Happy 11th anniversary, screamer wiki!

Module:Citation/CS1: Difference between revisions

Jump to: navigation, search

Module:Citation/CS1 (view source)

Revision as of 20:05, 30 April 2021

117,662 bytes removed ,  30 April 2021
m
Protected "Module:Citation/CS1" ([Edit=Allow only administrators] (indefinite) [Move=Allow only administrators] (indefinite))
(Created page with " require('Module:No globals'); --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- each of these counts against t...")
 
m (Protected "Module:Citation/CS1" ([Edit=Allow only administrators] (indefinite) [Move=Allow only administrators] (indefinite)))
 
(3 intermediate revisions by 2 users not shown)
Line 1: Line 1:
--[[--------------------------< U N C A T E G O R I Z E D _ N A M E S P A C E S >------------------------------


require('Module:No globals');
List of namespaces that should not be included in citation error categories.
Same as setting notracking = true by default.


--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
Note: Namespace names should use underscores instead of spaces.
 
each of these counts against the Lua upvalue limit


]]
]]


local validation; -- functions in Module:Citation/CS1/Date_validation
local uncategorized_namespaces = { 'User', 'Talk', 'User_talk', 'Wikipedia_talk',
'File_talk', 'Template_talk', 'Help_talk', 'Category_talk', 'Portal_talk',
'Book_talk', 'Draft_talk', 'Education_Program_talk', 'Module_talk', 'MediaWiki_talk' };
local uncategorized_subpages = {'/[Ss]andbox', '/[Tt]estcases', '/[^/]*[Ll]og', '/[Aa]rchive'}; -- list of Lua patterns found in page names of pages we should not categorize


local utilities; -- functions in Module:Citation/CS1/Utilities
local z ={}; -- table of tables in Module:Citation/CS1/Utilities


local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
--[[--------------------------< M E S S A G E S >--------------------------------------------------------------
local metadata; -- functions in Module:Citation/CS1/COinS
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


Translation table


--[[--------------------------< P A G E  S C O P E  V A R I A B L E S >--------------------------------------
The following contains fixed text that may be output as part of a citation.
 
This is separated from the main body to aid in future translations of this
declare variables here that have page-wide scope that are not brought in from other modules; that are created here and used here
module.


]]
]]


local added_deprecated_cat; -- Boolean flag so that the category is added only once
local messages = {
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category
['agency'] = '$1 $2', -- $1 is sepc, $2 is agency
 
['archived-dead'] = 'Archived from $1 on $2',
local Frame; -- holds the module's frame table
['archived-live'] = '$1 from the original on $2',
 
['archived-missing'] = 'Archived from the original$1 on $2',
 
['archived-unfit'] = 'Archived from the original on ',
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
['archived'] = 'Archived',
['by'] = 'By', -- contributions to authored works: introduction, foreword, afterword
['cartography'] = 'Cartography by $1',
['editor'] = 'ed.',
['editors'] = 'eds.',
['edition'] = '($1&nbsp;ed.)',
['episode'] = 'Episode $1',
['et al'] = 'et&nbsp;al.',
['in'] = 'In', -- edited works
['inactive'] = 'inactive',
['inset'] = '$1 inset',
['interview'] = 'Interviewed by $1',
['lay summary'] = 'Lay summary',
['mismatch'] = '<code class="cs1-code">&#124;$1=</code> / <code class="cs1-code">&#124;$2=</code> mismatch', -- $1 is year param name; $2 is date param name
['newsgroup'] = '[[Usenet newsgroup|Newsgroup]]:&nbsp;$1',
['notitle'] = 'No title', -- for |title=(()) and (in the future) |title=none
['original'] = 'the original',
['origdate'] = ' [$1]',
['published'] = ' (published $1)',
['retrieved'] = 'Retrieved $1',
['season'] = 'Season $1',
['section'] = '§&nbsp;$1',
['sections'] = '§§&nbsp;$1',
['series'] = '$1 $2', -- $1 is sepc, $2 is series
['seriesnum'] = 'Series $1',
['translated'] = 'Translated by $1',
['type'] = ' ($1)', -- for titletype
['written'] = 'Written at $1',


Locates and returns the first set value in a table of values where the order established in the table,
['vol'] = '$1 Vol.&nbsp;$2', -- $1 is sepc; bold journal style volume is in presentation{}
left-to-right (or top-to-bottom), is the order in which the values are evaluated.  Returns nil if none are set.
['vol-no'] = '$1 Vol.&nbsp;$2 no.&nbsp;$3', -- sepc, volume, issue
['issue'] = '$1 No.&nbsp;$2', -- $1 is sepc


This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs.  With the pairs
['j-vol'] = '$1 $2', -- sepc, volume; bold journal volume is in presentation{}
version the order of evaluation could not be guaranteed.  With the ipairs version, a nil value would terminate
['j-issue'] = ' ($1)',
the for-loop before it reached the actual end of the list.


]]
['nopp'] = '$1 $2'; -- page(s) without prefix; $1 is sepc


local function first_set (list, count)
['p-prefix'] = "$1 p.&nbsp;$2", -- $1 is sepc
local i = 1;
['pp-prefix'] = "$1 pp.&nbsp;$2", -- $1 is sepc
while i <= count do -- loop through all items in list
['j-page(s)'] = ': $1', -- same for page and pages
if utilities.is_set( list[i] ) then
return list[i]; -- return the first set list member
end
i = i + 1; -- point to next
end
end


 
['sheet'] = '$1 Sheet&nbsp;$2', -- $1 is sepc
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
['sheets'] = '$1 Sheets&nbsp;$2', -- $1 is sepc
 
['j-sheet'] = ': Sheet&nbsp;$1',
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
['j-sheets'] = ': Sheets&nbsp;$1',
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)
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source}, true ) } );
end
end
 
 
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
 
does this thing that purports to be a URI scheme seem to be a valid scheme?  The scheme is checked to see if it
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
Scheme names consist of a sequence of characters beginning with a
  letter and followed by any combination of letters, digits, plus
  ("+"), period ("."), or hyphen ("-").
 
returns true if it does, else false
 
]]
 
local function is_scheme (scheme)
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
end
 
 
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
 
Does this thing that purports to be a domain name seem to be a valid domain name?
 
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
BNF defined here: https://tools.ietf.org/html/rfc4234
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
see also [[Single-letter second-level domain]]
list of TLDs: https://www.iana.org/domains/root/db
 
RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
the first and last characters the name may use letters, digits, and the hyphen.
 
Also allowed are IPv4 addresses. IPv6 not supported
 
domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
is two or more alpha characters.  Any preceding '//' (from splitting a URL with a scheme) will be stripped
here.  Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal.
 
There are several tests:
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, .cash, and .today TLDs
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
two-character SL domains in gTLDs (where the gTLD is two or more letters)
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
IPv4 dot-decimal address format; TLD not allowed
 
returns true if domain appears to be a proper name and TLD or IPv4 address, else false
 
]=]
 
local function is_domain_name (domain)
if not domain then
return false; -- if not set, abandon
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
['language'] = '(in $1)',
['via'] = " &ndash; via $1",
['event'] = 'Event occurs at',
['minutes'] = 'minutes in',
if not domain:match ('^[%w]') then -- first character must be letter or digit
-- Determines the location of the help page
return false;
['help page link'] = 'Help:CS1 errors',
end
['help page label'] = 'help',
 
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
return false;
end
 
local patterns = { -- patterns that look like URLs
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
'%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars)
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}
 
for _, pattern in ipairs (patterns) do -- loop through the patterns list
if domain:match (pattern) then
return true; -- if a match then we think that this thing that purports to be a URL is a URL
end
end
 
for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
if domain:match ('%f[%w][%w]%.' .. d) then
return true
end
end
return false; -- no matches, we don't know what this thing is
end
 
 
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
 
returns true if the scheme and domain parts of a URL appear to be a valid URL; else false.
 
This function is the last step in the validation process.  This function is separate because there are cases that
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.
 
]]
 
local function is_url (scheme, domain)
if utilities.is_set (scheme) then -- if scheme is set check it and domain
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when URL is protocol-relative
end
end
 
 
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
 
Split a URL into a scheme, authority indicator, and domain.
 
First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#).
 
If protocol-relative URL, return nil scheme and domain else return nil for both scheme and domain.
 
When not protocol-relative, get scheme, authority indicator, and domain.  If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
 
Any URL that does not have news: scheme must have authority indicator (//).  TODO: are there other common schemes
like news: that don't use authority indicator?
 
Strip off any port and path;
 
]]
 
local function split_url (url_str)
local scheme, authority, domain;
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
-- categories
['cat wikilink'] = '[[Category:$1]]', -- $1 is the category name
[':cat wikilink'] = '[[:Category:$1|link]]', -- category name as maintenance message wikilink; $1 is the category name


if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL
-- Internal errors (should only occur if configuration is bad)
domain = url_str:match ('^//(%S*)')
['undefined_error'] = 'Called with an undefined error condition',
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
['unknown_ID_key'] = 'Unrecognized ID key', -- an ID key in id_handlers not found in ~/Identifiers func_map{}
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
['unknown_argument_map'] = 'Argument map not defined for this variable',
if utilities.is_set (authority) then
['bare_url_no_origin'] = 'Bare URL found but origin indicator is nil or empty',
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
}
if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
return scheme; -- return scheme only making domain nil which will cause an error message
end
else
if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test?
return scheme; -- return scheme only making domain nil which will cause an error message
end
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
end




--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
--[=[-------------------------< E T _ A L _ P A T T E R N S >--------------------------------------------------


checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs
This table provides Lua patterns for the phrase "et al" and variants in name text
(author, editor, etc.). The main module uses these to identify and emit the 'etal' message.


Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
]=]
# < > [ ] | { } _
except the underscore which is used as a space in wiki URLs and # which is used for section links
 
returns false when the value contains any of these characters.
 
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid URL (the
|<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
 
]]


local function link_param_ok (value)
local et_al_patterns = {
local scheme, domain;
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][%.\"']*$", -- variations on the 'et al' theme
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
"[;,]? *[\"']*%f[%a][Ee][Tt]%.? *[Aa][Ll][Ii][AaIi][Ee]?[%.\"']*$", -- variations on the 'et alia', 'et alii' and 'et aliae' themes (false positive 'et aliie' unlikely to match)
return false;
"[;,]? *%f[%a]and [Oo]thers", -- an alternative to et al.
end
"%[%[ *[Ee][Tt]%.? *[Aa][Ll]%.? *%]%]", -- a wikilinked form
"%(%( *[Ee][Tt]%.? *[Aa][Ll]%.? *%)%)", -- a double-bracketed form (to counter partial removal of ((...)) syntax)
"[%(%[] *[Ee][Tt]%.? *[Aa][Ll]%.? *[%)%]]", -- a bracketed form
}


scheme, domain = split_url (value); -- get scheme or nil and domain or nil from URL;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL
end


--[[--------------------------< E D I T O R _ M A R K U P _ P A T T E R N S >----------------------------------


--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
This table provides Lua patterns for the phrase "ed" and variants in name text
 
(author, editor, etc.). The main module uses these to identify and emit the
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
'extra_text_names' message. (It is not the only series of patterns for this message.)
 
|<title>= may be wiki-linked but not when |<param>-link= has a value.  This function emits an error message when
that condition exists
 
check <link> for inter-language interwiki-link prefix.  prefix must be a MediaWiki-recognized language
code and must begin with a colon.


]]
]]
local editor_markup_patterns = { -- these patterns match annotations at end of name
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'
'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)
'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'
'[,%.%s]%f[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive
-- these patterns match annotations at beginning of name
'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.'
'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also square brackets, case insensitive, optional brackets, 's'
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also square brackets, case insensitive, optional brackets


local function link_title_ok (link, lorig, title, torig)
-- these patterns match annotations that are the 'name'
local orig;
'^[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors; case insensitive
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value
}
if not link_param_ok (link) then -- check |<param>-link= markup
orig = lorig; -- identify the failing link parameter
elseif title:find ('%[%[') then -- check |title= for wikilink markup
orig = torig; -- identify the failing |title= parameter
elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki
local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix
 
if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon
orig = lorig; -- flag as error
end
end
end
 
if utilities.is_set (orig) then
link = ''; -- unset
table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)}); -- URL or wikilink in |title= with |title-link=;
end
return link; -- link if ok, empty string else
end




--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
--[[--------------------------< P R E S E N T A T I O N >------------------------


Determines whether a URL string appears to be valid.
Fixed presentation markup.  Originally part of citation_config.messages it has
 
been moved into its own, more semantically correct place.
First we test for space characters.  If any are found, return false.  Then split the URL into scheme and domain
portions, or for protocol-relative (//example.com) URLs, just the domain.  Use is_url() to validate the two
portions of the URL. If both are valid, or for protocol-relative if domain is valid, return true, else false.
 
Because it is different from a standard URL, and because this module used external_link() to make external links
that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4


]]
]]


local function check_url( url_str )
local presentation =
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL
{
return false;
-- Error output
end
-- .error class is specified at https://git.wikimedia.org/blob/mediawiki%2Fcore.git/9553bd02a5595da05c184f7521721fb1b79b3935/skins%2Fcommon%2Fshared.css#L538
local scheme, domain;
-- .citation-comment class is specified at Help:CS1_errors#Controlling_error_message_display
 
['hidden-error'] = '<span class="cs1-hidden-error error citation-comment">$1</span>',
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
['visible-error'] = '<span class="cs1-visible-error error citation-comment">$1</span>',
['hidden-maint'] = '<span class="cs1-maint citation-comment">$1</span>',
if 'news:' == scheme then -- special case for newsgroups
['accessdate'] = '<span class="reference-accessdate">$1$2</span>', -- to allow editors to hide accessdate using personal CSS
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
end
return is_url (scheme, domain); -- return true if value appears to be a valid URL
end
 
 
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
 
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
non-space characters following the opening bracket appear to be a URL.  The test will also find external wikilinks
that use protocol-relative URLs. Also finds bare URLs.
 
The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs.  The tests that
find bracketed URLs are required because the parameters that call this test (currently |title=, |chapter=, |work=,
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
is possible as might be [[en://Hus]].
 
]=]


local function is_parameter_ext_wikilink (value)
['bdi'] = '<bdi$1>$2</bdi>', -- bidirectional isolation used with |script-title= and the like
local scheme, domain;


if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
['cite'] = '<cite class="$1">$2</cite>'; -- |ref= not set so no id="..." attribute
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
['cite-id'] = '<cite id="$1" class="$2">$3</cite>'; -- for use when |ref= is set
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
elseif value:match ('%a%S*:%S+') then -- if bare URL with scheme; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
elseif value:match ('//%S+') then -- if protocol-relative bare URL: //yyyyy.zzz; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a URL
end


return is_url (scheme, domain); -- return true if value appears to be a valid URL
['format'] = ' <span class="cs1-format">($1)</span>', -- for |format=, |chapter-format=, etc.
end


-- various access levels, for |access=, |doi-access=, |arxiv=, ...
-- narrow no-break space &#8239; may work better than nowrap CSS. Or not? Browser support?


--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
['ext-link-access-signal'] = '<span class="$1" title="$2">$3</span>', -- external link with appropriate lock icon
['free'] = {class='cs1-lock-free', title='Freely accessible'}, -- classes defined in Module:Citation/CS1/styles.css
['registration'] = {class='cs1-lock-registration', title='Free registration required'},
['limited'] = {class='cs1-lock-limited', title='Free access subject to limited trial, subscription normally required'},
['subscription'] = {class='cs1-lock-subscription', title='Paid subscription required'},


loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
['interwiki-icon'] = '<span class="$1" title="$2">$3</span>',
 
['class-wikisource'] = 'cs1-ws-icon',
]]
 
local function check_for_url (parameter_list)
local error_message = '';
for k, v in pairs (parameter_list) do -- for each parameter in the list
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a URL add an error message
if utilities.is_set(error_message) then -- once we've added the first portion of the error message ...
error_message = error_message .. ", "; -- ... add a comma space separator
end
error_message = error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
if utilities.is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { utilities.set_message ( 'err_param_has_ext_link', {error_message}, true ) } );
end
end


['italic-title'] = "''$1''",


--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
['kern-left'] = '<span class="cs1-kern-left">$1</span>$2', -- spacing to use when title contains leading single or double quote mark
['kern-right'] = '$1<span class="cs1-kern-right">$2</span>', -- spacing to use when title contains trailing single or double quote mark


Escape sequences for content that will be used for URL descriptions
-- these for simple wikilinked titles [["text]], [[text"]] and [["text"]]
-- span wraps entire wikilink
['kern-wl-left'] = '<span class="cs1-kern-wl-left">$1</span>', -- when title contains leading single or double quote mark
['kern-wl-right'] = '<span class="cs1-kern-wl-left">$1</span>', -- when title contains trailing single or double quote mark
['kern-wl-both'] = '<span class="cs1-kern-wl-left cs1-kern-wl-right">$1</span>', -- when title contains leading and trailing single or double quote marks


]]
['nowrap1'] = '<span class="nowrap">$1</span>', -- for nowrapping an item: <span ...>yyyy-mm-dd</span>
['nowrap2'] = '<span class="nowrap">$1</span> $2', -- for nowrapping portions of an item: <span ...>dd mmmm</span> yyyy (note white space)


local function safe_for_url( str )
['ocins'] = '<span title="$1" class="Z3988"></span>',
if str:match( "%[%[.-%]%]" ) ~= nil then
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } );
end
return str:gsub( '[%[%]\n]', {
['parameter'] = '<code class="cs1-code">&#124;$1=</code>',
['['] = '&#91;',
[']'] = '&#93;',
['ps_cs1'] = '.'; -- CS1 style postscript (terminal) character
['\n'] = ' ' } );
['ps_cs2'] = ''; -- CS2 style postscript (terminal) character (empty string)
end
 
 
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
 
Format an external link with error checking


]]
['quoted-text'] = '<q>$1</q>', -- for wrapping |quote= content
['quoted-title'] = '"$1"',


local function external_link( URL, label, source, access)
['sep_cs1'] = '.', -- CS1 element separator
local error_str = "";
['sep_cs2'] = ',', -- CS2 separator
local domain;
['sep_nl'] = ';', -- CS1|2 style name-list separator between names is a semicolon
local path;
['sep_nl_and'] = ' and ', -- used as last nl sep when |name-list-style=and and list has 2 items
local base_url;
['sep_nl_end'] = '; and ', -- used as last nl sep when |name-list-style=and and list has 3+ names
['sep_name'] = ', ', -- CS1|2 style last/first separator is <comma><space>
['sep_nl_vanc'] = ',', -- Vancouver style name-list separator between authors is a comma
['sep_name_vanc'] = ' ', -- Vancouver style last/first separator is a space


if not utilities.is_set ( label ) then
['sep_list'] = ', ', -- used for |language= when list has 3+ items except for last sep which uses sep_list_end
label = URL;
['sep_list_pair'] = ' and ', -- used for |language= when list has 2 items
if utilities.is_set ( source ) then
['sep_list_end'] = ', and ', -- used as last list sep for |language= when list has 3+ items
error_str = utilities.set_message ( 'err_bare_url_missing_title', { utilities.wrap_style ('parameter', source) }, false, " " );
else
error( cfg.messages["bare_url_no_origin"] );
end
end
if not check_url( URL ) then
error_str = utilities.set_message ( 'err_bad_url', {utilities.wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path
['trans-italic-title'] = "&#91;''$1''&#93;",
if path then -- if there is a path portion
['trans-quoted-title'] = "&#91;$1&#93;", -- for |trans-title= and |trans-quote=
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values
['vol-bold'] = '$1 <b>$2</b>', -- sepc, volume; for bold journal cites; for other cites ['vol'] in messages{}
URL = table.concat ({domain, path}); -- and reassemble
}
end


base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL
if utilities.is_set (access) then -- access level (subscription, registration, limited)
base_url = utilities.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 ({base_url, error_str});
--[[--------------------------< A L I A S E S >---------------------------------
end
 
 
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------


Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
Aliases table for commonly passed parameters.
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
Parameter names on the right side in the assignments in this table must have been
defined in the Whitelist before they will be recognized as valid parameter names


]]
]]


local function deprecated_parameter(name)
local aliases = {
if not added_deprecated_cat then
['AccessDate'] = {'access-date', 'accessdate'}, -- Used by InternetArchiveBot
added_deprecated_cat = true; -- note that we've added this category
['Agency'] = 'agency',
table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } ); -- add error message
['ArchiveDate'] = {'archive-date', 'archivedate'}, -- Used by InternetArchiveBot
end
['ArchiveFormat'] = 'archive-format',
end
['ArchiveURL'] = {'archive-url', 'archiveurl'}, -- Used by InternetArchiveBot
['ASINTLD'] = 'asin-tld',
['At'] = 'at', -- Used by InternetArchiveBot
['Authors'] = {'authors', 'people', 'credits'},
['BookTitle'] = {'book-title', 'booktitle'},
['Cartography'] = 'cartography',
['Chapter'] = {'chapter', 'contribution', 'entry', 'article', 'section'},
['ChapterFormat'] = {'chapter-format', 'contribution-format', 'entry-format',
'article-format', 'section-format'};
['ChapterURL'] = {'chapter-url', 'contribution-url', 'entry-url', 'article-url',
'section-url', 'chapterurl'}, -- Used by InternetArchiveBot
['ChapterUrlAccess'] = {'chapter-url-access', 'contribution-url-access',
'entry-url-access', 'article-url-access', 'section-url-access'}, -- Used by InternetArchiveBot
['Class'] = 'class', -- cite arxiv and arxiv identifiers
['Collaboration'] = 'collaboration',
['Conference'] = {'conference', 'event'},
['ConferenceFormat'] = 'conference-format',
['ConferenceURL'] = 'conference-url', -- Used by InternetArchiveBot
['Date'] = {'date', 'air-date', 'airdate'}, -- air-date and airdate for cite episode and cite serial only
['Degree'] = 'degree',
['DF'] = 'df',
['DisplayAuthors'] = {'display-authors', 'display-subjects'},
['DisplayContributors'] = 'display-contributors',
['DisplayEditors'] = 'display-editors',
['DisplayInterviewers'] = 'display-interviewers',
['DisplayTranslators'] = 'display-translators',
['Docket'] = 'docket',
['DoiBroken'] = 'doi-broken-date',
['Edition'] = 'edition',
['Embargo'] = 'pmc-embargo-date',
['Encyclopedia'] = {'encyclopedia', 'encyclopaedia', 'dictionary'}, -- cite encyclopedia only
['Episode'] = 'episode', -- cite serial only TODO: make available to cite episode?
['Format'] = 'format',
['ID'] = {'id', 'ID'},
['Inset'] = 'inset',
['Issue'] = {'issue', 'number'},
['Language'] = {'language', 'lang'},
['LayDate'] = 'lay-date',
['LayFormat'] = 'lay-format',
['LaySource'] = 'lay-source',
['LayURL'] = 'lay-url',
['MailingList'] = {'mailing-list', 'mailinglist'}, -- cite mailing list only
['Map'] = 'map', -- cite map only
['MapFormat'] = 'map-format', -- cite map only
['MapURL'] = {'map-url', 'mapurl'}, -- cite map only -- Used by InternetArchiveBot
['MapUrlAccess'] = 'map-url-access', -- cite map only -- Used by InternetArchiveBot
['Minutes'] = 'minutes',
['Mode'] = 'mode',
['NameListStyle'] = 'name-list-style',
['Network'] = 'network',
['Newsgroup'] = 'newsgroup', -- cite newsgroup only
['NoPP'] = {'no-pp', 'nopp'},
['NoTracking'] = {'no-tracking', 'template-doc-demo'},
['Number'] = 'number', -- this case only for cite techreport
['OrigDate'] = {'orig-date', 'orig-year', 'origyear'},
['Others'] = 'others',
['Page'] = {'page', 'p'}, -- Used by InternetArchiveBot
['Pages'] = {'pages', 'pp'}, -- Used by InternetArchiveBot
['Periodical'] = {'journal', 'magazine', 'newspaper', 'periodical', 'website', 'work'},
['Place'] = {'place', 'location'},
['PostScript'] = 'postscript',
['PublicationDate'] = {'publication-date', 'publicationdate'},
['PublicationPlace'] = {'publication-place', 'publicationplace'},
['PublisherName'] = {'publisher', 'institution'},
['Quote'] = {'quote', 'quotation'},
['QuotePage'] = 'quote-page',
['QuotePages'] = 'quote-pages',
['Ref'] = 'ref',
['Scale'] = 'scale',
['ScriptChapter'] = {'script-chapter', 'script-contribution', 'script-entry',
'script-article', 'script-section'},
['ScriptMap'] = 'script-map',
['ScriptPeriodical'] = {'script-journal', 'script-magazine', 'script-newspaper',
'script-periodical', 'script-website', 'script-work'},
['ScriptQuote'] = 'script-quote',
['ScriptTitle'] = 'script-title', -- Used by InternetArchiveBot
['Season'] = 'season',
['Sections'] = 'sections', -- cite map only
['Series'] = {'series', 'version'},
['SeriesLink'] = {'series-link', 'serieslink'},
['SeriesNumber'] = {'series-number', 'series-no'},
['Sheet'] = 'sheet', -- cite map only
['Sheets'] = 'sheets', -- cite map only
['Station'] = 'station',
['Time'] = 'time',
['TimeCaption'] = 'time-caption',
['Title'] = 'title', -- Used by InternetArchiveBot
['TitleLink'] = {'title-link', 'episode-link', 'episodelink'}, -- Used by InternetArchiveBot
['TitleNote'] = 'department',
['TitleType'] = {'type', 'medium'},
['TransChapter'] = {'trans-article', 'trans-chapter', 'trans-contribution',
'trans-entry', 'trans-section'},
['Transcript'] = 'transcript',
['TranscriptFormat'] = 'transcript-format',
['TranscriptURL'] = {'transcript-url', 'transcripturl'}, -- Used by InternetArchiveBot
['TransMap'] = 'trans-map', -- cite map only
['TransPeriodical'] = {'trans-journal', 'trans-magazine', 'trans-newspaper',
'trans-periodical', 'trans-website', 'trans-work'},
['TransQuote'] = 'trans-quote',
['TransTitle'] = 'trans-title', -- Used by InternetArchiveBot
['URL'] = {'url', 'URL'}, -- Used by InternetArchiveBot
['UrlAccess'] = 'url-access', -- Used by InternetArchiveBot
['UrlStatus'] = 'url-status', -- Used by InternetArchiveBot
['Vauthors'] = 'vauthors',
['Veditors'] = 'veditors',
['Via'] = 'via',
['Volume'] = 'volume',
['Year'] = 'year',


['AuthorList-First'] = {"first#", "author-first#", "author#-first", "given#",
"author-given#", "author#-given"},
['AuthorList-Last'] = {"last#", "author-last#", "author#-last", "surname#",
"author-surname#", "author#-surname", "author#", "subject#", 'host#'},
['AuthorList-Link'] = {"author-link#", "author#-link", "subject-link#",
"subject#-link", "authorlink#", "author#link"},
['AuthorList-Mask'] = {"author-mask#", "author#-mask", "subject-mask#", "subject#-mask"},


--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
['ContributorList-First'] = {'contributor-first#', 'contributor#-first',
'contributor-given#', 'contributor#-given'},
['ContributorList-Last'] = {'contributor-last#', 'contributor#-last',
'contributor-surname#', 'contributor#-surname', 'contributor#'},
['ContributorList-Link'] = {'contributor-link#', 'contributor#-link'},
['ContributorList-Mask'] = {'contributor-mask#', 'contributor#-mask'},


Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote
['EditorList-First'] = {"editor-first#", "editor#-first", "editor-given#", "editor#-given"},
mark contained in a |title= or |chapter= parameter's value.
['EditorList-Last'] = {"editor-last#", "editor#-last", "editor-surname#",
 
"editor#-surname", "editor#"},
This function will positive kern either single or double quotes:
['EditorList-Link'] = {"editor-link#", "editor#-link"},
"'Unkerned title with leading and trailing single quote marks'"
['EditorList-Mask'] = {"editor-mask#", "editor#-mask"},
" '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 wiki-markup) are not kerned.
 
Replaces Unicode quote marks 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 = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
['InterviewerList-First'] = {'interviewer-first#', 'interviewer#-first',
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
'interviewer-given#', 'interviewer#-given'},
str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
['InterviewerList-Last'] = {'interviewer-last#', 'interviewer#-last',
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
'interviewer-surname#', 'interviewer#-surname', 'interviewer#'},
str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
['InterviewerList-Link'] = {'interviewer-link#', 'interviewer#-link'},
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
['InterviewerList-Mask'] = {'interviewer-mask#', 'interviewer#-mask'},
str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
 
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if utilities.is_set (cap) then
label = utilities.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 utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
return str;
end


['TranslatorList-First'] = {'translator-first#', 'translator#-first',
'translator-given#', 'translator#-given'},
['TranslatorList-Last'] = {'translator-last#', 'translator#-last',
'translator-surname#', 'translator#-surname', 'translator#'},
['TranslatorList-Link'] = {'translator-link#', 'translator#-link'},
['TranslatorList-Mask'] = {'translator-mask#', 'translator#-mask'},
}


--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------


|script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
--[[--------------------------< P U N C T _ S K I P >---------------------------
not be italicized and may be written right-to-left.  The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.


Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate RTL languages from the English left to right.
builds a table of parameter names that the extraneous terminal punctuation check should not check.


|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO 639-1 language code and a colon:
]]
|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
|script-title=ja : *** ***
|script-title=ja: *** ***
|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***


The prefix is checked for validity.  If it is a valid ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
local punct_skip = {};
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.


Supports |script-title=, |script-chapter=, |script-<periodical>=
local meta_params = { -- table of aliases[] keys (meta parameters); each key has a table of parameter names for a value
'BookTitle', 'Chapter', 'ScriptChapter', 'ScriptTitle', 'Title', 'TransChapter', 'Transcript', 'TransMap', 'TransTitle', -- title-holding parameters
'AuthorList-Mask', 'ContributorList-Mask', 'EditorList-Mask', 'InterviewerList-Mask', 'TranslatorList-Mask', -- name-list mask may have name separators
'PostScript', 'Quote', 'ScriptQuote', 'TransQuote', 'Ref', -- miscellaneous
'ArchiveURL', 'ChapterURL', 'ConferenceURL', 'LayURL', 'MapURL', 'TranscriptURL', 'URL', -- URL-holding parameters
}


]]
for _, meta_param in ipairs (meta_params) do -- for each meta parameter key
 
local params = aliases[meta_param]; -- get the parameter or the table of parameters associated with the meta parameter name
local function format_script_value (script_value, script_param)
if 'string' == type (params) then
local lang=''; -- initialize to empty string
punct_skip[params] = 1; -- just a single parameter
local name;
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not utilities.is_set (lang) then
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
return ''; -- script_value was just the prefix so return empty string
end
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if utilities.in_array (lang, cfg.script_lang_codes) then
utilities.add_prop_cat ('script_with_name', {name, lang})
else
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
else
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
for _, param in ipairs (params) do -- get the parameter name
lang = ''; -- invalid so set lang to empty string
punct_skip[param] = 1; -- add the parameter name to the skip table
end
local count;
else
param, count = param:gsub ('#', ''); -- remove enumerator marker from enumerated parameters
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
if 0 ~= count then -- if removed
end
punct_skip[param] = 1; -- add param name without enumerator marker
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL
 
return script_value;
end
 
 
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
 
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
wrapped in <bdi> tags.
]]
 
local function script_concatenate (title, script, script_param)
if utilities.is_set (script) then
script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error
if utilities.is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
return title;
end
 
 
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
 
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
from citation_config.messages - the reason this function is similar to but separate from wrap_style().
 
]]
 
local function wrap_msg (key, str, lower)
if not utilities.is_set ( str ) then
return "";
end
if true == lower then
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return utilities.substitute ( msg, str ); -- including template text
else
return utilities.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;
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
 
wl_type, D, L = utilities.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 utilities.is_set (str) then
ws_url = table.concat ({ -- build a Wikisource URL
wikisource_prefix, -- 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 utilities.is_set (str) then
ws_url = table.concat ({ -- build a Wikisource URL
wikisource_prefix, -- 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 utilities.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
wikisource_prefix, -- 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 fragment marker
end
 
return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil
end
 
 
--[[--------------------------< F O R M A T _ P E R I O D I C A L >--------------------------------------------
 
Format the three periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta-
parameter.
 
]]
 
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
local periodical_error = '';
 
if not utilities.is_set (periodical) then
periodical = ''; -- to be safe for concatenation
else
periodical = utilities.wrap_style ('italic-title', periodical); -- style
end
 
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 
if utilities.is_set (trans_periodical) then
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
if utilities.is_set (periodical) then
periodical = periodical .. ' ' .. trans_periodical;
else -- here when trans-periodical without periodical or script-periodical
periodical = trans_periodical;
periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'});
end
end
 
return periodical .. periodical_error;
end
 
 
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
 
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single chapter meta-
parameter (chapter_url_source used for error messages).
 
]]
 
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, 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 utilities.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 = utilities.wrap_style ('quoted-title', chapter);
end
end
 
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 
if utilities.is_set (chapter_url) then
chapter = external_link (chapter_url, 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
 
if utilities.is_set (trans_chapter) then
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter);
if utilities.is_set (chapter) then
chapter = chapter .. ' ' .. trans_chapter;
else -- here when trans_chapter without chapter or script-chapter
chapter = trans_chapter;
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>
chapter_error = ' ' .. utilities.set_message ('err_trans_missing_title', {chapter_source});
end
end
 
return chapter .. chapter_error;
end
 
 
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
This function searches a parameter's value for non-printable or invisible characters.  The search stops at the
first match.
 
This function will detect the visible replacement character when it is part of the Wikisource.
 
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().
 
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
parameter value.
 
]]
 
local function has_invisible_chars (param, v)
local position = ''; -- position of invisible char or starting position of stripmarker
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
local capture; -- used by stripmarker detection to hold name of the stripmarker
local i = 1;
local stripmarker, apostrophe;
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
if capture == v then -- if same there are no Unicode characters
return;
end
 
while cfg.invisible_chars[i] do
local char = cfg.invisible_chars[i][1] -- the character or group name
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 -- it's ok if one of the Indic scripts
position = nil; -- unset position
end
end
if position then
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
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
else
local err_msg;
if capture then
err_msg = capture .. ' ' .. char;
else
err_msg = char .. ' ' .. 'character';
end
end
table.insert( z.message_tail, { utilities.set_message ( 'err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true ) } ); -- add error message
return; -- and done with this parameter
end
end
end
end
i = i+1; -- bump our index
end
end
end
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
Argument wrapper.  This function provides support for argument mapping defined in the configuration file so that
multiple names can be transparently aliased to single internal variable.
]]
local function argument_wrapper ( args )
local origin = {};
return setmetatable({
ORIGIN = function ( self, k )
local dummy = self[k]; --force the variable to be loaded.
return origin[k];
end
},
{
__index = function ( tbl, k )
if origin[k] ~= nil then
return nil;
end
local args, list, v = args, cfg.aliases[k];
if type( list ) == 'table' then
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
end
elseif list ~= nil then
v, origin[k] = args[list], list;
else
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
end
-- Empty strings, not nil;
if v == nil then
v = '';
origin[k] = '';
end
tbl = rawset( tbl, k, v );
return v;
end,
});
end


--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------


When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
--[[-----------< S P E C I A L  C A S E  T R A N S L A T I O N S >------------
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY


DOES NOT yet support MMMM YYYY or any of the date ranges.
This table is primarily here to support internationalization.  Translations in
this table are used, for example, when an error message, category name, etc.,
is extracted from the English alias key.  There may be other cases where
this translation table may be useful.


]]
]]


local function nowrap_date (date)
local special_case_translation = {
local cap = '';
['AuthorList'] = 'authors list', -- used to assemble maintenance category names
local cap2 = '';
['ContributorList'] = 'contributors list', -- translation of these names plus translation of the base mainenance category names in maint_cats{} table below
 
['EditorList'] = 'editors list', -- must match the names of the actual categories
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
['InterviewerList'] = 'interviewers list', -- this group or translations used by name_has_ed_markup() and name_has_mult_names()
date = utilities.substitute (cfg.presentation['nowrap1'], date);
['TranslatorList'] = 'translators list',
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
return date;
-- Lua patterns to match pseudo-titles used by InternetArchiveBot and others as placeholder for unknown |title= value
end
['archived_copy'] = { -- used with CS1 maint: Archive[d] copy as title
['en'] = '^archived?%s+copy$', -- for English; translators: keep this because templates imported from en.wiki
['local'] = nil, -- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
},


-- Lua patterns to match generic titles; usually created by bots or reference filling tools
-- translators: replace ['local'] = nil with lowercase translation only when bots or tools create generic titles in your language
['generic_titles'] = {
-- patterns in this table should be lowercase only
-- leave ['local'] nil except when there is a matching generic title in your language
-- generic titles must be lowercase
-- boolean 'true' for plain-text searches; 'false' for pattern searches
{['en'] = {'^wayback%s+machine$', false}, ['local'] = nil},
{['en'] = {'are you a robot', true}, ['local'] = nil},
{['en'] = {'hugedomains.com', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?no +title[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'page not found', true}, ['local'] = nil},
{['en'] = {'subscribe to read', true}, ['local'] = nil},
{['en'] = {'^[%(%[{<]?unknown[>}%]%)]?$', false}, ['local'] = nil},
{['en'] = {'website is for sale', true}, ['local'] = nil},
{['en'] = {'^404', true}, ['local'] = nil},
{['en'] = {'internet archive wayback machine', true}, ['local'] = nil},
{['en'] = {'log into facebook', true}, ['local'] = nil},
{['en'] = {'redirecting...', true}, ['local'] = nil},
{['en'] = {'webcite query result', true}, ['local'] = nil},
{['en'] = {'wikiwix\'s cache', true}, ['local'] = nil},
}
}


--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
]]
local function set_titletype (cite_class, title_type)
if utilities.is_set (title_type) then
if 'none' == cfg.keywords_xlate[title_type] then
title_type = ''; -- if |type=none then type parameter not displayed
end
return title_type; -- if |type= has been set to any other value use that value
end
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
--[[--------------------------< 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 utilities.is_set (str) then
return str;
end


local accept; -- Boolean
--[[--------------------------< D A T E _ N A M E S >----------------------------------------------------------
str, accept = utilities.has_accept_as_written (str); -- remove accept-this-as-written markup when it wraps all of str
if accept then
return str; -- when markup removed, 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
str = str:gsub ('&#45;', '-'); -- replace HTML numeric entity with hyphen character
str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character
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
This table of tables lists local language date names and fallback English date names.
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
The code in Date_validation will look first in the local table for valid date names.
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
If date names are not found in the local table, the code will look in the English table.
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 whitespace
end
end
item = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of str
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
Because citations can be copied to the local wiki from en.wiki, the English is
end
required when the date-name translation function date_name_xlate() is used.


In these tables, season numbering is defined by
Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/)
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'. The standard
defines various divisions using numbers 21-41. CS1|2 only supports generic seasons.
EDTF does support the distinction between north and south hemisphere seasons
but CS1|2 has no way to make that distinction.


--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each)


Joins a sequence of strings together while checking for duplicate separation characters.
The standard does not address 'named' dates so, for the purposes of CS1|2,
Easter and Christmas are defined here as 98 and 99, which should be out of the
ISO 8601 (EDTF) range of uses for a while.


]]
]]


local function safe_join( tbl, duplicate_char )
local date_names = {
local f = {}; -- create a function table appropriate to type of 'duplicate character'
['en'] = { -- English
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12},
f.gsub = string.gsub
['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12},
f.match = string.match
['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36},
f.sub = string.sub
['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23},
else -- for multi-byte characters use the ustring library functions
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
f.gsub = mw.ustring.gsub
},
f.match = mw.ustring.match
['local'] = { -- replace these English date names with the local language equivalents
f.sub = mw.ustring.sub
['long'] = {['January'] = 1, ['February'] = 2, ['March'] = 3, ['April'] = 4, ['May'] = 5, ['June'] = 6, ['July'] = 7, ['August'] = 8, ['September'] = 9, ['October'] = 10, ['November'] = 11, ['December'] = 12},
end
['short'] = {['Jan'] = 1, ['Feb'] = 2, ['Mar'] = 3, ['Apr'] = 4, ['May'] = 5, ['Jun'] = 6, ['Jul'] = 7, ['Aug'] = 8, ['Sep'] = 9, ['Oct'] = 10, ['Nov'] = 11, ['Dec'] = 12},
['quarter'] = {['First Quarter'] = 33, ['Second Quarter'] = 34, ['Third Quarter'] = 35, ['Fourth Quarter'] = 36},
['season'] = {['Winter'] = 24, ['Spring'] = 21, ['Summer'] = 22, ['Fall'] = 23, ['Autumn'] = 23},
['named'] = {['Easter'] = 98, ['Christmas'] = 99},
},
['inv_local_l'] = {}, -- used in date reformatting; copy of date_names['local'].long where k/v are inverted: [1]='<local name>' etc.
['inv_local_s'] = {}, -- used in date reformatting; copy of date_names['local'].short where k/v are inverted: [1]='<local name>' etc.
['local_digits'] = {['0'] = '0', ['1'] = '1', ['2'] = '2', ['3'] = '3', ['4'] = '4', ['5'] = '5', ['6'] = '6', ['7'] = '7', ['8'] = '8', ['9'] = '9'}, -- used to convert local language digits to Western 0-9
['xlate_digits'] = {},
}


local str = ''; -- the output string
for name, i in pairs (date_names['local'].long) do -- this table is ['name'] = i
local comp = ''; -- what does 'comp' mean?
date_names['inv_local_l'][i] = name; -- invert to get [i] = 'name' for conversions from ymd
local end_chr = '';
local trim;
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then -- if output string is empty
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string)
else
comp = value;
end
-- typically duplicate_char is sepc
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
--  Because individual string segments often (always?) begin with terminal punct for the
--  preceding segment: 'First element' .. 'sepc next element' .. etc.?
trim = false;
end_chr = 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 = f.sub(str, 1, -2); -- remove it
elseif end_chr == "'" then -- if it might be wiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif  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 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 wiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
trim = true;
elseif  f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of 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 f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = f.sub(str, 1, -3); -- remove them both
end
end
 
if trim then
if value ~= comp then -- value does not equal comp when value contains HTML markup
local dup2 = duplicate_char;
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup
else
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; --add it to the output string
end
end
return str;
end
end


 
for name, i in pairs (date_names['local'].short) do -- this table is ['name'] = i
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
date_names['inv_local_s'][i] = name; -- invert to get [i] = 'name' for conversions from ymd
 
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9.  Puncutation not allowed.
 
]]
 
local function is_suffix (suffix)
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
return false;
end
end


 
for ld, ed in pairs (date_names.local_digits) do -- make a digit translation table for simple date translation from en to local language using local_digits table
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
date_names.xlate_digits [ed] = ld; -- en digit becomes index with local digit as the value
 
For Vancouver style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.
 
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
 
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
 
This original test:
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
was written outside 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, suffix)
if not suffix then
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
first = first:match ('(.-)[,%s]+'); -- get name/initials
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
end
end
if utilities.is_set (suffix) then
if not is_suffix (suffix) then
add_vanc_error (cfg.err_msg_supl.suffix);
return false; -- not a name with an appropriate suffix
end
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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 (cfg.err_msg_supl['non-Latin char']);
return false; -- not a string of Latin characters; Vancouver requires Romanization
end;
return true;
end
end


local df_template_patterns = { -- table of redirects to {{Use dmy dates}} and {{Use mdy dates}}
'{{ *[Uu]se +(dmy) +dates *[|}]', -- 1159k -- sorted by approximate transclusion count
'{{ *[Uu]se +(mdy) +dates *[|}]', -- 212k
'{{ *[Uu]se +(MDY) +dates *[|}]', -- 788
'{{ *[Uu]se +(DMY) +dates *[|}]', -- 343
'{{ *([Mm]dy) *[|}]', -- 176
'{{ *[Uu]se *(dmy) *[|}]', -- 156 + 18
'{{ *[Uu]se *(mdy) *[|}]', -- 149 + 11
'{{ *([Dd]my) *[|}]', -- 56
'{{ *[Uu]se +(MDY) *[|}]', -- 5
'{{ *([Dd]MY) *[|}]', -- 3
'{{ *[Uu]se(mdy)dates *[|}]', -- 1
'{{ *[Uu]se +(DMY) *[|}]', -- 0
'{{ *([Mm]DY) *[|}]', -- 0
}


--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
local function get_date_format ()
 
local content = mw.title.getCurrentTitle():getContent() or ''; -- get the content of the article or ''; new pages edited w/ve do not have 'content' until saved; ve does not preview; phab:T221625
Attempts to convert names to initials in support of |name-list-style=vanc. 
for _, pattern in ipairs (df_template_patterns) do -- loop through the patterns looking for {{Use dmy dates}} or {{Use mdy dates}} or any of their redirects
 
local start, _, match = content:find(pattern); -- match is the three letters indicating desired date format
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/.
if match then
 
content = content:match ('%b{}', start); -- get the whole template
Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered as Jr, 2nd, 3rd, etc.  See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
if content:match ('| *cs1%-dates *= *[lsy][sy]?') then -- look for |cs1-dates=publication date length access-/archive-date length
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
return match:lower() .. '-' .. content:match ('| *cs1%-dates *= *([lsy][sy]?)');
 
This function uses ustring functions because firstname initials may be any of the Unicode Latin characters accepted by is_good_vanc_name ().
 
]]
 
local function reduce_to_initials(first)
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
 
if not name then -- if not initials and a suffix
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
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 (cfg.err_msg_supl.suffix); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
else
else
return first; -- one or two initials without suffix; nothing to do
return match:lower() .. '-all'; -- no |cs1-dates= k/v pair; return value appropriate for use in |df=
end
end
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 initial at end of initials table
end
i = i+1; -- bump the counter
end
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
end


local global_df = get_date_format ();


--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
Formats a list of people (e.g. authors, contributors, editors, interviewers, translators)


names in the list will be linked when
--[[-----------------< V O L U M E ,  I S S U E ,  P A G E S >------------------
|<name>-link= has a value
|<name>-mask- does NOT have a value; masked names are presumed to have been rendered previously so should have been linked there


when |<name>-mask=0, the associated name is not rendered
These tables hold cite class values (from the template invocation) and identify those templates that support
|volume=, |issue=, and |page(s)= parameters.  Cite conference and cite map require further qualification which
is handled in the main module.


]]
]]


local function list_people (control, people, etal)
local templates_using_volume = {'citation', 'audio-visual', 'book', 'conference', 'encyclopaedia', 'interview', 'journal', 'magazine', 'map', 'news', 'report', 'techreport', 'thesis'}
local sep;
local templates_using_issue = {'citation', 'conference', 'episode', 'interview', 'journal', 'magazine', 'map', 'news', 'podcast'}
local namesep;
local templates_not_using_page = {'audio-visual', 'episode', 'mailinglist', 'newsgroup', 'podcast', 'serial', 'sign', 'speech'}
local format = control.format;
local maximum = control.maximum;
local lastauthoramp = control.lastauthoramp; -- TODO: delete after deprecation
local name_list = {};


if 'vanc' == format then -- Vancouver-like name styling?
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
lastauthoramp = nil; -- TODO: delete after deprecation -- unset because isn't used by Vancouver style
else
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
end
if sep:sub (-1, -1) ~= " " then sep = sep .. " " end
if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names
for i, person in ipairs (people) do
if utilities.is_set (person.last) then
local mask = person.mask;
local one;
local sep_one = sep;


if utilities.is_set (maximum) and i > maximum then
--[[
etal = true;
break;
end
if mask then
local n = tonumber (mask); -- convert to a number if it can be converted; nil else
if n then
one = 0 ~= n and string.rep("&mdash;",n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
else
one = mask; -- replace name with mask text (must include name-list separator)
sep_one = " "; -- modify name-list separator
end
else
one = person.last; -- get surname
local first = person.first -- get given name
if utilities.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
end
if utilities.is_set (person.link) then
one = utilities.make_wikilink (person.link, one); -- link author/editor
end
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
table.insert (name_list, one); -- add it to the list of names
table.insert (name_list, sep_one); -- add the proper name-list separator
end
end
end


local count = #name_list / 2; -- (number of names + number of separators) divided by 2
Patterns for finding extra text in |volume=, |issue=, |page=, |pages=
if 0 < count then
if 1 < count and not etal then
if 'amp' == format or utilities.is_set (lastauthoramp) then -- TODO: delete lastauthoramp after deprecation
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
elseif 'and' == format then
if 2 == count then
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
else
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
end
end
end
name_list[#name_list] = nil; -- erase the last separator
end
 
local result = table.concat (name_list); -- construct list
if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al.
end
return result, count; -- return name-list string and count of number of names (count used for editor names only)
end
 
 
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
 
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.
 
namelist is one of the contributor-, author-, or editor-name lists chosen in that order.  year is Year or anchor_year.


]]
]]


local function anchor_id (namelist, year)
local vol_iss_pg_patterns = {
local names={}; -- a table for the one to four names and year
good_ppattern = '^P[^%.PpGg]', -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123); TODO: this allows 'Pages' which it should not
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
bad_ppatterns = { -- patterns for |page= and |pages=
names[i] = v.last
'^[Pp][PpGg]?%.?[ %d]',
if i == 4 then break end -- if four then done
'^[Pp]ages?',
end
'^[Pp]gs.?',
table.insert (names, year); -- add the year at the end
},
local id = table.concat(names); -- concatenate names and year for CITEREF id
vpatterns = { -- patterns for |volume=
if utilities.is_set (id) then -- if concatenation is not an empty string
'^volumes?',
return "CITEREF" .. id; -- add the CITEREF portion
'^vols?[%.:=]?'
else
},
return ''; -- return an empty string; no reason to include CITEREF id in this citation
ipatterns = { -- patterns for |issue=
end
'^issues?',
end
'^iss[%.:=]?',
 
'^numbers?',
 
'^nos?%A', -- don't match 'november' or 'nostradamus'
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
'^nr[%.:=]?',
 
'^n[%.:= ]' -- might be a valid issue without separator (space char is sep char here)
Evaluates the content of name parameters (author, editor, etc.) 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 associated |display-<names>=etal parameter
 
]]
 
local function name_has_etal (name, etal, nocat, param)
 
if utilities.is_set (name) then -- name can be nil in which case just return
local patterns = cfg.et_al_patterns; --get patterns from configuration
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
if name:match (pattern) then -- if this 'et al' pattern is found in name
name = name:gsub (pattern, ''); -- remove the offending text
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
if not nocat then -- no categorization for |vauthors=
table.insert( z.message_tail, {utilities.set_message ('err_etal', {param})}); -- and set an error if not added
end
end
end
end
 
return name, etal;
end
 
 
--[[--------------------------< N A M E _ I S _ N U M E R I C >------------------------------------------------
 
Add maint cat when name parameter value does not contain letters. Does not catch mixed alphanumeric names so
|last=A. Green (1922-1987) does not get caught in the current version of this test but |first=(1888) is caught.
 
returns nothing
 
]]
 
local function name_is_numeric (name, list_name)
if utilities.is_set (name) then
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
end
end
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 extraneous 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.
 
returns nothing
 
]]
 
local function name_has_ed_markup (name, list_name)
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
 
if utilities.is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
utilities.set_message ('maint_extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
end
end
end


--[[--------------------------< K E Y W O R D S >-------------------------------


--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
These tables hold keywords for those parameters that have defined sets of acceptable keywords.
 
Evaluates the content of last/surname (authors etc.) parameters for multiple names.  Multiple names are indicated
if there is more than one comma or any semicolons.  If found, the function adds the multiple name maintenance category.
 
returns nothing


]]
]]


local function name_has_mult_names (name, list_name)
--[[-------------------< K E Y W O R D S  T A B L E >--------------------------
local _, commas, semicolons;
if utilities.is_set (name) then
_, commas = name:gsub (',', ''); -- count the number of commas
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
if 1 < commas or 0 < semicolons then
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
end
end
end


this is a list of keywords; each key in the list is associated with a table of
synonymous keywords possibly from different languages.


--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
for I18N: add local-language keywords to value table; do not change the key.
For example, adding the German keyword 'ja':
['affirmative'] = {'yes', 'true', 'y', 'ja'},


This function calls various name checking functions used to validate the content of the various name-holding
Because CS1|2 templates from en.wiki articles are often copied to other local wikis,
parameters.
it is recommended that the English keywords remain in these tables.


]]
]]


local function name_checks (last, first, list_name)
local keywords = {
local accept_name;
['amp'] = {'&', 'amp', 'ampersand'}, -- |name-list-style=
 
['and'] = {'and', 'serial'}, -- |name-list-style=
if utilities.is_set (last) then
['affirmative'] = {'yes', 'true', 'y'}, -- |no-tracking=, |no-pp= -- Used by InternetArchiveBot
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
['afterword'] = {'afterword'}, -- |contribution=
['bot: unknown'] = {'bot: unknown'}, -- |url-status= -- Used by InternetArchiveBot
if not accept_name then -- <last> not wrapped in accept-as-written markup
['cs1'] = {'cs1'}, -- |mode=
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
['cs2'] = {'cs2'}, -- |mode=
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
['dead'] = {'dead'}, -- |url-status= -- Used by InternetArchiveBot
name_is_numeric (last, list_name); -- check for names that are compsed of digits and punctuation
['dmy'] = {'dmy'}, -- |df=
end
['dmy-all'] = {'dmy-all'}, -- |df=
end
['foreword'] = {'foreword'}, -- |contribution=
 
['free'] = {'free'}, -- |url-access= -- Used by InternetArchiveBot
if utilities.is_set (first) then
['introduction'] = {'introduction'}, -- |contribution=
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
['limited'] = {'limited'}, -- |url-access= -- Used by InternetArchiveBot
 
['live'] = {'live'}, -- |url-status= -- Used by InternetArchiveBot
if not accept_name then -- <first> not wrapped in accept-as-written markup
['mdy'] = {'mdy'}, -- |df=
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
['mdy-all'] = {'mdy-all'}, -- |df=
name_is_numeric (first, list_name); -- check for names that are compsed of digits and punctuation
['none'] = {'none'}, -- |postscript=, |ref=, |title=, |type= -- Used by InternetArchiveBot
end
['off'] = {'off'}, -- |title= (potentially also: |title-link=, |postscript=, |ref=, |type=)
end
['preface'] = {'preface'}, -- |contribution=
 
['registration'] = {'registration'}, -- |url-access= -- Used by InternetArchiveBot
return last, first; -- done
['subscription'] = {'subscription'}, -- |url-access= -- Used by InternetArchiveBot
end
['unfit'] = {'unfit'}, -- |url-status= -- Used by InternetArchiveBot
 
['usurped'] = {'usurped'}, -- |url-status= -- Used by InternetArchiveBot
['vanc'] = {'vanc'}, -- |name-list-style=
['ymd'] = {'ymd'}, -- |df=
['ymd-all'] = {'ymd-all'}, -- |df=
-- ['yMd'] = {'yMd'}, -- |df=; not supported at en.wiki
-- ['yMd-all'] = {'yMd-all'}, -- |df=; not supported at en.wiki
}


--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments


Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
--[[------------------------< X L A T E _ K E Y W O R D S >---------------------
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
find |last4= and |last5= then the search is done.


This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
this function builds a list, keywords_xlate{}, of the keywords found in keywords{} where the values from keywords{}
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
become the keys in keywords_xlate{} and the keys from keywords{} become the values in keywords_xlate{}:
['affirmative'] = {'yes', 'true', 'y'}, -- in keywords{}
becomes
['yes'] = 'affirmative', -- in keywords_xlate{}
['true'] = 'affirmative',
['y'] = 'affirmative',


When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned
the purpose of this function is to act as a translator between a non-English keyword and its English equivalent
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps 'et al.' out of the
that may be used in other modules of this suite
template's metadata.  When this occurs, the page is added to a maintenance category.


]]
]]


local function extract_names(args, list_name)
local function xlate_keywords ()
local names = {}; -- table of names
local out_table = {}; -- output goes here
local last; -- individual name components
for k, keywords_t in pairs (keywords) do -- spin through the keywords table
local first;
for _, keyword in ipairs (keywords_t) do -- for each keyword
local link;
out_table[keyword] = k; -- create an entry in the output table where keyword is the key
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
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, link_alias; -- selected parameter aliases used in error messaging
while true do
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_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_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks
if first and not last then -- if there is a firstn without a matching lastn
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias
table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', {
first_alias, -- param name of alias missing its mate
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
}, 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
if 2 <= count then -- two missing names and we give up
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
local result;
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
if first then
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup
end
 
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
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, { utilities.set_message ( 'err_missing_name', {list_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
end
end
i = i + 1; -- point to next args location
end
end
return names, etal; -- all done, return our list of names and the etal flag
return out_table;
end
end


local keywords_xlate = xlate_keywords (); -- the list of translated keywords


--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------


Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
--[[----------------< M A K E _ K E Y W O R D S _ L I S T >---------------------


Returns the language name and associated two- or three-character code.  Because case of the source may be incorrect
this function assembles, for parameter-value validation, the list of keywords appropriate to that parameter.
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is
found, the Wikimedia version (assumed to be correct) is returned along with the code.  When there is no match, we
return the original language name string.


mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include
keywords_lists{}, is a table of tables from keywords{}
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 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 WikiMedia 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.
 
]]
 
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 langlc = mw.ustring.lower (lang); -- lower-case version for comparisons
 
for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower (name) then
if 2 == #code or 3 == #code then -- two- or three-character codes only; IETF extensions not supported
return name, code; -- so return the name and the code
end
ietf_code = code; -- remember that we found an IETF-like code and save its name
ietf_name = name; -- but keep looking for a 2- or 3-char code
end
end
-- didn't find name with 2- or 3-char code; if IETF-like code found return
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 >------------------------------------------
 
Gets language name from a provided two- or three-character ISO 639 code.  If a code is recognized by MediaWiki,
use the returned name; if not, then use the value that was provided with the language parameter.
 
When |language= contains a recognized language (either code or name), the page is assigned to the category for
that code: Category:Norwegian-language sources (no).  For valid three-character code languages, the page is assigned
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources.
 
Languages that are the same as the local wiki are not categorized.  MediaWiki does not recognize three-character
equivalents of two-character codes: code 'ar' is recognized but code 'ara' is not.
 
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are
separated from each other by commas with optional space characters.


]]
]]


local function language_parameter (lang)
local function make_keywords_list (keywords_lists)
local code; -- the two- or three-character language code
local out_table = {}; -- output goes here
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_table = {}; -- table made from the value assigned to |language=
 
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
 
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
 
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 name then -- there was a remapped code so
if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private IETF tag
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip IETF tags from code
end
else
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any IETF-like tags from code
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
end
end
 
if utilities.is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if utilities.is_set (code) then -- only 2- or 3-character codes
for _, keyword_list in ipairs (keywords_lists) do -- spin through keywords_lists{} and get a table of keywords
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
for _, keyword in ipairs (keyword_list) do -- spin through keyword_list{} and add each keyword, ...
 
table.insert (out_table, keyword); -- ... as plain text, to the output list
if cfg.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
utilities.add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character code)
utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support multiple three-character code categories per cs1|2 template
end
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled
utilities.add_prop_cat ('local_lang_source', {name, code}); -- categorize it
end
else
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
end
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
name = utilities.make_sep_list (#language_list, language_list);
if this_wiki_name == name then
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
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: '.'
]]
local function set_cs1_style (ps)
if not utilities.is_set (ps) then -- unless explicitly set to something
ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation
end
end
return cfg.presentation['sep_cs1'], ps; -- element separator
return out_table;
end
end




--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
--[[----------------< K E Y W O R D S _ L I S T S >-----------------------------
 
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: ','
 
]]
 
local function set_cs2_style (ps, ref)
if not utilities.is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation
end
if not utilities.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
end


this is a list of lists of valid keywords for the various parameters in [key].
Generally the keys in this table are the canonical en.wiki parameter names though
some are contrived because of use in multiple differently named parameters:
['yes_true_y'], ['id-access'].


--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
The function make_keywords_list() extracts the individual keywords from the
appropriate list in keywords{}.


When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
The lists in this table are used to validate the keyword assignment for the
rendered style.
parameters named in this table's keys.


]]
]]


local function get_settings_from_cite_class (ps, ref, cite_class)
local keywords_lists = {
local sep;
['yes_true_y'] = make_keywords_list ({keywords.affirmative}),
if (cite_class == "citation") then -- for citation templates (CS2)
['contribution'] = make_keywords_list ({keywords.afterword, keywords.foreword, keywords.introduction, keywords.preface}),
sep, ps, ref = set_cs2_style (ps, ref);
['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all']}),
else -- not a citation template so CS1
-- ['df'] = make_keywords_list ({keywords.dmy, keywords['dmy-all'], keywords.mdy, keywords['mdy-all'], keywords.ymd, keywords['ymd-all'], keywords.yMd, keywords['yMd-all']}), -- not supported at en.wiki
sep, ps = set_cs1_style (ps);
['mode'] = make_keywords_list ({keywords.cs1, keywords.cs2}),
end
['name-list-style'] = make_keywords_list ({keywords.amp, keywords['and'], keywords.vanc}),
['url-access'] = make_keywords_list ({keywords.subscription, keywords.limited, keywords.registration}),
['url-status'] = make_keywords_list ({keywords.dead, keywords.live, keywords.unfit, keywords.usurped, keywords['bot: unknown']}),
['id-access'] = make_keywords_list ({keywords.free}),
}


return sep, ps, ref -- return them all
end


--[[---------------------< S T R I P M A R K E R S >----------------------------


--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
Common pattern definition location for stripmarkers so that we don't have to go
 
hunting for them if (when) MediaWiki changes their form.
Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
config.CitationClass from the template's #invoke: to establish style.


]]
]]


local function set_style (mode, ps, ref, cite_class)
local stripmarkers = {
local sep;
['any'] = '\127[^\127]*UNIQ%-%-(%a+)%-[%a%d]+%-QINU[^\127]*\127', -- capture returns name of stripmarker
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
['math'] = '\127[^\127]*UNIQ%-%-math%-[%a%d]+%-QINU[^\127]*\127' -- math stripmarkers used in coins_cleanup() and coins_replace_math_stripmarker()
sep, ps, ref = set_cs2_style (ps, ref);
}
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
sep, ps = set_cs1_style (ps);
else -- anything but cs1 or cs2
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
 
if cfg.keywords_xlate[ps:lower()] == 'none' then -- if assigned value is 'none' then
ps = ''; -- set to empty string
end
return sep, ps, ref
end
 


--[=[-------------------------< I S _ P D F >------------------------------------------------------------------


Determines if a URL has the file extension that is one of the PDF file extensions used by [[MediaWiki:Common.css]] when
--[[------------< I N V I S I B L E _ C H A R A C T E R S >---------------------
applying the PDF icon to external links.


returns true if file extension is one of the recognized extensions, else false
This table holds non-printing or invisible characters indexed either by name or
by Unicode group. Values are decimal representations of UTF-8 codes.  The table
is organized as a table of tables because the Lua pairs keyword returns table
data in an arbitrary order.  Here, we want to process the table from top to bottom
because the entries at the top of the table are also found in the ranges specified
by the entries at the bottom of the table.


]=]
Also here is a pattern that recognizes stripmarkers that begin and end with the
 
delete characters.  The nowiki stripmarker is not an error but some others are
local function is_pdf (url)
because the parameter values that include them become part of the template's
return url:match ('%.pdf$') or url:match ('%.PDF$') or
metadata before stripmarker replacement.
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 >------------------------------------------------------
 
Applies CSS style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
not have a matching URL parameter.  If the format parameter is not set and the URL contains a file extension that
is recognized as a PDF document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.


]]
]]


local function style_format (format, url, fmt_param, url_param)
local invisible_defs = {
if utilities.is_set (format) then
del = '\127', -- used to distinguish between stripmarker and del char
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
zwj = '\226\128\141', -- used with capture because zwj may be allowed
if not utilities.is_set (url) then
}
format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} ); -- add an error message
end
elseif is_pdf (url) then -- format is not set so if URL is a PDF file then
format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF
else
format = ''; -- empty string for concatenation
end
return format;
end
 


--[[--------------------------< G E T _ D I S P L A Y _ N A M E S >--------------------------------------------
local invisible_chars = {
{'replacement', '\239\191\189'}, -- U+FFFD, EF BF BD
{'zero width joiner', '('.. invisible_defs.zwj .. ')'}, -- U+200D, E2 80 8D; capture because zwj may be allowed
{'zero width space', '\226\128\139'}, -- U+200B, E2 80 8B
{'hair space', '\226\128\138'}, -- U+200A, E2 80 8A
{'soft hyphen', '\194\173'}, -- U+00AD, C2 AD
{'horizontal tab', '\009'}, -- U+0009 (HT), 09
{'line feed', '\010'}, -- U+000A (LF), 0A
{'no-break space', '\194\160'}, -- U+00A0 (NBSP), C2 A0
{'carriage return', '\013'}, -- U+000D (CR), 0D
{'stripmarker', stripmarkers.any}, -- stripmarker; may or may not be an error; capture returns the stripmaker type
{'delete', '('.. invisible_defs.del .. ')'}, -- U+007F (DEL), 7F; must be done after stripmarker test; capture to distinguish isolated del chars not part of stripmarker
{'C0 control', '[\000-\008\011\012\014-\031]'}, -- U+0000–U+001F (NULL–US), 00–1F (except HT, LF, CR (09, 0A, 0D))
{'C1 control', '[\194\128-\194\159]'}, -- U+0080–U+009F (XXX–APC), C2 80 – C2 9F
-- {'Specials', '[\239\191\185-\239\191\191]'}, -- U+FFF9-U+FFFF, EF BF B9 – EF BF BF
-- {'Private use area', '[\238\128\128-\239\163\191]'}, -- U+E000–U+F8FF, EE 80 80 – EF A3 BF
-- {'Supplementary Private Use Area-A', '[\243\176\128\128-\243\191\191\189]'}, -- U+F0000–U+FFFFD, F3 B0 80 80 – F3 BF BF BD
-- {'Supplementary Private Use Area-B', '[\244\128\128\128-\244\143\191\189]'}, -- U+100000–U+10FFFD, F4 80 80 80 – F4 8F BF BD
}


Returns a number that defines the number of names displayed for author and editor name lists and a Boolean flag
--[[
to indicate when et al. should be appended to the name list.
Indic script makes use of zero width joiner as a character modifier so zwj
 
characters must be left in. This pattern covers all of the unicode characters
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and
for these languages:
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
Devanagari 0900–097F – https://unicode.org/charts/PDF/U0900.pdf
some variant of the text 'et al.').
Devanagari extended A8E0–A8FF – https://unicode.org/charts/PDF/UA8E0.pdf
 
Bengali 0980–09FF – https://unicode.org/charts/PDF/U0980.pdf
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the
Gurmukhi 0A00–0A7F – https://unicode.org/charts/PDF/U0A00.pdf
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
Gujarati 0A80–0AFF – https://unicode.org/charts/PDF/U0A80.pdf
the names in the name list followed by 'et al.'
Oriya 0B00–0B7F – https://unicode.org/charts/PDF/U0B00.pdf
 
Tamil 0B80–0BFF – https://unicode.org/charts/PDF/U0B80.pdf
In all other cases, returns nil and the previous state of the 'etal' flag.
Telugu 0C00–0C7F – https://unicode.org/charts/PDF/U0C00.pdf
 
Kannada 0C80–0CFF – https://unicode.org/charts/PDF/U0C80.pdf
inputs:
Malayalam 0D00–0D7F – https://unicode.org/charts/PDF/U0D00.pdf
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
plus the not-necessarily Indic scripts for Sinhala and Burmese:
count: #a or #e
Sinhala 0D80-0DFF - https://unicode.org/charts/PDF/U0D80.pdf
list_name: 'authors' or 'editors'
Myanmar 1000-109F - https://unicode.org/charts/PDF/U1000.pdf
etal: author_etal or editor_etal
Myanmar extended A AA60-AA7F - https://unicode.org/charts/PDF/UAA60.pdf
Myanmar extended B A9E0-A9FF - https://unicode.org/charts/PDF/UA9E0.pdf
the pattern is used by has_invisible_chars() and coins_cleanup()


]]
]]


local function get_display_names (max, count, list_name, etal)
local indic_script = '[\224\164\128-\224\181\191\224\163\160-\224\183\191\225\128\128-\225\130\159\234\167\160-\234\167\191\234\169\160-\234\169\191]';
if utilities.is_set (max) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
max = count + 1; -- number of authors + 1 so display all author name plus et al.
etal = true; -- overrides value set by extract_names()
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {cfg.special_case_translation [list_name], max}, true)}); -- add error message
max = nil;
end
else -- not a valid keyword or number
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {cfg.special_case_translation [list_name], max}, true)}); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
end
return max, etal;
end


-- list of emoji that use zwj character (U+200D) to combine with another emoji
local emoji = { -- indexes are decimal forms of the hex values in U+xxxx
[127752] = true, -- U+1F308 🌈 rainbow
[127806] = true, -- U+1F33E 🌾 ear of rice
[127859] = true, -- U+1F373 🍳 cooking
[127891] = true, -- U+1F393 🎓 graduation cap
[127908] = true, -- U+1F3A4 🎤 microphone
[127912] = true, -- U+1F3A8 🎨 artist palette
[127979] = true, -- U+1F3EB 🏫 school
[127981] = true, -- U+1F3ED 🏭 factory
[128102] = true, -- U+1F466 👦 boy
[128103] = true, -- U+1F467 👧 girl
[128104] = true, -- U+1F468 👨 man
[128105] = true, -- U+1F469 👩 woman
[128139] = true, -- U+1F48B 💋 kiss mark
[128187] = true, -- U+1F4BB 💻 personal computer
[128188] = true, -- U+1F4BC 💼 brief case
[128295] = true, -- U+1F527 🔧 wrench
[128300] = true, -- U+1F52C 🔬 microscope
[128488] = true, -- U+1F5E8 🗨 left speech bubble
[128640] = true, -- U+1F680 🚀 rocket
[128658] = true, -- U+1F692 🚒 fire engine
[129309] = true, -- U+1F91D 🤝 handshake
[129455] = true, -- U+1F9AF 🦯 probing cane
[129456] = true, -- U+1F9B0 🦰 emoji component red hair
[129457] = true, -- U+1F9B1 🦱 emoji component curly hair
[129458] = true, -- U+1F9B2 🦲 emoji component bald
[129459] = true, -- U+1F9B3 🦳 emoji component white hair
[129466] = true, -- U+1F9BA 🦺 safety vest
[129468] = true, -- U+1F9BC 🦼 motorized wheelchair
[129469] = true, -- U+1F9BD 🦽 manual wheelchair
[129489] = true, -- U+1F9D1 🧑 adult
[9760] = true, -- U+2620 ☠ skull and crossbones
[9792] = true, -- U+2640 ♀ female sign
[9794] = true, -- U+2642 ♂ male sign
[9877] = true, -- U+2695 ⚕ staff of aesculapius
[9878] = true, -- U+2696 ⚖ scales
[9992] = true, -- U+2708 ✈ airplane
[10084] = true, -- U+2764 ❤ heavy black heart
}


--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------


Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
--[[----------------------< L A N G U A G E  S U P P O R T >-------------------
abbreviation in the first characters of the parameter content.


check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
These tables and constants support various language-specific functionality.
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP


]]
]]


local function extra_text_in_page_check (page)
local this_wiki_code = mw.getContentLanguage():getCode(); -- get this wiki's language code
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?
if string.match (mw.site.server, 'wikidata') then
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
this_wiki_code = mw.getCurrentFrame():preprocess('{{int:lang}}'); -- on Wikidata so use interface language setting instead
 
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
utilities.set_message ('maint_extra_text'); -- add maint cat;
end
end
end
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
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 parentheses 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 ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
local name = name_table[i];
i = i + 1; -- bump indexer to next segment
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses
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 = utilities.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
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
]]
local function parse_vauthors_veditors (args, vparam, list_name)
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)
local languages = mw.language.fetchLanguageNames (this_wiki_code, 'all'); -- get a list of language names known to Wikimedia; used for |language= and interwiki tests
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas


for i, v_name in ipairs(v_name_table) do
local inter_wiki_map = {}; -- map of interwiki prefixes that are language-code prefixes
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
for k, v in pairs (mw.site.interwikiMap ('local')) do -- spin through the base interwiki map (limited to local)
local accept_name;
if languages[v["prefix"]] then -- if the prefix matches a known language code
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
inter_wiki_map[v["prefix"]] = true; -- add it to our local map
 
-- if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to suppress vanc formatting and error detection
-- last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parentheses
if accept_name then
last = v_name;
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 (cfg.err_msg_supl.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 initials or generational suffix
 
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
suffix = first; -- not initials so assume that whatever we got is a generational suffix
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
if not utilities.is_set (last) then
first = ''; -- unset
last = v_name; -- last empty because something wrong with first
add_vanc_error (cfg.err_msg_supl.name);
end
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error (cfg.err_msg_supl['missing comma']); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error (cfg.err_msg_supl.name); -- matches a space between two initials
end
else
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
end
end
if utilities.is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error (cfg.err_msg_supl.initials); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first, suffix); -- check first and last before restoring the suffix which may have a non-Latin digit
if utilities.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
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list
end
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 >------------------------
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
similarly, |editorn= (and aliases) highest and |editors= lowest
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
way to do this, I just haven't discovered what that way is.
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
]]
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local lastfirst = false;
if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ...
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
lastfirst = true;
end
end


if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
local local_lang_cat_enable = false; -- set to true to categorize pages where |language=<local wiki's language>
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
(true == lastfirst and utilities.is_set (xxxxors)) then
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end


if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if utilities.is_set (vxxxxors) then return 2 end;
if utilities.is_set (xxxxors) then return 3 end;
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
end


--[[--------------------< S C R I P T _ L A N G _ C O D E S >-------------------


--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
This table is used to hold ISO 639-1 two-character and ISO 639-3 three-character
 
language codes that apply only to |script-title= and |script-chapter=
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, live, dead, etc.).  When the parameter value has not been assigned a value (missing
or empty in the source template) the function returns the value specified by ret_val.  If the parameter value is one
of the list of allowed values returns the translated value; else, emits an error message and returns the value
specified by ret_val.


]]
]]


local function is_valid_parameter_value (value, name, possible, ret_val)
local script_lang_codes = {
if not utilities.is_set (value) then
'am', 'ar', 'be', 'bg', 'bn', 'bo', 'bs', 'dv', 'dz', 'el', 'fa', 'gu',  
return ret_val; -- an empty parameter is ok
'he', 'hi', 'hy', 'ja', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'lo',
elseif utilities.in_array (value, possible) then
'mk', 'ml', 'mn', 'mr', 'my', 'ne', 'or', 'ota', 'ps', 'ru', 'sd', 'si',
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
'sr', 'ta', 'te', 'tg', 'th', 'ti', 'ug', 'uk', 'ur', 'uz', 'yi', 'zh'
else
};
table.insert( z.message_tail, { utilities.set_message ( 'err_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return ret_val;
end
end
 


--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------


This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
--[[---------------< L A N G U A G E  R E M A P P I N G >----------------------
when the last character is not a sepc character or when the last three characters are not sepc followed by two
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
single space character.


]]
These tables hold language information that is different (correct) from MediaWiki's definitions


local function terminate_name_list (name_list, sepc)
For each ['code'] = 'language name' in lang_code_remap{} there must be a matching ['language name'] = {'language name', 'code'} in lang_name_remap{}
if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
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
return name_list .. sepc .. ' '; -- otherwise terminate the name list
end
end


lang_code_remap{}:
key is always lowercase ISO 639-1, -2, -3 language code or a valid lowercase IETF language tag
value is properly spelled and capitalized language name associated with key
only one language name per key;
key/value pair must have matching entry in lang_name_remap{}


--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
lang_name_remap{}:
 
key is always lowercase language name
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
value is a table the holds correctly spelled and capitalized language name [1] and associated code [2] (code must match a code key in lang_code_remap{})
or formatted issue, or an empty string if neither are set.
may have multiple keys referring to a common preferred name and code; For example:
['kolsch'] and ['kölsch'] both refer to 'Kölsch' and 'ksh'


]]
]]
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not utilities.is_set (volume) and not utilities.is_set (issue) then
return '';
end
if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end


if 'podcast' == cite_class and utilities.is_set (issue) then
local lang_code_remap = { -- used for |language= and |script-title= / |script-chapter=
return wrap_msg ('issue', {sepc, issue}, lower);
['als'] = 'Tosk Albanian', -- MediaWiki returns Alemannisch
end
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
 
['bla'] = 'Blackfoot', -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
local vol = ''; -- here for all cites except magazine
['bn'] = 'Bengali', -- MediaWiki returns Bangla
['ca-valencia'] = 'Valencian', -- IETF variant of Catalan
if utilities.is_set (volume) then
['crh'] = 'Crimean Tatar', -- synonymous with Crimean Turkish (return value from {{#language:crh|en}})
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals
['ilo'] = 'Ilocano', -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face
['ksh'] = 'Kölsch', -- MediaWiki: Colognian; use IANA/ISO 639 preferred name
elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters
['ksh-x-colog'] = 'Colognian', -- override MediaWiki ksh; no IANA/ISO 639 code for Colognian; IETF private code created at Module:Lang/data
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold
['mis-x-ripuar'] = 'Ripuarian', -- override MediaWiki ksh; no IANA/ISO 639 code for Ripuarian; IETF private code created at Module:Lang/data
utilities.add_prop_cat ('long_vol');
['nan-tw'] = 'Taiwanese Hokkien', -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese and support en.wiki preferred name
else -- four or less characters
}
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold
end
end
if utilities.is_set (issue) then
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
end
return vol;
end


local lang_name_remap = { -- used for |language=
['alemannisch'] = {'Swiss German', 'gsw'}, -- not an ISO or IANA language name; MediaWiki uses 'als' as a subdomain name for Alemannic Wikipedia: als.wikipedia.org
['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap
['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code
['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri Wikipedia: bh.wikipedia.org
['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replaces 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found
['blackfoot'] = {'Blackfoot', 'bla'}, -- MediaWiki/IANA/ISO 639: Siksika; use en.wiki preferred name
['colognian'] = {'Colognian', 'ksh-x-colog'}, -- MediaWiki preferred name for ksh
['crimean tatar'] = {'Crimean Tatar', 'crh'}, -- MediaWiki uses 'crh' as a subdomain name for Crimean Tatar Wikipedia: crh.wikipedia.org
['ilocano'] = {'Ilocano', 'ilo'}, -- MediaWiki/IANA/ISO 639: Iloko; use en.wiki preferred name
['kolsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name (use non-diacritical o instead of umlaut ö)
['kölsch'] = {'Kölsch', 'ksh'}, -- use IANA/ISO 639 preferred name
['ripuarian'] = {'Ripuarian', 'mis-x-ripuar'}, -- group of dialects; no code in MediaWiki or in IANA/ISO 639
['taiwanese hokkien'] = {'Taiwanese Hokkien', 'nan-TW'}, -- make room for MediaWiki/IANA/ISO 639 nan: Min Nan Chinese
['tosk albanian'] = {'Tosk Albanian', 'als'}, -- MediaWiki replaces 'Tosk Albanian' with 'Alemannisch' so 'Tosk Albanian' cannot be found
['valencian'] = {'Valencian', 'ca'}, -- variant of Catalan; categorizes as Catalan
}


--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------


adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
--[[---------------< P R O P E R T I E S _ C A T E G O R I E S >----------------
The return order is:
page, pages, sheet, sheets


Singular has priority over plural when both are provided.
Properties categories. These are used for investigating qualities of citations.


]]
]]


local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
local prop_cats = {
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
['foreign_lang_source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is foreign-language name, $2 is ISO639-1 code
if utilities.is_set (sheet) then
['foreign_lang_source_2'] = 'CS1 foreign language sources (ISO 639-2)|$1', -- |language= category; a cat for ISO639-2 languages; $1 is the ISO 639-2 code used as a sort key
if 'journal' == origin then
['local_lang_source'] = 'CS1 $1-language sources ($2)', -- |language= categories; $1 is local-language name, $2 is ISO639-1 code; not emitted when local_lang_cat_enable is false
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
['location test'] = 'CS1 location test',
else
['script'] = 'CS1 uses foreign language script', -- when language specified by |script-title=xx: doesn't have its own category
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
['script_with_name'] = 'CS1 uses $1-language script ($2)', -- |script-title=xx: has matching category; $1 is language name, $2 is ISO639-1 code
end
['jul_greg_uncertainty'] = 'CS1: Julian–Gregorian uncertainty', -- probably temporary cat to identify scope of template with dates 1 October 1582 – 1 January 1926
elseif utilities.is_set (sheets) then
['long_vol'] = 'CS1: long volume value', -- probably temporary cat to identify scope of |volume= values longer than 4 charachters
if 'journal' == origin then
['year_range_abbreviated'] = 'CS1: abbreviated year range', -- probably temporary cat to identify scope of |date=, |year= values using YYYY–YY form
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
}
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
 
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
if utilities.is_set (page) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif utilities.is_set (pages) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
return '', '', '', ''; -- return empty strings
end




--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
--[[-------------------< T I T L E _ T Y P E S >--------------------------------


returns one of the in-source locators: page, pages, or at.
Here we map a template's CitationClass to TitleType (default values for |type= parameter)
 
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link 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 title_types = {
local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
['AV-media-notes'] = 'Media notes',
['interview'] = 'Interview',
['mailinglist'] = 'Mailing list',
['map'] = 'Map',
['podcast'] = 'Podcast',
['pressrelease'] = 'Press release',
['report'] = 'Report',
['techreport'] = 'Technical report',
['thesis'] = 'Thesis',
}


if utilities.is_set (page) then
if utilities.is_set (pages) or utilities.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 tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
coins_pages = ws_label;
end
elseif utilities.is_set (pages) then
if utilities.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 tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
coins_pages = ws_label;
end
elseif utilities.is_set (at) then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
end
return page, pages, at, coins_pages;
end
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
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 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=
There are two mostly compatible archive.org URLs:
//web.archive.org/<timestamp>... -- the old form
//web.archive.org/web/<timestamp>... -- the new form
The old form does not support or map to the new form when it contains a display flag.  There are four identified flags
('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 function 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*/)
]=]
local function archive_url_check (url, date)
local err_msg = ''; -- start with the error message empty
local path, timestamp, flag; -- portions of the archive.org 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 ArchiveURL 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 = cfg.err_msg_supl.save;
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
elseif url:match('//liveweb%.archive%.org/') then
err_msg = cfg.err_msg_supl.liveweb;
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation
if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = cfg.err_msg_supl.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 utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element
err_msg = cfg.err_msg_supl.path;
elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element)
err_msg = cfg.err_msg_supl.flag;
elseif utilities.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 = cfg.err_msg_supl.flag;
else
return url, date; -- return ArchiveURL and ArchiveDate
end
end
-- if here, something not right so
table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } ); -- add error message and
if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
else
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
end
end
--[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------
check |place=, |publication-place=, |location= to see if these params include digits.  This function added because
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
returns the original parameter value without modification; added maint cat when parameter value contains digits


--[[===================<< E R R O R  M E S S A G I N G >>======================
]]
]]


local function place_check (param_val)
--[[----------< E R R O R  M E S S A G E  S U P P L I M E N T S >-------------
if not utilities.is_set (param_val) then -- parameter empty or omitted
return param_val; -- return that empty state
end
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
utilities.set_message ('maint_location'); -- yep, add maint cat
end
return param_val; -- and done
end


I18N for those messages that are supplemented with additional specific text that
describes the reason for the error


--[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------
TODO: merge this with special_case_translations{}?
 
compares |title= value against list of known generic title patterns.  Returns true when pattern matches; nil else
 
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
index [1].  index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
or a pattern search (false).  The intent of all this complexity is to make these searches as fast as possible so
that we don't run out of processing time on very large articles.
 
]]
]]


local function is_generic_title (title)
local err_msg_supl = {
title = mw.ustring.lower(title); -- switch title to lower case
['char'] = 'invalid character', -- |isbn=, |sbn=
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do --spin through the list of known generic title fragments
['check'] = 'checksum', -- |isbn=, |sbn=
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
['flag'] = 'flag', -- |archive-url=
return true; -- found English generic title so done
['form'] = 'invalid form', -- |isbn=, |sbn=
elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title
['group'] = 'invalid group id', -- |isbn=
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script
['initials'] = 'initials', -- Vancouver
return true; -- found local generic title so done
['journal'] = 'journal', -- |bibcode=
end
['length'] = 'length', -- |isbn=, |bibcode=, |sbn=
end
['liveweb'] = 'liveweb', -- |archive-url=
end
['missing comma'] = 'missing comma', -- Vancouver
end
['name'] = 'name', -- Vancouver
 
['non-Latin char'] = 'non-Latin character', -- Vancouver
['path'] = 'path', -- |archive-url=
['prefix'] = 'invalid prefix', -- |isbn=
['punctuation'] = 'punctuation', -- Vancouver
['save'] = 'save command', -- |archive-url=
['suffix'] = 'suffix', -- Vancouver
['timestamp'] = 'timestamp', -- |archive-url=
['value'] = 'value', -- |bibcode=
['year'] = 'year', -- |bibcode=
}


--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------


compares |title= to 'Archived copy' (place holder added by bots that can't find proper title); if matches, return true; nil else
--[[--------------< E R R O R _ C O N D I T I O N S >---------------------------


]]
Error condition table.  This table has two sections: errors at the top, maintenance
at the bottom.  Maint 'messaging' does not have a 'message' (message=nil)


local function is_archived_copy (title)
The following contains a list of IDs for various error conditions defined in the
title = mw.ustring.lower(title); -- switch title to lower case
code. For each ID, we specify a text message to display, an error category to
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
include, and whether the error message should be wrapped as a hidden comment.
return true;
elseif cfg.special_case_translation.archived_copy['local'] then
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
return true;
end
end
end


Anchor changes require identical changes to matching anchor in Help:CS1 errors


--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
TODO: rename error_conditions{} to something more generic; create separate error
 
and maint tables inside that?
This is the main function doing the majority of the citation formatting.


]]
]]


local function citation0( config, args)
local error_conditions = {
--[[
err_accessdate_missing_url = {
Load Input Parameters
message = '<code class="cs1-code">&#124;access-date=</code> requires <code class="cs1-code">&#124;url=</code>',
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
anchor = 'accessdate_missing_url',
]]
category = 'CS1 errors: access-date without URL',
local A = argument_wrapper ( args );
hidden = false
local i
},
 
err_apostrophe_markup = {
-- Pick out the relevant fields from the arguments.  Different citation templates
message = 'Italic or bold markup not allowed in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
-- define different field names for the same underlying things.
anchor = 'apostrophe_markup',
 
category = 'CS1 errors: markup',
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
hidden = false
 
},
local author_etal;
err_archive_missing_date = {
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;archive-date=</code>',
local Authors;
anchor = 'archive_missing_date',
 
category = 'CS1 errors: archive-url',
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
hidden = false
local Collaboration = A['Collaboration'];
},
 
err_archive_missing_url = {
do -- to limit scope of selected
message = '<code class="cs1-code">&#124;archive-url=</code> requires <code class="cs1-code">&#124;url=</code>',
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
anchor = 'archive_missing_url',
if 1 == selected then
category = 'CS1 errors: archive-url',
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
hidden = false
elseif 2 == selected then
},
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
err_archive_url = {
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
message = '<code class="cs1-code">&#124;archive-url=</code> is malformed: $1', -- $1 is error message detail
elseif 3 == selected then
anchor = 'archive_url',
Authors = A['Authors']; -- use content of |authors=
category = 'CS1 errors: archive-url',
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
hidden = false
utilities.set_message ('maint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
},
end
err_arxiv_missing = {
end
message = '<code class="cs1-code">&#124;arxiv=</code> required',
if utilities.is_set (Collaboration) then
anchor = 'arxiv_missing',
author_etal = true; -- so that |display-authors=etal not required
category = 'CS1 errors: arXiv', -- same as bad arxiv
end
hidden = false
end
},
 
err_asintld_missing_asin = {
local Others = A['Others'];
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;asin=</code>', -- $1 is parameter name
 
anchor = 'asintld_missing_asin',
local editor_etal;
category = 'CS1 errors: ASIN TLD',
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
hidden = false
local Editors;
},
 
err_bad_arxiv = {
do -- to limit scope of selected
message = 'Check <code class="cs1-code">&#124;arxiv=</code> value',
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
anchor = 'bad_arxiv',
if 1 == selected then
category = 'CS1 errors: arXiv',
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
hidden = false
elseif 2 == selected then
},
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
err_bad_asin = {
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
message = 'Check <code class="cs1-code">&#124;asin=</code> value',
elseif 3 == selected then
anchor = 'bad_asin',
Editors = A['Editors']; -- use content of |editors=
category ='CS1 errors: ASIN',
end
hidden = false
end
},
 
err_bad_asin_tld = {
local translator_etal;
message = 'Check <code class="cs1-code">&#124;asin-tld=</code> value',
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
anchor = 'bad_asin_tld',
local Translators; -- assembled translators name list
category ='CS1 errors: ASIN TLD',
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
hidden = false
 
},
local interviewer_etal;
err_bad_bibcode = {
local interviewers_list = {};
message = 'Check <code class="cs1-code">&#124;bibcode=</code> $1', -- $1 is error message detail
local Interviewers; -- used later
anchor = 'bad_bibcode',
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
category = 'CS1 errors: bibcode',
 
hidden = false
local contributor_etal;
},
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
err_bad_biorxiv = {
local Contributors; -- assembled contributors name list
message = 'Check <code class="cs1-code">&#124;biorxiv=</code> value',
 
anchor = 'bad_biorxiv',
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
category = 'CS1 errors: bioRxiv',
local Chapter_origin = A:ORIGIN ('Chapter');
hidden = false
local Contribution; -- because contribution is required for contributor(s)
},
if 'contribution' == A:ORIGIN ('Chapter') then
err_bad_citeseerx = {
Contribution = A['Chapter']; -- get the name of the contribution
message = 'Check <code class="cs1-code">&#124;citeseerx=</code> value',
end
anchor = 'bad_citeseerx',
 
category = 'CS1 errors: citeseerx',
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
hidden = false
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
},
err_bad_date = {
if 0 < #c then
message = 'Check date values in: $1', -- $1 is a parameter name list
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
anchor = 'bad_date',
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
category = 'CS1 errors: dates',
c = {}; -- blank the contributors' table; it is used as a flag later
hidden = false
end
},
if 0 == #a then -- |contributor= requires |author=
err_bad_doi = {
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'author')}); -- add missing author error message
message = 'Check <code class="cs1-code">&#124;doi=</code> value',
c = {}; -- blank the contributors' table; it is used as a flag later
anchor = 'bad_doi',
end
category = 'CS1 errors: DOI',
end
hidden = false
else -- if not a book cite
},
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters?
err_bad_hdl = {
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_ignored')}); -- add contributor ignored error message
message = 'Check <code class="cs1-code">&#124;hdl=</code> value',
end
anchor = 'bad_hdl',
Contribution = nil; -- unset
category = 'CS1 errors: HDL',
end
hidden = false
 
},
if utilities.is_set (Others) then
err_bad_isbn = {
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
message = 'Check <code class="cs1-code">&#124;isbn=</code> value: $1', -- $1 is error message detail
utilities.set_message ('maint_others');
anchor = 'bad_isbn',
end
category = 'CS1 errors: ISBN',
end
hidden = false
 
},
local Year = A['Year'];
err_bad_ismn = {
local PublicationDate = A['PublicationDate'];
message = 'Check <code class="cs1-code">&#124;ismn=</code> value',
local OrigDate = A['OrigDate'];
anchor = 'bad_ismn',
local Date = A['Date'];
category = 'CS1 errors: ISMN',
local LayDate = A['LayDate'];
hidden = false
------------------------------------------------- Get title data
},
local Title = A['Title'];
err_bad_issn = {
local ScriptTitle = A['ScriptTitle'];
message = 'Check <code class="cs1-code">&#124;$1issn=</code> value', -- $1 is 'e' or '' for eissn or issn
local BookTitle = A['BookTitle'];
anchor = 'bad_issn',
local Conference = A['Conference'];
category = 'CS1 errors: ISSN',
local TransTitle = A['TransTitle'];
hidden = false
local TransTitle_origin = A:ORIGIN ('TransTitle');
},
local TitleNote = A['TitleNote'];
err_bad_jfm = {
local TitleLink = A['TitleLink'];
message = 'Check <code class="cs1-code">&#124;jfm=</code> value',
 
anchor = 'bad_jfm',
local auto_select = ''; -- default is auto
category = 'CS1 errors: JFM',
local accept_link;
hidden = false
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup
},
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
err_bad_jstor = {
auto_select = TitleLink; -- remember selection for later
message = 'Check <code class="cs1-code">&#124;jstor=</code> value',
TitleLink = ''; -- treat as if |title-link= would have been empty
anchor = 'bad_jstor',
end
category = 'CS1 errors: JSTOR',
 
hidden = false
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
},
 
err_bad_lccn = {
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
message = 'Check <code class="cs1-code">&#124;lccn=</code> value',
if 'map' == config.CitationClass and 'section' == A:ORIGIN ('Chapter') then
anchor = 'bad_lccn',
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
category = 'CS1 errors: LCCN',
Chapter = ''; -- unset for now; will be reset later from |map= if present
hidden = false
end
},
 
err_bad_mr = {
local ScriptChapter = A['ScriptChapter'];
message = 'Check <code class="cs1-code">&#124;mr=</code> value',
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
anchor = 'bad_mr',
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
category = 'CS1 errors: MR',
local TransChapter = A['TransChapter'];
hidden = false
local TransChapter_origin = A:ORIGIN ('TransChapter');
},
local TitleType = A['TitleType'];
err_bad_oclc = {
local Degree = A['Degree'];
message = 'Check <code class="cs1-code">&#124;oclc=</code> value',
local Docket = A['Docket'];
anchor = 'bad_oclc',
local ArchiveFormat = A['ArchiveFormat'];
category = 'CS1 errors: OCLC',
 
hidden = false
local ArchiveDate;
},
local ArchiveURL;
err_bad_ol = {
 
message = 'Check <code class="cs1-code">&#124;ol=</code> value',
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
anchor = 'bad_ol',
category = 'CS1 errors: OL',
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
hidden = false
 
},
local URL = A['URL']
err_bad_osti = {
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
message = 'Check <code class="cs1-code">&#124;osti=</code> value',
local ChapterURL = A['ChapterURL'];
anchor = 'bad_osti',
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
category = 'CS1 errors: OSTI',
local ConferenceFormat = A['ConferenceFormat'];
hidden = false
local ConferenceURL = A['ConferenceURL'];
},
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
err_bad_paramlink = { -- for |title-link=, |author/editor/translator-link=, |series-link=, |episode-link=
 
message = 'Check <code class="cs1-code">&#124;$1=</code> value', -- $1 is parameter name
local Periodical = A['Periodical'];
anchor = 'bad_paramlink',
local Periodical_origin = '';
category = 'CS1 errors: parameter link',
if utilities.is_set (Periodical) then
hidden = false
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
},
local i;
err_bad_pmc = {
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated
message = 'Check <code class="cs1-code">&#124;pmc=</code> value',
if i then -- non-zero when markup was stripped so emit an error message
anchor = 'bad_pmc',
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {Periodical_origin}, true)});
category = 'CS1 errors: PMC',
end
hidden = false
end
},
 
err_bad_pmid = {
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
message = 'Check <code class="cs1-code">&#124;pmid=</code> value',
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error
anchor = 'bad_pmid',
table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
category = 'CS1 errors: PMID',
end
hidden = false
 
},
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
err_bad_rfc = {
Periodical_origin = A:ORIGIN('MailingList');
message = 'Check <code class="cs1-code">&#124;rfc=</code> value',
end
anchor = 'bad_rfc',
 
category = 'CS1 errors: RFC',
local ScriptPeriodical = A['ScriptPeriodical'];
hidden = false
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
},
 
err_bad_s2cid = {
-- web and news not tested for now because of
message = 'Check <code class="cs1-code">&#124;s2cid=</code> value',
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
anchor = 'bad_s2cid',
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
category = 'CS1 errors: S2CID',
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
hidden = false
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
},
if p[config.CitationClass]  then
err_bad_sbn = {
table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
message = 'Check <code class="cs1-code">&#124;sbn=</code> value: $1', -- $1 is error message detail
end
anchor = 'bad_sbn',
end
category = 'CS1 errors: SBN',
 
hidden = false
local TransPeriodical = A['TransPeriodical'];
},
local TransPeriodical_origin = A:ORIGIN ('TransPeriodical');
err_bad_ssrn = {
 
message = 'Check <code class="cs1-code">&#124;ssrn=</code> value',
local Series = A['Series'];
anchor = 'bad_ssrn',
category = 'CS1 errors: SSRN',
local Volume;
hidden = false
local Issue;
},
local Page;
err_bad_url = {
local Pages;
message = 'Check $1 value', -- $1 is parameter name
local At;
anchor = 'bad_url',
 
category = 'CS1 errors: URL',
if 'citation' == config.CitationClass then
hidden = false
if utilities.is_set (Periodical) then
},
if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
err_bad_usenet_id = {
Volume = A['Volume']; -- but does for all other 'periodicals'
message = 'Check <code class="cs1-code">&#124;message-id=</code> value',
end
anchor = 'bad_message_id',
elseif utilities.is_set (ScriptPeriodical) then
category = 'CS1 errors: message-id',
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
hidden = false
Volume = A['Volume']; -- but does for all other 'periodicals'
},
end
err_bad_zbl = {
else
message = 'Check <code class="cs1-code">&#124;zbl=</code> value',
Volume = A['Volume']; -- and does for non-'periodical' cites
anchor = 'bad_zbl',
end
category = 'CS1 errors: Zbl',
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
hidden = false
Volume = A['Volume'];
},
end
err_bare_url_missing_title = {
 
message = '$1 missing title', -- $1 is parameter name
if 'citation' == config.CitationClass then
anchor = 'bare_url_missing_title',
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
category = 'CS1 errors: bare URL',
utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
hidden = false
Issue = hyphen_to_dash (A['Issue']);
},
end
err_biorxiv_missing = {
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
message = '<code class="cs1-code">&#124;biorxiv=</code> required',
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
anchor = 'biorxiv_missing',
Issue = hyphen_to_dash (A['Issue']);
category = 'CS1 errors: bioRxiv', -- same as bad bioRxiv
end
hidden = false
end
},
 
err_chapter_ignored = {
local Position = '';
message = '<code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then
anchor = 'chapter_ignored',
Page = A['Page'];
category = 'CS1 errors: chapter ignored',
Pages = hyphen_to_dash (A['Pages']);
hidden = false
At = A['At'];
},
end
err_citation_missing_title = {
 
message = 'Missing or empty <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
local Edition = A['Edition'];
anchor = 'citation_missing_title',
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
category = 'CS1 errors: missing title',
local Place = place_check (A['Place'], A:ORIGIN('Place'));
hidden = false
},
local PublisherName = A['PublisherName'];
err_citeseerx_missing = {
local PublisherName_origin = A:ORIGIN('PublisherName');
message = '<code class="cs1-code">&#124;citeseerx=</code> required',
if utilities.is_set (PublisherName) then
anchor = 'citeseerx_missing',
local i = 0;
category = 'CS1 errors: citeseerx', -- same as bad citeseerx
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
hidden = false
if i then -- non-zero when markup was stripped so emit an error message
},
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
err_cite_web_url = { -- this error applies to cite web and to cite podcast
end
message = 'Missing or empty <code class="cs1-code">&#124;url=</code>',
end
anchor = 'cite_web_url',
 
category = 'CS1 errors: requires URL',
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
hidden = false
local Newsgroup_origin = A:ORIGIN('Newsgroup');
},
 
err_class_ignored = {
if 'newsgroup' == config.CitationClass then
message = '<code class="cs1-code">&#124;class=</code> ignored',
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
anchor = 'class_ignored',
local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
category = 'CS1 errors: class',
if utilities.is_set (error_text) then
hidden = false
table.insert( z.message_tail, {error_text, error_state} );
},
end
err_contributor_ignored = {
end
message = '<code class="cs1-code">&#124;contributor=</code> ignored',
 
anchor = 'contributor_ignored',
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
category = 'CS1 errors: contributor',
end
hidden = false
 
},
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
err_contributor_missing_required_param = {
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
message = '<code class="cs1-code">&#124;contributor=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
UrlAccess = nil;
anchor = 'contributor_missing_required_param',
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
category = 'CS1 errors: contributor',
end
hidden = false
},
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
err_deprecated_params = {
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
message = 'Cite uses deprecated parameter <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
ChapterUrlAccess = nil;
anchor = 'deprecated_params',
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
category = 'CS1 errors: deprecated parameters',
end
hidden = false
 
},
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
err_disp_name = {
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name; $2 is the assigned value
MapUrlAccess = nil;
anchor = 'disp_name',
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'map-url'}, true ) } );
category = 'CS1 errors: display-names',
end
hidden = false,
 
},
local Via = A['Via'];
err_doibroken_missing_doi = {
local AccessDate = A['AccessDate'];
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;doi=</code>', -- $1 is parameter name
local Agency = A['Agency'];
anchor = 'doibroken_missing_doi',
 
category = 'CS1 errors: DOI',
local Language = A['Language'];
hidden = false
local Format = A['Format'];
},
local ChapterFormat = A['ChapterFormat'];
err_embargo_missing_pmc = {
local DoiBroken = A['DoiBroken'];
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;pmc=</code>', -- $1 is parameter name
local ID = A['ID'];
anchor = 'embargo_missing_pmc',
local ASINTLD = A['ASINTLD'];
category = 'CS1 errors: PMC embargo',
local IgnoreISBN = is_valid_parameter_value (A['IgnoreISBN'], A:ORIGIN('IgnoreISBN'), cfg.keywords_lists['yes_true_y'], nil);
hidden = false
local Embargo = A['Embargo'];
},
local Class = A['Class']; -- arxiv class identifier
err_empty_citation = {
 
message = 'Empty citation',
local Quote = A['Quote'];
anchor = 'empty_citation',
local QuotePage = A['QuotePage'];
category = 'CS1 errors: empty citation',
local QuotePages = A['QuotePages'];
hidden = false
local ScriptQuote = A['ScriptQuote'];
},
local TransQuote = A['TransQuote'];
err_etal = {
 
message = 'Explicit use of et al. in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
local LayFormat = A['LayFormat'];
anchor = 'explicit_et_al',
local LayURL = A['LayURL'];
category = 'CS1 errors: explicit use of et al.',
local LaySource = A['LaySource'];
hidden = false
local Transcript = A['Transcript'];
},
local TranscriptFormat = A['TranscriptFormat'];
err_extra_text_edition = {
local TranscriptURL = A['TranscriptURL']
message = '<code class="cs1-code">&#124;edition=</code> has extra text',
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
anchor = 'extra_text_edition',
 
category = 'CS1 errors: extra text: edition',
local LastAuthorAmp = is_valid_parameter_value (A['LastAuthorAmp'], A:ORIGIN('LastAuthorAmp'), cfg.keywords_lists['yes_true_y'], nil);
hidden = false,
 
},
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
err_extra_text_issue = {
if 'nocat' == A:ORIGIN('NoTracking') then
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
utilities.set_message ('maint_nocat'); -- this one so that we get the message; see main categorization at end of citation0()
anchor = 'extra_text_issue',
end
category = 'CS1 errors: extra text: issue',
hidden = false,
--local variables that are not cs1 parameters
},
local use_lowercase; -- controls capitalization of certain static text
err_extra_text_pages = {
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
local anchor_year; -- used in the CITEREF identifier
anchor = 'extra_text_pages',
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
category = 'CS1 errors: extra text: pages',
 
hidden = false,
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
},
if not utilities.is_set (DF) then
err_extra_text_volume = {
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
message = '<code class="cs1-code">&#124;$1=</code> has extra text', -- $1 is parameter name
end
anchor = 'extra_text_volume',
 
category = 'CS1 errors: extra text: volume',
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
hidden = true,
local PostScript;
},
local Ref = A['Ref'];
err_first_missing_last = {
if 'harv' == Ref then
message = '<code class="cs1-code">&#124;$1=</code> missing <code class="cs1-code">&#124;$2=</code>', -- $1 is first alias, $2 is matching last alias
utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value
anchor = 'first_missing_last',
elseif not utilities.is_set (Ref) then
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
Ref = 'harv'; -- set as default when not set externally
hidden = false
end
},
err_format_missing_url = {
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], Ref, config.CitationClass);
message = '<code class="cs1-code">&#124;$1=</code> requires <code class="cs1-code">&#124;$2=</code>', -- $1 is format parameter $2 is url parameter
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
anchor = 'format_missing_url',
 
category = 'CS1 errors: format without URL',
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
hidden = false
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
},
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
err_generic_title = {
no_tracking_cats = "true"; -- set no_tracking_cats
message = 'Cite uses generic title',
end
anchor = 'generic_title',
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
category = 'CS1 errors: generic title',
if this_page.text:match (v) then -- test page name against each pattern
hidden = false,
no_tracking_cats = "true"; -- set no_tracking_cats
},
break; -- bail out if one is found
err_invalid_param_val = {
end
message = 'Invalid <code class="cs1-code">&#124;$1=$2</code>', -- $1 is parameter name $2 is parameter value
end
anchor = 'invalid_param_val',
end
category = 'CS1 errors: invalid parameter value',
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
hidden = false
utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category
},
 
err_invisible_char = {
local coins_pages;
message = '$1 in $2 at position $3', -- $1 is invisible char $2 is parameter name $3 is position number
anchor = 'invisible_char',
Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);
category = 'CS1 errors: invisible characters',
 
hidden = false
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
},
 
err_missing_name = {
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
message = 'Missing <code class="cs1-code">&#124;$1$2=</code>', -- $1 is modified NameList; $2 is enumerator
utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
anchor = 'missing_name',
if PublicationPlace == Place then
category = 'CS1 errors: missing name', -- author, contributor, editor, interviewer, translator
Place = ''; -- unset; don't need both if they are the same
hidden = false
end
},
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
err_missing_periodical = {
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
message = 'Cite $1 requires <code class="cs1-code">&#124;$2=</code>', -- $1 is cs1 template name; $2 is canonical periodical parameter name for cite $1
end
anchor = 'missing_periodical',
 
category = 'CS1 errors: missing periodical',
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
hidden = true
},
--[[
err_missing_pipe = {
Parameter remapping for cite encyclopedia:
message = 'Missing pipe in: <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
When the citation has these parameters:
anchor = 'missing_pipe',
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title=
category = 'CS1 errors: missing pipe',
|encyclopedia= and |article= then map |encyclopedia= to |title=
hidden = false
 
},
|trans-title= maps to |trans-chapter= when |title= is re-mapped
err_param_access_requires_param = {
|url= maps to |chapter-url= when |title= is remapped
message = '<code class="cs1-code">&#124;$1-access=</code> requires <code class="cs1-code">&#124;$1=</code>', -- $1 is parameter name
anchor = 'param_access_requires_param',
All other combinations of |encyclopedia=, |title=, and |article= are not modified
category = 'CS1 errors: param-access',
hidden = false
]]
},
 
err_param_has_ext_link = {
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
message = 'External link in <code class="cs1-code">$1</code>', -- $1 is parameter name
 
anchor = 'param_has_ext_link',
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
category = 'CS1 errors: external links',
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
hidden = false
table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
},
Encyclopedia = nil; -- unset because not supported by this template
err_parameter_ignored = {
end
message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored', -- $1 is parameter name
end
anchor = 'parameter_ignored',
 
category = 'CS1 errors: unsupported parameter',
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
hidden = false
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error
},
table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
err_parameter_ignored_suggest = {
end
message = 'Unknown parameter <code class="cs1-code">&#124;$1=</code> ignored (<code class="cs1-code">&#124;$2=</code> suggested)', -- $1 is unknown parameter $2 is suggested parameter name
 
anchor = 'parameter_ignored_suggest',
if utilities.is_set (Encyclopedia) then
category = 'CS1 errors: unsupported parameter',
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
hidden = false
Periodical_origin = A:ORIGIN ('Encyclopedia');
},
end
err_redundant_parameters = {
 
message = 'More than one of $1 specified', -- $1 is error message detail
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
anchor = 'redundant_parameters',
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
category = 'CS1 errors: redundant parameter',
if not utilities.is_set (Chapter) then
hidden = false
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
},
ScriptChapter = ScriptTitle;
err_script_parameter = {
ScriptChapter_origin = A:ORIGIN('ScriptTitle')
message = 'Invalid <code class="cs1-code">&#124;$1=</code>: $2', -- $1 is parameter name $2 is script language code or error detail
TransChapter = TransTitle;
anchor = 'script_parameter',
ChapterURL = URL;
category = 'CS1 errors: script parameters',
ChapterURL_origin = A:ORIGIN('URL')
hidden = false
 
},
ChapterUrlAccess = UrlAccess;
err_ssrn_missing = {
 
message = '<code class="cs1-code">&#124;ssrn=</code> required',
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
anchor = 'ssrn_missing',
Chapter = utilities.make_wikilink (TitleLink, Chapter);
category = 'CS1 errors: SSRN', -- same as bad arxiv
end
hidden = false
Title = Periodical;
},
ChapterFormat = Format;
err_text_ignored = {
Periodical = ''; -- redundant so unset
message = 'Text "$1" ignored', -- $1 is ignored text
TransTitle = '';
anchor = 'text_ignored',
URL = '';
category = 'CS1 errors: unrecognized parameter',
Format = '';
hidden = false
TitleLink = '';
},
ScriptTitle = '';
err_trans_missing_title = {
end
message = '<code class="cs1-code">&#124;trans-$1=</code> requires <code class="cs1-code">&#124;$1=</code> or <code class="cs1-code">&#124;script-$1=</code>', -- $1 is base parameter name
elseif utilities.is_set (Chapter) then -- |title= not set
anchor = 'trans_missing_title',
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
category = 'CS1 errors: translated title',
Periodical = ''; -- redundant so unset
hidden = false
end
},
end
err_param_unknown_empty = {
end
message = 'Cite has empty unknown parameter$1: $2', -- $1 is 's' or empty space; $2 is emty unknown param list
 
anchor = 'param_unknown_empty',
-- special case for cite techreport.
category = 'CS1 errors: empty unknown parameters',
if (config.CitationClass == "techreport") then -- special case for cite techreport
hidden = false
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
},
if not utilities.is_set (ID) then -- can we use ID for the "number"?
err_vancouver = {
ID = A['Number']; -- yes, use it
message = 'Vancouver style error: $1 in name $2', -- $1 is error detail, $2 is the nth name
else -- ID has a value so emit error message
anchor = 'vancouver',
table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
category = 'CS1 errors: Vancouver style',
end
hidden = false
end
},
end
err_wikilink_in_url = {
 
message = 'URL–wikilink conflict', -- uses ndash
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
anchor = 'wikilink_in_url',
if 'conference' == config.CitationClass then
category = 'CS1 errors: URL–wikilink conflict', -- uses ndash
if utilities.is_set (BookTitle) then
hidden = false
Chapter = Title;
},
Chapter_origin = 'title';
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURL_origin = URL_origin;
URL_origin = '';
ChapterFormat = Format;
TransChapter = TransTitle;
TransChapter_origin = TransTitle_origin;
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
 
-- cite map oddities
local Cartography = "";
local Scale = "";
local Sheet = A['Sheet'] or '';
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
if utilities.is_set (Chapter) then
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
end
Chapter = A['Map'];
Chapter_origin = A:ORIGIN('Map');
ChapterURL = A['MapURL'];
ChapterURL_origin = A:ORIGIN('MapURL');
TransChapter = A['TransMap'];
ScriptChapter = A['ScriptMap']
ScriptChapter_origin = A:ORIGIN('ScriptMap')
 
ChapterUrlAccess = MapUrlAccess;
ChapterFormat = A['MapFormat'];
 
Cartography = A['Cartography'];
if utilities.is_set ( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
Scale = A['Scale'];
if utilities.is_set ( Scale ) then
Scale = sepc .. " " .. Scale;
end
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 SeriesLink = A['SeriesLink'];
 
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set
 
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if utilities.is_set (Network) then table.insert(n, Network); end
if utilities.is_set (Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
 
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
ChapterLink = TitleLink; -- alias |episode-link=
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURL_origin = A:ORIGIN('URL');
Title = Series; -- promote series to title
TitleLink = SeriesLink;
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
Series = utilities.make_wikilink (ChapterLink, Series);
end
URL = ''; -- unset
TransTitle = '';
ScriptTitle = '';
else -- now oddities that are cite serial
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
Series = utilities.make_wikilink (SeriesLink, Series);
end
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
end
end
-- end of {{cite episode}} stuff
 
-- handle type parameter for those CS1 citations that have default values
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
end
end
 
if utilities.is_set (TitleType) then -- if type parameter is specified
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
-- TODO: Hack on TitleType to fix bunched parentheses problem
end
 
-- legacy: 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 utilities.is_set (Date) then
Date = Year; -- promote Year to Date
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
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'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
['date'] = {val = Date, name = Date_origin},
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
['pmc-embargo-date'] = {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')},
};
 
local error_list = {};
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
 
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
utilities.add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
 
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
local mismatch = validation.year_date_check (Year, Date);
if 0 == mismatch then -- |year= does not match a year-value in |date=
table.insert (error_list, '<code class="cs1-code">&#124;year= / &#124;date= mismatch</code>');
elseif 1 == mismatch then -- |year= matches year-value in |date=
utilities.set_message ('maint_date_year'); -- add a maint cat
end
end
if 0 == #error_list then -- error free dates only; 0 when error_list is empty
local modified = false; -- flag
if utilities.is_set (DF) then -- if we need to reformat dates
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate
end
 
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
modified = true;
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
end
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment the next three lines.  Not supported by en.wiki (for obvious reasons)
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
-- if validation.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, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)}); -- add this error message
end
end -- end of do
 
local ID_list_coins = identifiers.extract_ids (args); -- gets identifiers and their values from args; this list used for COinS and source for build_id_list()
if utilities.is_set (DoiBroken) and not ID_list_coins['DOI'] then
table.insert (z.message_tail, {utilities.set_message ('err_doibroken_missing_doi', A:ORIGIN('DoiBroken'))});
end
local ID_access_levels = identifiers.extract_id_access_levels (args, ID_list_coins);
local ID_list = identifiers.build_id_list (ID_list_coins, {IdAccessLevels = ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo = Embargo, Class = Class}); -- render identifiers
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- add error message
end
 
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
end
 
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
 
if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead
    if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
if identifiers.auto_link_urls[auto_select] then -- manual selection
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
URL = identifiers.auto_link_urls['doi'];
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
end
 
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url=
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message
AccessDate = ''; -- unset
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 utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
end
 
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Title = ''; -- set title to empty string
utilities.set_message ('maint_untitled'); -- add maint cat
end
 
check_for_url ({ -- add error message when any of these parameters hold a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[Periodical_origin] = Periodical,
[PublisherName_origin] = PublisherName
});
 
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
-- is the article title, and Chapter is a section within the article.  So, we remap
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
end
end
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
end
 
-- this is the function call to COinS()
local OCinSoutput = metadata.COinS({
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wiki-markup
['Degree'] = Degree; -- cite thesis only
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wiki-markup
['PublicationPlace'] = PublicationPlace,
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Season'] = COinS_date.rftssn,
['Quarter'] = COinS_date.rftquarter,
['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['ID_list'] = ID_list_coins,
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in these templates; 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 and utilities.is_set (Newsgroup) then
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
end
 
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
do
local last_first_list;
local control = {
format = NameListStyle, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
mode = Mode
};


do -- do editor name list first because the now unsupported coauthors used to modify control table
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal);
last_first_list, EditorCount = list_people(control, e, editor_etal);
if utilities.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
end
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
else
Editors = last_first_list; -- either an author name list or an empty string
end


if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
--[[--------------------------< M A I N T >-------------------------------------
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, 'translators', translator_etal);
Translators = list_people (control, t, translator_etal);
end
do -- now do contributors
control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal);
Contributors = list_people (control, c, contributor_etal);
end
do -- now do authors
control.maximum , author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal);


last_first_list = list_people(control, a, author_etal);
maint messages do not have a message (message = nil); otherwise the structure
is the same as error messages


if utilities.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
end
else
Authors = last_first_list; -- either an author name list or an empty string
end
end -- end of do
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
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');
Format = style_format (Format, URL, 'format', 'url');
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
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 (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
if not utilities.is_set (URL) then
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
table.insert( z.message_tail, { utilities.set_message ( 'err_cite_web_url', {}, true ) } );
end
-- do we have |accessdate= without either |url= or |chapter-url=?
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
end
local OriginalURL, OriginalURL_origin, OriginalFormat, OriginalAccess;
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
if utilities.is_set ( ArchiveURL ) then
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
OriginalFormat = ChapterFormat; -- and original |chapter-format=
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's URL
ChapterURL_origin = 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 utilities.is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
URL = ArchiveURL -- swap-in the archive's URL
URL_origin = 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 utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
local chap_param;
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
chap_param = A:ORIGIN ('Chapter')
elseif utilities.is_set (TransChapter) then
chap_param = A:ORIGIN ('TransChapter')
elseif utilities.is_set (ChapterURL) then
chap_param = A:ORIGIN ('ChapterURL')
elseif utilities.is_set (ScriptChapter) then
chap_param = ScriptChapter_origin;
else utilities.is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
if utilities.is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
ScriptChapter = '';
ChapterFormat = '';
end
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
if utilities.is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
end
Chapter = Chapter .. sepc .. ' ';
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
-- Format main title
local plain_title = false;
local accept_title;
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
Title = cfg.messages['notitle']; -- replace by predefined "No title" message
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
ScriptTitle = ''; -- just mute for now
TransTitle = ''; -- just mute for now
plain_title = true; -- suppress text decoration for descriptive title
utilities.set_message ('maint_untitled'); -- add maint cat
end
if not accept_title then -- <Title> not wrapped in accept-as-written markup
if '...' == Title:sub (-3) then -- if ellipsis 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
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
end
if is_generic_title (Title) then
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message
end
end
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) 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 = utilities.wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
Title = utilities.wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
end
local TransError = "";
if utilities.is_set (TransTitle) then
if utilities.is_set (Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} );
end
end
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
if utilities.is_set (TitleLink) and utilities.is_set (URL) then
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both
TitleLink = ''; -- unset
end
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format;
URL = ''; -- unset these because no longer needed
Format = "";
elseif utilities.is_set (TitleLink) and not utilities.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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
ws_url, ws_label, L = wikisource_url_make (Title:gsub('[\'"](.-)[\'"]', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip 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 = utilities.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
if utilities.is_set (Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
if utilities.is_set (Conference) then
if utilities.is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif utilities.is_set (ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
end
if not utilities.is_set (Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
if utilities.is_set (Minutes) then
if utilities.is_set (Time) then
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if utilities.is_set (Time) then
local TimeCaption = A['TimeCaption']
if not utilities.is_set (TimeCaption) then
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
TimeCaption = TimeCaption:lower();
end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end
else
Position = " " .. Position;
At = '';
end
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
local Inset = A['Inset'];
if utilities.is_set ( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
if utilities.is_set ( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif utilities.is_set ( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
At = At .. Inset .. Section;
end
if utilities.is_set (Language) then
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
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
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
if utilities.is_set (Translators) then
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
end
if utilities.is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if utilities.is_set (Edition) then
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
utilities.set_message ('maint_extra_text', 'edition'); -- add maint cat
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
------------------------------------ totally unrelated data
Via = utilities.is_set (Via) and  wrap_msg ('via', Via) or '';
if utilities.is_set (AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
  if "thesis" == config.CitationClass and utilities.is_set (Docket) then
ID = sepc .. " Docket " .. Docket .. ID;
end
  if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
if utilities.is_set (URL) then
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
end
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
if utilities.is_set (Quote) then
if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks
Quote = Quote:sub(2, -2); -- strip them off
end
end
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
if utilities.is_set (ScriptQuote) then
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
end
if utilities.is_set (TransQuote) then
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
TransQuote = TransQuote:sub(2, -2); -- strip them off
end
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
end
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
local quote_prefix = '';
if utilities.is_set (QuotePage) then
if not NoPP then
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
end
elseif utilities.is_set (QuotePages) then
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', '';
elseif not NoPP then
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', '';
end
end
                       
Quote = quote_prefix .. ": " .. Quote;
else
Quote = sepc .. " " .. Quote;
end
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
local Archived
if utilities.is_set (ArchiveURL) then
local arch_text;
if not utilities.is_set (ArchiveDate) then
ArchiveDate = utilities.set_message ('err_archive_missing_date');
end
if "live" == UrlStatus then
arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not utilities.is_set (OriginalURL) then
Archived = Archived .. " " .. utilities.set_message ('err_archive_missing_url');  
end
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
arch_text = cfg.messages['archived-unfit'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
if 'bot: unknown' == UrlStatus then
utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added
else
utilities.set_message ('maint_unfit'); -- and add a category if not already added
end
else -- UrlStatus is empty, 'dead'
arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else -- OriginalUrl not set
arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ utilities.set_message ('err_archive_missing_url'), ArchiveDate } );
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Archived = ""
end
local Lay = '';
if utilities.is_set (LayURL) then
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
if utilities.is_set (LaySource) then
LaySource = " &ndash; ''" .. utilities.safe_for_italics (LaySource) .. "''";
else
LaySource = "";
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 utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
end
if utilities.is_set (Transcript) then
if utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
end
local Publisher;
if utilities.is_set (PublicationDate) then
PublicationDate = wrap_msg ('published', PublicationDate);
end
if utilities.is_set (PublisherName) then
if utilities.is_set (PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
end
elseif utilities.is_set (PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
-- Several of the above rely upon detecting this as nil, so do it last.
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
if utilities.is_set (Title) or utilities.is_set (TitleNote) then
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
else
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
end
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
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
if utilities.is_set (Conference) then -- and if |event= is set
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
end
end
-- Piece all bits together at last.  Here, all should be non-nil.
-- We build things this way because it is more efficient in LUA
-- not to keep reassigning to the same string variable over and over.
local tcommon;
local tcommon2; -- used for book cite when |contributor= is set
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
if utilities.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 );
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
else
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
end
elseif 'map' == config.CitationClass then -- special cases for cite map
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif utilities.is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
end
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume, Others, Edition, Publisher, Agency}, sepc );
end
if #ID_list > 0 then
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
else
ID_list = ID;
end
local idcommon;
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, Lay, Quote }, sepc );
else
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
end
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
if utilities.is_set (Date) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
else -- neither of authors and editors set
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
else
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
end
end
end
if utilities.is_set (Authors) then
if (not utilities.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
if utilities.is_set (Editors) then
local in_text = " ";
local post_text = "";
if utilities.is_set (Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then
in_text = in_text:lower() -- 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'] .. ")";
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if utilities.is_set (Editors) and utilities.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 utilities.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
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif utilities.is_set (Editors) then
if utilities.is_set (Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
else
Editors = Editors .. ", " .. cfg.messages['editors'];
end
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
end
if utilities.is_set (PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1, -sepc:len() - 1);
end
text = safe_join( {text, PostScript}, sepc );
-- Now enclose the whole thing in a <cite/> element
local options = {};
if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref=
else
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2');
end
if utilities.is_set (Ref) and 'none' ~= cfg.keywords_xlate[Ref:lower()] then
local id = Ref
if ('harv' == Ref ) then
local namelist = {}; -- holds selected contributor, author, editor name list
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
if #c > 0 then -- if there is a contributor list
namelist = c; -- select it
elseif #a > 0 then -- or an author list
namelist = a;
elseif #e > 0 then -- or an editor list
namelist = e;
end
if #namelist > 0 then -- if there are names in 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 = utilities.set_message ('err_empty_citation');
z.message_tail = {};
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
if 0 ~= #z.message_tail then
table.insert (render, ' ');
for i,v in ipairs( z.message_tail ) do
if utilities.is_set (v[1]) then
if i == #z.message_tail then
table.insert (render, utilities.error_comment ( v[1], v[2] ));
else
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
end
end
end
end
if 0 ~= #z.maintenance_cats then
local maint_msgs = {}; -- here we collect all of the maint messages
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
local maint = {}; -- here we assemble a maintenence message
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint, utilities.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, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
end
if not no_tracking_cats then
for _, v in ipairs( z.error_categories ) do
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.properties_cats ) do -- append properties categories
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
elseif 'nocat' == A:ORIGIN('NoTracking') then -- peculiar special case; can't track nocat without tracking nocat
table.insert (render, utilities.make_wikilink ('Category:CS1 maint: nocat')); -- hand-set this category because it is supposed to be temporary
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
]]
]]
maint_archived_copy = {
message = nil,
anchor = 'archived_copy',
category = 'CS1 maint: archived copy as title',
hidden = true,
},
maint_authors = {
message = nil,
anchor = 'authors',
category = 'CS1 maint: uses authors parameter',
hidden = true,
},
maint_bot_unknown = {
message = nil,
anchor = 'bot:_unknown',
category = 'CS1 maint: bot: original URL status unknown',
hidden = true,
},
maint_date_format = {
message = nil,
anchor = 'date_format',
category = 'CS1 maint: date format',
hidden = true,
},
maint_date_year = {
message = nil,
anchor = 'date_year',
category = 'CS1 maint: date and year',
hidden = true,
},
maint_discouraged = {
message = nil,
anchor = 'discouraged',
category = 'CS1 maint: discouraged parameter',
hidden = true,
},
maint_doi_ignore = {
message = nil,
anchor = 'doi_ignore',
category = 'CS1 maint: ignored DOI errors',
hidden = true,
},
maint_doi_inactive = {
message = nil,
anchor = 'doi_inactive',
category = 'CS1 maint: DOI inactive',
hidden = true,
},
maint_doi_inactive_dated = {
message = nil,
anchor = 'doi_inactive_dated',
category = 'CS1 maint: DOI inactive as of $2$3$1', -- $1 is year, $2 is month-name or empty string, $3 is space or empty string
hidden = true,
},
maint_extra_punct = {
message = nil,
anchor = 'extra_punct',
category = 'CS1 maint: extra punctuation',
hidden = true,
},
maint_extra_text_names = {
message = nil,
anchor = 'extra_text_names',
category = 'CS1 maint: extra text: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_isbn_ignore = {
message = nil,
anchor = 'ignore_isbn_err',
category = 'CS1 maint: ignored ISBN errors',
hidden = true,
},
maint_issn_ignore = {
message = nil,
anchor = 'ignore_issn',
category = 'CS1 maint: ignored ISSN errors',
hidden = true,
},
maint_jfm_format = {
message = nil,
anchor = 'jfm_format',
category = 'CS1 maint: JFM format',
hidden = true,
},
maint_location = {
message = nil,
anchor = 'location',
category = 'CS1 maint: location',
hidden = true,
},
maint_mr_format = {
message = nil,
anchor = 'mr_format',
category = 'CS1 maint: MR format',
hidden = true,
},
maint_mult_names = {
message = nil,
anchor = 'mult_names',
category = 'CS1 maint: multiple names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_numeric_names = {
message = nil,
anchor = 'numeric_names',
category = 'CS1 maint: numeric names: $1', -- $1 is '<name>s list'; gets value from special_case_translation table
hidden = true,
},
maint_others = {
message = nil,
anchor = 'others',
category = 'CS1 maint: others',
hidden = true,
},
maint_others_avm = {
message = nil,
anchor = 'others_avm',
category = 'CS1 maint: others in cite AV media (notes)',
hidden = true,
},
maint_pmc_embargo = {
message = nil,
anchor = 'embargo',
category = 'CS1 maint: PMC embargo expired',
hidden = true,
},
maint_pmc_format = {
message = nil,
anchor = 'pmc_format',
category = 'CS1 maint: PMC format',
hidden = true,
},
maint_postscript = {
message = nil,
anchor = 'postscript',
category = 'CS1 maint: postscript',
hidden = true,
},
maint_ref_duplicates_default = {
message = nil,
anchor = 'ref_default',
category = 'CS1 maint: ref duplicates default',
hidden = true,
},
maint_ref_harv = {
message = nil,
anchor = 'ref_harv',
category = 'CS1 maint: ref=harv',
hidden = true,
},
maint_unfit = {
message = nil,
anchor = 'unfit',
category = 'CS1 maint: unfit URL',
hidden = true,
},
maint_unknown_lang = {
message = nil,
anchor = 'unknown_lang',
category = 'CS1 maint: unrecognized language',
hidden = true,
},
maint_untitled = {
message = nil,
anchor = 'untitled',
category = 'CS1 maint: untitled periodical',
hidden = true,
},
maint_zbl = {
message = nil,
anchor = 'zbl',
category = 'CS1 maint: Zbl',
hidden = true,
},
}


local function validate (name, cite_class, empty)
local name = tostring (name);
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
local state;
local function state_test (state, name) -- local function to do testing of state values
if true == state then return true; end -- valid actively supported parameter
if false == state then
if empty then return nil; end -- deprecated empty parameters are treated as unknowns
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return nil;
end
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
return nil;
end
if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[name];
if true == state_test (state, name) then return true; end
state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
if true == state_test (state, name) then return true; end
-- limited enumerated parameters list
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[enum_name];
if true == state_test (state, name) then return true; end
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
if utilities.in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list
state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
if true == state_test (state, name) then return true; end
end -- if here, fall into general validation
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
if true == state_test (state, name) then return true; end
-- all enumerated parameters allowed
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.numbered_arguments[enum_name];
if true == state_test (state, name) then return true; end
return false; -- not supported because not found or name is set to nil
end
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
check <value> for inter-language interwiki-link markup.  <prefix> must be a MediaWiki-recognized language
code.  when these values have the form (without leading colon):
[[<prefix>:link|label]] return label as plain-text
[[<prefix>:link]] return <prefix>:link as plain-text
return value as is else
]=]


local function inter_wiki_check (parameter, value)
--[[--------------------------< I D _ H A N D L E R S >--------------------------------------------------------
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
local _;
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
end
return value;
end


The following contains a list of values for various defined identifiers.  For each
identifier we specify a variety of information necessary to properly render the
identifier in the citation.


--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
parameters: a list of parameter aliases for this identifier; first in the list is the canonical form
 
link: Wikipedia article name
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
redirect: a local redirect to a local Wikipedia article name;  at en.wiki, 'ISBN (identifier)' is a redirect to 'International Standard Book Number'
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
q: Wikidata q number for the identifier
parameter that is missing its pipe.  There are two tests made:
label: the label preceeding the identifier; label is linked to a Wikipedia article (in this order):
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
redirect from id_handlers['<id>'].redirect when use_identifier_redirects is true
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
Wikidata-supplied article name for the local wiki from id_handlers['<id>'].q
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc. To prevent false positives XML/HTML
local article name from id_handlers['<id>'].link
tags are removed before the search.
prefix: the first part of a URL that will be concatenated with a second part which usually contains the identifier
 
suffix: optional third part to be added after the identifier
If a missing pipe is detected, this function adds the missing pipe maintenance category.
encode: true if URI should be percent-encoded; otherwise false
 
COinS: identifier link or keyword for use in COinS:
for identifiers registered at info-uri.info use: info:.... where '...' is the appropriate identifier label
for identifiers that have COinS keywords, use the keyword: rft.isbn, rft.issn, rft.eissn
for |asin= and |ol=, which require assembly, use the keyword: url
for others make a URL using the value in prefix/suffix and #label, use the keyword: pre (not checked; any text other than 'info', 'rft', or 'url' works here)
set to nil to leave the identifier out of the COinS
separator: character or text between label and the identifier in the rendered citation
id_limit: for those identifiers with established limits, this property holds the upper limit
access: use this parameter to set the access level for all instances of this identifier.
the value must be a valid access level for an identifier (see ['id-access'] in this file).
custom_access: to enable custom access level for an identifier, set this parameter
to the parameter that should control it (normally 'id-access')
]]
]]


local function missing_pipe_check (parameter, value)
local id_handlers = {
local capture;
['ARXIV'] = {
value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc.
parameters = {'arxiv', 'eprint'},
 
link = 'arXiv',
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
redirect = 'arXiv (identifier)',
if capture and validate (capture) then -- if the capture is a valid parameter name
q = 'Q118398',
table.insert( z.message_tail, {utilities.set_message ('err_missing_pipe', parameter)});
label = 'arXiv',
end
prefix = '//arxiv.org/abs/', -- protocol-relative tested 2013-09-04
end
encode = false,
 
COinS = 'info:arxiv',
separator = ':',
access = 'free', -- free to read
},
['ASIN'] = {
parameters = { 'asin', 'ASIN' },
link = 'Amazon Standard Identification Number',
redirect = 'ASIN (identifier)',
q = 'Q1753278',
label = 'ASIN',
prefix = '//www.amazon.',
COinS = 'url',
separator = '&nbsp;',
encode = false;
},
['BIBCODE'] = {
parameters = {'bibcode'},
link = 'Bibcode',
redirect = 'Bibcode (identifier)',
q = 'Q25754',
label = 'Bibcode',
prefix = 'https://ui.adsabs.harvard.edu/abs/',
encode = false,
COinS = 'info:bibcode',
separator = ':',
custom_access = 'bibcode-access',
},
['BIORXIV'] = {
parameters = {'biorxiv'},
link = 'bioRxiv',
redirect = 'bioRxiv (identifier)',
q = 'Q19835482',
label = 'bioRxiv',
prefix = '//doi.org/',
COinS = 'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = '&nbsp;',
},
['CITESEERX'] = {
parameters = {'citeseerx'},
link = 'CiteSeerX',
redirect = 'CiteSeerX (identifier)',
q = 'Q2715061',
label = 'CiteSeerX',
prefix = '//citeseerx.ist.psu.edu/viewdoc/summary?doi=',
COinS =  'pre', -- use prefix value
access = 'free', -- free to read
encode = true,
separator = '&nbsp;',
},
['DOI'] = { -- Used by InternetArchiveBot
parameters = { 'doi', 'DOI'},
link = 'Digital object identifier',
redirect = 'doi (identifier)',
q = 'Q25670',
label = 'doi',
prefix = '//doi.org/',
COinS = 'info:doi',
separator = ':',
encode = true,
custom_access = 'doi-access',
},
['EISSN'] = {
parameters = {'eissn', 'EISSN'},
link = 'International Standard Serial Number#Electronic ISSN',
redirect = 'eISSN (identifier)',
q = 'Q46339674',
label = 'eISSN',
prefix = '//www.worldcat.org/issn/',
COinS = 'rft.eissn',
encode = false,
separator = '&nbsp;',
},
['HDL'] = {
parameters = { 'hdl', 'HDL' },
link = 'Handle System',
redirect = 'hdl (identifier)',
q = 'Q3126718',
label = 'hdl',
prefix = '//hdl.handle.net/',
COinS = 'info:hdl',
separator = ':',
encode = true,
custom_access = 'hdl-access',
},
['ISBN'] = { -- Used by InternetArchiveBot
parameters = {'isbn', 'ISBN', 'isbn13', 'ISBN13'},
link = 'International Standard Book Number',
redirect = 'ISBN (identifier)',
q = 'Q33057',
label = 'ISBN',
prefix = 'Special:BookSources/',
COinS = 'rft.isbn',
separator = '&nbsp;',
},
['ISMN'] = {
parameters = {'ismn', 'ISMN'},
link = 'International Standard Music Number',
redirect = 'ISMN (identifier)',
q = 'Q1666938',
label = 'ISMN',
prefix = '', -- not currently used;
COinS = nil, -- nil because we can't use pre or rft or info:
separator = '&nbsp;',
},
['ISSN'] = {
parameters = {'issn', 'ISSN'},
link = 'International Standard Serial Number',
redirect = 'ISSN (identifier)',
q = 'Q131276',
label = 'ISSN',
prefix = '//www.worldcat.org/issn/',
COinS = 'rft.issn',
encode = false,
separator = '&nbsp;',
},
['JFM'] = {
parameters = {'jfm', 'JFM'},
link = 'Jahrbuch über die Fortschritte der Mathematik',
redirect = 'JFM (identifier)',
q = '',
label = 'JFM',
prefix = '//zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
['JSTOR'] = {
parameters = {'jstor', 'JSTOR'},
link = 'JSTOR',
redirect = 'JSTOR (identifier)',
q = 'Q1420342',
label = 'JSTOR',
prefix = '//www.jstor.org/stable/', -- protocol-relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
custom_access = 'jstor-access',
},
['LCCN'] = {
parameters = {'lccn', 'LCCN'},
link = 'Library of Congress Control Number',
redirect = 'LCCN (identifier)',
q = 'Q620946',
label = 'LCCN',
prefix = '//lccn.loc.gov/', -- protocol-relative tested 2015-12-28
COinS = 'info:lccn',
encode = false,
separator = '&nbsp;',
},
['MR'] = {
parameters = {'mr', 'MR'},
link = 'Mathematical Reviews',
redirect = 'MR (identifier)',
q = 'Q211172',
label = 'MR',
prefix = '//www.ams.org/mathscinet-getitem?mr=', -- protocol-relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
['OCLC'] = {
parameters = {'oclc', 'OCLC'},
link = 'OCLC',
redirect = 'OCLC (identifier)',
q = 'Q190593',
label = 'OCLC',
prefix = '//www.worldcat.org/oclc/',
COinS = 'info:oclcnum',
encode = true,
separator = '&nbsp;',
id_limit = 9999999999, -- 10-digits
},
['OL'] = {
parameters = { 'ol', 'OL' },
link = 'Open Library',
redirect = 'OL (identifier)',
q = 'Q1201876',
label = 'OL',
prefix = '//openlibrary.org/',
COinS = 'url',
separator = '&nbsp;',
encode = true,
custom_access = 'ol-access',
},
['OSTI'] = {
parameters = {'osti', 'OSTI'},
link = 'Office of Scientific and Technical Information',
redirect = 'OSTI (identifier)',
q = 'Q2015776',
label = 'OSTI',
prefix = '//www.osti.gov/biblio/', -- protocol-relative tested 2018-09-12
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = 23000000,
custom_access = 'osti-access',
},
['PMC'] = {
parameters = {'pmc', 'PMC'},
link = 'PubMed Central',
redirect = 'PMC (identifier)',
q = 'Q229883',
label = 'PMC',
prefix = '//www.ncbi.nlm.nih.gov/pmc/articles/PMC',
suffix = '',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = 8100000,
access = 'free', -- free to read
},
['PMID'] = {
parameters = {'pmid', 'PMID'},
link = 'PubMed Identifier',
redirect = 'PMID (identifier)',
q = 'Q2082879',
label = 'PMID',
prefix = '//pubmed.ncbi.nlm.nih.gov/',
COinS = 'info:pmid',
encode = false,
separator = '&nbsp;',
id_limit = 34400000,
},
['RFC'] = {
parameters = {'rfc', 'RFC'},
link = 'Request for Comments',
redirect = 'RFC (identifier)',
q = 'Q212971',
label = 'RFC',
prefix = '//tools.ietf.org/html/rfc',
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
id_limit = 9000,
access = 'free', -- free to read
},
['SBN'] = {
parameters = {'sbn', 'SBN'},
link = 'Standard Book Number', -- redirect to International_Standard_Book_Number#History
redirect = 'SBN (identifier)',
label = 'SBN',
prefix = 'Special:BookSources/0-', -- prefix has leading zero necessary to make 9-digit sbn a 10-digit isbn
COinS = nil, -- nil because we can't use pre or rft or info:
separator = '&nbsp;',
},
['SSRN'] = {
parameters = {'ssrn', 'SSRN'},
link = 'Social Science Research Network',
redirect = 'SSRN (identifier)',
q = 'Q7550801',
label = 'SSRN',
prefix = '//ssrn.com/abstract=', -- protocol-relative tested 2013-09-04
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
id_limit = 4000000,
access = 'free', -- always free to read
},
['S2CID'] = {
parameters = {'s2cid', 'S2CID'},
link = 'Semantic Scholar',
redirect = 'S2CID (identifier)',
q = 'Q22908627',
label = 'S2CID',
prefix = 'https://api.semanticscholar.org/CorpusID:',
COinS = 'pre', -- use prefix value
encode = false,
separator = '&nbsp;',
id_limit = 235000000,
custom_access = 's2cid-access',
},
['USENETID'] = {
parameters = {'message-id'},
link = 'Usenet',
redirect = 'Usenet (identifier)',
q = 'Q193162',
label = 'Usenet:',
prefix = 'news:',
encode = false,
COinS = 'pre', -- use prefix value
separator = '&nbsp;',
},
['ZBL'] = {
parameters = {'zbl', 'ZBL' },
link = 'Zentralblatt MATH',
redirect = 'Zbl (identifier)',
q = 'Q190269',
label = 'Zbl',
prefix = '//zbmath.org/?format=complete&q=an:',
COinS = 'pre', -- use prefix value
encode = true,
separator = '&nbsp;',
},
}


--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked


--[[--------------------------< E X P O R T S >---------------------------------
]]
]]


local function has_extraneous_punc (param, value)
return {
if 'number' == type (param) then
use_identifier_redirects = true, -- when true use redirect name for identifier label links
return;
end
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
if cfg.punct_skip[param] then
return; -- parameter name found in the skip table so done
end
if value:match ('[,;:]$') then
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
end
end
 


--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
aliases = aliases,
 
special_case_translation = special_case_translation,
This is used by templates such as {{cite book}} to create the actual citation text.
date_names = date_names,
 
err_msg_supl = err_msg_supl,
]]
error_conditions = error_conditions,
 
editor_markup_patterns = editor_markup_patterns,
local function citation(frame)
et_al_patterns = et_al_patterns,
Frame = frame; -- save a copy in case we need to display an error message in preview mode
global_df = global_df,
local pframe = frame:getParent()
id_handlers = id_handlers,
local styles;
keywords_lists = keywords_lists,
keywords_xlate = keywords_xlate,
stripmarkers=stripmarkers,
invisible_chars = invisible_chars,
invisible_defs = invisible_defs,
indic_script = indic_script,
emoji = emoji,
local_lang_cat_enable = local_lang_cat_enable,
maint_cats = maint_cats,
messages = messages,
presentation = presentation,
prop_cats = prop_cats,
punct_skip = punct_skip,
script_lang_codes = script_lang_codes,
lang_code_remap = lang_code_remap,
lang_name_remap = lang_name_remap,
this_wiki_code = this_wiki_code,
title_types = title_types,
uncategorized_namespaces = uncategorized_namespaces,
uncategorized_subpages = uncategorized_subpages,
templates_using_volume = templates_using_volume,
templates_using_issue = templates_using_issue,
templates_not_using_page = templates_not_using_page,
vol_iss_pg_patterns = vol_iss_pg_patterns,
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
inter_wiki_map = inter_wiki_map,
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
languages = languages,
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
}
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox');
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
styles = 'Module:Citation/CS1/sandbox/styles.css';
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
utilities = require ('Module:Citation/CS1/Utilities');
validation = require ('Module:Citation/CS1/Date_validation');
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 selected 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
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 
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 error_text, error_state;
 
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame
config[k] = v;
-- args[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep?
end
 
local capture; -- the single supported capture when matching unknown parameters using patterns
local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing
for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame
v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
if v ~= '' then
if ('string' == 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
-- exclude empty numbered parameters
if v:match("%S+") ~= nil then
error_text, error_state = utilities.set_message ( 'err_text_ignored', {v}, true );
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state = utilities.set_message ( 'err_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
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
else
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
end
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
capture = k:match (pattern); -- the whole match if no capture in pattern else the capture if a match
if capture then -- if the pattern matches
param = utilities.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 = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {param}, true ); -- suggested param not supported by this template
v = ''; -- unset
end
end
end
if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion?
if suggestions.suggestions[ k:lower() ] ~= nil then
error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
else
error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end  
if error_text ~= '' then
table.insert( z.message_tail, {error_text, error_state} );
end
end
 
args[k] = v; -- save this parameter and its value
 
elseif not utilities.is_set (v) then -- for empty parameters
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list
end
-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
-- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
-- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
end
 
if 0 ~= #empty_unknowns then -- create empty unknown error message
table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
}, true )});
end
 
for k, v in pairs( args ) do
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v); -- look for invisible characters
end
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label
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 {citation = citation};
JrMPaaLABoLrQoyU
13,301

edits

Retrieved from "https://screamer.wiki/Special:MobileDiff/30784...50741"

Navigation menu