456 ⟶ 1,820:
return names, etal; -- all done, return our list of names
end
 
 
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Llinell 1,477 ⟶ 1,842:
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local lastfirst = false;
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1|first1= without a |last1=; this ...
select_one( args, cfg.aliases[list_name .. '-LastFirst'], 'none', 21 ) thenor -- ... also catches the case where |first= is used with |vauthors=
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
lastfirst=true;
end
Llinell 1,506 ⟶ 1,873:
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
in the source template) the function refurnsreturns true. If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.
 
Llinell 1,533 ⟶ 1,900:
 
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]. ') then -- if lastalready name in list ends with sepcproperly charterminated
return name_list; -- just return the name list
elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
Llinell 1,562 ⟶ 1,931:
end
end
 
local vol = ''; -- here for all cites except magazine
if is_set (volume) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals
if (4 < mw.ustring.len(volume)) then
vol = substitute (cfg.messagespresentation['j-vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face
elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters
else
vol = wrap_stylesubstitute (cfg.messages['volj-boldvol'], {sepc, hyphen_to_dash(volume)}); -- not bold
add_prop_cat ('long_vol');
else -- four or less characters
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold
end
end
Llinell 1,578 ⟶ 1,950:
end
 
 
 
 
 
 
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
 
not currently used
 
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
returns list unchanged if there are no commas else strips whitespace and then reformats the list
 
]]
--[[
local function normalize_page_list (list)
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
list = table.concat (list, ', '); -- and now make a normalized list
return list;
end
]]
 
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
Llinell 1,628 ⟶ 1,978:
end
 
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
 
if is_set (page) then
if is_journal then
Llinell 1,652 ⟶ 2,002:
return '', '', '', ''; -- return empty strings
end
 
 
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
 
returns one of the in-source locators: page, pages, or at.
 
If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain text
for use in COinS. This COinS thing is done because here we convert an interwiki link to and external link and
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?
 
TODO: add support for sheet and sheets?; streamline;
 
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
to a new name)?
 
]]
 
local function insource_loc_get (page, pages, at)
local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
 
if is_set (page) then
if is_set (pages) or is_set(at) then
pages = ''; -- unset the others
at = '';
end
extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
 
ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label
if ws_url then
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
coins_pages = ws_label;
end
elseif is_set (pages) then
if is_set (at) then
at = ''; -- unset
end
extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
 
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label
if ws_url then
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
coins_pages = ws_label;
end
elseif is_set (at) then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label
if ws_url then
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
at = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
end
return page, pages, at, coins_pages;
end
 
 
 
Llinell 1,657 ⟶ 2,064:
 
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the
save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...) archive.org saves a snapshot
archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allow
unwitting readers to do.
 
When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
 
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
|archive-date= and an error message when:
|archive-url= holds an archive.org save command url
|archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
correct place
otherwise returns |archive-url= and |archive-date=
 
Llinell 1,676 ⟶ 2,085:
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
we don't check for these specific flags but we do check the form.
 
This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modified
archive url:
for save command errors, return undated wildcard (/*/)
for timestamp errors when the timestamp has a wildcard, return the url unmodified
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
 
]=]
Llinell 1,683 ⟶ 2,098:
local path, timestamp, flag; -- portions of the archive.or url
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url
return url, date; -- not an archive.org archive, return archiveURLArchiveURL and ArchiveDate
end
 
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page
err_msg = 'save command';
table.insert( z.message_tail, { set_error( 'archive_url', {'save command'}, true ) } ); -- add error message
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
return '', ''; -- return empty strings for archiveURL and ArchiveDate
elseif url:match('//liveweb%.archive%.org/') then
end
err_msg = 'liveweb';
 
if url:match('//web%.archive%.org/web/%*/') or url:match('//web%.archive%.org/%*/') then -- wildcard with or without 'web/' path element
table.insert( z.message_tail, { set_error( 'archive_url', {'wildcard'}, true ) } ); -- add error message and
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
 
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = 'timestamp';
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
err_msg = 'path';
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
err_msg = 'flag';
elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = 'flag';
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
return url, date; -- return archiveURL and ArchiveDate
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = 'timestamp';
if '*' ~= flag then
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
err_msg = 'path';
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
err_msg = 'flag';
elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = 'flag';
else
return url, date; -- return archiveURL and ArchiveDate
end
end
-- if here, something not right so
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
if is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for archiveURL and ArchiveDate
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
else
 
return url, date; -- preview mode so return archiveURL and ArchiveDate
 
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
 
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a
parameter that is missing its pipe:
{{cite ... |title=Title access-date=2016-03-17}}
 
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 
]]
 
local function missing_pipe_check (value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
 
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
add_maint_cat ('missing_pipe');
end
end
Llinell 1,757 ⟶ 2,151:
-- Pick out the relevant fields from the arguments. Different citation templates
-- define different field names for the same underlying things.
 
-- set default parameter values defined by |mode= parameter.
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
 
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
Llinell 1,772 ⟶ 2,173:
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
end
if is_set (Collaboration) then
Llinell 1,778 ⟶ 2,182:
end
 
local Coauthors = A['Coauthors'];
local Others = A['Others'];
 
Llinell 1,794 ⟶ 2,197:
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged
end
end
 
local translator_etal;
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local Translators; -- assembled translators name list
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 
local interviewer_etal;
local interviewers_list = {};
local Interviewers; -- used later
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
 
local contributor_etal;
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local Contributors; -- assembled contributors name list
Llinell 1,827 ⟶ 2,238:
NameListFormat = ''; -- anything else, set to empty string
end
 
if is_set (Others) then
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
add_maint_cat ('others');
end
end
 
local Year = A['Year'];
Llinell 1,857 ⟶ 2,274:
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
-- local ArchiveDate = A['ArchiveDate'];
-- local ArchiveURL = A['ArchiveURL'];
-- if ArchiveURL:match('//web%.archive%.org/save/') then -- if an archive.org save command url, we don't want to save target page ...
-- ArchiveURL = ''; -- every time a reader clicks the link so
-- ArchiveDate = ''; -- unset these
-- table.insert( z.message_tail, { set_error( 'archive_save', {}, true ) } ); -- and add error message
-- end
local DeadURL = A['DeadURL']
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
Llinell 1,887 ⟶ 2,297:
local At;
 
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
Volume = A['Volume'];
end
-- conference & map books do not support issue
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = hyphen_to_dash (A['Issue']);
end
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = hyphen_to_dash ( A['Pages'] );
At = A['At'];
end
Llinell 1,909 ⟶ 2,320:
RegistrationRequired=nil;
end
 
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end
 
local UrlAccess = A['UrlAccess'];
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
UrlAccess = nil;
end
if not is_set(URL) and is_set(UrlAccess) then
UrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } );
end
 
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription=
end
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message
RegistrationRequired = nil; -- unset; prefer |access= over |registration=
end
 
local ChapterUrlAccess = A['ChapterUrlAccess'];
if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', cfg.keywords ['url-access']) then -- same as url-access
ChapterUrlAccess = nil;
end
if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then
ChapterUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'chapter-url'}, true ) } );
end
 
Llinell 1,932 ⟶ 2,371:
 
local ID_list = extract_ids( args );
local ID_access_levels = extract_id_access_levels( args, ID_list );
 
local Quote = A['Quote'];
Llinell 1,945 ⟶ 2,385:
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
end
 
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
Llinell 1,952 ⟶ 2,393:
end
 
--local variables that are not cs1 parameters
--these are used by cite interview
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];
 
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
Llinell 1,966 ⟶ 2,402:
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
DF = ''; -- not valid, set to empty string
end
if not is_set (DF) then
DF = cfg.global_df;
end
 
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
Llinell 1,979 ⟶ 2,413:
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
 
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
Llinell 1,992 ⟶ 2,426:
end
 
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
 
local coins_pages;
Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);
 
local NoPP = A['NoPP']
Llinell 2,002 ⟶ 2,440:
end
 
-- both |publication-place= and |place= (|location=) allowed if different
if is_set(Page) then
if is_set(Pages) or is_set(At) then
Pages = ''; -- unset the others
At = '';
end
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
elseif is_set(Pages) then
if is_set(At) then
At = ''; -- unset
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
 
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
Llinell 2,022 ⟶ 2,447:
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title
 
|trans_titletrans-title maps to |trans_chaptertrans-chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped
 
All other combinations of |encyclopedia, |title, and |article are not modified
 
]]
 
local Encyclopedia = A['Encyclopedia'];
Llinell 2,046 ⟶ 2,471:
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
 
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter = '[[' ..make_wikilink (TitleLink .. '|' .., Chapter .. ']]');
end
Title = Periodical;
Llinell 2,065 ⟶ 2,492:
end
 
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
if not is_set(ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
Llinell 2,076 ⟶ 2,503:
end
 
-- special case for cite interviewmailing list
if (config.CitationClass == "interview") then
if is_set(Program) then
ID = ' ' .. Program;
end
if is_set(Callsign) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. Callsign;
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
 
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
else
Others = '(Interview)';
end
end
 
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
Llinell 2,115 ⟶ 2,510:
end
 
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if 'conference' == config.CitationClass then
if is_set(BookTitle) then
Llinell 2,121 ⟶ 2,516:
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURLorigin = URLorigin;
URLorigin = '';
Llinell 2,135 ⟶ 2,531:
end
 
-- cite map oddities
local Cartography = "";
local Scale = "";
Llinell 2,143 ⟶ 2,539:
Chapter = A['Map'];
ChapterURL = A['MapURL'];
ChapterUrlAccess = UrlAccess;
TransChapter = A['TransMap'];
ChapterURLorigin = A:ORIGIN('MapURL');
Llinell 2,157 ⟶ 2,554:
end
 
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
Llinell 2,195 ⟶ 2,592:
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURLorigin = A:ORIGIN('URL');
Llinell 2,202 ⟶ 2,600:
 
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
Chapter = '[[' ..make_wikilink (ChapterLink .. '|' .., Chapter .. ']]'); -- ok to wikilink
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' ..make_wikilink (ChapterLink .. '|' .., Series .. ']]'); -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
end
URL = ''; -- unset
Llinell 2,214 ⟶ 2,612:
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
Series = '[[' ..make_wikilink (SeriesLink .. '|' .., Series .. ']]');
end
Series = wrap_style ('italic-title', Series); -- series is italicized
end
end
-- end of {{cite episode}} stuff
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data.
do
if 'arxiv' == config.CitationClass then
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message
elseif is_set (Series) then -- series is an alias of version
end
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
Series = ''; -- unset
if 'arxiv' == config.CitationClass then
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
end
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
 
if 'biorxiv' == config.CitationClass then
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
PublisherNamePeriodical = 'bioRxiv'; -- (ifset theto articlebioRxiv hasfor beenCOinS; publishedafter that, usemust citebe journal,set to orempty other)string
end
Chapter = '';
 
URL = '';
if 'citeseerx' == config.CitationClass then
Format = '';
Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string
Page = ''; Pages = ''; At = '';
end
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
 
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notesinterview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. "' ' .. cfg.title_types ['thesis"']:lower();
end
end
 
if is_set(TitleType) then -- if type parameter is specified
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
-- TODO: Hack on TitleType to fix bunched parentheses problem
end
 
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
 
if not is_set (Date) then
Date = Year; -- promote Year to Date
Llinell 2,266 ⟶ 2,662:
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
else
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
end
else
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
end
 
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
 
--[[
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
we get the date used in the metadata.
 
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
['access-date'] = {val=AccessDate, name=A:ORIGIN ('AccessDate')},
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};
['archive-date'] = {val=ArchiveDate, name=A:ORIGIN ('ArchiveDate')},
 
['date'] = {val=Date, name=Date_origin},
['doi-broken-date'] = {val=DoiBroken, name=A:ORIGIN ('DoiBroken')},
['embargo'] = {val=Embargo, name=A:ORIGIN ('Embargo')},
['lay-date'] = {val=LayDate, name=A:ORIGIN ('LayDate')},
['publication-date'] ={val=PublicationDate, name=A:ORIGIN ('PublicationDate')},
['year'] = {val=Year, name=A:ORIGIN ('Year')},
};
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
 
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
 
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
Llinell 2,296 ⟶ 2,710:
end
end
if not is_set(error_message) then -- error free dates only
local modified = false; -- flag
if is_set (DF) then -- if we need to reformat dates
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
end
 
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
if is_set(error_message) then
modified = true;
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
elseif is_set (DF) then
if reformat_dates (date_parameters_list, DF, false) then -- reformat to DF format, use long month names if appropriate
AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with reformatted values
ArchiveDate = date_parameters_list['archive-date'];
Date = date_parameters_list['date'];
DoiBroken = date_parameters_list['doi-broken-date'];
LayDate = date_parameters_list['lay-date'];
PublicationDate = date_parameters_list['publication-date'];
end
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment these three lines. Not supported by en.wiki (for obvious reasons)
-- set date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
-- if date_name_xlate (date_parameters_list, false) then
-- modified = true;
-- end
 
if modified then -- if the date_parameters_list values were modified
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
ArchiveDate = date_parameters_list['archive-date'].val;
Date = date_parameters_list['date'].val;
DoiBroken = date_parameters_list['doi-broken-date'].val;
LayDate = date_parameters_list['lay-date'].val;
PublicationDate = date_parameters_list['publication-date'].val;
end
else
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
end -- end of do
 
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
Embargo = is_embargoed (Embargo); --
 
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
Llinell 2,319 ⟶ 2,751:
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = ''; -- unset
end
 
end
end
 
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
-- Test if citation has no title
if not is_set(Title) and
Llinell 2,378 ⟶ 2,815:
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = coins_pages or get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName,
Llinell 2,387 ⟶ 2,824:
}, config.CitationClass);
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite citeseerx}} AFTER generation of COinS data.
if in_array (config.CitationClass, {'arxiv', =='biorxiv', config.CitationClass'citeseerx'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in citethese arxivtemplates; if article has been published, use cite journal
end
 
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil ));
end
end
Llinell 2,407 ⟶ 2,844:
do
local last_first_list;
-- local maximum;
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn
mode = Mode
};
 
do -- do editor name list first because the now unsupported coauthors canused to modify control table
control.maximum , editor_etal = get_display_authors_editorsget_display_names (A['DisplayEditors'], #e, 'editors', editor_etal);
last_first_list, EditorCount = list_people(control, e, editor_etal);
 
if is_set (Editors) then
Editors, editor_etal = name_has_etal (Editors, editor_etal, false, 'editors'); -- find and remove variations on et al.
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
Llinell 2,433 ⟶ 2,871:
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
do -- now do interviewers
control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal);
Interviewers = list_people (control, interviewers_list, interviewer_etal);
end
do -- now do translators
control.maximum , translator_etal = get_display_names (A['DisplayTranslators'], #t; -- number of, 'translators', translator_etal);
Translators = list_people (control, t, falsetranslator_etal); -- et al not currently supported
end
do -- now do contributors
control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c; -- number of, 'contributors', contributor_etal);
Contributors = list_people (control, c, falsecontributor_etal); -- et al not currently supported
-- control.maximum = #c; -- number of contributors
-- Contributors = list_people(control, c, false); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editorsget_display_names (A['DisplayAuthors'], #a, 'authors', author_etal);
 
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal);
 
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Llinell 2,466 ⟶ 2,905:
end
 
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
 
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Llinell 2,479 ⟶ 2,915:
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
 
-- special case for chapter format so no error message or cat when chapter not supported
if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
Llinell 2,497 ⟶ 2,933:
end
 
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
DeadURL = DeadURL:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
if is_set (ChapterURL) then -- swapped -- URL not set so if chapter-url is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalFormat = ChapterFormat; -- and original |chapter-format=
if 'no' ~= DeadURL then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls
end
elseif is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived urls
end
end
end
 
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
local chap_param;
Llinell 2,552 ⟶ 2,991:
end
 
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
if is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
Llinell 2,565 ⟶ 3,004:
 
-- Format main title.
if is_set (ArchiveURL) and mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation['archived_copy']) then -- if title is 'Archived copy' (place holder added by bots that can't find proper title)
if is_set(TitleLink) and is_set(Title) then
add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
end
 
if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup:
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup
else
if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title=
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
end
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
Llinell 2,594 ⟶ 3,043:
end
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive
-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available
-- local err_msg
-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message
-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this
-- Title = Title .. (err_msg or '');
-- end
-- else
-- Title = temp_title;
-- end
 
if is_set(Title) then
if not is_set (TitleLink) and is_set (URL) then
Title = external_link (URL, Title, URLorigin, UrlAccess) .. TransTitle .. TransError .. Format;
URL = ''; -- unset these because no longer needed
Format = "";
elseif is_set (TitleLink) and not is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
local ws_url, ws_label;
Title = Title .. TransError;
ws_url, ws_label, L = wikisource_url_make (Title); -- make ws url from |title= interwiki link; link portion L becomes tool tip label
if ws_url then
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Title = Title .. TransTitle .. TransError;
end
end
else
Title = TransTitle .. TransError;
end
 
Llinell 2,625 ⟶ 3,081:
if is_set (Conference) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
end
 
Llinell 2,683 ⟶ 3,139:
else
Language=""; -- language not specified so make sure this is an empty string;
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
 
Llinell 2,688 ⟶ 3,147:
if is_set (Translators) then
Others = safe_join ({sepc .. ' Translated', bywrap_msg (' ..translated', Translators, ..use_lowercase), Others}, sepc);
end
if is_set (Interviewers) then
 
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (Edition) then
Llinell 2,702 ⟶ 3,164:
 
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; -- TODO: presentation
 
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 
Llinell 2,712 ⟶ 3,175:
end
 
--[[
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.
 
]]
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
Llinell 2,729 ⟶ 3,192:
 
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation'mode is cs2, lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
 
-- neither of these work; don't know why; it seems that substitute() isn't being called
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
Llinell 2,743 ⟶ 3,206:
end
 
ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
 
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin, UrlAccess );
end
 
Llinell 2,766 ⟶ 3,229:
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');
Llinell 2,773 ⟶ 3,236:
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
if 'bot: unknown' == DeadURL then
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
else
add_maint_cat ('unfit'); -- and add a category if not already added
end
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else
Llinell 2,800 ⟶ 3,268:
end
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Llinell 2,810 ⟶ 3,278:
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
end
 
local Publisher;
if is_set(PeriodicalPublicationDate) andthen
PublicationDate = wrap_msg ('published', PublicationDate);
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
end
if is_set(PublisherName) then
if is_set(PublicationPlacePublisherName) then
Publisher =if is_set(PublicationPlace) .. ": " .. PublisherName;then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
else
Publisher = PublisherName;
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
end
elseif is_set(PublicationPlace) then
Publisher= elseif is_set(PublicationPlace;) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
else
Publisher = "";
Publisher = PublicationDate;
end
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
else
Publisher = PublicationDate;
end
end
if is_set(Publisher) then
Publisher = " (" .. Publisher .. ")";
end
else
if is_set(PublicationDate) then
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
end
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
elseif is_set(PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
end
Llinell 2,867 ⟶ 3,310:
end
 
--[[
Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
Llinell 2,888 ⟶ 3,331:
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = safe_join ({Others .., sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
Language, Edition, Publisher, Agency, Volume}, sepc );
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
Llinell 2,910 ⟶ 3,351:
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
 
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Llinell 2,922 ⟶ 3,364:
end
local idcommon;
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
else
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
end
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
Llinell 2,938 ⟶ 3,386:
end
if is_set(Authors) then
if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
if is_set(Coauthors) then
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
Authors = Authors .. ', ' .. Coauthors;
else
Authors = Authors .. '; ' .. Coauthors;
end
end
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
Llinell 2,953 ⟶ 3,394:
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then
in_text = in_text:lower() end -- lowercase for cs2
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
post_text = " (" .. cfg.messages['editors'] .. ")";
if EditorCount <= 1 then
end
post_text = ", " .. cfg.messages['editor'];
else
post_text = ", " .. cfg.messages['editors'];
end
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
Llinell 2,967 ⟶ 3,409:
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if is_set (Editors) and is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if (not is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
Llinell 2,993 ⟶ 3,435:
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if in_array(config.CitationClass==, {"journal","citation"}) and is_set(Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
Llinell 3,030 ⟶ 3,472:
namelist = e;
end
idif =#namelist anchor_id> (namelist,0 year);then -- goif makethere theare CITEREFnames anchorin namelist
id = anchor_id (namelist, year); -- go make the CITEREF anchor
else
id = ''; -- unset
end
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>","")) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains
z.error_categories = {};
text = set_error('empty_citation');
Llinell 3,041 ⟶ 3,487:
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
 
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
texttable.insert =(render, substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
texttable.insert =(render, substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
 
texttable.insert = text ..(render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
 
if #z.message_tail0 ~= 0#z.message_tail then
table.insert (render, ' ');
text = text .. " ";
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if i == #z.message_tail then
texttable.insert = text ..(render, error_comment( v[1], v[2] ));
else
texttable.insert = text ..(render, error_comment( v[1] .. "; ", v[2] ));
end
end
Llinell 3,062 ⟶ 3,510:
end
 
if #z.maintenance_cats0 ~= 0#z.maintenance_cats then
local maint_msgs = {}; -- here we collect all of the maint messages
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
local maint = {}; -- here we assemble a maintenence message
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint, make_wikilink (':Category:' .. v, 'link')); -- add the link
table.insert (maint, ')'); -- and close it
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
end
table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
end
Llinell 3,073 ⟶ 3,526:
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
for _, v in ipairs( z.error_categories ) do
texttable.insert =(render, text ..make_wikilink ('[[Category:' .. v ..']]'));
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
texttable.insert =(render, text ..make_wikilink ('[[Category:' .. v ..']]'));
end
for _, v in ipairs( z.properties_cats ) do -- append maintenanceproperties categories
texttable.insert =(render, text ..make_wikilink ('[[Category:' .. v ..']]'));
end
end
 
return table.concat (render);
end
 
 
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
 
Looks for a parameter's name in one of several whitelists.
 
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
return text
 
local function validate (name, cite_class)
local name = tostring (name);
local state;
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[name];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
state = whitelist[cite_class .. '_basic_arguments'][name]; -- look in the parameter-list for the template identified by cite_class
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- limited enumerated parameters list
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[name];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- all enumerated parameters allowed
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.numbered_arguments[name];
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- not supported because not found or name is set to nil
end
 
 
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
 
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a
parameter that is missing its pipe:
{{cite ... |title=Title access-date=2016-03-17}}
 
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 
]]
 
local function missing_pipe_check (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
 
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {set_error ('missing_pipe',parameter)});
end
end
 
 
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
Llinell 3,092 ⟶ 3,634:
]]
 
local function cs1.citation(frame)
Frame = frame; -- save a copy incase we need to display an error message in preview mode
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata, styles;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
Llinell 3,103 ⟶ 3,646:
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
styles = 'Module:Citation/CS1/sandbox/styles.css';
else -- otherwise
Llinell 3,111 ⟶ 3,655:
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
 
end
 
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 
Llinell 3,121 ⟶ 3,667:
year_date_check = validation.year_date_check;
reformat_dates = validation.reformat_dates;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
date_name_xlate = validation.date_name_xlate;
 
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
in_array = utilities.in_array;
Llinell 3,131 ⟶ 3,679:
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
remove_wiki_linkis_wikilink = utilities.remove_wiki_linkis_wikilink;
make_wikilink = utilities.make_wikilink;
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/UtilitiesIdentifiers
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
extract_id_access_levels = identifiers.extract_id_access_levels;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
Llinell 3,143 ⟶ 3,693:
COinS = metadata.COinS;
 
local args = {}; -- table where we store all of the template's arguments
local suggestions = {}; -- table where we store suggestions if we need to loadData them
local args = {};
local suggestions = {};
local error_text, error_state;
 
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
config[k] = v;
-- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}}
args[k] = v;
end
 
Llinell 3,157 ⟶ 3,706:
for k, v in pairs( pframe.args ) do
if v ~= '' then
if not validate('string' k== type (k)) then
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
end
if not validate( k, config.CitationClass ) then
error_text = "";
if type( k ) ~= 'string' then
Llinell 3,164 ⟶ 3,716:
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
Llinell 3,177 ⟶ 3,729:
capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match
if capture then -- if the pattern matches
param = substitute ( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message
error_text, error_state = set_error ('parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = set_error( 'parameter_ignored', {param}, true ); -- suggested param not supported by this template
end
end
end
Llinell 3,186 ⟶ 3,742:
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
Llinell 3,193 ⟶ 3,750:
end
end
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
-- TODO: is this the best place for this translation?
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then -- here when v is empty string
args[k] = v; -- why do we do this? we don't support 'empty' parameters
end
end
Llinell 3,206 ⟶ 3,763:
end
end
return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})});
end
 
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
return cs1;
]]
 
return {citation = citation};
Wedi dod o "https://cy.wikipedia.org/wiki/Modiwl:Citation/CS1"