Module:Citation/CS1: Difference between revisions

Jump to navigation Jump to search

Module:Citation/CS1 (view source)

Revision as of 11:47, 5 August 2022

20,388 bytes removed ,  11:47, 5 August 2022
no edit summary
No edit summary
No edit summary
Line 1: Line 1:
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------


each of these counts against the Lua upvalue limit
local z = {
error_categories = {}; -- for categorizing citations that contain errors
error_ids = {};
message_tail = {};
maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance
}


--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
]]
]]
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation


local validation; -- functions in Module:Citation/CS1/Date_validation
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
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
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
 


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


declare variables here that have page-wide scope that are not brought in from
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
other modules; that are created here and used here
This function is global because it is called from both this module and from Date validation


]]
]]
 
function is_set( var )
local added_deprecated_cat; -- Boolean flag so that the category is added only once
return not (var == nil or var == '');
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category
end
local added_generic_name_errs; -- Boolean flag so we only emit one generic name error / category and stop testing names once an error is encountered
local Frame; -- holds the module's frame table
local is_preview_mode; -- true when article is in preview mode; false when using 'Preview page with this template' (previewing the module)
local is_sandbox; -- true when using sandbox modules to render citation
 


--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Line 45: Line 39:
local i = 1;
local i = 1;
while i <= count do -- loop through all items in list
while i <= count do -- loop through all items in list
if utilities.is_set( list[i] ) then
if is_set( list[i] ) then
return list[i]; -- return the first set list member
return list[i]; -- return the first set list member
end
end
Line 52: Line 46:
end
end


--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------


--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Whether needle is in haystack
 
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 
added_vanc_errs is a Boolean declared in page scope variables above


]]
]]


local function add_vanc_error (source, position)
local function in_array( needle, haystack )
if added_vanc_errs then return end
if needle == nil then
return false;
added_vanc_errs = true; -- note that we've added this category
end
utilities.set_message ('err_vancouver', {source, position});
for n,v in ipairs( haystack ) do
if v == needle then
return n;
end
end
return false;
end
end


--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------


--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
Populates numbered arguments in a message string using an argument table.
 
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)
local function substitute( msg, args )
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
end
end


--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------


--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
Wraps error messages with css markup according to the state of hidden.


Does this thing that purports to be a domain name seem to be a valid domain name?
]]
local function error_comment( content, hidden )
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
end


Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
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
Sets an error condition and returns the appropriate error message.  The actual placement of the error message in the output is
the first and last characters the name may use letters, digits, and the hyphen.
the responsibility of the calling function.


Also allowed are IPv4 addresses. IPv6 not supported
]]
local function set_error( error_id, arguments, raw, prefix, suffix )
local error_state = cfg.error_conditions[ error_id ];
prefix = prefix or "";
suffix = suffix or "";
if error_state == nil then
error( cfg.messages['undefined_error'] );
elseif is_set( error_state.category ) then
table.insert( z.error_categories, error_state.category );
end
local message = substitute( error_state.message, arguments );
message = message .. " ([[" .. cfg.messages['help page link'] ..
"#" .. error_state.anchor .. "|" ..
cfg.messages['help page label'] .. "]])";
z.error_ids[ error_id ] = true;
if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
and z.error_ids['citation_missing_title'] then
return '', false;
end
message = table.concat({ prefix, message, suffix });
if raw == true then
return message, error_state.hidden;
end
return error_comment( message, error_state.hidden );
end


domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
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:
Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
the first character of the whole domain name including subdomains must be a letter or a digit
To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.
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 added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats
 
local function add_maint_cat (key, arguments)
local function is_domain_name (domain)
if not added_maint_cats [key] then
if not domain then
added_maint_cats [key] = true; -- note that we've added this category
return false; -- if not set, abandon
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if not domain:match ('^[%w]') then -- first character must be letter or digit
return false;
end
end
end


if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
return false;
end


local patterns = { -- patterns that look like URLs
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
'%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
local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
if domain:match ('%f[%w][%w]%.' .. d) then
local function add_prop_cat (key, arguments)
return true
if not added_prop_cats [key] then
end
added_prop_cats [key] = true; -- note that we've added this category
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
return false; -- no matches, we don't know what this thing is
end
end


--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------


--[[--------------------------< I S _ U R L >------------------------------------------------------------------
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
 
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
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)
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
if utilities.is_set (scheme) then -- if scheme is set check it and domain
local function add_vanc_error ()
return is_scheme (scheme) and is_domain_name (domain);
if not added_vanc_errs then
else
added_vanc_errs = true; -- note that we've added this category
return is_domain_name (domain); -- scheme not set when URL is protocol-relative
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
end
end
end
end




--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------


Split a URL into a scheme, authority indicator, and domain.
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 ("-").


First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#).
returns true if it does, else false


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
local function is_scheme (scheme)
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
end


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;
--[=[-------------------------< 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?


local function split_url (url_str)
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
local scheme, authority, domain;
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;
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
see also [[Single-letter second-level domain]]
list of tlds: https://www.iana.org/domains/root/db


if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
domain = url_str:match ('^//(%S*)')
the first and last characters the name may use letters, digits, and the hyphen.
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
if utilities.is_set (authority) then
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


Also allowed are IPv4 addresses. IPv6 not supported


--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
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 incase it is necessary for IPv4 dot decimal.


checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs
There are several tests:
the first character of the whole domain name including subdomains must be a letter or a digit
single-letter/digit second-level domains in the .org TLD
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


Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
returns true if domain appears to be a proper name and tld or IPv4 address, else false
# < > [ ] | { } _
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
local function is_domain_name (domain)
|<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
if not domain then
 
return false; -- if not set, abandon
]]
end
 
local function link_param_ok (value)
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
local scheme, domain;
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
return false;
return false;
end
end
if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
return true;
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
return true;
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
return true;
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
end
end


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
--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------


Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
--[[--------------------------< I S _ U R L >------------------------------------------------------------------


|<title>= may be wiki-linked but not when |<param>-link= has a value. This function emits an error message when
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
that condition exists


check <link> for inter-language interwiki-link prefix.  prefix must be a MediaWiki-recognized language
This function is the last step in the validation process.  This function is separate because there are cases that
code and must begin with a colon.
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.


]]
]]


local function link_title_ok (link, lorig, title, torig)
local function is_url (scheme, domain)
local orig;
if is_set (scheme) then -- if scheme is set check it and domain
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value
return is_scheme (scheme) and is_domain_name (domain);
if not link_param_ok (link) then -- check |<param>-link= markup
else
orig = lorig; -- identify the failing link parameter
return is_domain_name (domain); -- scheme not set when url is protocol relative
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
utilities.set_message ('err_bad_paramlink', orig); -- URL or wikilink in |title= with |title-link=;
end
end
return link; -- link if ok, empty string else
end
end




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


Determines whether a URL string appears to be valid.
Split a url into a scheme, authority indicator, and domain.
 
If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
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
When not protocol relative, get scheme, authority indicator, and domain.  If there is an authority indicator (one
that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name
or more '/' characters following the scheme's colon), make sure that there are only 2.
is at https://tools.ietf.org/html/rfc5536#section-3.1.4


]]
]]


local function check_url( url_str )
local function split_url (url_str)
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL
local scheme, authority, domain;
return false;
end
url_str = url_str:gsub ('(%a)/.*', '%1'); -- strip path information (the capture prevents false replacement of '//')
local scheme, domain;


scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
domain = url_str:match ('^//(%S*)')
if 'news:' == scheme then -- special case for newsgroups
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
domain = nil; -- set to nil which will cause an error message
end
end
end
return is_url (scheme, domain); -- return true if value appears to be a valid URL
return scheme, domain;
end
end




--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
 
checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls


Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
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.
except the underscore which is used as a space in wiki urls and # which is used for section links


The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs.  The tests that
returns false when the value contains any of these characters.
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]].


]=]
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 is_parameter_ext_wikilink (value)
]]
local scheme, domain;


if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
local function link_param_ok (value)
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
local scheme, domain;
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz]
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
return false;
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
end


return is_url (scheme, domain); -- return true if value appears to be a valid URL
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
end




--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
 
Determines whether a URL string appears to be valid.


loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
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.


]]
]]


local function check_for_url (parameter_list, error_list)
local function check_url( url_str )
for k, v in pairs (parameter_list) do -- for each parameter in the list
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a URL add an error message
return false;
table.insert (error_list, utilities.wrap_style ('parameter', k));
end
end
end
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
end




--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
--[=[-------------------------< 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]].
 
]=]


Escape sequences for content that will be used for URL descriptions
local function is_parameter_ext_wikilink (value)
local scheme, domain;


]]
value = value:gsub ('([^%s/])/[%a%d].*', '%1'); -- strip path information (the capture prevents false replacement of '//')


local function safe_for_url( str )
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
if str:match( "%[%[.-%]%]" ) ~= nil then  
scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S+).*%]')
utilities.set_message ('err_wikilink_in_url', {});
elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]');
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
scheme, domain = value:match ('(%a%S*:)(%S+)');
elseif value:match ('//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text
domain = value:match ('//(%S*%.%S+)'); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a url
end
end
 
return str:gsub( '[%[%]\n]', {
return is_url (scheme, domain); -- return true if value appears to be a valid url
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
end




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


Format an external link with error checking
loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.


]]
]]


local function external_link (URL, label, source, access)
local function check_for_url (parameter_list)
local err_msg = '';
local error_message = '';
local domain;
for k, v in pairs (parameter_list) do -- for each parameter in the list
local path;
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
local base_url;
if 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
if not utilities.is_set (label) then
end
label = URL;
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
if utilities.is_set (source) then
end
utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)});
else
error (cfg.messages["bare_url_no_origin"]);
end
end
if not check_url (URL) then
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)});
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values
URL = table.concat ({domain, path}); -- and reassemble
end
end
 
if is_set (error_message) then -- done looping, if there is an error message, display it
base_url = table.concat ({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
 
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
end
return base_url;
end
end




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


Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the
Protects a string that will be wrapped in wiki italic markup '' ... ''
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
Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
poorly under Mediawiki's HTML tidy.


]]
]]


local function deprecated_parameter(name)
local function safe_for_italics( str )
if not added_deprecated_cat then
if not is_set(str) then
added_deprecated_cat = true; -- note that we've added this category
return str;
utilities.set_message ('err_deprecated_params', {name}); -- add error message
else
if str:sub(1,1) == "'" then str = "<span />" .. str; end
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
-- Remove newlines as they break italics.
return str:gsub( '\n', ' ' );
end
end
end
end


--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------


--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Escape sequences for content that will be used for URL descriptions


Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote
]]
mark contained in a |title= or |chapter= parameter's value.


This function will positive kern either single or double quotes:
local function safe_for_url( str )
"'Unkerned title with leading and trailing single quote marks'"
if str:match( "%[%[.-%]%]" ) ~= nil then
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
Double single quotes (italic or bold wiki-markup) are not kerned.
end
 
Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
return str:gsub( '[%[%]\n]', {
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
 
--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------
 
Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
argument; protects italic styled parameters.  Additional text taken from citation_config.presentation - the reason
this function is similar to but separate from wrap_msg().
 
]]


Call this function for chapter titles, for website titles, etc.; not for book titles.
local function wrap_style (key, str)
if not is_set( str ) then
return "";
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
str = safe_for_italics( str );
end


]=]
return substitute( cfg.presentation[key], {str} );
end


local function kern_quotes (str)
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
local cap = '';
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]]
Format an external link with error checking
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
str = utilities.substitute (cfg.presentation['kern-left'], str);
str = utilities.substitute (cfg.presentation['kern-right'], str);
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = utilities.substitute (cfg.presentation['kern-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = utilities.substitute (cfg.presentation['kern-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 = mw.ustring.match (label, "^([\"\'][^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
local function external_link( URL, label, source )
if utilities.is_set (cap) then
local error_str = "";
label = utilities.substitute (cfg.presentation['kern-left'], cap);
if not is_set( label ) then
end
label = URL;
if is_set( source ) then
cap = mw.ustring.match (label, "^(.+[^\'][\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
if utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-right'], cap);
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
else
else
str = label;
error( cfg.messages["bare_url_no_origin"] );
end
end
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
end
return str;
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end
end


--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------


--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
Formats a wiki style external link


|script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
]]
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.
local function external_link_id(options)
local url_string = options.id;
if options.encode == true or options.encode == nil then
url_string = mw.uri.encode( url_string );
end
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
options.link, options.label, options.separator or "&nbsp;",
options.prefix, url_string, options.suffix or "",
mw.text.nowiki(options.id)
);
end


|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:
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
|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
Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
is not added.  At this time there is no error message for this condition.
parameters in the citation.
 
Supports |script-title=, |script-chapter=, |script-<periodical>=


]]
]]


local function format_script_value (script_value, script_param)
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local lang=''; -- initialize to empty string
local function deprecated_parameter(name)
local name;
if not page_in_deprecated_cat then
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
page_in_deprecated_cat = true; -- note that we've added this category
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
if not utilities.is_set (lang) then
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing title part']}); -- 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', {name, lang})
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['unknown language code']}); -- unknown script-language; add error message
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['invalid language code']}); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
end
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing prefix']}); -- no language code prefix; add error message
end
end
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL
end


return script_value;
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
end


Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.


--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Call this function for chapter titles, for website titles, etc; not for book titles.


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 kern_quotes (str)
local cap='';
local cap2='';
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if is_set (cap) then
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
end


local function script_concatenate (title, script, script_param)
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
if utilities.is_set (script) then
if is_set (cap) then
script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
if utilities.is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
end
return title;
return str;
end
end


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


--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
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.


Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
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.
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().


]]
|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO639-1 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:*** ***


local function wrap_msg (key, str, lower)
The prefix is checked for validity.  If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
if not utilities.is_set ( str ) then
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
return "";
is not added.  At this time there is no error message for this condition.
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=
Supports |script-title= and |script-chapter=


TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
]]


local function wikisource_url_make (str)
local function format_script_value (script_value)
local wl_type, D, L;
local lang=''; -- initialize to empty string
local ws_url, ws_label;
local name;
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
 
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
if not is_set (lang) then
 
return ''; -- script_value was just the prefix so return empty string
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
end
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
-- if we get this far we have prefix and script
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if utilities.is_set (str) then
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
ws_url = table.concat ({ -- build a Wikisource URL
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
wikisource_prefix, -- prefix
-- is prefix one of these language codes?
str, -- article title
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
});
add_prop_cat ('script_with_name', {name, lang})
ws_label = str; -- label for the URL
else
end
add_prop_cat ('script')
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
end
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
if utilities.is_set (str) then
else
ws_label = D; -- get ws article name from display portion of interwiki link
lang = ''; -- invalid so set lang to empty string
ws_url = table.concat ({ -- build a Wikisource URL
wikisource_prefix, -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl


if ws_url then
return script_value;
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
end


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


--[[----------------< F O R M A T _ P E R I O D I C A L >-----------------------
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
 
wrapped in <bdi> tags.
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 function script_concatenate (title, script)
 
if is_set (script) then
if not utilities.is_set (periodical) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
periodical = ''; -- to be safe for concatenation
if is_set (script) then
else
title = title .. ' ' .. script; -- concatenate title and script title
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;
utilities.set_message ('err_trans_missing_title', {'periodical'});
end
end
end
end
 
return title;
return periodical;
end
end




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


Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
and |chapter-url= into a single chapter meta- parameter (chapter_url_source used
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
for error messages).
from citation_config.messages - the reason this function is similar to but separate from wrap_style().


]]
]]


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 function wrap_msg (key, str, lower)
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link
if not is_set( str ) then
if ws_url then
return "";
ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters
chapter = ws_label;
end
end
 
if true == lower then
if not utilities.is_set (chapter) then
local msg;
chapter = ''; -- to be safe for concatenation
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return substitute( msg, str ); -- including template text
else
else
if false == no_quotes then
return substitute( cfg.messages[key], str );
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
end
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>
utilities.set_message ('err_trans_missing_title', {chapter_source});
end
end
 
return chapter;
end
end




--[[----------------< H A S _ I N V I S I B L E _ C H A R S >-------------------
--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------


This function searches a parameter's value for non-printable or invisible characters.
This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
The search stops at the first match.
provided by the template.


This function will detect the visible replacement character when it is part of the Wikisource.
Input:
args – pointer to the arguments table from calling template
alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration
index – for enumerated parameters, identifies which one
enumerated – true/false flag used choose how enumerated aliases are examined
value – value associated with an alias that has previously been selected; nil if not yet selected
selected – the alias that has previously been selected; nil if not yet selected
error_list – list of aliases that are duplicates of the alias already selected


Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers
Returns:
(gallery, math, pre, ref) and identifies them with a slightly different error message.
value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected
See also coins_cleanup().
selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected
 
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 function is_alias_used (args, alias, index, enumerated, value, selected, error_list)
local position = ''; -- position of invisible char or starting position of stripmarker
if enumerated then -- is this a test for an enumerated parameters?
local capture; -- used by stripmarker detection to hold name of the stripmarker
alias = alias:gsub ('#', index); -- replace '#' with the value in index
local stripmarker; -- boolean set true when a stripmarker is found
else
 
alias = alias:gsub ('#', ''); -- remove '#' if it exists
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
end


for _, invisible_char in ipairs (cfg.invisible_chars) do
if is_set(args[alias]) then -- alias is in the template's argument list
local char_name = invisible_char[1]; -- the character or group name
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
local pattern = invisible_char[2]; -- the pattern used to find it
local skip;
position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern
for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias
if v == alias then
if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
skip = true;
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
break; -- has been added so stop looking
position = nil; -- unset position
end
elseif cfg.emoji[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
position = nil; -- unset position
end
end
end
if not skip then -- has not been added so
table.insert( error_list, alias ); -- add error alias to the error list
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 cfg.invisible_defs.del == capture 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 and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
err_msg = capture .. ' ' .. char_name;
else
err_msg = char_name .. ' ' .. 'character';
end
 
utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}); -- add error message
return; -- and done with this parameter
end
end
else
value = args[alias]; -- not yet selected an alias, so select this one
selected = alias;
end
end
end
end
return value, selected; -- return newly selected alias, or previously selected alias
end
end




--[[-------------------< A R G U M E N T _ W R A P P E R >----------------------
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
 
Chooses one matching parameter from a list of parameters to consider.  The list of parameters to consider is just
names.  For parameters that may be enumerated, the position of the numerator in the parameter name is identified
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
 
Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
 


Argument wrapper.  This function provides support for argument mapping defined
Generates an error if more than one match is present.
in the configuration file so that multiple names can be transparently aliased to
single internal variable.


]]
]]


local function argument_wrapper ( args )
local function select_one( args, aliases_list, error_condition, index )
local origin = {};
local value = nil; -- the value assigned to the selected parameter
local selected = ''; -- the name of the parameter we have chosen
return setmetatable({
local error_list = {};
ORIGIN = function ( self, k )
 
local dummy = self[k]; -- force the variable to be loaded.
if index ~= nil then index = tostring(index); end
return origin[k];
 
for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list
if alias:match ('#') then -- if this alias can be enumerated
if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias
end
value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias
else
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias
end
end
},
end
{
 
__index = function ( tbl, k )
if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
if origin[k] ~= nil then
local error_str = "";
return nil;
for _, k in ipairs( error_list ) do
end
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
error_str = error_str .. wrap_style ('parameter', k);
local args, list, v = args, cfg.aliases[k];
end
if #error_list > 1 then
if type( list ) == 'table' then
error_str = error_str .. cfg.messages['parameter-final-separator'];
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
else
if origin[k] == nil then
error_str = error_str .. cfg.messages['parameter-pair-separator'];
origin[k] = ''; -- Empty string, not nil
end
end
error_str = error_str .. wrap_style ('parameter', selected);
elseif list ~= nil then
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
v, origin[k] = args[list], list;
end
else
-- maybe let through instead of raising an error?
return value, selected;
-- v, origin[k] = args[k], k;
end
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 >-------------------------
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L 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 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.
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 nowrap_date (date)
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local cap = '';
local chapter_error = '';
local cap2 = '';
 
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
date = utilities.substitute (cfg.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
if not is_set (chapter) then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
chapter = ''; -- to be safe for concatenation
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
else
if false == no_quotes then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
chapter = wrap_style ('quoted-title', chapter);
end
end
end
return date;
end


chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
if is_set (transchapter) then
transchapter = wrap_style ('trans-quoted-title', transchapter);
if is_set (chapter) then
chapter = chapter ..  ' ' .. transchapter;
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end


--[[--------------------------< S E T _ T I T L E T Y P E >---------------------
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
end


This function sets default title types (equivalent to the citation including
return chapter .. chapter_error;
|type=<default value>) for those templates that have defaults. Also handles the
end
special case where it is desirable to omit the title type from the rendered citation
(|type=none).


]]
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------


local function set_titletype (cite_class, title_type)
This function searches a parameter's value for nonprintable or invisible characters. The search stops at the
if utilities.is_set (title_type) then
first match.
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
This function will detect the visible replacement character when it is part of the wikisource.
end


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().


--[[--------------------------< S A F E _ J O I N >-----------------------------
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.


Joins a sequence of strings together while checking for duplicate separation characters.
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 safe_join( tbl, duplicate_char )
local function has_invisible_chars (param, v)
local f = {}; -- create a function table appropriate to type of 'duplicate character'
local position = ''; -- position of invisible char or starting position of stripmarker
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
f.gsub = string.gsub
local capture; -- used by stripmarker detection to hold name of the stripmarker
f.match = string.match
local i=1;
f.sub = string.sub
local stripmarker, apostrophe;
else -- for multi-byte characters use the ustring library functions
f.gsub = mw.ustring.gsub
f.match = mw.ustring.match
f.sub = mw.ustring.sub
end


local str = ''; -- the output string
while cfg.invisible_chars[i] do
local comp = ''; -- what does 'comp' mean?
local char=cfg.invisible_chars[i][1] -- the character or group name
local end_chr = '';
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
local trim;
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then -- if output string is empty
if position then
str = value; -- assign value to it (first time through the loop)
-- if 'nowiki' == capture or 'math' == capture or ('ref' == capture and 'quote' == param) then -- nowiki, math, or quote param and ref stripmarker (not an error condition)
elseif value ~= '' then
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup.
stripmarker = true; -- set a flag
comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string)
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
elseif 'apostrophe' == char then -- apostrophe template uses &zwj;, hair space and zero-width space
apostrophe = true;
elseif true == apostrophe and in_array (char, {'zero width joiner', 'zero width space', 'hair space'}) then
position = nil; -- unset
else
else
comp = value;
local err_msg;
if capture then
err_msg = capture .. ' ' .. char;
else
err_msg = char .. ' ' .. 'character';
end
 
table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message
return; -- and done with this parameter
end
end
-- typically duplicate_char is sepc
end
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
i=i+1; -- bump our index
--  Because individual string segments often (always?) begin with terminal punct for the
end
--  preceding segment: 'First element' .. 'sepc next element' .. etc.?
end
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
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
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
 
 
--[[--------------------------< I S _ S U F F I X >-----------------------------


returns true if suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
Argument wrapper.  This function provides support for argument mapping defined in the configuration file so that
Puncutation not allowed.
multiple names can be transparently aliased to single internal variable.


]]
]]


local function is_suffix (suffix)
local function argument_wrapper( args )
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
local origin = {};
return true;
end
return setmetatable({
return false;
ORIGIN = function( self, k )
end
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] = select_one( args, list, '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'] );
end
-- Empty strings, not nil;
if v == nil then
v = cfg.defaults[k] or '';
origin[k] = '';
end
tbl = rawset( tbl, k, v );
return v;
end,
});
end


--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.


--[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
Parameters in the whitelist can have three values:
 
true - active, supported parameters
For Vancouver style, author/editor names are supposed to be rendered in Latin
false - deprecated, supported parameters
(read ASCII) characters.  When a name uses characters that contain diacritical
nil - unsupported parameters
marks, those characters are to be 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. The module doesn't do this
so editors may/must.
 
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, position)
local function validate( name )
if not suffix then
local name = tostring( name );
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
local state = whitelist.basic_arguments[ name ];
first = first:match ('(.-)[,%s]+'); -- get name/initials
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
-- Normal arguments
end
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
if utilities.is_set (suffix) then
if not is_suffix (suffix) then
-- Arguments with numbers in them
add_vanc_error (cfg.err_msg_supl.suffix, position);
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
return false; -- not a name with an appropriate suffix
state = whitelist.numbered_arguments[ name ];
end
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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
return false; -- Not supported because not found or name is set to nil
add_vanc_error (cfg.err_msg_supl['non-Latin char'], position);
return false; -- not a string of Latin characters; Vancouver requires Romanization
end;
return true;
end
end




--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
-- Formats a wiki style internal link
local function internal_link_id(options)
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
options.link, options.label, options.separator or "&nbsp;",
options.prefix, options.id, options.suffix or "",
mw.text.nowiki(options.id)
);
end


Attempts to convert names to initials in support of |name-list-style=vanc. 


Names in |firstn= may be separated by spaces or hyphens, or for initials, a period.
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.


Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is
as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
This code only accepts and understands generational suffix in the Vancouver format
because Roman numerals look like, and can be mistaken for, initials.


This function uses ustring functions because firstname initials may be any of the
DOES NOT yet support MMMM YYYY or any of the date ranges.
Unicode Latin characters accepted by is_good_vanc_name ().


]]
]]


local function reduce_to_initials(first, position)
local function nowrap_date (date)
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
local cap='';
local cap2='';


if not name then -- if not initials and a suffix
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
date = substitute (cfg.presentation['nowrap1'], date);
end
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 = substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
return date;
end


if name then -- if first is initials with or without suffix
--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------
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, position); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
else
return first; -- one or two initials without suffix; nothing to do
end
end
end -- if here then name has 3 or more uppercase letters so treat them as a word


local initials, names = {}, {}; -- tables to hold name parts and initials
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
local i = 1; -- counter for number of initials
If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes,
spaces and other non-isxn characters.


names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
]]


while names[i] do -- loop through the table
local function is_valid_isxn (isxn_str, len)
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
local temp = 0;
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
if is_suffix (names[i]) then -- if a legitimate suffix
len = len+1; -- adjust to be a loop counter
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
break; -- and done because suffix must fall at the end of a name
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
end -- no error message if not a suffix; possibly because of Romanization
temp = temp + 10*( len - i ); -- it represents 10 decimal
end
else
if 3 > i then
temp = temp + tonumber( string.char(v) )*(len-i);
table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table
end
end
i = i + 1; -- bump the counter
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
return table.concat(initials) -- Vancouver format does not include spaces.
end
end




--[[--------------------------< L I S T _ P E O P L E >--------------------------
--[[--------------------------< IS _ V A L I D _ I S X N  _ 1 3 >----------------------------------------------
 
ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length
and stripped of dashes, spaces and other non-isxn-13 characters.
 
]]


Formats a list of people (authors, contributors, editors, interviewers, translators)
local function is_valid_isxn_13 (isxn_str)
local temp=0;
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
for i, v in ipairs( isxn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
end
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
end


names in the list will be linked when
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
|<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
Determines whether an ISBN string is valid


]]
]]


local function list_people (control, people, etal)
local function check_isbn( isbn_str )
local sep;
if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
local namesep;
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
local format = control.format;
local len = isbn_str:len();
local maximum = control.maximum;
local name_list = {};
if len ~= 10 and len ~= 13 then
return false;
end


if 'vanc' == format then -- Vancouver-like name styling?
if len == 10 then
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
return is_valid_isxn(isbn_str, 10);
else
else
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
local temp = 0;
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
return is_valid_isxn_13 (isbn_str);
end
end
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
--[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
 
for i, person in ipairs (people) do
Determines whether an ISMN string is valid.  Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
if utilities.is_set (person.last) then
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
local mask = person.mask;
section 2, pages 9–12.
local one;
 
local sep_one = sep;
]]
 
local function ismn (id)
local handler = cfg.id_handlers['ISMN'];
local text;
local valid_ismn = true;
 
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn


if utilities.is_set (maximum) and i > maximum then
if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
etal = true;
valid_ismn = false;
break;
else
end
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
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, nil, i) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials (first, i); -- 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
end


local count = #name_list / 2; -- (number of names + number of separators) divided by 2
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
if 0 < count then
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if 1 < count and not etal then
if 'amp' == format then
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet
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 false == valid_ismn then
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
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al.
end  
end
return result, count; -- return name-list string and count of number of names (count used for editor names only)
return text;
end
end


--[[--------------------------< I S S N >----------------------------------------------------------------------


--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------
Validate and format an issn.  This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
digits with a space.  When that condition occurred, the resulting link looked like this:


Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327]  -- can't have spaces in an external link
returns an empty string.
This code now prevents that by inserting a hyphen at the issn midpoint.  It also validates the issn for length and makes sure that the checkdigit agrees
with the calculated value.  Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn
error message.  The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
 
]]


namelist is one of the contributor-, author-, or editor-name lists chosen in that
local function issn(id)
order.  year is Year or anchor_year.
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local handler = cfg.id_handlers['ISSN'];
local text;
local valid_issn = true;


]]
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn


local function make_citeref_id (namelist, year)
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
local names={}; -- a table for the one to four names and year
valid_issn=false; -- wrong length or improper character
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
else
names[i] = v.last
valid_issn=is_valid_isxn(id, 8); -- validate issn
if i == 4 then break end -- if four then done
end
end
table.insert (names, year); -- add the year at the end
 
local id = table.concat(names); -- concatenate names and year for CITEREF id
if true == valid_issn then
if utilities.is_set (id) then -- if concatenation is not an empty string
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
return "CITEREF" .. id; -- add the CITEREF portion
else
else
return ''; -- return an empty string; no reason to include CITEREF id in this citation
id = issn_copy; -- if not valid, use the show the invalid issn with error message
end
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if false == valid_issn then
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
end
return text
end
end


--[[--------------------------< A M A Z O N >------------------------------------------------------------------


--[[--------------------------< C I T E _ C L A S S _A T T R I B U T E _M A K E >------------------------------
Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
characters.  If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.


construct <cite> tag class attribute for this citation.
]]
 
<cite_class> – config.CitationClass from calling template
<mode> – value from |mode= parameter


]]
local function amazon(id, domain)
local err_cat = ""


local function cite_class_attribute_make (cite_class, mode)
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
local class_t = {};
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
table.insert (class_t, 'citation'); -- required for blue highlight
if 'citation' ~= cite_class then
table.insert (class_t, cite_class); -- identify this template for user css
table.insert (class_t, utilities.is_set (mode) and mode or 'cs1'); -- identify the citation style for user css or javascript
else
else
table.insert (class_t, utilities.is_set (mode) and mode or 'cs2'); -- identify the citation style for user css or javascript
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
if check_isbn( id ) then -- see if asin value is isbn10
add_maint_cat ('ASIN');
elseif not is_set (err_cat) then
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not isbn10
end
elseif not id:match("^%u[%d%u]+$") then
err_cat =  ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
end
end
end
for _, prop_key in ipairs (z.prop_keys_t) do
if not is_set(domain) then
table.insert (class_t, prop_key); -- identify various properties for user css or javascript
domain = "com";
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
domain = "co." .. domain;
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
end
end
 
local handler = cfg.id_handlers['ASIN'];
return table.concat (class_t, ' '); -- make a big string and done
return external_link_id({link=handler.link,
label=handler.label, prefix=handler.prefix .. domain .. "/dp/",
id=id, encode=handler.encode, separator = handler.separator}) .. err_cat;
end
end


--[[--------------------------< A R X I V >--------------------------------------------------------------------


--[[---------------------< N A M E _ H A S _ E T A L >--------------------------
See: http://arxiv.org/help/arxiv_identifier


Evaluates the content of name parameters (author, editor, etc.) for variations on
format and error check arXiv identifier.  There are three valid forms of the identifier:
the theme of et al.  If found, the et al. is removed, a flag is set to true and
the first form, valid only between date codes 9108 and 0703 is:
the function returns the modified name and the flag.
arXiv:<archive>.<class>/<date code><number><version>
 
where:
This function never sets the flag to false but returns its previous state because
<archive> is a string of alpha characters - may be hyphenated; no other punctuation
it may have been set by previous passes through this function or by the associated
<class> is a string of alpha characters - may be hyphenated; no other punctuation
|display-<names>=etal parameter
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
first digit of YY for this form can only 9 and 0
<number> is a three-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented)
the second form, valid from April 2007 through December 2014 is:
arXiv:<date code>.<number><version>
where:
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
<number> is a four-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces


the third form, valid from January 2015 is:
arXiv:<date code>.<number><version>
where:
<date code> and <version> are as defined for 0704-1412
<number> is a five-digit number
]]
]]


local function name_has_etal (name, etal, nocat, param)
local function arxiv (id, class)
 
local handler = cfg.id_handlers['ARXIV'];
if utilities.is_set (name) then -- name can be nil in which case just return
local year, month, version;
local patterns = cfg.et_al_patterns; -- get patterns from configuration
local err_cat = '';
local text;
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
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
name = name:gsub (pattern, ''); -- remove the offending text
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
year = tonumber(year);
if not nocat then -- no categorization for |vauthors=
month = tonumber(month);
utilities.set_message ('err_etal', {param}); -- and set an error if not added
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
end
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
end
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
end
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
end


return name, etal;
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
 
if is_set (class) then
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
else
class = ''; -- empty string for concatenation
end
return text .. class;
end
end


--[[
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
1. Remove all blanks.
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
3. If there is a hyphen in the string:
a. Remove it.
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
1. All these characters should be digits, and there should be six or less. (not done in this function)
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.


--[[---------------------< N A M E _ I S _ N U M E R I C >----------------------
Returns a normalized lccn for lccn() to validate.  There is no error checking (step 3.b.1) performed in this function.
]]
 
local function normalize_lccn (lccn)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
 
if nil ~= string.find (lccn,'/') then
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end
 
local prefix
local suffix
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
 
if nil ~= suffix then -- if there was a hyphen
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
lccn=prefix..suffix; -- reassemble the lccn
end
return lccn;
end


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
Format LCCN link and do simple error checking.  LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the
current version of this test but |first=(1888) is caught.
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/


returns nothing
length = 8 then all digits
length = 9 then lccn[1] is lower case alpha
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
length = 12 then lccn[1] and lccn[2] are both lower case alpha


]]
]]


local function name_is_numeric (name, list_name)
local function lccn(lccn)
if utilities.is_set (name) then
local handler = cfg.id_handlers['LCCN'];
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
local err_cat =  ''; -- presume that LCCN is valid
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
local id = lccn; -- local copy of the lccn
 
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
local len = id:len(); -- get the length of the lccn
 
if 8 == len then
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
end
elseif 9 == len then -- LCCN should be adddddddd
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
end
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
elseif 12 == len then -- LCCN should be aadddddddddd
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
end
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
end
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
end


--[[
Format PMID and do simple error checking.  PMIDs are sequential numbers beginning at 1 and counting up.  This code checks the PMID to see that it
contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.
]]


--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
local function pmid(id)
local test_limit = 30000000; -- update this value as PMIDs approach
local handler = cfg.id_handlers['PMID'];
local err_cat =  ''; -- presume that PMID is valid
if id:match("[^%d]") then -- if PMID has anything but digits
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
else -- PMID is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
end
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end


Evaluates the content of last/surname (authors etc.) parameters for multiple names.
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
Multiple names are indicated if there is more than one comma or any "unescaped"
semicolons. Escaped semicolons are ones used as part of selected HTML entities.
If the condition is met, the function adds the multiple name maintenance category.


returns nothing
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.  If embargo date is
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
|embargo= was not set in this cite.


]]
]]


local function name_has_mult_names (name, list_name)
local function is_embargoed (embargo)
local _, commas, semicolons, nbsps;
if is_set (embargo) then
if utilities.is_set (name) then
local lang = mw.getContentLanguage();
_, commas = name:gsub (',', ''); -- count the number of commas
local good1, embargo_date, good2, todays_date;
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
-- nbsps probably should be its own separate count rather than merged in
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
-- some way with semicolons because Lua patterns do not support the
-- grouping operator that regex does, which means there is no way to add
if good1 and good2 then -- if embargo date and today's date are good dates
-- more entities to escape except by adding more counts with the new
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
-- entities
return embargo; -- still embargoed
_, nbsps = name:gsub ('&nbsp;',''); -- count nbsps
else
add_maint_cat ('embargo')
-- There is exactly 1 semicolon per &nbsp; entity, so subtract nbsps
return ''; -- unset because embargo has expired
-- from semicolons to 'escape' them. If additional entities are added,
end
-- they also can be subtracted.
if 1 < commas or 0 < (semicolons - nbsps) then
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
end
end
end
end
return ''; -- |embargo= not set return empty string
end
end


--[[--------------------------< P M C >------------------------------------------------------------------------


--[=[-------------------------< I S _ G E N E R I C >----------------------------------------------------------
Format a PMC, do simple error checking, and check for embargoed articles.


Compares values assigned to various parameters according to the string provided as <item> in the function call.
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
<item> can have on of two values:
be linked to the article.  If the embargo date is today or in the past, or if it is empty or omitted, then the
'generic_names' – for name-holding parameters: |last=, |first=, |editor-last=, etc
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
'generic_titles' – for |title=


There are two types of generic tests.  The 'accept' tests look for a pattern that should not be rejected by the
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
'reject' test.  For example,
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link.  Function is_embargoed ()
|author=[[John Smith (author)|Smith, John]]
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
would be rejected by the 'author' reject test.  But piped wikilinks with 'author' disambiguation should not be
rejected so the 'accept' test prevents that from happening.  Accept tests are always performed before reject
tests.


Each of the 'accept' and 'reject' sequence tables hold tables for en.wiki (['en']) and local.wiki (['local'])
PMCs are sequential numbers beginning at 1 and counting up.  This code checks the PMC to see that it contains only digits and is less
that each can hold a test sequence table  The sequence table holds, at index [1], a test pattern, and, at index
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
[2], a boolean control value.  The control value 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.


Returns
]]
true when a reject test finds the pattern or string
false when an accept test finds the pattern or string
nil else


]=]
local function pmc(id, embargo)
local test_limit = 5000000; -- update this value as PMCs approach
local handler = cfg.id_handlers['PMC'];
local err_cat =  ''; -- presume that PMC is valid
local text;
 
if id:match("[^%d]") then -- if PMC has anything but digits
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
else -- PMC is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
end
end
if is_set (embargo) then -- is PMC is still embargoed?
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
return text;
end
 
-- Formats a DOI and checks for DOI errors.
 
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
--  Prefix: directory indicator '10.' followed by a registrant code
--  Suffix: character string of any length chosen by the registrant
 
-- This function checks a DOI name for: prefix/suffix.  If the doi name contains spaces or endashes,
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.


local function is_generic (item, value, wiki)
-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
local test_val;
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
local str_lower = { -- use string.lower() for en.wiki (['en']) and use mw.ustring.lower() or local.wiki (['local'])
['en'] = string.lower,
['local'] = mw.ustring.lower,
}
local str_find = { -- use string.find() for en.wiki (['en']) and use mw.ustring.find() or local.wiki (['local'])
['en'] = string.find,
['local'] = mw.ustring.find,
}


local function test (val, test_t, wiki) -- local function to do the testing; <wiki> selects lower() and find() functions
local function doi(id, inactive)
val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value
local cat = ""
return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched
local handler = cfg.id_handlers['DOI'];
local text;
if is_set(inactive) then
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
if is_set(inactive_year) then
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
else
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
else
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
inactive = ""
end
end
local test_types_t = {'accept', 'reject'}; -- test accept patterns first, then reject patterns
local wikis_t = {'en', 'local'}; -- do tests for each of these keys; en.wiki first, local.wiki second


for _, test_type in ipairs (test_types_t) do -- for each test type
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
for _, generic_value in pairs (cfg.special_case_translation[item][test_type]) do -- spin through the list of generic value fragments to accept or reject
cat = ' ' .. set_error( 'bad_doi' );
for _, wiki in ipairs (wikis_t) do
if generic_value[wiki] then
if test (value, generic_value[wiki], wiki) then -- go do the test
return ('reject' == test_type); -- param value rejected, return true; false else
end
end
end
end
end
end
return text .. inactive .. cat
end
end




--[[--------------------------< N A M E _ I S _ G E N E R I C >------------------------------------------------
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------


calls is_generic() to determine if <name> is a 'generic name' listed in cfg.generic_names; <name_alias> is the
Formats an OpenLibrary link, and checks for associated errors.
parameter name used in error messaging


]]
]]
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];


local function name_is_generic (name, name_alias)
if ( code == "A" ) then
if not added_generic_name_errs  and is_generic ('generic_names', name) then
return external_link_id({link=handler.link, label=handler.label,
utilities.set_message ('err_generic_name', name_alias); -- set an error message
prefix=handler.prefix .. 'authors/OL',
added_generic_name_errs = true;
id=id, separator=handler.separator, encode = handler.encode})
elseif ( code == "M" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix=handler.prefix .. 'books/OL',
id=id, separator=handler.separator, encode = handler.encode})
elseif ( code == "W" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix=handler.prefix .. 'works/OL',
id=id, separator=handler.separator, encode = handler.encode})
else
return external_link_id({link=handler.link, label=handler.label,
prefix=handler.prefix .. 'OL',
id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' );
end
end
end
end




--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------


This function calls various name checking functions used to validate the content of the various name-holding parameters.
Validate and format a usenet message id.  Simple error checking, looks for 'id-left@id-right' not enclosed in
'<' and/or '>' angle brackets.


]]
]]


local function name_checks (last, first, list_name, last_alias, first_alias)
local function message_id (id)
local accept_name;
local handler = cfg.id_handlers['USENETID'];


if utilities.is_set (last) then
text = external_link_id({link = handler.link, label = handler.label,
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
end
return text
end


if not accept_name then -- <last> not wrapped in accept-as-written markup
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
name_is_generic (last, last_alias); -- check for names found in the generic names list
end
end


if utilities.is_set (first) then
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).


if not accept_name then -- <first> not wrapped in accept-as-written markup
]]
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
 
name_is_generic (first, first_alias); -- check for names found in the generic names list
local function set_titletype (cite_class, title_type)
end
if is_set(title_type) then
local wl_type, D = utilities.is_wikilink (first);
if "none" == title_type then
if 0 ~= wl_type then
title_type = ""; -- if |type=none then type parameter not displayed
first = D;
utilities.set_message ('err_bad_paramlink', first_alias);
end
end
return title_type; -- if |type= has been set to any other value use that value
end
end


return last, first; -- done
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
end


--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
Removes irrelevant text and dashes from ISBN number
Similar to that used for Special:BookSources
]]


--[[----------------------< E X T R A C T _ N A M E S >-------------------------
local function clean_isbn( isbn_str )
return isbn_str:gsub( "[^-0-9X]", "" );
end


Gets name list from the input arguments
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------


Searches through args in sequential order to find |lastn= and |firstn= parameters
Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
(or their aliases), and their matching link and mask parameters. Stops searching
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
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
local function escape_lua_magic_chars (argument)
search is done.
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
return argument;
end


This function emits an error message when there is a |firstn= without a matching
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
|lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not
required to have a matching |firstn=.


When an author or editor parameter contains some form of 'et al.', the 'et al.'
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
is stripped from the parameter and a flag (etal) returned that will cause list_people()
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.
'et al.' out of the template's metadata.  When this occurs, an error is emitted.


]]
]]


local function extract_names(args, list_name)
local function strip_apostrophe_markup (argument)
local names = {}; -- table of names
if not is_set (argument) then return argument; end
local last; -- individual name components
local first;
local link;
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
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
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
argument=argument:gsub("%'%'%'%'", "");
elseif argument:match ("%'%'%'") then -- bold (3)
argument=argument:gsub("%'%'%'", "");
elseif argument:match ("%'%'") then -- italic (2)
argument=argument:gsub("%'%'", "");
else
break;
end
end
return argument; -- done
end


last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
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, last_alias, first_alias); -- multiple names, extraneous annotation, etc. checks


if first and not last then -- if there is a firstn without a matching lastn
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias
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
}); -- 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
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup
of %27%27...
end
]]


names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
local function make_coins_title (title, script)
n = n + 1; -- point to next location in the names table
if is_set (title) then
if 1 == count then -- if the previous name was missing
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
utilities.set_message ('err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}); -- add this error message
else
end
title=''; -- if not set, make sure title is an empty string
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
end
if is_set (script) then
i = i + 1; -- point to next args location
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
else
script=''; -- if not set, make sure script is an empty string
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
end
return title .. script; -- return the concatenation
return names, etal; -- all done, return our list of names and the etal flag
end
end


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


--[[--------------------------< N A M E _ T A G _ G E T >------------------------------------------------------
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
 
attempt to decode |language=<lang_param> and return language name and matching tag; nil else.
 
This function looks for:
<lang_param> as a tag in cfg.lang_code_remap{}
<lang_param> as a name in cfg.lang_name_remap{}
<lang_param> as a name in cfg.mw_languages_by_name_t
<lang_param> as a tag in cfg.mw_languages_by_tag_t
when those fail, presume that <lang_param> is an IETF-like tag that MediaWiki does not recognize.  Strip all
script, region, variant, whatever subtags from <lang_param> to leave just a two or three character language tag
and look for the new <lang_param> in cfg.mw_languages_by_tag_t{}
 
on success, returns name (in properly capitalized form) and matching tag (in lowercase); on failure returns nil


]]
]]


local function name_tag_get (lang_param)
local function get_coins_pages (pages)
local lang_param_lc = mw.ustring.lower (lang_param); -- use lowercase as an index into the various tables
local pattern;
local name;
if not is_set (pages) then return pages; end -- if no page numbers then we're done
local tag;
 
name = cfg.lang_code_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name
if name then -- when <name>, <lang_param> is a tag for a remapped language name
return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc>
end
 
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags
name = cfg.lang_code_remap[tag]; -- attempt to get remapped language name with language subtag only
if name then -- when <name>, <tag> is a tag for a remapped language name
return name, tag; -- so return <name> from remap and <tag>
end
 
if cfg.lang_name_remap[lang_param_lc] then -- not a tag, assume <lang_param_lc> is a name; attempt to get remapped language tag
return cfg.lang_name_remap[lang_param_lc][1], cfg.lang_name_remap[lang_param_lc][2]; -- for this <lang_param_lc>, return a (possibly) new name and appropriate tag
end
 
tag = cfg.mw_languages_by_name_t[lang_param_lc]; -- assume that <lang_param_lc> is a language name; attempt to get its matching tag
if tag then
while true do
return cfg.mw_languages_by_tag_t[tag], tag; -- <lang_param_lc> is a name so return the name from the table and <tag>
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
if nil == pattern then break; end -- no more urls
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like?
return pages;
end


name = cfg.mw_languages_by_tag_t[lang_param_lc]; -- assume that <lang_param_lc> is a tag; attempt to get its matching language name
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
local function remove_wiki_link( str )
if name then
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name>
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end
end));
end
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- is <lang_param_lc> an IETF-like tag that MediaWiki doesn't recognize? <tag> gets the language subtag; nil else


if tag then
-- Converts a hyphen to a dash
name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag>
local function hyphen_to_dash( str )
if name then
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag
return str;
end
end
end
return str:gsub( '-', '–' );
end
end


--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------


--[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------
Joins a sequence of strings together while checking for duplicate separation characters.


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
local function safe_join( tbl, duplicate_char )
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
Note: we use string functions here, rather than ustring functions.
for '639-2' codes: Category:CS1 ISO 639-2 language sources.
 
This has considerably faster performance and should work correctly as
Languages that are the same as the local wiki are not categorized.  MediaWiki does
long as the duplicate_char is strict ASCII.  The strings
not recognize three-character equivalents of two-character codes: code 'ar' is
in tbl may be ASCII or UTF8.
recognized but code 'ara' is not.
]]
 
This function supports multiple languages in the form |language=nb, French, th
local str = ''; -- the output string
where the language names or codes are separated from each other by commas with
local comp = ''; -- what does 'comp' mean?
optional space characters.
local end_chr = '';
 
local trim;
]]
for _, value in ipairs( tbl ) do
 
if value == nil then value = ''; end
local function language_parameter (lang)
local tag; -- some form of IETF-like language tag; language subtag with optional region, sript, vatiant, etc subtags
local lang_subtag; -- ve populates |language= with mostly unecessary region subtags the MediaWiki does not recognize; this is the base language subtag
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_t = {}; -- 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_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
 
for _, lang in ipairs (names_t) do -- reuse lang here because we don't yet know if lang is a language name or a language tag
name, tag = name_tag_get (lang); -- attempt to get name/tag pair for <lang>; <name> has proper capitalization; <tag> is lowercase
 
if utilities.is_set (tag) then
lang_subtag = tag:gsub ('^(%a%a%a?)%-.*', '%1'); -- for categorization, strip any IETF-like tags from language tag
 
if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language
if 2 == lang_subtag:len() then -- and is a two-character tag
-- utilities.add_prop_cat ('foreign-lang-source', {name, lang_subtag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character tag)
utilities.add_prop_cat ('foreign-lang-source-2', {lang_subtag}, lang_subtag); -- categorize it differently TODO: support multiple three-character tag 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, lang_subtag}); -- categorize it
end
else
name = lang; -- return whatever <lang> has so that we show something
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
end
table.insert (language_list, name);
if str == '' then -- if output string is empty
name = ''; -- so we can reuse it
str = value; -- assign value to it (first time through the loop)
end
elseif value ~= '' then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
name = utilities.make_sep_list (#language_list, language_list);
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
if (1 == #language_list) and (lang_subtag == cfg.this_wiki_code) then -- when only one language, find lang name in this wiki lang name; for |language=en-us, 'English' in 'American English'
else
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
comp = value;
end
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
-- typically duplicate_char is sepc
--[[ TODO: should only return blank or name rather than full list
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
so we can clean up the bunched parenthetical elements Language, Type, Format
--  Because individual string segments often (always?) begin with terminal punct for th
]]
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
end
trim = false;
end_chr = str:sub(-1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = str:sub(1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''  
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:sub(1,-3); -- remove them both
end
end


 
if trim then
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
if value ~= comp then -- value does not equal comp when value contains html markup
 
local dup2 = duplicate_char;
Gets the default CS style configuration for the given mode.
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
Returns default separator and either postscript as passed in or the default.
In CS1, the default postscript and separator are '.'.
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
In CS2, the default postscript is the empty string and the default separator is ','.
else
 
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
]]
end
 
end
local function set_cs_style (postscript, mode)
end
if utilities.is_set(postscript) then
str = str .. value; --add it to the output string
-- emit a maintenance message if user postscript is the default cs1 postscript
-- we catch the opposite case for cs2 in set_style
if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then
utilities.set_message ('maint_postscript');
end
end
else
postscript = cfg.presentation['ps_' .. mode];
end
end
return cfg.presentation['sep_' .. mode], postscript;
return str;
end
end


--[[--------------------------< S E T _ S T Y L E >-----------------------------
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------


Sets the separator and postscript styles. Checks the |mode= first and the
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
#invoke CitationClass second. Removes the postscript if postscript == none.
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


local function set_style (mode, postscript, cite_class)
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
local sep;
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
if 'cs2' == mode then
sep, postscript = set_cs_style (postscript, 'cs2');
elseif 'cs1' == mode then
sep, postscript = set_cs_style (postscript, 'cs1');
elseif 'citation' == cite_class then
sep, postscript = set_cs_style (postscript, 'cs2');
else
sep, postscript = set_cs_style (postscript, 'cs1');
end


if cfg.keywords_xlate[postscript:lower()] == 'none' then
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
-- emit a maintenance message if user postscript is the default cs2 postscript
because the code editor gets confused between character insertion point and cursor position.
-- we catch the opposite case for cs1 in set_cs_style
if 'cs2' == mode or 'citation' == cite_class then
utilities.set_message ('maint_postscript');
end
postscript = '';
end
return sep, postscript
end


]]


--[=[-------------------------< I S _ P D F >-----------------------------------
local function is_good_vanc_name (last, first)
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
add_vanc_error ();
return false; -- not a string of latin characters; Vancouver required Romanization
end;
return true;
end


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


returns true if file extension is one of the recognized extensions, else false
Attempts to convert names to initials in support of |name-list-format=vanc. 


]=]
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/.


local function is_pdf (url)
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
return url:match ('%.pdf$') or url:match ('%.PDF$') or
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end


This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().


--[[--------------------------< S T Y L E _ F O R M A T >-----------------------
]]


Applies CSS style to |format=, |chapter-format=, etc.  Also emits an error message
local function reduce_to_initials(first)
if the format parameter does not have a matching URL parameter.  If the format parameter
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
is not set and the URL contains a file extension that is recognized as a PDF document
local initials = {}
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
local i = 0; -- counter for number of initials
the appropriate styling.
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
 
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
]]
i = i + 1; -- bump the counter
 
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
local function style_format (format, url, fmt_param, url_param)
end
if utilities.is_set (format) then
return table.concat(initials) -- Vancouver format does not include spaces.
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
if not utilities.is_set (url) then
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
end


--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------


--[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------
Formats a list of people (e.g. authors / editors)


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.


When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
return the number and the previous state of the 'etal' flag (false by default
local sep;
but may have been set to true if the name list contains some variant of the text 'et al.').
local namesep;
local format = control.format
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
local text = {}


When the value assigned to |display-xxxxors= is the keyword 'etal', return a number
if 'vanc' == format then -- Vancouver-like author/editor name styling?
that is one greater than the number of authors in the list and set the 'etal' flag true.
sep = ','; -- name-list separator between authors is a comma
This will cause the list_people() to display all of the names in the name list followed by 'et al.'
namesep = ' '; -- last/first separator is a space
 
else
In all other cases, returns nil and the previous state of the 'etal' flag.
sep = ';' -- name-list separator between authors is a semicolon
 
namesep = ', ' -- last/first separator is <comma><space>
inputs:
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
count: #a or #e
list_name: 'authors' or 'editors'
etal: author_etal or editor_etal
 
]]
 
local function get_display_names (max, count, list_name, etal, param)
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
utilities.set_message ('err_disp_name', {param, max}); -- add error message
max = nil;
end
else -- not a valid keyword or number
utilities.set_message ('err_disp_name', {param, max}); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
end
end
return max, etal;
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
 
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
local result = table.concat(text) -- construct list
if etal and 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 go a last-first list and etal so add et al.
end
return result, count
end
end


--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------


--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
 
Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be
some form of p. or pp. abbreviation in the first characters of the parameter content.


check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value:
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px
      where x and X are letters and # is a digit
bad pattern:  '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG


]]
]]
 
local function anchor_id (namelist, year)
local function extra_text_in_page_check (val, name)
local names={}; -- a table for the one to four names and year
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
names[i] = v.last
if val:match (pattern) then -- when a match, error so
if i == 4 then break end -- if four then done
utilities.set_message ('err_extra_text_pages', name); -- add error message
end
return; -- and done
table.insert (names, year); -- add the year at the end
end
local id = table.concat(names); -- concatenate names and year for CITEREF id
end
if is_set (id) then -- if concatenation is not an empty string
end
return "CITEREF" .. id; -- add the CITEREF portion
else
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end
end




--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------


Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
Evaluates the content of author and editor name parameters 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.


For |volume=:
This function never sets the flag to false but returns it's previous state because it may have been set by
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
are allowed.


For |issue=:
]]
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
parameter content (all case insensitive).
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
<val> is |volume= or |issue= parameter value
<name> is |volume= or |issue= parameter name for error message
<selector> is 'v' for |volume=, 'i' for |issue=


sets error message on failure; returns nothing
local function name_has_etal (name, etal, nocat)


]]
if is_set (name) then -- name can be nil in which case just return
 
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
local function extra_text_in_vol_iss_check (val, name, selector)
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
if not utilities.is_set (val) then
return;
if name:match (etal_pattern) then -- variants on et al.
end
name = name:gsub (etal_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;
if not nocat then -- no categorization for |vauthors=
 
add_maint_cat ('etal'); -- and add a category if not already added
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
end
val = val:lower(); -- force parameter value to lower case
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
name = name:gsub (others_pattern, ''); -- if found, remove
if val:match (pattern) then -- when a match, error so
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
utilities.set_message (handler, name); -- add error message
if not nocat then -- no categorization for |vauthors=
return; -- and done
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
end
end
return name, etal; --
end
end


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


--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
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.


split apart a |vauthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
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=
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
rendered citation and in the metadata. Individual author names may be wikilinked


|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
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
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps 'et al.' out of the
template's metadata.  When this occurs, the page is added to a maintenance category.


]=]
]]


local function get_v_name_table (vparam, output_table, output_link_table)
local function extract_names(args, list_name)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local names = {}; -- table of names
local wl_type, label, link; -- wl_type not used here; just a placeholder
local last; -- individual name components
local first;
local i = 1;
local link;
local mask;
while name_table[i] do
local i = 1; -- loop counter/indexer
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
local n = 1; -- output table indexer
local name = name_table[i];
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
i = i + 1; -- bump indexer to next segment
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') 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


local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );


--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.


This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
if first and not last then -- if there is a firstn without a matching lastn
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
 
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
count = count + 1; -- number of times we haven't found last and first
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
if 2 <= count then -- two missing names and we give up
tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.
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
if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last
table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link;
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, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
return names, etal; -- all done, return our list of names
end


Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------


This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for
any of the parameters listed in each cfg.id_handlers['...'].parameters.  If found, adds the parameter and value to
the identifier list.  Emits redundant error message is more than one alias exists in args


]]
]]


local function parse_vauthors_veditors (args, vparam, list_name)
local function extract_ids( args )
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local id_list = {}; -- list of identifiers found in args
local v_name_table = {};
for k, v in pairs( cfg.id_handlers ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table
local v_link_table = {}; -- when name is wikilinked, targets go in this table
v = select_one( args, v.parameters, 'redundant_parameters' ); -- v.parameters is a table of aliases for k; here we pick one from args if present
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list
local last, first, link, mask, suffix;
end
local corporate = false;
return id_list;
end


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)
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
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
Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
local accept_name;
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>


if accept_name then
inputs:
last = v_name;
id_list – table of identifiers built by extract_ids()
corporate = true; -- flag used in list_people()
options – table of various template parameter values used to modify some manually handled identifiers
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, i);
 
end
local function build_id_list( id_list, options )
local lastfirstTable = {}
local new_list, handler = {};
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+$') then -- mw.ustring here so that later we will catch non-Latin characters
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
suffix = first; -- not initials so assume that whatever we got is a generational suffix
first = table.remove(lastfirstTable); -- get what should be the initials from the table
for k, v in pairs( id_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table
end
-- fallback to read-only cfg
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
handler = setmetatable( { ['id'] = v }, fallback(k) );
if not utilities.is_set (last) then
first = ''; -- unset
last = v_name; -- last empty because something wrong with first
add_vanc_error (cfg.err_msg_supl.name, i);
end
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error (cfg.err_msg_supl.initials, i); -- 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
if utilities.is_set (first) then
if handler.mode == 'external' then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
table.insert( new_list, {handler.label, external_link_id( handler ) } );
add_vanc_error (cfg.err_msg_supl.initials, i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
elseif handler.mode == 'internal' then
end
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit
elseif handler.mode ~= 'manual' then
if utilities.is_set (suffix) then
error( cfg.messages['unknown_ID_mode'] );
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
elseif k == 'DOI' then
suffix = ''; -- unset so we don't add this suffix to all subsequent names
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
elseif k == 'ARXIV' then
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );  
elseif k == 'ASIN' then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );  
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' or k == 'OLA' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISMN' then
table.insert( new_list, {handler.label, ismn( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
else
if not corporate then
error( cfg.messages['unknown_manual_ID'] );
is_good_vanc_name (last, '', nil, i);
end
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
end
return names, etal; -- all done, return our list of names
function comp( a, b ) -- used in following table.sort()
return a[1] < b[1];
end
table.sort( new_list, comp );
for k, v in ipairs( new_list ) do
new_list[k] = v[2];
end
return new_list;
end
end
 


--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------


--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities.


Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
2015-12-10: there is a bug in mw.text.unstripNoWiki ().  It replaced math stripmarkers with the appropriate content
select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
when it shouldn't.  See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29


Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest;
TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible
|editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn)
characters table?
]]


When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
local function coins_cleanup (value)
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content
way to do this, I just haven't discovered what that way is.
value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">&#39;s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s
value = value:gsub ('&zwj;\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe
value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11)
value = value:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with plain space
value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space
value = value:gsub ('&zwj;', ''); -- remove &zwj; entities
value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space
value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space
return value;
end


Emits an error message when more than one xxxxor name source is provided.


In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.
--[[--------------------------< C O I N S >--------------------------------------------------------------------
 
COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.


]]
]]


local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local function COinS(data, class)
local lastfirst = false;
if 'table' ~= type(data) or nil == next(data) then
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 ...
return '';
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
end
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
 
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
for k, v in pairs (data) do -- spin through all of the metadata parameter values
lastfirst = true;
if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed)
data[k] = coins_cleanup (v);
end
end
end


if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
local ctx_ver = "Z39.88-2004";
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
(true == lastfirst and utilities.is_set (xxxxors)) then
-- treat table strictly as an array with only set values.
local err_name;
local OCinSoutput = setmetatable( {}, {
if 'AuthorList' == list_name then -- figure out which name should be used in error message
__newindex = function(self, key, value)
err_name = 'author';
if is_set(value) then
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
end
end
});
if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or  
('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier
if 'arxiv' == class then -- set genre according to the type of citation template we are rendering
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
elseif 'conference' == class then
OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set)
elseif 'web' == class then
OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set)
else
OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only
if is_set (data.Map) then
OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical
else
OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles
end
-- these used onlu for periodicals
OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall
OCinSoutput["rft.chron"] = data.Chron; -- free-form date components
OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata
 
elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier
if 'report' == class or 'techreport' == class then -- cite report and cite techreport
OCinSoutput["rft.genre"] = "report";
elseif 'conference' == class then -- cite conference when Periodical not set
OCinSoutput["rft.genre"] = "conference";
elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then
if is_set (data.Chapter) then
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title
else
else
err_name = 'editor';
if 'map' == class or 'interview' == class then
OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview
else
OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia
end
end
end
utilities.set_message ('err_redundant_parameters', err_name .. '-name-list parameters'); -- add error message
else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
OCinSoutput["rft.genre"] = "unknown";
end
OCinSoutput["rft.btitle"] = data.Title; -- book only
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
OCinSoutput["rft.series"] = data.Series; -- book only
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
OCinSoutput["rft.edition"] = data.Edition; -- book only
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
end
-- and now common parameters (as much as possible)
OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
if k == 'ISBN' then v = clean_isbn( v ) end
local id = cfg.id_handlers[k].COinS;
if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
elseif string.sub (id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords
OCinSoutput[ id ] = v;
elseif id then -- when cfg.id_handlers[k].COinS is not nil
OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v }; -- others; provide a url
end
end
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;
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
if utilities.is_set (xxxxors) then return 3 end;
local id, value = cfg.id_handlers[k].COinS;
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
OCinSoutput[ id ] = value;
end
end
]]
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers
if k == 1 then -- for the first author name only
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
elseif is_set(last) then  
OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name
end
else -- for all other authors
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation
end
end
end
 
OCinSoutput.rft_id = data.URL;
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end
end




--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
--[[--------------------------< 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 code.  Handles the special case that is Norwegian where
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
 
Returns the language name and associated ISO639-1 code.  Because case of the source may be incorrect 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.


This function is used to validate a parameter's assigned value for those parameters that have only a limited number
mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included
of allowable values (yes, y, true, live, dead, etc.).  When the parameter value has not been assigned a value (missing
in the list will be found if that name is provided in the |language= parameter.  For example, if |language=Samaritan Aramaic, that name will be
or empty in the source template) the function returns the value specified by ret_val.  If the parameter value is one
found with the associated code 'sam', not an ISO639-1 code.  When names are found and the associated code is not two characters, this function
of the list of allowed values returns the translated value; else, emits an error message and returns the value
returns only the Wikimedia language name.
specified by ret_val.


TODO: explain <invert>
Adapted from code taken from Module:Check ISO 639-1.


]]
]]


local function is_valid_parameter_value (value, name, possible, ret_val, invert)
local function get_iso639_code (lang)
if not utilities.is_set (value) then
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
return ret_val; -- an empty parameter is ok
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
end
end
 
if (not invert and utilities.in_array (value, possible)) then -- normal; <value> is in <possible> table
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
elseif invert and not utilities.in_array (value, possible) then -- invert; <value> is not in <possible> table
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
return value; -- return <value> as it is
else
for code, name in pairs(languages) do -- scan the list to see if we can find our language
utilities.set_message ('err_invalid_param_val', {name, value}); -- not an allowed value so add error message
if langlc == mw.ustring.lower(name) then
return ret_val;
if 2 ~= code:len() then -- ISO639-1 codes only
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
end


--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------


--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
Get language name from ISO639-1 code value provided.  If a code is valid use the returned name; if not, then use the value that was provided with the language parameter.


This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
There is an exception.  There are three ISO639-1 codes for Norewegian language variants.  There are two official variants: Norwegian Bokmål (code 'nb') and
when the last character is not a sepc character or when the last three characters are not sepc followed by two
Norwegian Nynorsk (code 'nn').  The third, code 'no',  is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless.  However, it appears
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.
single space character.


]]
Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and
return 'Norwegian' when editors use |language=no.  We presume that editors don't know about the variants or can't descriminate between them.


local function terminate_name_list (name_list, sepc)
See Help talk:Citation Style_1#An ISO 639-1 language name test
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


When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
the page is a mainspace page and the ISO639-1 code is not 'en'.  Similarly, if the  parameter is |language=Norwegian, it will be categorized in the same way.


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


returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
]]
or formatted issue, or an empty string if neither are set.
 
local function language_parameter (lang)
local code; -- the ISO639-1 two character code
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=


]]
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
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


-- same condition as in format_pages_sheets()
for _, lang in ipairs (names_table) do -- reuse lang
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);


local is_numeric_vol = volume and (volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')); -- is only uppercase roman numerals or only digits?
if lang:match ('^%a%a%-') then -- strip ietf language tags from code
local is_long_vol = volume and (4 < mw.ustring.len(volume)); -- is |volume= value longer than 4 characters?
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
end
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
end
if is_set (name) then -- if Language specified a valid ISO639-1 code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if volume and (not is_numeric_vol and is_long_vol) then -- when not all digits or Roman numerals, is |volume= longer than 4 characters?
if is_set (code) then
utilities.add_prop_cat ('long-vol'); -- yes, add properties cat
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
end
if 'en' ~= code then -- English not the language
 
add_prop_cat ('foreign_lang_source', {name, code})
if is_journal then -- journal-style formatting
local vol = '';
if utilities.is_set (volume) then
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals?
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters?
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, utilities.hyphen_to_dash (volume)}); -- not bold
else -- four or fewer characters
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, utilities.hyphen_to_dash (volume)}); -- bold
end
end
else
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
end
if utilities.is_set (issue) then
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
table.insert (language_list, name);
end
name = ''; -- so we can reuse it
return vol;
end
end
if 'podcast' == cite_class and utilities.is_set (issue) then
code = #language_list -- reuse code as number of languages in the list
return wrap_msg ('issue', {sepc, issue}, lower);
if 2 >= code then
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
elseif 2 < code then
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
end
 
if 'English' == name then
-- all other types of citation
return ''; -- if one language and that language is English return an empty string (no annotation)
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, utilities.hyphen_to_dash (volume), issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, utilities.hyphen_to_dash (volume)}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
end


--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------


--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
Set style settings for CS1 citation templates. Returns separator and postscript settings
 
]]


adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
local function set_cs1_style (ps)
The return order is:
if not is_set (ps) then -- unless explicitely set to something
page, pages, sheet, sheets
ps = '.'; -- terminate the rendered citation with a period
end
return '.', ps; -- separator is a full stop
end
 
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------


Singular has priority over plural when both are provided.
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings


]]
]]


local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
local function set_cs2_style (ps, ref)
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
if utilities.is_set (sheet) then
ps = ''; -- make sure it isn't nil
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
else
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif utilities.is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
end
 
if not is_set (ref) then -- if |ref= is not set
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
ref = "harv"; -- set default |ref=harv
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
end
return ',', ps, ref; -- separator is a comma
return '', '', '', ''; -- return empty strings
end
end


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


--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
rendered style.


returns one of the in-source locators: page, pages, or at.
]]
 
local function get_settings_from_cite_class (ps, ref, cite_class)
local sep;
if (cite_class == "citation") then -- for citation templates (CS2)
sep, ps, ref = set_cs2_style (ps, ref);
else -- not a citation template so CS1
sep, ps = set_cs1_style (ps);
end


If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
return sep, ps, ref -- return them all
for use in COinS.  This COinS thing is done because here we convert an interwiki-link to an external link and
end
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;
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------


TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
to a new name)?
config.CitationClass from the template's #invoke: to establish style.


]]
]]


local function insource_loc_get (page, page_orig, pages, pages_orig, at)
local function set_style (mode, ps, ref, cite_class)
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?)
local sep;
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
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 'none' == ps:lower() 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
applying the pdf icon to external links.


if utilities.is_set (page) then
returns true if file extension is one of the recognized extension, else false
if utilities.is_set (pages) or utilities.is_set (at) then
pages = ''; -- unset the others
at = '';
end
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.


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, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.


ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label
local function is_pdf (url)
if ws_url then
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
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
end


--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------


add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value
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 is_unique_archive_url (archive, url, c_url, source, date)
local function style_format (format, url, fmt_param, url_param)
if utilities.is_set (archive) then
if is_set (format) then
if archive == url or archive == c_url then
format = wrap_style ('format', format); -- add leading space, parenthases, resize
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); -- add error message
if not is_set (url) then
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
end
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
end
 
return format;
return archive, date;
end
end


--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------


--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
Returns a number that may or may not limit the length of the author or editor name lists.


Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the  
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
save snapshot URL or to calendar pages.  When the archive URL is 'https://web.archive.org/save/' (or http://...)
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
archive.org saves a snapshot of the target page in the URL. That is something that Wikipedia should not allow
some variant of the text 'et al.').
unwitting readers to do.


When the archive.org URL does not have a complete timestamp, archive.org chooses a snapshot according to its own
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
algorithm or provides a calendar 'search' result.  [[WP:ELNO]] discourages links to search results.
number of authors in the list and set the 'etal' flag true.  This will cause the list_people() to display all of
the names in the name list followed by 'et al.'


This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
In all other cases, returns nil and the previous state of the 'etal' flag.
|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
local function get_display_authors_editors (max, count, list_name, etal)
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
if is_set (max) then
we don't check for these specific flags but we do check the form.
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.
This function supports a preview mode.  When the article is rendered in preview mode, this function may return a modified
etal = true; -- overrides value set by extract_names()
archive URL:
elseif max:match ('^%d+$') then -- if is a string of numbers
for save command errors, return undated wildcard (/*/)
max = tonumber (max); -- make it a number
for timestamp errors when the timestamp has a wildcard, return the URL unmodified
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
add_maint_cat ('disp_auth_ed', list_name);
 
]=]
 
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 path then -- malformed in some way; pattern did not match
err_msg = cfg.err_msg_supl.timestamp;
elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = cfg.err_msg_supl.timestamp;
if '*' ~= flag then
local replacement = timestamp:match ('^%d%d%d%d%d%d') or timestamp:match ('^%d%d%d%d'); -- get the first 6 (YYYYMM) or first 4 digits (YYYY)
if replacement then -- nil if there aren't at least 4 digits (year)
replacement = replacement .. string.rep ('0', 14 - replacement:len()); -- year or yearmo (4 or 6 digits) zero-fill to make 14-digit timestamp
url=url:gsub ('(//web%.archive%.org/[^%d]*)%d[^/]*', '%1' .. replacement .. '*', 1) -- for preview, modify ts to 14 digits plus splat for calendar display
end
end
end
elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element
else -- not a valid keyword or number
err_msg = cfg.err_msg_supl.path;
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
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)
max = nil; -- unset
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
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
end
-- if here, something not right so
utilities.set_message ('err_archive_url', {err_msg}); -- add error message and
return max, etal;
 
if is_preview_mode then
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
else
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
end
end
end


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


--[[--------------------------< P L A C 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.
abbreviation in the first characters of the parameter content.


check |place=, |publication-place=, |location= to see if these params include digits. This function added because
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
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


returns the original parameter value without modification; added maint cat when parameter value contains digits
]]


]]
local function extra_text_in_page_check (page)
-- local good_pattern = '^P[^%.P%l]';
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
-- local bad_pattern = '^[Pp][Pp]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';


local function place_check (param_val)
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
if not utilities.is_set (param_val) then -- parameter empty or omitted
add_maint_cat ('extra_text');
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
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
return param_val; -- and done
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
end
end




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


compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else
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 paranethese ((corporate name)) to suppress the format tests.
 
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.


]]
]]


local function is_archived_copy (title)
local function parse_vauthors_veditors (args, vparam, list_name)
title = mw.ustring.lower(title); -- switch title to lower case
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
local v_name_table = {};
return true;
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
elseif cfg.special_case_translation.archived_copy['local'] then
local last, first, link, mask;
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
local corporate = false;
return true;
 
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)
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ();
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
 
for i, v_name in ipairs(v_name_table) do
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name:match ('^%(%((.+)%)%)$')
corporate = true;
elseif string.find(v_name, "%s") then
    lastfirstTable = {}
    lastfirstTable = mw.text.split(v_name, "%s")
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
end
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ();
end
end
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
end
return names, etal; -- all done, return our list of names
end
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


--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
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.


This is the main function doing the majority of the citation formatting.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.


]]
]]


local function citation0( config, args )
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
--[[
local lastfirst = false;
Load Input Parameters
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
]]
lastfirst=true;
local A = argument_wrapper ( args );
end
local i


-- Pick out the relevant fields from the arguments.  Different citation templates
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
-- define different field names for the same underlying things.
(is_set (vxxxxors) and is_set (xxxxors)) or
 
(true == lastfirst and is_set (xxxxors)) then
local author_etal;
local err_name;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
if 'AuthorList' == list_name then -- figure out which name should be used in error message
local Authors;
err_name = 'author';
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
else
local Collaboration = A['Collaboration'];
err_name = 'editor';
 
do -- to limit scope of selected
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
if 1 == selected then
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
utilities.set_message ('maint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
end
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
if utilities.is_set (Collaboration) then
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
author_etal = true; -- so that |display-authors=etal not required
end
end
end


local editor_etal;
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
if is_set (vxxxxors) then return 2 end;
if 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


do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn
if 1 == selected then
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
elseif 2 == selected then
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
end
end
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
local Chapter_origin = A:ORIGIN ('Chapter');
local Contribution; -- because contribution is required for contributor(s)
if 'contribution' == Chapter_origin then
Contribution = Chapter; -- get the name of the contribution
end
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
if 0 < #c then
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
utilities.set_message ('err_contributor_missing_required_param', 'contribution'); -- add missing contribution error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
utilities.set_message ('err_contributor_missing_required_param', 'author'); -- add missing author error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
end
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?
utilities.set_message ('err_contributor_ignored'); -- add contributor ignored error message
end
Contribution = nil; -- unset
end


local Title = A['Title'];
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
local TitleLink = A['TitleLink'];


local auto_select = ''; -- default is auto
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
local accept_link;
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
true; else, emits an error message and returns false.
auto_select = TitleLink; -- remember selection for later
TitleLink = ''; -- treat as if |title-link= would have been empty
end


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
]]


local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
local function is_valid_parameter_value (value, name, possible)
if 'map' == config.CitationClass and 'section' == Chapter_origin then
if not is_set (value) then
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
return true; -- an empty parameter is ok
Chapter = ''; -- unset for now; will be reset later from |map= if present
elseif in_array(value:lower(), possible) then
return true;
else
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
end
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
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.
]]


local Periodical = A['Periodical'];
local function terminate_name_list (name_list, sepc)
local Periodical_origin = '';
if (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
if utilities.is_set (Periodical) then
return name_list .. " "; -- don't add another
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
else
local i;
return name_list .. sepc .. ' '; -- otherwise terninate the name list
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
utilities.set_message ('err_apostrophe_markup', {Periodical_origin});
end
end
end
end


if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error TODO: make a function for this and similar?
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')});
end


Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
Periodical_origin = A:ORIGIN('MailingList');
end


local ScriptPeriodical = A['ScriptPeriodical'];
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
or formatted issue, or an empty string if neither are set.


-- web and news not tested for now because of
]]
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
if not is_set (volume) and not is_set (issue) then
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
return '';
if p[config.CitationClass]  then
utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]});
end
end
end
local Volume;
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
if is_set (volume) and is_set (issue) then
if 'citation' == config.CitationClass then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
if utilities.is_set (Periodical) then
elseif is_set (volume) then
if not utilities.in_array (Periodical_origin, cfg.citation_no_volume_t) then -- {{citation}} does not render |volume= when these parameters are used
return wrap_msg ('vol', {sepc, volume}, lower);
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif utilities.is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
end
else
else
Volume = A['Volume']; -- and does for non-'periodical' cites
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
end
Volume = A['Volume'];
end
local vol = '';
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v');
 
if is_set (volume) then
local Issue;
if (4 < mw.ustring.len(volume)) then
if 'citation' == config.CitationClass then
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, cfg.citation_issue_t) then -- {{citation}} may render |issue= when these parameters are used
else
Issue = utilities.hyphen_to_dash (A['Issue']);
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
end
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
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
Issue = utilities.hyphen_to_dash (A['Issue']);
end
end
end
end
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end


local Page;
local Pages;
local At;
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = utilities.hyphen_to_dash (A['Pages']);
At = A['At'];
end


local Edition = A['Edition'];
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
local Place = place_check (A['Place'], A:ORIGIN('Place'));
local PublisherName = A['PublisherName'];
local PublisherName_origin = A:ORIGIN('PublisherName');
if utilities.is_set (PublisherName) then
local i = 0;
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
if i then -- non-zero when markup was stripped so emit an error message
utilities.set_message ('err_apostrophe_markup', {PublisherName_origin});
end
end


local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
local Newsgroup_origin = A:ORIGIN('Newsgroup');
The return order is:
page, pages, sheet, sheets


if 'newsgroup' == config.CitationClass then
Singular has priority over plural when both are provided.
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
utilities.set_message ('err_parameter_ignored', {PublisherName_origin});
end


PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
]]
end


local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL?
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if is_set (sheet) then
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
if 'journal' == origin then
UrlAccess = nil;
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
utilities.set_message ('err_param_access_requires_param', 'url');
else
end
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
local ChapterURL = A['ChapterURL'];
elseif is_set (sheets) then
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
if 'journal' == origin then
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
ChapterUrlAccess = nil;
else
utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')});
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
end


local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
MapUrlAccess = nil;
utilities.set_message ('err_param_access_requires_param', {'map-url'});
end


local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
if is_set (page) then
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
if is_journal then
 
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
elseif not nopp then
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
else
no_tracking_cats = "true"; -- set no_tracking_cats
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
end
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
elseif is_set(pages) then
if this_page.text:match (v) then -- test page name against each pattern
if is_journal then
no_tracking_cats = "true"; -- set no_tracking_cats
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
break; -- bail out if one is found
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
end
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
end
end
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
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
local coins_pages;
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
return '', '', '', ''; -- return empty strings
end


local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------


if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
This is the main function doing the majority of the citation formatting.
utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
if PublicationPlace == Place then
Place = ''; -- unset; don't need both if they are the same
end
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end


if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
]]
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ScriptChapter = A['ScriptChapter'];
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
local Format = A['Format'];
local ChapterFormat = A['ChapterFormat'];
local TransChapter = A['TransChapter'];
local TransChapter_origin = A:ORIGIN ('TransChapter');
local TransTitle = A['TransTitle'];
local ScriptTitle = A['ScriptTitle'];
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title=
|encyclopedia= and |article= then map |encyclopedia= to |title=


|trans-title= maps to |trans-chapter= when |title= is re-mapped
local function citation0( config, args)
|url= maps to |chapter-url= when |title= is remapped
--[[
Load Input Parameters
All other combinations of |encyclopedia=, |title=, and |article= are not modified
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
]]
]]
local A = argument_wrapper( args );
local i


local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
-- Pick out the relevant fields from the arguments.  Different citation templates
-- define different field names for the same underlying things.
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
local Authors;
local NameListFormat = A['NameListFormat'];


if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
do -- to limit scope of selected
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')});
if 1 == selected then
Encyclopedia = nil; -- unset because not supported by this template
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
end
elseif 2 == selected then
end
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
 
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
elseif 3 == selected then
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error TODO: make a function for this and similar?
Authors = A['Authors']; -- use content of |authors=
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)});
end
end
end


if utilities.is_set (Encyclopedia) then
local Coauthors = A['Coauthors'];
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
local Others = A['Others'];
Periodical_origin = A:ORIGIN ('Encyclopedia');
end


if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
local editor_etal;
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
if not utilities.is_set (Chapter) then
local Editors;
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle')
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL_origin = URL_origin;


ChapterUrlAccess = UrlAccess;
do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
if 1 == selected then
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
elseif 2 == selected then
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
end
end


if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
Chapter = utilities.make_wikilink (TitleLink, Chapter);
local Translators; -- assembled translators name list
end
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
Title = Periodical;
ChapterFormat = Format;
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
Periodical = ''; -- redundant so unset
local Contributors; -- assembled contributors name list
TransTitle = '';
local Contribution = A['Contribution'];
URL = '';
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
Format = '';
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
TitleLink = '';
ScriptTitle = '';
if 0 < #c then
end
if not is_set (Contribution) then -- |contributor= requires |contribution=
elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
c = {}; -- blank the contributors' table; it is used as a flag later
Periodical = ''; -- redundant so unset
end
if 0 == #a then -- |contributor= requires |author=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
end
end
end
else -- if not a book cite
if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters?
table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message
end
Contribution = nil; -- unset
end
end


-- special case for cite techreport.
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
local ID = A['ID'];
NameListFormat = ''; -- anything else, set to empty string
if (config.CitationClass == "techreport") then -- special case for cite techreport
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"?
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')});
end
end
end
end


-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
local Year = A['Year'];
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local PublicationDate = A['PublicationDate'];
local Conference = A['Conference'];
local OrigYear = A['OrigYear'];
local BookTitle = A['BookTitle'];
local Date = A['Date'];
local TransTitle_origin = A:ORIGIN ('TransTitle');
local LayDate = A['LayDate'];
if 'conference' == config.CitationClass then
------------------------------------------------- Get title data
if utilities.is_set (BookTitle) then
local Title = A['Title'];
Chapter = Title;
local ScriptTitle = A['ScriptTitle'];
Chapter_origin = 'title';
local BookTitle = A['BookTitle'];
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
local Conference = A['Conference'];
ChapterURL = URL;
local TransTitle = A['TransTitle'];
ChapterUrlAccess = UrlAccess;
local TitleNote = A['TitleNote'];
ChapterURL_origin = URL_origin;
local TitleLink = A['TitleLink'];
URL_origin = '';
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
ChapterFormat = Format;
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
TransChapter = TransTitle;
TransChapter_origin = TransTitle_origin;
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
-- CS1/2 mode
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
-- separator character and postscript
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
-- controls capitalization of certain static text
local use_lowercase = ( sepc == ',' );
-- 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 --TODO: make a function for this and similar?
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}); -- 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;
local Chapter = A['Chapter'];
ChapterFormat = A['MapFormat'];
local ScriptChapter = A['ScriptChapter'];
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
local Degree = A['Degree'];
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
local ArchiveURL = A['ArchiveURL'];
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local ChapterURL = A['ChapterURL'];
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter


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.
local Series = A['Series'];
local Series = A['Series'];
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local SeriesLink = A['SeriesLink'];
local Volume;
local Issue;
local Page;
local Pages;
local At;


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
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
 
Volume = A['Volume'];
local Network = A['Network'];
end
local Station = A['Station'];
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
local s, n = {}, {};
Issue = A['Issue'];
-- do common parameters first
end
if utilities.is_set (Network) then table.insert(n, Network); end
local Position = '';
if utilities.is_set (Station) then table.insert(n, Station); end
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
ID = table.concat(n, sepc .. ' ');
Page = A['Page'];
Pages = hyphen_to_dash( A['Pages'] );
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
At = A['At'];
local Season = A['Season'];
end
local SeriesNumber = A['SeriesNumber'];


if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set TODO: make a function for this and similar?
local Edition = A['Edition'];
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}); -- add error message
local PublicationPlace = A['PublicationPlace']
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
local Place = A['Place'];
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
local PublisherName = A['PublisherName'];
ScriptChapter = ScriptTitle;
local RegistrationRequired = A['RegistrationRequired'];
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
ChapterLink = TitleLink; -- alias |episode-link=
RegistrationRequired=nil;
TransChapter = TransTitle;
end
ChapterURL = URL;
local SubscriptionRequired = A['SubscriptionRequired'];
ChapterUrlAccess = UrlAccess;
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
ChapterURL_origin = URL_origin;
SubscriptionRequired=nil;
ChapterFormat = Format;
end


Title = Series; -- promote series to title
local Via = A['Via'];
TitleLink = SeriesLink;
local AccessDate = A['AccessDate'];
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
local ArchiveDate = A['ArchiveDate'];
local Agency = A['Agency'];
local DeadURL = A['DeadURL']
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
DeadURL = ''; -- anything else, set to empty string
end


if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
local Language = A['Language'];
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
local Format = A['Format'];
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
local ChapterFormat = A['ChapterFormat'];
Series = utilities.make_wikilink (ChapterLink, Series);
local DoiBroken = A['DoiBroken'];
end
local ID = A['ID'];
URL = ''; -- unset
local ASINTLD = A['ASINTLD'];
TransTitle = '';
local IgnoreISBN = A['IgnoreISBN'];
ScriptTitle = '';
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
Format = '';
IgnoreISBN = nil; -- anything else, set to empty string
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
local TitleType = A['TitleType'];
local Degree = A['Degree'];
if utilities.in_array (config.CitationClass, {'AV-media-notes', 'interview', 'mailinglist', 'map', 'podcast', 'pressrelease', 'report', 'speech', '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
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier


if utilities.is_set (TitleType) then -- if type parameter is specified
local ID_list = extract_ids( args );
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 Quote = A['Quote'];
local Date = A['Date'];
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
local PublicationDate = A['PublicationDate'];
local Year = A['Year'];


if not utilities.is_set (Date) then
local LayFormat = A['LayFormat'];
Date = Year; -- promote Year to Date
local LayURL = A['LayURL'];
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
local LaySource = A['LaySource'];
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
local Transcript = A['Transcript'];
Date = PublicationDate; -- promote PublicationDate to Date
local TranscriptFormat = A['TranscriptFormat'];
PublicationDate = ''; -- unset, no longer needed
local TranscriptURL = A['TranscriptURL']
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
else
 
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
end
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
no_tracking_cats = nil; -- set to empty string
end
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
--these are used by cite interview
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];


--[[
--local variables that are not cs1 parameters
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
local use_lowercase; -- controls capitalization of certain static text
we get the date used in the metadata.
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local anchor_year; -- used in the CITEREF identifier
Date validation supporting code is in Module:Citation/CS1/Date_validation
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
]]


local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
if not utilities.is_set (DF) then
local Mode = A['Mode'];
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text


local ArchiveURL;
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
local ArchiveDate;
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
local ArchiveFormat = A['ArchiveFormat'];
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
break; -- bail out if one is found
end
end
end


ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL


local NoPP = A['NoPP']  
local AccessDate = A['AccessDate'];
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
local LayDate = A['LayDate'];
NoPP = true;
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
else
local DoiBroken = A['DoiBroken'];
NoPP = nil; -- unset, used as a flag later
local Embargo = A['Embargo'];
end
local anchor_year; -- used in the CITEREF identifier
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 is_set(Page) then
if COinS_date.inter_cal_cat then
if is_set(Pages) or is_set(At) then
utilities.add_prop_cat ('jul-greg-uncertainty');
Pages = ''; -- unset the others
At = '';
end
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
 
elseif is_set(Pages) then
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
if is_set(At) then
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
At = ''; -- unset
end
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
if 0 == #error_list then -- error free dates only; 0 when error_list is empty
end
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
-- both |publication-place= and |place= (|location=) allowed if different
modified = true;
if not is_set(PublicationPlace) and is_set(Place) then
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
end
-- for those wikis that can and want to have English date names translated to the local language; not supported at en.wiki
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
if cfg.date_name_auto_xlate_enable and validation.date_name_xlate (date_parameters_list, cfg.date_digit_auto_xlate_enable ) then
utilities.set_message ('maint_date_auto_xlated'); -- add maint cat
--[[
modified = true;
Parameter remapping for cite encyclopedia:
end
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title


if modified then -- if the date_parameters_list values were modified
|trans_title maps to |trans_chapter when |title is re-mapped
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
|url maps to |chapterurl when |title is remapped
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
utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}); -- add this error message
end
end -- end of do


local ID_list = {}; -- sequence table of rendered identifiers
All other combinations of |encyclopedia, |title, and |article are not modified
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
local Class = A['Class']; -- arxiv class identifier
local ID_support = {
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')},
}


ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
]]


-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
local Encyclopedia = A['Encyclopedia'];
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
utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message
end


Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
if is_set(Title) or is_set (ScriptTitle) then
if not is_set(Chapter) then
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
ScriptChapter = ScriptTitle;
TransChapter = TransTitle;
ChapterURL = URL;
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
end
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset
TransTitle = '';
URL = '';
Format = '';
TitleLink = '';
ScriptTitle = '';
end
else -- |title not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Periodical = ''; -- redundant so unset
end
end
end
end


-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
if not is_set(ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
end
end
end


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
-- special case for cite interview
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
if (config.CitationClass == "interview") then
if identifiers.auto_link_urls[auto_select] then -- manual selection
if is_set(Program) then
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
ID = ' ' .. Program;
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=
end
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
if is_set(Callsign) then
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
if is_set(ID) then
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=
ID = ID .. sepc .. ' ' .. Callsign;
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
else
URL = identifiers.auto_link_urls['doi'];
ID = ' ' .. Callsign;
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
end
end
end
 
if is_set(City) then
if utilities.is_set (URL) then -- set when using an identifier-created URL
if is_set(ID) then
if utilities.is_set (AccessDate) then -- |access-date= requires |url=; identifier-created URL is not |url=
ID = ID .. sepc .. ' ' .. City;
utilities.set_message ('err_accessdate_missing_url'); -- add an error message
else
AccessDate = ''; -- unset
ID = ' ' .. City;
end
end
end


if utilities.is_set (ArchiveURL) then -- |archive-url= requires |url=; identifier-created URL is not |url=
if is_set(Others) then
utilities.set_message ('err_archive_missing_url'); -- add an error message
if is_set(TitleType) then
ArchiveURL = ''; -- unset
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
end
else
Others = '(Interview)';
end
end
end
end


-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- special case for cite mailing list
-- Test if citation has no title
if (config.CitationClass == "mailinglist") then
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
Periodical = A ['MailingList'];
utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'});
elseif 'mailinglist' == A:ORIGIN('Periodical') then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
end


if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
if 'conference' == config.CitationClass then
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
if is_set(BookTitle) then
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Chapter = Title;
Title = ''; -- set title to empty string
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
utilities.set_message ('maint_untitled'); -- add maint cat
ChapterURL = URL;
end
ChapterURLorigin = URLorigin;
 
URLorigin = '';
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
ChapterFormat = Format;
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
TransChapter = TransTitle;
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
Title = BookTitle;
-- is the article title, and Chapter is a section within the article.  So, we remap
Format = '';
-- TitleLink = '';
local coins_chapter = Chapter; -- default assuming that remapping not required
TransTitle = '';
local coins_title = Title; -- et tu
URL = '';
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
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
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
local QuotePage = A['QuotePage'];
local QuotePages = utilities.hyphen_to_dash (A['QuotePages']);


-- this is the function call to COinS()
-- cite map oddities
local OCinSoutput = metadata.COinS({
local Cartography = "";
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
local Scale = "";
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
local Sheet = A['Sheet'] or '';
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic / accept-as-written markup
local Sheets = A['Sheets'] or '';
['Degree'] = Degree; -- cite thesis only
if config.CitationClass == "map" then
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic / accept-as-written markup
Chapter = A['Map'];
['PublicationPlace'] = PublicationPlace,
ChapterURL = A['MapURL'];
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
TransChapter = A['TransMap'];
['Season'] = COinS_date.rftssn,
ChapterURLorigin = A:ORIGIN('MapURL');
['Quarter'] = COinS_date.rftquarter,
ChapterFormat = A['MapFormat'];
['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,
Cartography = A['Cartography'];
['Volume'] = Volume,
if is_set( Cartography ) then
['Issue'] = Issue,
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links
end
['Edition'] = Edition,
Scale = A['Scale'];
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
if is_set( Scale ) then
['URL'] = first_set ({ChapterURL, URL}, 2),
Scale = sepc .. " " .. Scale;
['Authors'] = coins_author,
end
['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
end


-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
local AirDate = A['AirDate'];
end
local SeriesLink = A['SeriesLink'];
 
if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then
local Editors;
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))});
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
end
local Contributors; -- assembled contributors name list
local Network = A['Network'];
local contributor_etal;
local Station = A['Station'];
local Translators; -- assembled translators name list
local s, n = {}, {};
local translator_etal;
-- do common parameters first
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
if is_set(Network) then table.insert(n, Network); end
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
if is_set(Station) then table.insert(n, Station); end
local Interviewers;
ID = table.concat(n, sepc .. ' ');
local interviewers_list = {};
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
local interviewer_etal;
Date = AirDate;
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.
do
local last_first_list;
local control = {
format = NameListStyle, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
mode = Mode
};


do -- do editor name list first because the now unsupported coauthors used to modify control table
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
local Season = A['Season'];
Editors, EditorCount = list_people (control, e, editor_etal);
local SeriesNumber = A['SeriesNumber'];


if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
EditorCount = 2; -- spoof to display (eds.) annotation
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
end
-- assemble a table of parts concatenated later into Series
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
if 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;
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURLorigin = 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 is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
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 is_set (Series) and is_set (SeriesLink) then
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
end
Series = wrap_style ('italic-title', Series); -- series is italicized
end
end
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
if 'arxiv' == config.CitationClass then
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
elseif is_set (Series) then -- series is an alias of version
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
Series = ''; -- unset
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
end
end
do -- now do interviewers
control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal, A:ORIGIN ('DisplayInterviewers'));
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
Interviewers = list_people (control, interviewers_list, interviewer_etal);
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
end
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
do -- now do translators
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators'));
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
Translators = list_people (control, t, translator_etal);
 
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
Chapter = '';
URL = '';
Format = '';
Page = ''; Pages = ''; At = '';
end
end
do -- now do contributors
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
end
Contributors = list_people (control, c, contributor_etal);
 
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
end
end
do -- now do authors
end
control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));


last_first_list = list_people (control, a, author_etal);
if is_set(TitleType) then -- if type parameter is specified
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
end
 
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
if not 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 is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
end
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 and mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date);


if utilities.is_set (Authors) then
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
local mismatch = year_date_check (Year, Date)
if author_etal then
if 0 == mismatch then -- |year= does not match a year-value in |date=
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
if is_set (error_message) then -- if there is already an error message
error_message = error_message .. ', '; -- tack on this additional message
end
end
else
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
Authors = last_first_list; -- either an author name list or an empty string
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
end
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


end
if is_set(error_message) then
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
end -- end of do


local ConferenceFormat = A['ConferenceFormat'];
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
local ConferenceURL = A['ConferenceURL'];
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Embargo = is_embargoed (Embargo); --
Format = style_format (Format, URL, 'format', 'url');


-- special case for chapter format so no error message or cat when chapter not supported
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
if not is_set (Embargo) then -- if not embargoed or embargo has expired
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
end
end
end


if not utilities.is_set (URL) then
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
-- Test if citation has no title
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
if not is_set(Title) and
utilities.set_message ('err_cite_web_url');
not is_set(TransTitle) and
end
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
-- do we have |accessdate= without either |url= or |chapter-url=?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
else
utilities.set_message ('err_accessdate_missing_url');
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
AccessDate = '';
end
end
end
if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
end


local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
check_for_url ({ -- add error message when any of these parameters contains a URL
local OriginalURL
['title']=Title,
local OriginalURL_origin
[A:ORIGIN('Chapter')]=Chapter,
local OriginalFormat
[A:ORIGIN('Periodical')]=Periodical,
local OriginalAccess;
[A:ORIGIN('PublisherName')] = PublisherName,
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
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
ChapterURL = ArchiveURL -- swap-in the archive's URL
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
-- is the article title, and Chapter is a section within the article. So, we remap
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs
end
local coins_chapter = Chapter; -- default assuming that remapping not required
elseif utilities.is_set (URL) then
local coins_title = Title; -- et tu
OriginalURL = URL; -- save copy of original source URL
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
OriginalFormat = Format; -- and original |format=
coins_chapter = Title; -- remap
OriginalAccess = UrlAccess;
coins_title = Periodical;
 
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
elseif utilities.is_set (UrlStatus) then -- if |url-status= is set when |archive-url= is not set
end
utilities.set_message ('maint_url_status'); -- add maint cat
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
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
-- this is the function call to COinS()
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
local OCinSoutput = COinS({
local chap_param;
['Periodical'] = Periodical,
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
['Encyclopedia'] = Encyclopedia,
chap_param = A:ORIGIN ('Chapter')
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
elseif utilities.is_set (TransChapter) then
['Map'] = Map,
chap_param = A:ORIGIN ('TransChapter')
['Degree'] = Degree; -- cite thesis only
elseif utilities.is_set (ChapterURL) then
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
chap_param = A:ORIGIN ('ChapterURL')
['PublicationPlace'] = PublicationPlace,
elseif utilities.is_set (ScriptChapter) then
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
chap_param = ScriptChapter_origin;
['Season'] = COinS_date.rftssn,
else utilities.is_set (ChapterFormat)
['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?
chap_param = A:ORIGIN ('ChapterFormat')
['Series'] = Series,
end
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
 
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
end


if utilities.is_set (chap_param) then -- if we found one
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
utilities.set_message ('err_chapter_ignored', {chap_param}); -- add error message
if 'newsgroup' == config.CitationClass then
Chapter = ''; -- and set them to empty string to be safe with concatenation
if is_set (PublisherName) then
TransChapter = '';
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
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
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 ;
-- Now perform various field substitutions.
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
-- We also add leading spaces and surrounding markup and punctuation to the
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
-- 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 maximum;
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
};
 
do -- do editor name list first because coauthors can modify control table
maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
-- Preserve old-style implicit et al.
if not is_set(maximum) and #e == 4 then  
maximum = 3;
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
end
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
control.maximum = maximum;
local plain_title = false;
local accept_title;
last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
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 "(())"
if is_set (Editors) then
Title = cfg.messages['notitle']; -- replace by predefined "No title" message
if editor_etal then
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
ScriptTitle = ''; -- just mute for now
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
TransTitle = ''; -- just mute for now
else
plain_title = true; -- suppress text decoration for descriptive title
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
utilities.set_message ('maint_untitled'); -- add maint cat
end
end
else
Editors = last_first_list; -- either an author name list or an empty string
end


if not accept_title then -- <Title> not wrapped in accept-as-written markup
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title=
EditorCount = 2; -- spoof to display (eds.) annotation
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
end
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
end
 
do -- now do translators
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
control.maximum = #t; -- number of translators
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
end
end
 
do -- now do contributors
if is_generic ('generic_titles', Title) then
control.maximum = #c; -- number of contributors
utilities.set_message ('err_generic_title'); -- set an error message
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
end
end
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);


if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
control.lastauthoramp = nil;
('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
control.maximum = #a + 1;
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks
end
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
last_first_list = list_people(control, a, author_etal, 'author');
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


if utilities.is_set (TransTitle) then
if is_set (Authors) then
if utilities.is_set (Title) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
TransTitle = " " .. TransTitle;
if author_etal then
else
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
utilities.set_message ('err_trans_missing_title', {'title'});
end
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
utilities.set_message ('err_wikilink_in_url'); -- 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 .. 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;
else
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle;
Authors = last_first_list; -- either an author name list or an empty string
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;
else
Title = Title .. TransTitle;
end
end
end -- end of do
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
else
Title = TransTitle;
end
end


if utilities.is_set (Place) then
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
-- 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 (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
end


local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
if  not is_set(URL) then --and
if utilities.is_set (Conference) then
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
if utilities.is_set (ConferenceURL) then
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
end
-- Test if accessdate is given without giving a URL
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test?
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif utilities.is_set (ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
end
end


local Position = '';
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
if not utilities.is_set (Position) then
DeadURL = DeadURL:lower(); -- used later when assembling archived text
local Minutes = A['Minutes'];
if is_set( ArchiveURL ) then
local Time = A['Time'];
if is_set (URL) then
 
OriginalURL = URL; -- save copy of original source URL
if utilities.is_set (Minutes) then
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
if utilities.is_set (Time) then --TODO: make a function for this and similar?
OriginalFormat = Format; -- and original |format=
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')});
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
end
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
else
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
if utilities.is_set (Time) then
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
local TimeCaption = A['TimeCaption']
OriginalFormat = ChapterFormat; -- and original |format=
if not utilities.is_set (TimeCaption) then
if 'no' ~= DeadURL then
TimeCaption = cfg.messages['event'];
ChapterURL = ArchiveURL -- swap-in the archive's url
if sepc ~= '.' then
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
TimeCaption = TimeCaption:lower();
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end
end
end
else
Position = " " .. Position;
At = '';
end
end


Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
local chap_param;
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
chap_param = A:ORIGIN ('Chapter')
elseif is_set (TransChapter) then
chap_param = A:ORIGIN ('TransChapter')
elseif is_set (ChapterURL) then
chap_param = A:ORIGIN ('ChapterURL')
elseif is_set (ScriptChapter) then
chap_param = A:ORIGIN ('ScriptChapter')
else is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end


At = utilities.is_set (At) and (sepc .. " " .. At) or "";
if is_set (chap_param) then -- if we found one
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
if config.CitationClass == 'map' then
Chapter = ''; -- and set them to empty string to be safe with concatenation
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
TransChapter = '';
local Inset = A['Inset'];
ChapterURL = '';
ScriptChapter = '';
if utilities.is_set ( Inset ) then
ChapterFormat = '';
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
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 ( Sections ) then
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
elseif utilities.is_set ( Section ) then
no_quotes = true; -- then render it unquoted
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
end
end
At = At .. Inset .. Section;
end


local Others = A['Others'];
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
if is_set (Chapter) then
if config.CitationClass == "AV-media-notes"
if 'map' == config.CitationClass and is_set (TitleType) then
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now
Chapter = Chapter .. ' ' .. TitleType;
utilities.set_message ('maint_others_avm')
end
else
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
utilities.set_message ('maint_others');
elseif 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
end
end
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
 
-- Format main title.
if utilities.is_set (Translators) then
if is_set(TitleLink) and is_set(Title) then
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
end
if utilities.is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
end
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap_style ('quoted-title', Title);
local TitleNote = A['TitleNote'];
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
if utilities.is_set (Edition) then
elseif 'report' == config.CitationClass then -- no styling for cite report
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
utilities.set_message ('err_extra_text_edition'); -- add error message
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
end
Edition = " " .. wrap_msg ('edition', Edition);
else
else
Edition = '';
Title = wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = wrap_style ('trans-italic-title', TransTitle);
end
end


Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
TransError = "";
local Agency = A['Agency'];
if is_set(TransTitle) then
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
if is_set(Title) then
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
TransTitle = " " .. TransTitle;
 
else
if utilities.is_set (AccessDate) then
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
local retrv_text = " " .. cfg.messages['retrieved']
end
 
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
end
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
Title = Title .. TransTitle;
local Docket = A['Docket'];
if is_set(Title) then
  if "thesis" == config.CitationClass and utilities.is_set (Docket) then
if not is_set(TitleLink) and is_set(URL) then  
ID = sepc .. " Docket " .. Docket .. ID;
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
end
URL = "";
  if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
Format = "";
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
else
Title = Title .. TransError;
end
end
end


if utilities.is_set (URL) then
if is_set(Place) then
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
end


local Quote = A['Quote'];
if is_set (Conference) then
local TransQuote = A['TransQuote'];
if is_set (ConferenceURL) then
local ScriptQuote = A['ScriptQuote'];
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
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
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
end


Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
if not is_set(Position) then
local Minutes = A['Minutes'];
if utilities.is_set (ScriptQuote) then
local Time = A['Time'];
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 is_set(Minutes) then
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
if is_set (Time) then
TransQuote = TransQuote:sub(2, -2); -- strip them off
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
end
end
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
end
else
 
if is_set(Time) then
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
local TimeCaption = A['TimeCaption']
local quote_prefix = '';
if not is_set(TimeCaption) then
if utilities.is_set (QuotePage) then
TimeCaption = cfg.messages['event'];
extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc.
if sepc ~= '.' then
if not NoPP then
TimeCaption = TimeCaption:lower();
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
end
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
end
elseif utilities.is_set (QuotePages) then
extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc.
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
Position = " " .. TimeCaption .. " " .. Time;
end
end
                       
Quote = quote_prefix .. ": " .. Quote;
else
Quote = sepc .. " " .. Quote;
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 = is_set(At) and (sepc .. " " .. At) or "";
Position = is_set(Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
local Section = A['Section'];
local Sections = A['Sections'];
local Inset = A['Inset'];
if is_set( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
if is_set( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif is_set( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
At = At .. Inset .. Section;
end


PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
if 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;
end
end
Others = is_set(Others) and (sepc .. " " .. Others) or "";
-- We check length of PostScript here because it will have been nuked by
if is_set (Translators) then
-- the quote parameters. We'd otherwise emit a message even if there wasn't
Others = sepc .. ' Translated by ' .. Translators .. Others;
-- a displayed postscript.
-- TODO: Should the max size (1) be configurable?
-- TODO: Should we check a specific pattern?
if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then
utilities.set_message ('maint_postscript')
end
end
 
local Archived;
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if utilities.is_set (ArchiveURL) then
if is_set (Edition) then
local arch_text;
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
if not utilities.is_set (ArchiveDate) then
add_maint_cat ('extra_text', 'edition');
utilities.set_message ('err_archive_missing_date');
ArchiveDate = ''; -- empty string for concatenation
end
end
if "live" == UrlStatus then
Edition = " " .. wrap_msg ('edition', Edition);
arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
if utilities.is_set (ArchiveDate) then
Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'],
{external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } );
else
Archived = '';
end
if not utilities.is_set (OriginalURL) then
utilities.set_message ('err_archive_missing_url');
Archived = ''; -- empty string for concatenation
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
if utilities.is_set (ArchiveDate) then
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
else
Archived = ''; -- unset for concatenation
end
end
else -- OriginalUrl not set
arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
utilities.set_message ('err_archive_missing_url');
Archived = ''; -- empty string for concatenation
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
else
Archived = '';
Edition = '';
end
local Lay = '';
local LaySource = A['LaySource'];
local LayURL = A['LayURL'];
local LayFormat = A['LayFormat'];
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
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
end


local TranscriptURL = A['TranscriptURL']
Series = is_set(Series) and (sepc .. " " .. Series) or "";
local TranscriptFormat = A['TranscriptFormat'];
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
local Transcript = A['Transcript'];
 
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
if utilities.is_set (Transcript) then
 
if utilities.is_set (TranscriptURL) then
------------------------------------ totally unrelated data
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
if is_set(Via) then
end
Via = " " .. wrap_msg ('via', Via);
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
end
end


local Publisher;
--[[
if utilities.is_set (PublicationDate) then
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
PublicationDate = wrap_msg ('published', PublicationDate);
note is displayed. There are no error messages for this condition.
 
]]
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif is_set (RegistrationRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
end
end
if utilities.is_set (PublisherName) then
 
if utilities.is_set (PublicationPlace) then
if is_set(AccessDate) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
local retrv_text = " " .. cfg.messages['retrieved']
else
 
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
end
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
elseif utilities.is_set (PublicationPlace) then
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
-- neither of these work; don't know why; it seems that substitute() isn't being called
else
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
Publisher = PublicationDate;
end
end
local TransPeriodical =  A['TransPeriodical'];
if is_set(ID) then ID = sepc .." ".. ID; end
local TransPeriodical_origin =  A:ORIGIN ('TransPeriodical');
  if "thesis" == config.CitationClass and is_set(Docket) then
-- Several of the above rely upon detecting this as nil, so do it last.
ID = sepc .." Docket ".. Docket .. ID;
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
end
  if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
local Language = A['Language'];
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
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
end


--[[
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
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 = TitleType; -- move TitleType to TitleNote so that it renders ahead of |event=
TitleType = ''; -- and unset


if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
if is_set(URL) then
if utilities.is_set (Conference) then -- and if |event= is set
URL = " " .. external_link( URL, nil, URLorigin );
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
end
end
end


-- Piece all bits together at last.  Here, all should be non-nil.
if is_set(Quote) then
-- We build things this way because it is more efficient in LUA
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
-- not to keep reassigning to the same string variable over and over.
Quote = Quote:sub(2,-2); -- strip them off
 
end
local tcommon;
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
local tcommon2; -- used for book cite when |contributor= is set
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
local Archived
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?
if is_set(ArchiveURL) then
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
if not is_set(ArchiveDate) then
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
ArchiveDate = set_error('archive_missing_date');
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
end
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
if "no" == DeadURL then
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
local arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');  
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if in_array (DeadURL, {'unfit', 'usurped'}) then
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else
else
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
local arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( arch_text,
{ set_error('archive_missing_url'), ArchiveDate } );
end
end
 
elseif is_set (ArchiveFormat) then
elseif 'map' == config.CitationClass then -- special cases for cite map
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
else
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
Archived = ""
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
end
if #ID_list > 0 then
local Lay = '';
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
if is_set(LayURL) then
else
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
ID_list = ID;
if is_set(LaySource) then
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
else
LaySource = "";
end
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
end
elseif 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
end
 
local Via = A['Via'];
if is_set(Transcript) then
Via = utilities.is_set (Via) and  wrap_msg ('via', Via) or '';
if is_set(TranscriptURL) then
local idcommon;
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
end
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc );
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
else
elseif is_set(TranscriptURL) then
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
end
end
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;


local OrigDate = A['OrigDate'];
local Publisher;
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
if is_set(Periodical) and
if utilities.is_set (Date) then
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
if is_set(PublisherName) then
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
if is_set(PublicationPlace) then
else -- neither of authors and editors set
Publisher = PublicationPlace .. ": " .. PublisherName;
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
else
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
Publisher = PublisherName;
end
elseif is_set(PublicationPlace) then
Publisher= PublicationPlace;
else  
Publisher = "";
end
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
else
else
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
Publisher = PublicationDate;
end
end
end
end
end
if is_set(Publisher) then
if utilities.is_set (Authors) then
Publisher = " (" .. Publisher .. ")";
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
end
if utilities.is_set (Editors) then
else
local in_text = " ";
if is_set(PublicationDate) then
local post_text = "";
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
if utilities.is_set (Chapter) and 0 == #c then
end
in_text = in_text .. cfg.messages['in'] .. " "
if is_set(PublisherName) then
if (sepc ~= '.') then
if is_set(PublicationPlace) then
in_text = in_text:lower() -- lowercase for cs2
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
else
post_text = " (" .. cfg.messages['editors'] .. ")";
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
end
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
elseif is_set(PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
end
-- Several of the above rely upon detecting this as nil, so do it last.
if is_set(Periodical) then
if is_set(Title) or is_set(TitleNote) then
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
else
Periodical = wrap_style ('italic-title', Periodical)
end
end
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
end
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
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
if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
]]
end
if "speech" == config.CitationClass then -- cite speech only
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
TitleNote = " (Speech)"; -- annotate the citation
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
if 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
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
end
elseif utilities.is_set (Editors) then
end
if utilities.is_set (Date) then
 
if EditorCount <= 1 then
-- Piece all bits together at last.  Here, all should be non-nil.
Editors = Editors .. ", " .. cfg.messages['editor'];
-- We build things this way because it is more efficient in LUA
else
-- not to keep reassigning to the same string variable over and over.
Editors = Editors .. ", " .. cfg.messages['editors'];
 
end
local tcommon;
local tcommon2; -- used for book cite when |contributor= is set
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
Language, Edition, Publisher, Agency, Volume}, sepc );
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
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
else
if EditorCount <= 1 then
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
 
else
elseif 'map' == config.CitationClass then -- special cases for cite map
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else
elseif is_set (Periodical) then -- map in a periodical
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
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
end
end
elseif 'episode' == config.CitationClass then -- special case for cite episode
if utilities.is_set (PostScript) and PostScript ~= sepc then
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc.
else -- all other CS1 templates
text = text:sub(1, -sepc:len() - 1);
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
end
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
text = safe_join( {text, PostScript}, sepc );
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;


-- Now enclose the whole thing in a <cite> element
if is_set(Date) then
local options_t = {};
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
options_t.class = cite_class_attribute_make (config.CitationClass, Mode);
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
 
else -- neither of authors and editors set
local Ref = is_valid_parameter_value (A['Ref'], A:ORIGIN('Ref'), cfg.keywords_lists['ref'], nil, true); -- nil when |ref=harv; A['Ref'] else
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
 
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
if 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then
else
local namelist_t = {}; -- holds selected contributor, author, editor name list
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
end
 
if #c > 0 then -- if there is a contributor list
namelist_t = c; -- select it
elseif #a > 0 then -- or an author list
namelist_t = a;
elseif #e > 0 then -- or an editor list
namelist_t = e;
end
end
local citeref_id;
end
if #namelist_t > 0 then -- if there are names in namelist_t
if is_set(Authors) then
citeref_id = make_citeref_id (namelist_t, year); -- go make the CITEREF anchor
if is_set(Coauthors) then
if mw.uri.anchorEncode (citeref_id) == ((Ref and mw.uri.anchorEncode (Ref)) or '') then -- Ref may already be encoded (by {{sfnref}}) so citeref_id must be encoded before comparison
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
utilities.set_message ('maint_ref_duplicates_default');
Authors = Authors .. ', ' .. Coauthors;
else
Authors = Authors .. '; ' .. Coauthors;
end
end
else
citeref_id = ''; -- unset
end
end
options_t.id = Ref or citeref_id;
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
end
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
 
if string.len (text:gsub('%b<>', '')) <= 2 then -- remove html and html-like tags; then get length of what remains;
z.error_cats_t = {}; -- blank the categories list
z.error_msgs_t = {}; -- blank the error messages list
OCinSoutput = nil; -- blank the metadata string
text = ''; -- blank the the citation
utilities.set_message ('err_empty_citation'); -- set empty citation message and category
end
local render_t = {}; -- here we collect the final bits for concatenation into the rendered citation
 
if utilities.is_set (options_t.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render_t, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options_t.id), mw.text.nowiki(options_t.class), text})); -- when |ref= is set or when there is a namelist
else
table.insert (render_t, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options_t.class), text})); -- when |ref=none or when namelist_t empty and |ref= is missing or is empty
end
 
if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span
table.insert (render_t, utilities.substitute (cfg.presentation['ocins'], OCinSoutput)); -- format and append metadata to the citation
end
 
local template_name = ('citation' == config.CitationClass) and 'citation' or 'cite ' .. (cfg.citation_class_map_t[config.CitationClass] or config.CitationClass);
local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]';
local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: ';
 
if 0 ~= #z.error_msgs_t then
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, template_link));
 
table.insert (render_t, ' '); -- insert a space between citation and its error messages
table.sort (z.error_msgs_t); -- sort the error messages list; sorting includes wrapping <span> and <code> tags; hidden-error sorts ahead of visible-error
 
local hidden = true; -- presume that the only error messages emited by this template are hidden
for _, v in ipairs (z.error_msgs_t) do -- spin through the list of error messages
if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name
hidden = false; -- found one; so don't hide the error message prefix
break; -- and done because no need to look further
end
end
end
 
if is_set(Editors) then
z.error_msgs_t[1] = table.concat ({utilities.error_comment (msg_prefix, hidden), z.error_msgs_t[1]}); -- add error message prefix to first error message to prevent extraneous punctuation
local in_text = " ";
table.insert (render_t, table.concat (z.error_msgs_t, '; ')); -- make a big string of error messages and add it to the rendering
local post_text = "";
end
if is_set(Chapter) and 0 == #c then
 
in_text = in_text .. cfg.messages['in'] .. " "
if 0 ~= #z.maint_cats_t then
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, template_link));
else
 
if EditorCount <= 1 then
table.sort (z.maint_cats_t); -- sort the maintenance messages list
post_text = ", " .. cfg.messages['editor'];
 
else
local maint_msgs_t = {}; -- here we collect all of the maint messages
post_text = ", " .. cfg.messages['editors'];
 
end
if 0 == #z.error_msgs_t then -- if no error messages
end
table.insert (maint_msgs_t, msg_prefix); -- insert message prefix in maint message livery
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
for _, v in ipairs( z.maint_cats_t ) do -- append maintenance categories
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
table.insert (maint_msgs_t, -- assemble new maint message and add it to the maint_msgs_t table
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
table.concat ({v, ' (', utilities.substitute (cfg.messages[':cat wikilink'], v), ')'})
Authors = by_text .. Authors; -- author follows title so tweak it here
);
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
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
end
table.insert (render_t, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs_t, ' '))); -- wrap the group of maint messages with proper presentation and save
elseif is_set(Editors) then
end
if is_set(Date) then
 
if EditorCount <= 1 then
if not no_tracking_cats then
Editors = Editors .. ", " .. cfg.messages['editor'];
for _, v in ipairs (z.error_cats_t) do -- append error categories
else
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
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
end
for _, v in ipairs (z.maint_cats_t) do -- append maintenance categories
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
else
end
if config.CitationClass=="journal" and is_set(Periodical) then
for _, v in ipairs (z.prop_cats_t) do -- append properties categories
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
else
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
end
end
end
if 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 );


return table.concat (render_t); -- make a big string and done
-- Now enclose the whole thing in a <cite/> element
end
local options = {};
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
options.class = config.CitationClass;
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
else
options.class = "citation";
end
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
if ('harv' == Ref ) then
local namelist = {}; -- holds selected contributor, author, editor name list
-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
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
id = anchor_id (namelist, year); -- go make the CITEREF anchor
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
z.error_categories = {};
text = set_error('empty_citation');
z.message_tail = {};
end
if is_set(options.id) then
text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
else
text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
end


--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
local empty_span = '<span style="display:none;">&nbsp;</span>';
-- Note: Using display: none on the COinS span breaks some clients.
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
text = text .. OCinS;
if #z.message_tail ~= 0 then
text = text .. " ";
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if i == #z.message_tail then
text = text .. error_comment( v[1], v[2] );
else
text = text .. error_comment( v[1] .. "; ", v[2] );
end
end
end
end


Looks for a parameter's name in one of several whitelists.
if #z.maintenance_cats ~= 0 then
 
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
Parameters in the whitelist can have three values:
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
true - active, supported parameters
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
false - deprecated, supported parameters
end
nil - unsupported parameters
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
end
]]
no_tracking_cats = no_tracking_cats:lower();
 
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
local function validate (name, cite_class, empty)
for _, v in ipairs( z.error_categories ) do
local name = tostring (name);
text = text .. '[[Category:' .. v ..']]';
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
end
local state;
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
local function state_test (state, name) -- local function to do testing of state values
text = text .. '[[Category:' .. v ..']]';
if true == state then return true; end -- valid actively supported parameter
if false == state then
if empty then return nil; end -- empty deprecated parameters are treated as unknowns
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
if 'tracked' == state then
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
local base_name = name:gsub ('%d', ''); -- strip enumerators from parameter names that have them to get the base name
text = text .. '[[Category:' .. v ..']]';
utilities.add_prop_cat ('tracked-param', {base_name}, base_name); -- add a properties category; <base_name> modifies <key>
return true;
end
end
return nil;
end
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
return nil;
end
end
return text
end


if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
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
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the first match.
if true == state_test (state, name) then return true; end


-- limited enumerated parameters list
Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
replacement character. That replacement character is not detected by this test though it is visible to readers
state = whitelist.limited_numbered_arguments[enum_name];
of the rendered citation.  This function will detect the replacement character when it is part of the wikisource.
if true == state_test (state, name) then return true; end


return false; -- not supported because not found or name is set to nil
Output of this function is an error message that identifies the character or the Unicode group that the character
end -- end limited parameter-set templates
belongs to along with its position in the parameter value.


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
local function has_invisible_chars (param, v)
end -- if here, fall into general validation
local position = '';
local i=1;
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
while cfg.invisible_chars[i] do
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
local char=cfg.invisible_chars[i][1] -- the character or group name
state = whitelist.numbered_arguments[enum_name];
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
if true == state_test (state, name) then return true; end
v = mw.text.unstripNoWiki( v ); -- remove nowiki stripmarkers
 
position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
return false; -- not supported because not found or name is set to nil
if position then
end
table.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('parameter', param), position}, true ) } ); -- add error message
 
return; -- and done with this parameter
 
end
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
i=i+1; -- bump our index
 
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)
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
utilities.set_message ('err_bad_paramlink', parameter); -- emit an error message
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
end
end
return value;
end
end
]]


--[[--------------------------< Z . C I T A T I O N >----------------------------------------------------------


--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
This is used by templates such as {{cite book}} to create the actual citation text.
 
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
parameter that is missing its pipe.  There are two tests made:
{{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
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc.  To prevent false positives XML/HTML
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.


]]
]]


local function missing_pipe_check (parameter, value)
function z.citation(frame)
local capture;
local pframe = frame:getParent()
value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc.
local validation;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ...
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code


capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
else -- otherwise
if capture and validate (capture) then -- if the capture is a valid parameter name
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...
utilities.set_message ('err_missing_pipe', parameter);
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code
end
end
end


dates = validation.dates; -- imported functions
year_date_check = validation.year_date_check;


--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
local args = {};
local suggestions = {};
local error_text, error_state;


look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
local config = {};
for k, v in pairs( frame.args ) do
config[k] = v;
args[k] = v;  
end


]]
local capture; -- the single supported capture when matching unknown parameters using patterns
 
for k, v in pairs( pframe.args ) do
local function has_extraneous_punc (param, value)
if v ~= '' then
if 'number' == type (param) then
if not validate( k ) then
return;
error_text = "";
end
if type( k ) ~= 'string' then
-- Exclude empty numbered parameters
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
if v:match("%S+") ~= nil then
if cfg.punct_skip[param] then
error_text, error_state = set_error( 'text_ignored', {v}, true );
return; -- parameter name found in the skip table so done
end
end
elseif validate( k:lower() ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
if value:match ('[,;:]$') then
else
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
end
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
if value:match ('^=') then -- sometimes an extraneous '=' character appears ...
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
else
end
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
end
end
 
end
 
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
--[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------
capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match
 
if capture then -- if the pattern matches
look for extraneous url parameter values; parameters listed in skip table are not checked
param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)
 
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message
]]
end
 
end
local function has_extraneous_url (url_param_t)
if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion?
local url_error_t = {};
if suggestions.suggestions[ k:lower() ] ~= nil then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
check_for_url (url_param_t, url_error_t); -- extraneous url check
else
if 0 ~= #url_error_t then -- non-zero when there are errors
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
table.sort (url_error_t);
end
utilities.set_message ('err_param_has_ext_link', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message
end
end
end  
end
if error_text ~= '' then
 
table.insert( z.message_tail, {error_text, error_state} );
 
end
--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
 
This is used by templates such as {{cite book}} to create the actual citation text.
 
]]
 
local function citation(frame)
Frame = frame; -- save a copy in case we need to display an error message in preview mode
local sandbox = '/sandbox' -- i18n: replace this rvalue with the name that your wiki uses to identify sandbox subpages
is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true); -- is this invoke the sandbox module?
sandbox = is_sandbox and sandbox or ''; -- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else
 
local pframe = frame:getParent()
local styles;
cfg = mw.loadData ('Module:Citation/CS1/Configuration' .. sandbox); -- load sandbox versions of support modules when {{#invoke:Citation/CS1/sandbox|...}}; live modules else
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';
   
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
 
is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}'));
 
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; -- used as a flag
 
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
end
if not validate( k, config.CitationClass ) then
args[k] = v;
if type (k) ~= 'string' then -- exclude empty numbered parameters
elseif args[k] ~= nil or (k == 'postscript') then
if v:match("%S+") ~= nil then
args[k] = v;
error_text = utilities.set_message ('err_text_ignored', {v});
end
end
elseif validate (k:lower(), config.CitationClass) then
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, k:lower()}); -- 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 is_sandbox 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 = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message
else
error_text = utilities.set_message ('err_parameter_ignored', {k}); -- 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 explicit suggestion?
if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
utilities.set_message ('err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]});
else
utilities.set_message ('err_parameter_ignored', {k});
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
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
end
if 0 ~= #empty_unknowns then -- create empty unknown error message
utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
});
end
local url_param_t = {};


for k, v in pairs( args ) do
for k, v in pairs( args ) do
if 'string' == type (k) then -- don't evaluate positional parameters
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v); -- look for invisible characters
has_invisible_chars (k, v);
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
 
if 'string' == type (k) and not cfg.url_skip[k] then -- when parameter k is not positional and not in url skip table
url_param_t[k] = v; -- make a parameter/value list for extraneous url check
end
end
end
end
 
return citation0( config, args)
has_extraneous_url (url_param_t); -- look for url in parameter values where a url does not belong
 
return table.concat ({
frame:extensionTag ('templatestyles', '', {src=styles}),
citation0( config, args)
});
end
end


 
return z
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
]]
 
return {citation = citation};
Retrieved from "https://en.churchofgod.wiki/Special:MobileDiff/391"

Navigation menu