Module:Citation/CS1: Difference between revisions

Synch from sandbox;
m>Trappist the monk
m (is_parameter_ext_wikilink() fix;)
m>Trappist the monk
(Synch from sandbox;)
Line 1: Line 1:


local z = {
local cs1 ={};
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 >--------------------------------------
--[[--------------------------< 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 cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local dates, year_date_check, reformat_dates -- functions in Module:Citation/CS1/Date_validation
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist


--[[--------------------------< I S _ S E T >------------------------------------------------------------------
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
add_maint_cat, wrap_style, safe_for_italics, remove_wiki_link;


Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
local z ={}; -- tables in Module:Citation/CS1/Utilities
This function is global because it is called from both this module and from Date validation


]]
local extract_ids, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
function is_set( var )
 
return not (var == nil or var == '');
local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS
end
 
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


--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Line 46: Line 40:
end
end


--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------


Whether needle is in haystack
Adds a category to z.properties_cats using names from the configuration file with additional text if any.


]]
]]


local function in_array( needle, haystack )
local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
if needle == nil then
local function add_prop_cat (key, arguments)
return false;
if not added_prop_cats [key] then
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
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 >----------------------------------------------------------
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------


Populates numbered arguments in a message string using an argument table.
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.


]]
]]


local function substitute( msg, args )
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
local function add_vanc_error ()
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
end
end
end


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


Wraps error messages with css markup according to the state of hidden.
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
 
does this thing that purports to be a uri scheme seem to be a valid scheme?  The scheme is checked to see if it
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
Scheme names consist of a sequence of characters beginning with a
  letter and followed by any combination of letters, digits, plus
  ("+"), period ("."), or hyphen ("-").
 
returns true if it does, else false


]]
]]
local function error_comment( content, hidden )
 
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
local function is_scheme (scheme)
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
end
end


--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------


Sets an error condition and returns the appropriate error message.  The actual placement of the error message in the output is
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
the responsibility of the calling function.


]]
Does this thing that purports to be a domain name seem to be a valid domain name?
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


--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
BNF defined here: https://tools.ietf.org/html/rfc4234
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
see also [[Single-letter second-level domain]]
list of tlds: https://www.iana.org/domains/root/db


Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between
To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.
the first and last characters the name may use letters, digits, and the hyphen.


]]
Also allowed are IPv4 addresses. IPv6 not supported


local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats
domain is expected to be stripped of any path so that the last character in the last character of the tld. tld
local function add_maint_cat (key, arguments)
is two or more alpha characters.  Any preceding '//' (from splitting a url with a scheme) will be stripped
if not added_maint_cats [key] then
here.  Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
added_maint_cats [key] = true; -- note that we've added this category
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
end
end


--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
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


Adds a category to z.properties_cats using names from the configuration file with additional text if any.
returns true if domain appears to be a proper name and tld or IPv4 address, else false


]]
]=]


local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
local function is_domain_name (domain)
local function add_prop_cat (key, arguments)
if not domain then
if not added_prop_cats [key] then
return false; -- if not set, abandon
added_prop_cats [key] = true; -- note that we've added this category
end
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
return false;
end
-- Do most common case first
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then     -- three or more character hostname.hostname or hostname.tld
return true;
elseif domain:match ('%f[%a%d][%a%d]%.org$') 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 ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
end
end
end
end


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


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




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


does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it
When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
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
Strip off any port and path;


]]
]]


local function is_scheme (scheme)
local function split_url (url_str)
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
local scheme, authority, domain;
end
url_str = url_str:gsub ('([%a%d])%.?/.*$', '%1'); -- strip FQDN terminator and path (the capture prevents false replacement of '//')


if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
domain = url_str:match ('^//(%S*)')
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
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
return scheme; -- return scheme only making domain nil which will cause an error message
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
end
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------


--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
 
Does this thing that purports to be a domain name seem to be a valid domain name?


Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
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;
except the underscore which is used as a space in wiki urls and # which is used for section links
see also [[Single-letter second-level domain]]
list of tlds: https://www.iana.org/domains/root/db


rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
returns false when the value contains any of these characters.
the first and last characters the name may use letters, digits, and the hyphen.


Also allowed are IPv4 addresses. IPv6 not supported
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).


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.


There are several tests:
local function link_param_ok (value)
the first character of the whole domain name including subdomains must be a letter or a digit
local scheme, domain;
single-letter/digit second-level domains in the .org TLD
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
q, x, and z SL domains in the .com TLD
return false;
i and q SL domains in the .net TLD
end
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)
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
IPv4 dot-decimal address format; TLD not allowed
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.
 
|<title>= may be wikilinked but not when |<param>-link= has a value.  This function emits an error message when
that condition exists


returns true if domain appears to be a proper name and tld or IPv4 address, else false
]]


]=]
local function link_title_ok (link, lorig, title, torig)
local orig;


local function is_domain_name (domain)
if is_set (link) then -- don't bother if link doesn't have a value
if not domain then
if not link_param_ok (link) then -- check |<param>-link= markup
return false; -- if not set, abandon
orig = lorig; -- identify the failing link parameter
elseif not link_param_ok (title) then -- check |<title>-link= markup
orig = torig; -- identify the failing link parameter
end
end
end
 
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if is_set (orig) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=;
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
return false;
end
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$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
return true;
elseif domain:match ('%f[%a][iq]%.net$') 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


Determines whether a URL string appears to be valid.


--[[--------------------------< I S _ U R L >------------------------------------------------------------------
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.


returns true if the scheme and domain parts of a url appear to be a valid url; else false.
Because it is different from a standard url, and because this module used external_link() to make external links
 
that work for standard and news: links, we validate newsgroup names hereThe specification for a newsgroup name
This function is the last step in the validation processThis function is separate because there are cases that
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
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 function check_url( url_str )
if is_set (scheme) then -- if scheme is set check it and domain
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
return is_scheme (scheme) and is_domain_name (domain);
return false;
else
return is_domain_name (domain); -- scheme not set when url is protocol relative
end
end
end
local scheme, domain;


scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
if 'news:' == scheme then -- special case for newsgroups
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
end
return is_url (scheme, domain); -- return true if value appears to be a valid url
end


--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
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.


When not protocol relative, get scheme, authority indicator, and domain.  If there is an authority indicator (one
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
or more '/' characters following the scheme's colon), make sure that there are only 2.


]]
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.


local function split_url (url_str)
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls.  The tests that
local scheme, authority, domain;
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]]
url_str = url_str:gsub ('(%a)/.*', '%1'); -- strip path information (the capture prevents false replacement of '//')
is possible as might be [[en://Hus]].


if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
]=]
domain = url_str:match ('^//(%S*)')
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
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
return scheme, domain;
end


local function is_parameter_ext_wikilink (value)
local scheme, domain;


--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
 
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
elseif value:match ('//%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a url
end
 
return is_url (scheme, domain); -- return true if value appears to be a valid url
end


Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
# < > [ ] | { } _
except the underscore which is used as a space in wiki urls and # which is used for section links


returns false when the value contains any of these characters.
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------


When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).


]]
]]


local function link_param_ok (value)
local function check_for_url (parameter_list)
local scheme, domain;
local error_message = '';
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
for k, v in pairs (parameter_list) do -- for each parameter in the list
return false;
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
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
end
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
if is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
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
end




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


Determines whether a URL string appears to be valid.
Escape sequences for content that will be used for URL descriptions
 
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_url( url_str )
local function safe_for_url( str )
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
if str:match( "%[%[.-%]%]" ) ~= nil then  
return false;
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
end
end
local scheme, domain;
 
return str:gsub( '[%[%]\n]', {
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;  
['['] = '&#91;',
return is_url (scheme, domain); -- return true if value appears to be a valid url
[']'] = '&#93;',
['\n'] = ' ' } );
end
end


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


--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
Format an external link with error checking


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
local function external_link( URL, label, source )
find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,
local error_str = "";
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
if not is_set( label ) then
is possible as might be [[en://Hus]].
label = URL;
 
if is_set( source ) then
]=]
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
else
error( cfg.messages["bare_url_no_origin"] );
end
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end
 
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------


local function is_parameter_ext_wikilink (value)
Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
local scheme, domain;
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
parameters in the citation.


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


if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S+).*%]')
local function deprecated_parameter(name)
elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
if not page_in_deprecated_cat then
domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]');
page_in_deprecated_cat = true; -- note that we've added this category
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
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 is_url (scheme, domain); -- return true if value appears to be a valid url
end
end


--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------


--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
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.


loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
Call this function for chapter titles, for website titles, etc; not for book titles.


]]
]]


local function check_for_url (parameter_list)
local function kern_quotes (str)
local error_message = '';
local cap='';
for k, v in pairs (parameter_list) do -- for each parameter in the list
local cap2='';
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
if is_set(error_message) then -- once we've added the first portion of the error message ...
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
error_message=error_message .. ", "; -- ... add a comma space separator
if is_set (cap) then
end
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
end
if is_set (error_message) then -- done looping, if there is an error message, display it
 
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
if is_set (cap) then
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
end
return str;
end
end


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


--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
|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.


Protects a string that will be wrapped in wiki 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.


Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
|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:
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
|script-title=ja:*** *** (where * represents a Japanese character)
poorly under Mediawiki's HTML tidy.
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 ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.
Supports |script-title= and |script-chapter=
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
]]


local function safe_for_italics( str )
local function format_script_value (script_value)
if not is_set(str) then
local lang=''; -- initialize to empty string
return str;
local name;
else
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
if str:sub(1,1) == "'" then str = "<span />" .. str; end
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
if not is_set (lang) then
return ''; -- script_value was just the prefix so return empty string
-- Remove newlines as they break italics.
end
return str:gsub( '\n', ' ' );
-- if we get this far we have prefix and script
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, {'am', 'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ml', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
add_prop_cat ('script')
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
return script_value;
end
end


--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
 
Escape sequences for content that will be used for URL descriptions


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 safe_for_url( str )
local function script_concatenate (title, script)
if str:match( "%[%[.-%]%]" ) ~= nil then  
if is_set (script) then
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
end
return title;
return str:gsub( '[%[%]\n]', {
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
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
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
argument; protects italic styled parameters.  Additional text taken from citation_config.presentation - the reason
 
this function is similar to but separate from wrap_msg().
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
from citation_config.messages - the reason this function is similar to but separate from wrap_style().


]]
]]


local function wrap_style (key, str)
local function wrap_msg (key, str, lower)
if not is_set( str ) then
if not is_set( str ) then
return "";
return "";
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
str = safe_for_italics( str );
end
end
if true == lower then
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return substitute( msg, str ); -- including template text
else
return substitute( cfg.messages[key], str );
end
end


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


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


Format an external link with error checking
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 external_link( URL, label, source )
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local error_str = "";
local chapter_error = '';
if not is_set( label ) then
label = URL;
if not is_set (chapter) then
if is_set( source ) then
chapter = ''; -- to be safe for concatenation
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
else
else
if false == no_quotes then
error( cfg.messages["bare_url_no_origin"] );
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
end
chapter = wrap_style ('quoted-title', chapter);
end
end
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end


--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped


Formats a wiki style external link
if is_set (transchapter) then
 
transchapter = wrap_style ('trans-quoted-title', transchapter);
]]
if is_set (chapter) then
 
chapter = chapter ..  ' ' .. transchapter;
local function external_link_id(options)
else -- here when transchapter without chapter or script-chapter
local url_string = options.id;
chapter = transchapter; --
if options.encode == true or options.encode == nil then
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
url_string = mw.uri.encode( url_string );
end
end
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


--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
end
 
return chapter .. chapter_error;
end


Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
parameters in the citation.


]]
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the
first match.


local page_in_deprecated_cat; -- sticky flag so that the category is added only once
This function will detect the visible replacement character when it is part of the wikisource.
local function deprecated_parameter(name)
if not page_in_deprecated_cat then
page_in_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
end


--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
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().


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.
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
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.


Call this function for chapter titles, for website titles, etc; not for book titles.
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 kern_quotes (str)
local function has_invisible_chars (param, v)
local cap='';
local position = ''; -- position of invisible char or starting position of stripmarker
local cap2='';
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
local capture; -- used by stripmarker detection to hold name of the stripmarker
local i=1;
local stripmarker, apostrophe;
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true
if is_set (cap) then
if capture == v then -- if same there are no unicode characters
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
return;
end
end


cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
while cfg.invisible_chars[i] do
if is_set (cap) then
local char=cfg.invisible_chars[i][1] -- the character or group name
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
end
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
return str;
end
if position then
 
-- 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)
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
 
stripmarker = true; -- set a flag
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
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
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
position = nil; -- unset
in italic markup.
elseif 'apostrophe' == char then -- apostrophe template uses &zwj;, hair space and zero-width space
 
apostrophe = true;
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.
elseif true == apostrophe and in_array (char, {'zero width joiner', 'zero width space', 'hair space'}) then
position = nil; -- unset
else
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
i=i+1; -- bump our index
end
end


|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:*** ***


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
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.


Supports |script-title= and |script-chapter=
Argument wrapper.  This function provides support for argument mapping defined in the configuration file so that
multiple names can be transparently aliased to single internal variable.


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


local function format_script_value (script_value)
local function argument_wrapper( args )
local lang=''; -- initialize to empty string
local origin = {};
local name;
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
return setmetatable({
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
ORIGIN = function( self, k )
if not is_set (lang) then
local dummy = self[k]; --force the variable to be loaded.
return ''; -- script_value was just the prefix so return empty string
return origin[k];
end
end
-- if we get this far we have prefix and script
},
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
{
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
__index = function ( tbl, k )
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
if origin[k] ~= nil then
-- is prefix one of these language codes?
return nil;
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
end
add_prop_cat ('script_with_name', {name, lang})
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
else
add_prop_cat ('script')
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
end
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
-- Empty strings, not nil;
lang = ''; -- invalid so set lang to empty string
if v == nil then
end
v = cfg.defaults[k] or '';
end
origin[k] = '';
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
end
 
return script_value;
tbl = rawset( tbl, k, v );
return v;
end,
});
end
end


--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.


Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
Parameters in the whitelist can have three values:
wrapped in <bdi> tags.
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
]]


local function script_concatenate (title, script)
local function validate( name )
if is_set (script) then
local name = tostring( name );
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
local state = whitelist.basic_arguments[ name ];
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
-- 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
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
return title;
return false; -- Not supported because not found or name is set to nil
end
end




--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
 
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY


Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
DOES NOT yet support MMMM YYYY or any of the date ranges.
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
from citation_config.messages - the reason this function is similar to but separate from wrap_style().


]]
]]


local function wrap_msg (key, str, lower)
local function nowrap_date (date)
if not is_set( str ) then
local cap='';
return "";
local cap2='';
end
 
if true == lower then
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
local msg;
date = substitute (cfg.presentation['nowrap1'], date);
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return substitute( msg, str ); -- including template text
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
else
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
return substitute( cfg.messages[key], str );
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
end
return date;
end
end


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


--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
 
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
provided by the template.
 
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
 
Returns:
value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected
selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected


]]
]]


local function is_alias_used (args, alias, index, enumerated, value, selected, error_list)
local function set_titletype (cite_class, title_type)
if enumerated then -- is this a test for an enumerated parameters?
if is_set(title_type) then
alias = alias:gsub ('#', index); -- replace '#' with the value in index
if "none" == title_type then
else
title_type = ""; -- if |type=none then type parameter not displayed
alias = alias:gsub ('#', ''); -- remove '#' if it exists
end
return title_type; -- if |type= has been set to any other value use that value
end
end


if is_set(args[alias]) then -- alias is in the template's argument list
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
local skip;
for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias
if v == alias then
skip = true;
break; -- has been added so stop looking
end
end
if not skip then -- has not been added so
table.insert( error_list, alias ); -- add error alias to the error list
end
else
value = args[alias]; -- not yet selected an alias, so select this one
selected = alias;
end
end
return value, selected; -- return newly selected alias, or previously selected alias
end
end




--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------


Chooses one matching parameter from a list of parameters to consider.  The list of parameters to consider is just
Converts a hyphen to a dash
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.
 
 
Generates an error if more than one match is present.


]]
]]


local function select_one( args, aliases_list, error_condition, index )
local function hyphen_to_dash( str )
local value = nil; -- the value assigned to the selected parameter
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
local selected = ''; -- the name of the parameter we have chosen
return str;
local error_list = {};
end
 
return str:gsub( '-', '' );
if index ~= nil then index = tostring(index); end
 
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
 
if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
local error_str = "";
for _, k in ipairs( error_list ) do
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
error_str = error_str .. wrap_style ('parameter', k);
end
if #error_list > 1 then
error_str = error_str .. cfg.messages['parameter-final-separator'];
else
error_str = error_str .. cfg.messages['parameter-pair-separator'];
end
error_str = error_str .. wrap_style ('parameter', selected);
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
end
return value, selected;
end
end




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


Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
Joins a sequence of strings together while checking for duplicate separation characters.
parameter (chapter_url_source used for error messages).


]]
]]


local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local function safe_join( tbl, duplicate_char )
local chapter_error = '';
--[[
Note: we use string functions here, rather than ustring functions.
This has considerably faster performance and should work correctly as
long as the duplicate_char is strict ASCII.  The strings
in tbl may be ASCII or UTF8.
]]
if not is_set (chapter) then
local str = ''; -- the output string
chapter = ''; -- to be safe for concatenation
local comp = ''; -- what does 'comp' mean?
else
local end_chr = '';
if false == no_quotes then
local trim;
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
for _, value in ipairs( tbl ) do
chapter = wrap_style ('quoted-title', chapter);
if value == nil then value = ''; end
end
end
if str == '' then -- if output string is empty
 
str = value; -- assign value to it (first time through the loop)
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
elseif value ~= '' then
 
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
if is_set (transchapter) then
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
transchapter = wrap_style ('trans-quoted-title', transchapter);
else
if is_set (chapter) then
comp = value;
chapter = chapter .. ' ' .. transchapter;
end
else -- here when transchapter without chapter or script-chapter
-- typically duplicate_char is sepc
chapter = transchapter; --  
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
--  Because individual string segments often (always?) begin with terminal punct for th
end
--   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
if is_set (chapterurl) then
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
if end_chr == duplicate_char then -- if same as separator
end
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


return chapter .. chapter_error;
if trim then
end
if value ~= comp then -- value does not equal comp when value contains html markup
 
local dup2 = duplicate_char;
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
 
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
first match.
else
value = value:sub( 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 _ G O O D _ V A N C _ N A M E >--------------------------------------------


This function will detect the visible replacement character when it is part of the wikisource.
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.


Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
and identifies them with a slightly different error message. See also coins_cleanup().
[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


Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
|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


Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
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
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
because the code editor gets confused between character insertion point and cursor position.
parameter value.


]]
]]


local function has_invisible_chars (param, v)
local function is_good_vanc_name (last, first)
local position = ''; -- position of invisible char or starting position of stripmarker
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
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
add_vanc_error ();
local capture; -- used by stripmarker detection to hold name of the stripmarker
return false; -- not a string of latin characters; Vancouver required Romanization
local i=1;
end;
local stripmarker, apostrophe;
return true;
end
 
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------


while cfg.invisible_chars[i] do
Attempts to convert names to initials in support of |name-list-format=vanc.
local char=cfg.invisible_chars[i][1] -- the character or group name
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position then
-- 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)
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
stripmarker = true; -- set a flag
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
position = nil; -- unset
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
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
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/.
return; -- and done with this parameter
 
end
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
end
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/.
i=i+1; -- bump our index
 
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
 
]]
 
local function reduce_to_initials(first)
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
local initials = {}
local i = 0; -- counter for number of initials
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
end
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
end


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


--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
Formats a list of people (e.g. authors / editors)
 
Argument wrapper. This function provides support for argument mapping defined in the configuration file so that
multiple names can be transparently aliased to single internal variable.


]]
]]


local function argument_wrapper( args )
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
local origin = {};
local sep;
local namesep;
return setmetatable({
local format = control.format
ORIGIN = function( self, k )
local maximum = control.maximum
local dummy = self[k]; --force the variable to be loaded.
local lastauthoramp = control.lastauthoramp;
return origin[k];
local text = {}
end
 
},
if 'vanc' == format then -- Vancouver-like author/editor name styling?
{
sep = ','; -- name-list separator between authors is a comma
__index = function ( tbl, k )
namesep = ' '; -- last/first separator is a space
if origin[k] ~= nil then
else
return nil;
sep = ';' -- name-list separator between authors is a semicolon
end
namesep = ', ' -- last/first separator is <comma><space>
end
local args, list, v = args, cfg.aliases[k];
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if type( list ) == 'table' then
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
v, origin[k] = select_one( args, list, 'redundant_parameters' );
if origin[k] == nil then
for i,person in ipairs(people) do
origin[k] = ''; -- Empty string, not nil
if is_set(person.last) then
end
local mask = person.mask
elseif list ~= nil then
local one
v, origin[k] = args[list], list;
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
else
-- maybe let through instead of raising an error?
one = person.last
-- v, origin[k] = args[k], k;
local first = person.first
error( cfg.messages['unknown_argument_map'] );
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
end
table.insert( text, one )
-- Empty strings, not nil;
table.insert( text, sep_one )
if v == nil then
end
v = cfg.defaults[k] or '';
end
origin[k] = '';
 
end
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
tbl = rawset( tbl, k, v );
if count > 1 and is_set(lastauthoramp) and not etal then
return v;
text[#text-2] = " & "; -- replace last separator with ampersand text
end,
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


--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
Looks for a parameter's name in the whitelist.
 
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.


Parameters in the whitelist can have three values:
namelist is one of the contributor-, author-, or editor-name lists chosen in that order.  year is Year or anchor_year.
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]


local function validate( name )
]]
local name = tostring( name );
local function anchor_id (namelist, year)
local state = whitelist.basic_arguments[ name ];
local names={}; -- a table for the one to four names and year
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
-- Normal arguments
names[i] = v.last
if true == state then return true; end -- valid actively supported parameter
if i == 4 then break end -- if four then done
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
table.insert (names, year); -- add the year at the end
-- Arguments with numbers in them
local id = table.concat(names); -- concatenate names and year for CITEREF id
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
if is_set (id) then -- if concatenation is not an empty string
state = whitelist.numbered_arguments[ name ];
return "CITEREF" .. id; -- add the CITEREF portion
if true == state then return true; end -- valid actively supported parameter
else
if false == state then
return ''; -- return an empty string; no reason to include CITEREF id in this citation
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
return false; -- Not supported because not found or name is set to nil
end
end




-- Formats a wiki style internal link
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
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


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.


--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal


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.
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 nowrap_date (date)
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
local cap='';
local cap2='';
if name:match (etal_pattern) then -- variants on et al.
 
name = name:gsub (etal_pattern, ''); -- if found, remove
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
date = substitute (cfg.presentation['nowrap1'], date);
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
end
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
end
return name, etal; --
return date;
end
end


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


ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
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,
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
spaces and other non-isxn characters.
find |last4= and |last5= then the search is done.


]]
This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.


local function is_valid_isxn (isxn_str, len)
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
local temp = 0;
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/ConfigurationThis keeps 'et al.' out of the  
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
template's metadata. When this occurs, the page is added to a maintenance category.
len = len+1; -- adjust to be a loop counter
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
temp = temp + 10*( len - i ); -- it represents 10 decimal
else
temp = temp + tonumber( string.char(v) )*(len-i);
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
end
 
 
--[[--------------------------< 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.


]]
]]


local function is_valid_isxn_13 (isxn_str)
local function extract_names(args, list_name)
local temp=0;
local names = {}; -- table of names
local last; -- individual name components
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
local first;
for i, v in ipairs( isxn_str ) do
local link;
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
local mask;
end
local i = 1; -- loop counter/indexer
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
local n = 1; -- output table indexer
end
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


--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
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 );


Determines whether an ISBN string is valid
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.


]]
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_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?
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
link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup


local function check_isbn( isbn_str )
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
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
n = n + 1; -- point to next location in the names table
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
if 1 == count then -- if the previous name was missing
local len = isbn_str:len();
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
end
if len ~= 10 and len ~= 13 then
count = 0; -- reset the counter, we're looking for two consecutive missing names
return false;
end
end
i = i + 1; -- point to next args location
 
if len == 10 then
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
return is_valid_isxn(isbn_str, 10);
else
local temp = 0;
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
return is_valid_isxn_13 (isbn_str);
end
end
return names, etal; -- all done, return our list of names
end
end


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


Determines whether an ISMN string is validSimilar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
Validates language names provided in |language= parameter if not an ISO639-1 codeHandles the special case that is Norwegian where
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
section 2, pages 9–12.


]]
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.


local function ismn (id)
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
local handler = cfg.id_handlers['ISMN'];
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
local text;
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
local valid_ismn = true;
returns only the Wikimedia language name.


id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn
Adapted from code taken from Module:Check ISO 639-1.


if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
]]
valid_ismn = false;
 
else
local function get_iso639_code (lang)
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
end
end
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet
if false == valid_ismn then
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
end
return text;
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() 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
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
end


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


Validate and format an issnThis code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
Get language name from ISO639-1 code value providedIf a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
digits with a space. When that condition occurred, the resulting link looked like this:


|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
There is an exceptionThere are three ISO639-1 codes for Norewegian language variantsThere are two official variants: Norwegian Bokmål (code 'nb') and
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
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
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.
with the calculated valueIncorrect 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.


]]
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 issn(id)
See Help talk:Citation Style_1#An ISO 639-1 language name test
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
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.


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
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.
valid_issn=false; -- wrong length or improper character
else
valid_issn=is_valid_isxn(id, 8); -- validate issn
end


if true == valid_issn then
]]
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
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


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


Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
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.


]]
for _, lang in ipairs (names_table) do -- reuse lang


local function amazon(id, domain)
if lang:match ('^%a%a%-') then -- strip ietf language tags from code
local err_cat = ""
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
 
end
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") 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
if not is_set(domain) then
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
local handler = cfg.id_handlers['ASIN'];
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
--[[--------------------------< A R X I V >--------------------------------------------------------------------
See: http://arxiv.org/help/arxiv_identifier
format and error check arXiv identifier.  There are three valid forms of the identifier:
the first form, valid only between date codes 9108 and 0703 is:
arXiv:<archive>.<class>/<date code><number><version>
where:
<archive> is a string of alpha characters - may be hyphenated; no other punctuation
<class> is a string of alpha characters - may be hyphenated; no other punctuation
<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:
if is_set (name) then -- if Language specified a valid ISO639-1 code
arXiv:<date code>.<number><version>
code = lang:lower(); -- save it
where:
else
<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
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
<number> is a four-digit number
end
<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 arxiv (id, class)
local handler = cfg.id_handlers['ARXIV'];
local year, month, version;
local err_cat = '';
local text;
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
if is_set (code) then
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
year = tonumber(year);
if 'en' ~= code then -- English not the language
month = tonumber(month);
add_prop_cat ('foreign_lang_source', {name, code})
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
end
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
table.insert (language_list, name);
year = tonumber(year);
name = ''; -- so we can reuse it
month = tonumber(month);
end
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)?
code = #language_list -- reuse code as number of languages in the list
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
if 2 >= code then
end
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
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
elseif 2 < code then
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
year = tonumber(year);
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
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
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
end
 
if 'English' == name then
text = external_link_id({link = handler.link, label = handler.label,
return ''; -- if one language and that language is English return an empty string (no annotation)
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
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
return text .. class;
end
end


--[[
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
 
1. Remove all blanks.
Set style settings for CS1 citation templates. Returns separator and postscript settings
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.


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)
local function set_cs1_style (ps)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
if not is_set (ps) then -- unless explicitely set to something
 
ps = '.'; -- terminate the rendered citation with a period
if nil ~= string.find (lccn,'/') then
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end
end
return '.', ps; -- separator is a full stop
end
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings


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
local function set_cs2_style (ps, ref)
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
lccn=prefix..suffix; -- reassemble the lccn
ps = ''; -- make sure it isn't nil
end
end
if not is_set (ref) then -- if |ref= is not set
return lccn;
ref = "harv"; -- set default |ref=harv
end
end
return ',', ps, ref; -- separator is a comma
end


--[[
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
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
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/


length = 8 then all digits
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
length = 9 then lccn[1] is lower case alpha
rendered style.
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 lccn(lccn)
local function get_settings_from_cite_class (ps, ref, cite_class)
local handler = cfg.id_handlers['LCCN'];
local sep;
local err_cat =  ''; -- presume that LCCN is valid
if (cite_class == "citation") then -- for citation templates (CS2)
local id = lccn; -- local copy of the lccn
sep, ps, ref = set_cs2_style (ps, ref);
 
else -- not a citation template so CS1
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
sep, ps = set_cs1_style (ps);
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
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
end


if not is_set (err_cat) and nil ~= lccn:find ('%s') then
return sep, ps, ref -- return them all
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
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


--[[
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
Format PMID and do simple error checkingPMIDs 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.
Establish basic style settings to be used when rendering the citationUses |mode= if set and valid or uses
config.CitationClass from the template's #invoke: to establish style.
 
]]
]]


local function pmid(id)
local function set_style (mode, ps, ref, cite_class)
local test_limit = 30000000; -- update this value as PMIDs approach
local sep;
local handler = cfg.id_handlers['PMID'];
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
local err_cat =  ''; -- presume that PMID is valid
sep, ps, ref = set_cs2_style (ps, ref);
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
if id:match("[^%d]") then -- if PMID has anything but digits
sep, ps = set_cs1_style (ps);
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
else -- anything but cs1 or cs2
else -- PMID is only digits
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
local id_num = tonumber(id); -- convert id to a number for range testing
end
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
if 'none' == ps:lower() then -- if assigned value is 'none' then
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
ps = ''; -- set to empty string
end
end
end
return external_link_id({link = handler.link, label = handler.label,
return sep, ps, ref
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
end


--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------


Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
applying the pdf icon to external links.
|embargo= was not set in this cite.


]]
returns true if file extension is one of the recognized extension, else false
 
]=]


local function is_embargoed (embargo)
local function is_pdf (url)
if is_set (embargo) then
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
local lang = mw.getContentLanguage();
local good1, embargo_date, good2, todays_date;
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
if good1 and good2 then -- if embargo date and today's date are good dates
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
return embargo; -- still embargoed
else
add_maint_cat ('embargo')
return ''; -- unset because embargo has expired
end
end
end
return ''; -- |embargo= not set return empty string
end
end


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


Format a PMC, do simple error checking, and check for embargoed articles.
Applies css style to |format=, |chapter-format=, etcAlso emits an error message if the format parameter does
 
not have a matching url parameterIf the format parameter is not set and the url contains a file extension that
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
be linked to the articleIf the embargo date is today or in the past, or if it is empty or omitted, then the
the appropriate styling.
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
 
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC linkFunction is_embargoed ()
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
 
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
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.


]]
]]


local function pmc(id, embargo)
local function style_format (format, url, fmt_param, url_param)
local test_limit = 5000000; -- update this value as PMCs approach
if is_set (format) then
local handler = cfg.id_handlers['PMC'];
format = wrap_style ('format', format); -- add leading space, parenthases, resize
local err_cat =  ''; -- presume that PMC is valid
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
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
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
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
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
format = ''; -- empty string for concatenation
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
end
return text;
return format;
end
end


-- Formats a DOI and checks for DOI errors.
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------


-- DOI names contain two parts: prefix and suffix separated by a forward slash.
Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag
--  Prefix: directory indicator '10.' followed by a registrant code
to indicate when et al. should be appended to the name list.
--  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,
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
some variant of the text 'et al.').


-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
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.'


local function doi(id, inactive)
In all other cases, returns nil and the previous state of the 'etal' flag.
local cat = ""
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


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
inputs:
cat = ' ' .. set_error( 'bad_doi' );
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
end
count: #a or #e
return text .. inactive .. cat
list_name: 'authors' or 'editors'
end
etal: author_etal or editor_etal
 
 
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
 
Formats an OpenLibrary link, and checks for associated errors.


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


if ( code == "A" ) then
local function get_display_authors_editors (max, count, list_name, etal)
return external_link_id({link=handler.link, label=handler.label,
if is_set (max) then
prefix=handler.prefix .. 'authors/OL',
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
id=id, separator=handler.separator, encode = handler.encode})
max = count + 1; -- number of authors + 1 so display all author name plus et al.
elseif ( code == "M" ) then
etal = true; -- overrides value set by extract_names()
return external_link_id({link=handler.link, label=handler.label,
elseif max:match ('^%d+$') then -- if is a string of numbers
prefix=handler.prefix .. 'books/OL',
max = tonumber (max); -- make it a number
id=id, separator=handler.separator, encode = handler.encode})
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
elseif ( code == "W" ) then
add_maint_cat ('disp_auth_ed', list_name);
return external_link_id({link=handler.link, label=handler.label,
end
prefix=handler.prefix .. 'works/OL',
else -- not a valid keyword or number
id=id, separator=handler.separator, encode = handler.encode})
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
else
max = nil; -- unset; as if |display-xxxxors= had not been set
return external_link_id({link=handler.link, label=handler.label,
end
prefix=handler.prefix .. 'OL',
id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' );
end
end
return max, etal;
end
end


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


--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
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.


Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
'<' and/or '>' angle brackets.
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP


]]
]]


local function message_id (id)
local function extra_text_in_page_check (page)
local handler = cfg.id_handlers['USENETID'];
-- 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]';


text = external_link_id({link = handler.link, label = handler.label,
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
add_maint_cat ('extra_text');
end
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
end  
-- add_maint_cat ('extra_text');
-- end
return text
end
end


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


This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).


]]
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.


local function set_titletype (cite_class, title_type)
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
if is_set(title_type) then
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
if "none" == title_type then
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
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 sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
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


]]
]]


local function clean_isbn( isbn_str )
local function parse_vauthors_veditors (args, vparam, list_name)
return isbn_str:gsub( "[^-0-9X]", "" );
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
end
local v_name_table = {};
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask;
local corporate = false;


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


Returns a string where all of lua's magic characters have been escaped. This is important because functions like
for i, v_name in ipairs(v_name_table) do
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
]]
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
local function escape_lua_magic_chars (argument)
last = v_name:match ('^%(%((.+)%)%)$')
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
corporate = true;
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
elseif string.find(v_name, "%s") then
return argument;
local lastfirstTable = {}
end
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
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
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
-- 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
return names, etal; -- all done, return our list of names
end


Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.


]]
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.


local function strip_apostrophe_markup (argument)
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
if not is_set (argument) then return argument; end
similarly, |editorn= (and aliases) highest and |editors= lowest


while true do
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
way to do this, I just haven't discovered what that way is.
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
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


--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
Emits an error message when more than one xxxxor name source is provided.


Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.


Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
of %27%27...
]]
]]


local function make_coins_title (title, script)
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
if is_set (title) then
local lastfirst = false;
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
else
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
title=''; -- if not set, make sure title is an empty string
lastfirst=true;
end
end
if is_set (script) then
 
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
(is_set (vxxxxors) and is_set (xxxxors)) or
else
(true == lastfirst and is_set (xxxxors)) then
script=''; -- if not set, make sure script is an empty string
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
end
if is_set (title) and is_set (script) then
 
script = ' ' .. script; -- add a space before we concatenate
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
end
if is_set (vxxxxors) then return 2 end;
return title .. script; -- return the concatenation
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
end


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


Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
 
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.


]]
]]


local function get_coins_pages (pages)
local function is_valid_parameter_value (value, name, possible)
local pattern;
if not is_set (value) then
if not is_set (pages) then return pages; end -- if no page numbers then we're done
return true; -- an empty parameter is ok
elseif in_array(value:lower(), possible) then
while true do
return true;
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
else
if nil == pattern then break; end -- no more urls
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
return false
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
end


-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
 
local function remove_wiki_link( str )
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
 
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
end));
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 function terminate_name_list (name_list, sepc)
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
return name_list .. sepc .. ' '; -- otherwise terninate the name list
end
end
end


-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end


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


Joins a sequence of strings together while checking for duplicate separation characters.
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 safe_join( tbl, duplicate_char )
--[[
Note: we use string functions here, rather than ustring functions.
This has considerably faster performance and should work correctly as
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
long as the duplicate_char is strict ASCII.  The strings
if not is_set (volume) and not is_set (issue) then
in tbl may be ASCII or UTF8.
return '';
]]
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
local str = ''; -- the output string
local vol = '';
local comp = ''; -- what does 'comp' mean?
local end_chr = '';
local trim;
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then -- if output string is empty
if is_set (volume) then
str = value; -- assign value to it (first time through the loop)
if (4 < mw.ustring.len(volume)) then
elseif value ~= '' then
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
else
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
else
end
comp = value;
end
end
if is_set (issue) then
-- typically duplicate_char is sepc
return vol .. substitute (cfg.messages['j-issue'], issue);
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
end
--  Because individual string segments often (always?) begin with terminal punct for th
return vol;
--  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
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
value = value:sub( 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 _ G O O D _ V A N C _ N A M E >--------------------------------------------


For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.


This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
[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/)
not currently used
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods


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
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
because the code editor gets confused between character insertion point and cursor position.
returns list unchanged if there are no commas else strips whitespace and then reformats the list


]]
--[[
local function normalize_page_list (list)
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
list = table.concat (list, ', '); -- and now make a normalized list
return list;
end
]]
]]


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


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


Attempts to convert names to initials in support of |name-list-format=vanc.
Singular has priority over plural when both are provided.


Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
]]


Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
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/.
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
else
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif 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


This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);


]]
if is_set (page) then
 
if is_journal then
local function reduce_to_initials(first)
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
elseif not nopp then
local initials = {}
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
local i = 0; -- counter for number of initials
else
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
end
i = i + 1; -- bump the counter
elseif is_set(pages) then
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
if is_journal then
return 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 '', 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
return table.concat(initials) -- Vancouver format does not include spaces.
return '', '', '', ''; -- return empty strings
end
end


--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------


Formats a list of people (e.g. authors / editors)
This is the main function doing the majority of the citation formatting.


]]
]]


local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
local function citation0( config, args)
local sep;
--[[
local namesep;
Load Input Parameters
local format = control.format
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
local maximum = control.maximum
]]
local lastauthoramp = control.lastauthoramp;
local A = argument_wrapper( args );
local text = {}
local i
 
-- 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'];
local Collaboration = A['Collaboration'];


if 'vanc' == format then -- Vancouver-like author/editor name styling?
do -- to limit scope of selected
sep = ','; -- name-list separator between authors is a comma
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
namesep = ' '; -- last/first separator is a space
if 1 == selected then
else
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
sep = ';' -- name-list separator between authors is a semicolon
elseif 2 == selected then
namesep = ', ' -- last/first separator is <comma><space>
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=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
end
if is_set (Collaboration) then
author_etal = true; -- so that |display-authors=etal not required
end
end
end
local Coauthors = A['Coauthors'];
local Others = A['Others'];
local editor_etal;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
local Editors;
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
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local Translators; -- assembled translators name list
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
local Contributors; -- assembled contributors name list
local Contribution = A['Contribution'];
for i,person in ipairs(people) do
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
if is_set(person.last) then
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
local mask = person.mask
local one
if 0 < #c then
local sep_one = sep;
if not is_set (Contribution) then -- |contributor= requires |contribution=
if is_set (maximum) and i > maximum then
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
etal = true;
c = {}; -- blank the contributors' table; it is used as a flag later
break;
end
elseif (mask ~= nil) then
if 0 == #a then -- |contributor= requires |author=
local n = tonumber(mask)
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message
if (n ~= nil) then
c = {}; -- blank the contributors' table; it is used as a flag later
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
end
table.insert( text, one )
table.insert( text, sep_one )
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?
local count = #text / 2; -- (number of names + number of separators) divided by 2
table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message
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
end
text[#text] = nil; -- erase the last separator
Contribution = nil; -- unset
end
end
 
local result = table.concat(text) -- construct list
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
NameListFormat = ''; -- anything else, set to empty string
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
end
end
return result, count
end


--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local Date = A['Date'];
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set


Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.
local Chapter = A['Chapter'];
 
local ScriptChapter = A['ScriptChapter'];
namelist is one of the contributor-, author-, or editor-name lists chosen in that order.  year is Year or anchor_year.
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


]]
local Series = A['Series'];
local function anchor_id (namelist, year)
local names={}; -- a table for the one to four names and year
local Volume;
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
local Issue;
names[i] = v.last
local Page;
if i == 4 then break end -- if four then done
local Pages;
local At;
 
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
Volume = A['Volume'];
end
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = A['Issue'];
end
end
table.insert (names, year); -- add the year at the end
local Position = '';
local id = table.concat(names); -- concatenate names and year for CITEREF id
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
if is_set (id) then -- if concatenation is not an empty string
Page = A['Page'];
return "CITEREF" .. id; -- add the CITEREF portion
Pages = hyphen_to_dash( A['Pages'] );
else
At = A['At'];
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end
end


local Edition = A['Edition'];
local PublicationPlace = A['PublicationPlace']
local Place = A['Place'];
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end


--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
local Via = A['Via'];
local AccessDate = A['AccessDate'];
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


Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,
local Language = A['Language'];
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
local Format = A['Format'];
 
local ChapterFormat = A['ChapterFormat'];
This function never sets the flag to false but returns it's previous state because it may have been set by
local DoiBroken = A['DoiBroken'];
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
local ID = A['ID'];
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
IgnoreISBN = nil; -- anything else, set to empty string
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
 
local ID_list = extract_ids( args );


]]
local Quote = A['Quote'];


local function name_has_etal (name, etal, nocat)
local LayFormat = A['LayFormat'];
local LayURL = A['LayURL'];
local LaySource = A['LaySource'];
local Transcript = A['Transcript'];
local TranscriptFormat = A['TranscriptFormat'];
local TranscriptURL = A['TranscriptURL']
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL


if is_set (name) then -- name can be nil in which case just return
local LastAuthorAmp = A['LastAuthorAmp'];
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
LastAuthorAmp = nil; -- set to empty string
end
if name:match (etal_pattern) then -- variants on et al.
local no_tracking_cats = A['NoTracking'];
name = name:gsub (etal_pattern, ''); -- if found, remove
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
no_tracking_cats = nil; -- set to empty string
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
end
return name, etal; --
end


--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
--these are used by cite interview
Gets name list from the input arguments
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];


Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
--local variables that are not cs1 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
local use_lowercase; -- controls capitalization of certain static text
find |last4= and |last5= then the search is done.
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local anchor_year; -- used in the CITEREF identifier
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification


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=
local DF = A['DF']; -- date format set in cs1|2 template
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
DF = ''; -- not valid, set to empty string
end


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
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the
local Mode = A['Mode'];
template's metadata.  When this occurs, the page is added to a maintenance category.
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
 
Mode = '';
]]
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
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 function extract_names(args, list_name)
--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 names = {}; -- table of names
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
local last; -- individual name components
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
local first;
no_tracking_cats = "true"; -- set no_tracking_cats
local link;
end
local mask;
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
local i = 1; -- loop counter/indexer
if this_page.text:match (v) then -- test page name against each pattern
local n = 1; -- output table indexer
no_tracking_cats = "true"; -- set no_tracking_cats
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)
break; -- bail out if one is found
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
end
end
end


local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
while true do
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
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 );


last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
local NoPP = A['NoPP']
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
NoPP = true;
else
NoPP = nil; -- unset, used as a flag later
end


if first and not last then -- if there is a firstn without a matching lastn
if is_set(Page) then
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
if is_set(Pages) or is_set(At) then
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
Pages = ''; -- unset the others
count = count + 1; -- number of times we haven't found last and first
At = '';
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
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
end
i = i + 1; -- point to next args location
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
end
elseif is_set(Pages) then
if is_set(At) then
return names, etal; -- all done, return our list of names
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.
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
end
 
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


]]
-- both |publication-place= and |place= (|location=) allowed if different
 
if not is_set(PublicationPlace) and is_set(Place) then
local function extract_ids( args )
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
local id_list = {}; -- list of identifiers found in args
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
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
if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list
end
end
return id_list;
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title


--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
|trans_title maps to |trans_chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped


Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
All other combinations of |encyclopedia, |title, and |article are not modified
 
inputs:
id_list – table of identifiers built by extract_ids()
options – table of various template parameter values used to modify some manually handled identifiers


]]
]]


local function build_id_list( id_list, options )
local Encyclopedia = A['Encyclopedia'];
local new_list, handler = {};


function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
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
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
if is_set(Title) or is_set (ScriptTitle) then
-- fallback to read-only cfg
if not is_set(Chapter) then
handler = setmetatable( { ['id'] = v }, fallback(k) );
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
ScriptChapter = ScriptTitle;
if handler.mode == 'external' then
TransChapter = TransTitle;
table.insert( new_list, {handler.label, external_link_id( handler ) } );
ChapterURL = URL;
elseif handler.mode == 'internal' then
if not is_set (ChapterURL) and is_set (TitleLink) then
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
elseif handler.mode ~= 'manual' then
end
error( cfg.messages['unknown_ID_mode'] );
Title = Periodical;
elseif k == 'DOI' then
ChapterFormat = Format;
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
Periodical = ''; -- redundant so unset
elseif k == 'ARXIV' then
TransTitle = '';
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
URL = '';
elseif k == 'ASIN' then
Format = '';
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );  
TitleLink = '';
elseif k == 'LCCN' then
ScriptTitle = '';
table.insert( new_list, {handler.label, lccn( v ) } );
end
elseif k == 'OL' or k == 'OLA' then
else -- |title not set
table.insert( new_list, {handler.label, openlibrary( v ) } );
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
elseif k == 'PMC' then
Periodical = ''; -- redundant so unset
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
end
elseif k == 'PMID' then
end
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
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
error( cfg.messages['unknown_manual_ID'] );
end
end
function comp( a, b ) -- used in following table.sort()
return a[1] < b[1];
end
end
 
table.sort( new_list, comp );
-- Special case for cite techreport.
for k, v in ipairs( new_list ) do
if (config.CitationClass == "techreport") then -- special case for cite techreport
new_list[k] = v[2];
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
end
return new_list;
end
 


--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------
-- special case for cite interview
 
if (config.CitationClass == "interview") then
Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities.
if is_set(Program) then
 
ID = ' ' .. Program;
2015-12-10: there is a bug in mw.text.unstripNoWiki ().  It replaced math stripmarkers with the appropriate content
when it shouldn't.  See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29
 
TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible
characters table?
]]
 
local function coins_cleanup (value)
value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content
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
 
 
--[[--------------------------< C O I N S >--------------------------------------------------------------------
 
COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
 
]]
 
local function COinS(data, class)
if 'table' ~= type(data) or nil == next(data) then
return '';
end
 
for k, v in pairs (data) do -- spin through all of the metadata parameter values
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 is_set(Callsign) then
 
if is_set(ID) then
local ctx_ver = "Z39.88-2004";
ID = ID .. sepc .. ' ' .. Callsign;
else
-- treat table strictly as an array with only set values.
ID = ' ' .. Callsign;
local OCinSoutput = setmetatable( {}, {
__newindex = function(self, key, value)
if is_set(value) then
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
end
end
end
end
});
if is_set(City) then
if is_set(ID) then
if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or
ID = ID .. sepc .. ' ' .. City;
('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
else
OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles
ID = ' ' .. City;
end
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only
end
if is_set (data.Map) then
 
OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
else
OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles
Others = ' ' .. 'Interview with ' .. Others;
end
end
-- these used onlu for periodicals
else
OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall
Others = '(Interview)';
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
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
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
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
end
-- and now common parameters (as much as possible)
 
OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
Periodical = A ['MailingList'];
if k == 'ISBN' then v = clean_isbn( v ) end
elseif 'mailinglist' == A:ORIGIN('Periodical') then
local id = cfg.id_handlers[k].COinS;
Periodical = ''; -- unset because mailing list is only used for cite mailing list
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


--[[
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
if 'conference' == config.CitationClass then
local id, value = cfg.id_handlers[k].COinS;
if is_set(BookTitle) then
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
Chapter = Title;
if string.sub( id or "", 1, 4 ) == 'info' then
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
ChapterURL = URL;
else
ChapterURLorigin = URLorigin;
OCinSoutput[ id ] = value;
URLorigin = '';
ChapterFormat = Format;
TransChapter = TransTitle;
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
end
]]
 
local last, first;
-- cite map oddities
for k, v in ipairs( data.Authors ) do
local Cartography = "";
last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers
local Scale = "";
if k == 1 then -- for the first author name only
local Sheet = A['Sheet'] or '';
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
local Sheets = A['Sheets'] or '';
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
if config.CitationClass == "map" then
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
Chapter = A['Map'];
elseif is_set(last) then
ChapterURL = A['MapURL'];
OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name
TransChapter = A['TransMap'];
end
ChapterURLorigin = A:ORIGIN('MapURL');
else -- for all other authors
ChapterFormat = A['MapFormat'];
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation
Cartography = A['Cartography'];
elseif is_set(last) then
if is_set( Cartography ) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
end
Scale = A['Scale'];
if is_set( Scale ) then
Scale = sepc .. " " .. Scale;
end
end
end
end


OCinSoutput.rft_id = data.URL;
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
OCinSoutput = setmetatable( OCinSoutput, nil );
local AirDate = A['AirDate'];
local SeriesLink = A['SeriesLink'];
-- 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


link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set


--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
Date = AirDate;
end


Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];


Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
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
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
with the code. When there is no match, we return the original language name string.
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
 
end
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
-- assemble a table of parts concatenated later into Series
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
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
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
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
returns only the Wikimedia language name.
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
 
Issue = ''; -- unset because this is not a unique parameter
Adapted from code taken from Module:Check ISO 639-1.
 
]]
 
local function get_iso639_code (lang)
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
end
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
Chapter = Title; -- promote title parameters to chapter
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
ScriptChapter = ScriptTitle;
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
for code, name in pairs(languages) do -- scan the list to see if we can find our language
ChapterURL = URL;
if langlc == mw.ustring.lower(name) then
ChapterURLorigin = A:ORIGIN('URL');
if 2 ~= code:len() then -- ISO639-1 codes only
return name; -- so return the name but not the code
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
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
Series = wrap_style ('italic-title', Series); -- series is italicized
end
end
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
-- end of {{cite episode}} stuff
end


--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
-- 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
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message


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.
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
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end


There is an exception.  There are three ISO639-1 codes for Norewegian language variants.  There are two official variants: Norwegian Bokmål (code 'nb') and
-- handle type parameter for those CS1 citations that have default values
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
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
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.
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
end
end


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
if is_set(TitleType) then -- if type parameter is specified
return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them.
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
end


See Help talk:Citation Style_1#An ISO 639-1 language name test
-- 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


When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
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.


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.
--[[
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);


local function language_parameter (lang)
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
local code; -- the ISO639-1 two character code
local mismatch = year_date_check (Year, Date)
local name; -- the language name
if 0 == mismatch then -- |year= does not match a year-value in |date=
local language_list = {}; -- table of language names to be rendered
if is_set (error_message) then -- if there is already an error message
local names_table = {}; -- table made from the value assigned to |language=
error_message = error_message .. ', '; -- tack on this additional message
 
end
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
end
end
 
if is_set(error_message) then
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
elseif is_set (DF) then
local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate};
if reformat_dates (date_parameters_list, DF, false) then -- reformat to DF format, use long month names if appropriate
AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with reformatted values
ArchiveDate = date_parameters_list['archive-date']; -- TODO: move all dates into this table at the beginning and ...
Date = date_parameters_list['date']; -- ... use them from this table? no in-and-out like we're doing here
DoiBroken = date_parameters_list['doi-broken-date'];
Embargo = date_parameters_list['embargo'];
LayDate = date_parameters_list['lay-date'];
PublicationDate = date_parameters_list['publication-date'];
end
end
end -- end of do


for _, lang in ipairs (names_table) do -- reuse lang
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
Embargo = is_embargoed (Embargo); --  


if lang:match ('^%a%a%-') then -- strip ietf language tags from code
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
if not is_set (Embargo) then -- if not embargoed or embargo has expired
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
end
end
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
end
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
 
end
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
-- Test if citation has no title
if is_set (name) then -- if Language specified a valid ISO639-1 code
if not is_set(Title) and
code = lang:lower(); -- save it
not is_set(TransTitle) and
else
not is_set(ScriptTitle) then
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
end
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
if is_set (code) then
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
if 'en' ~= code then -- English not the language
add_prop_cat ('foreign_lang_source', {name, code})
end
end
else
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
end
code = #language_list -- reuse code as number of languages in the list
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
if 2 >= code then
Title = ''; -- set title to empty string
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
add_maint_cat ('untitled');
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
if 'English' == name then
return ''; -- if one language and that language is English return an empty string (no annotation)
end
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end


--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
check_for_url ({ -- add error message when any of these parameters contains a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[A:ORIGIN('PublisherName')] = PublisherName
});


Set style settings for CS1 citation templates. Returns separator and postscript settings
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
 
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
]]
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
 
-- is the article title, and Chapter is a section within the article.  So, we remap
local function set_cs1_style (ps)
if not is_set (ps) then -- unless explicitely set to something
local coins_chapter = Chapter; -- default assuming that remapping not required
ps = '.'; -- terminate the rendered citation with a period
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
end
end
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
end
end
return '.', ps; -- separator is a full stop
end


--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
-- this is the function call to COinS()
 
local OCinSoutput = COinS({
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
['Periodical'] = Periodical,
 
['Encyclopedia'] = Encyclopedia,
]]
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
 
['Degree'] = Degree; -- cite thesis only
local function set_cs2_style (ps, ref)
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
['PublicationPlace'] = PublicationPlace,
ps = ''; -- make sure it isn't nil
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Season'] = COinS_date.rftssn,
['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = 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
end
if not is_set (ref) then -- if |ref= is not set
 
ref = "harv"; -- set default |ref=harv
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
end
end
end
return ',', ps, ref; -- separator is a comma
end


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


When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
rendered style.


]]
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
do
local last_first_list;
-- local 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
};


local function get_settings_from_cite_class (ps, ref, cite_class)
do -- do editor name list first because coauthors can modify control table
local sep;
control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
if (cite_class == "citation") then -- for citation templates (CS2)
last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
sep, ps, ref = set_cs2_style (ps, ref);
else -- not a citation template so CS1
sep, ps = set_cs1_style (ps);
end


return sep, ps, ref -- return them all
if is_set (Editors) then
end
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else
Editors = last_first_list; -- either an author name list or an empty string
end


--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
 
EditorCount = 2; -- spoof to display (eds.) annotation
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
end
config.CitationClass from the template's #invoke: to establish style.
end
do -- now do translators
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
end
do -- now do contributors
control.maximum = #c; -- number of contributors
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);


]]
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal, 'author');


local function set_style (mode, ps, ref, cite_class)
if is_set (Authors) then
local sep;
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
if author_etal then
sep, ps, ref = set_cs2_style (ps, ref);
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
end
sep, ps = set_cs1_style (ps);
else
else -- anything but cs1 or cs2
Authors = last_first_list; -- either an author name list or an empty string
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
end
end -- end of do
if 'none' == ps:lower() then -- if assigned value is 'none' then
ps = ''; -- set to empty string
end
return sep, ps, ref
if is_set (Authors) and is_set (Collaboration) then
end
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
end


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


Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
applying the pdf icon to external links.
-- 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');


returns true if file extension is one of the recognized extension, else false
-- 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


]=]
if  not is_set(URL) then --and
 
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
local function is_pdf (url)
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
end
end
 
-- Test if accessdate is given without giving a URL
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
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 ) } );
Applies css style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
AccessDate = '';
not have a matching url parameter.  If the format parameter is not set and the url contains a file extension that
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.
 
]]
 
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parenthases, resize
if not is_set (url) then
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;
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 >------------------------
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
 
DeadURL = DeadURL:lower(); -- used later when assembling archived text
Returns a number that may or may not limit the length of the author or editor name lists.
if is_set( ArchiveURL ) then
 
if is_set (URL) then
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
OriginalURL = URL; -- save copy of original source URL
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
some variant of the text 'et al.').
OriginalFormat = Format; -- and original |format=
 
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
URL = ArchiveURL -- swap-in the archive's url
number of authors in the list and set the 'etal' flag true.  This will cause the list_people() to display all of
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
the names in the name list followed by 'et al.'
Format = ArchiveFormat or ''; -- swap in archive's format
 
end
In all other cases, returns nil and the previous state of the 'etal' flag.
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
 
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
]]
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
 
OriginalFormat = ChapterFormat; -- and original |format=
local function get_display_authors_editors (max, count, list_name, etal)
if 'no' ~= DeadURL then
if is_set (max) then
ChapterURL = ArchiveURL -- swap-in the archive's url
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
max = count + 1; -- number of authors + 1 so display all author name plus et al.
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
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 and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cat ('disp_auth_ed', list_name);
end
end
else -- not a valid keyword or number
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset
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
return max, etal;
end


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


Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
if is_set (chap_param) then -- if we found one
abbreviation in the first characters of the parameter content.
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
ScriptChapter = '';
ChapterFormat = '';
end
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end


check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
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
if is_set (Chapter) then
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
if 'map' == config.CitationClass and is_set (TitleType) then
 
Chapter = Chapter .. ' ' .. TitleType;
]]
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
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


local function extra_text_in_page_check (page)
-- Format main title.
-- local good_pattern = '^P[^%.P%l]';
if is_set(TitleLink) and is_set(Title) then
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?
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
-- local bad_pattern = '^[Pp][Pp]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
 
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
add_maint_cat ('extra_text');
end
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- 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);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
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


--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
local TransError = "";
 
if is_set(TransTitle) then
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
if is_set(Title) then
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
TransTitle = " " .. TransTitle;
 
else
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
end
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
URL = "";
Format = "";
else
Title = Title .. TransError;
end
end


This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
if is_set(Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end


]]
if is_set (Conference) then
 
if is_set (ConferenceURL) then
local function parse_vauthors_veditors (args, vparam, list_name)
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
end
local v_name_table = {};
Conference = sepc .. " " .. Conference .. ConferenceFormat;
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
elseif is_set(ConferenceURL) then
local last, first, link, mask;
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
local corporate = false;
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)
if not is_set(Position) then
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
local Minutes = A['Minutes'];
add_vanc_error ();
local Time = A['Time'];
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 is_set(Minutes) then
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
if is_set (Time) then
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
last = v_name:match ('^%(%((.+)%)%)$')
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$') then
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
end
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
if is_set(Time) then
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
local TimeCaption = A['TimeCaption']
end
if not is_set(TimeCaption) then
TimeCaption = cfg.messages['event'];
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
if sepc ~= '.' then
add_vanc_error ();
TimeCaption = TimeCaption:lower();
end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end
end
-- this from extract_names ()
else
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
Position = " " .. Position;
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
At = '';
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


--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);


Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
At = is_set(At) and (sepc .. " " .. At) or "";
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
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


Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
if is_set( Sections ) then
similarly, |editorn= (and aliases) highest and |editors= lowest
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


When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
if is_set (Language) then
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc
way to do this, I just haven't discovered what that way is.
else
Language=""; -- language not specified so make sure this is an empty string;
end


Emits an error message when more than one xxxxor name source is provided.
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then
Others = sepc .. ' Translated by ' .. Translators .. Others;
end


In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (Edition) then
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
add_maint_cat ('extra_text', 'edition');
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end


]]
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";


local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
local lastfirst = false;
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
lastfirst=true;
end


if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
------------------------------------ totally unrelated data
(is_set (vxxxxors) and is_set (xxxxors)) or
if is_set(Via) then
(true == lastfirst and is_set (xxxxors)) then
Via = " " .. wrap_msg ('via', Via);
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
end


if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
--[[
if is_set (vxxxxors) then return 2 end;
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
if is_set (xxxxors) then return 3 end;
note is displayed. There are no error messages for this condition.
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
end


]]
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


--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
if is_set(AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']


This function is used to validate a parameter's assigned value for those parameters that have only a limited number
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
true; else, emits an error message and returns false.
-- neither of these work; don't know why; it seems that substitute() isn't being called
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if is_set(ID) then ID = sepc .." ".. ID; end
  if "thesis" == config.CitationClass and is_set(Docket) then
ID = sepc .." Docket ".. Docket .. ID;
end
  if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end


]]
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );


local function is_valid_parameter_value (value, name, possible)
if is_set(URL) then
if not is_set (value) then
URL = " " .. external_link( URL, nil, URLorigin );
return true; -- an empty parameter is ok
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


 
if is_set(Quote) then
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
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
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
end
when the last character is not a sepc character or when the last three characters are not sepc followed by two
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
single space character.
 
]]
 
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
return name_list .. sepc .. ' '; -- otherwise terninate the name list
end
end
end
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
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 format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
local Archived
if not is_set (volume) and not is_set (issue) then
if is_set(ArchiveURL) then
return '';
if not is_set(ArchiveDate) then
end
ArchiveDate = set_error('archive_missing_date');
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if "no" == DeadURL then
if is_set (volume) and is_set (issue) then
local arch_text = cfg.messages['archived'];
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
if sepc ~= "." then arch_text = arch_text:lower() end
elseif is_set (volume) then
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
return wrap_msg ('vol', {sepc, volume}, lower);
{ 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
return wrap_msg ('issue', {sepc, issue}, lower);
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
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Archived = ""
end
end
local vol = '';
local Lay = '';
if is_set(LayURL) then
if is_set (volume) then
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
if (4 < mw.ustring.len(volume)) then
if is_set(LaySource) then  
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
else
else
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
LaySource = "";
end
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
if is_set (issue) then
 
return vol .. substitute (cfg.messages['j-issue'], issue);
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
end
end
return vol;
end


 
local Publisher;
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
if is_set(Periodical) and
 
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
if is_set(PublisherName) then
The return order is:
if is_set(PublicationPlace) then
page, pages, sheet, sheets
Publisher = PublicationPlace .. ": " .. PublisherName;
 
else
Singular has priority over plural when both are provided.
Publisher = PublisherName;
 
]]
 
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
else
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
end
elseif is_set (sheets) then
elseif is_set(PublicationPlace) then
if 'journal' == origin then
Publisher= PublicationPlace;
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
Publisher = "";
end
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
else
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
Publisher = PublicationDate;
end
end
end
end
end
if is_set(Publisher) then
 
Publisher = " (" .. Publisher .. ")";
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
 
if is_set (page) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
end
elseif is_set(pages) then
else
if is_journal then
if is_set(PublicationDate) then
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
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}), '', '';
if is_set(PublisherName) then
elseif not nopp then
if is_set(PublicationPlace) then
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
else
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
elseif is_set(PublicationPlace) then  
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else  
Publisher = PublicationDate;
end
end
end
end
return '', '', '', ''; -- return empty strings
-- Several of the above rely upon detecting this as nil, so do it last.
end
if is_set(Periodical) then
 
if is_set(Title) or is_set(TitleNote) then
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)
 
else
This is the main function doing the majority of the citation formatting.
Periodical = wrap_style ('italic-title', Periodical)
end
end


--[[
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
]]
 
if "speech" == config.CitationClass then -- cite speech only
local function citation0( config, args)
TitleNote = " (Speech)"; -- annotate the citation
--[[
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
Load Input Parameters
if is_set (Conference) then -- and if |event= is set
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
]]
end
local A = argument_wrapper( args );
local i
 
-- 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'];
 
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
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=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
end
end
end
end


local Coauthors = A['Coauthors'];
-- Piece all bits together at last.  Here, all should be non-nil.
local Others = A['Others'];
-- We build things this way because it is more efficient in LUA
-- not to keep reassigning to the same string variable over and over.


local editor_etal;
local tcommon;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
local tcommon2; -- used for book cite when |contributor= is set
local Editors;
 
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
do -- to limit scope of selected
if is_set(Others) then Others = Others .. sepc .. " " end
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
if 1 == selected then
Language, Edition, Publisher, Agency, Volume}, sepc );
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
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
elseif 3 == selected then
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Editors = A['Editors']; -- use content of |editors=
else
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
end
end
end


local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
elseif 'map' == config.CitationClass then -- special cases for cite map
local Translators; -- assembled translators name list
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
local Contributors; -- assembled contributors name list
else -- a sheet or stand-alone map
local Contribution = A['Contribution'];
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
end
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
if 0 < #c then
elseif 'episode' == config.CitationClass then -- special case for cite episode
if not is_set (Contribution) then -- |contributor= requires |contribution=
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
else -- all other CS1 templates
c = {}; -- blank the contributors' table; it is used as a flag later
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
end
Volume, Others, Edition, Publisher, Agency}, sepc );
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
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
 
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
if #ID_list > 0 then
NameListFormat = ''; -- anything else, set to empty string
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
else
ID_list = ID;
end
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;


local Year = A['Year'];
if is_set(Date) then
local PublicationDate = A['PublicationDate'];
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
local OrigYear = A['OrigYear'];
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
local Date = A['Date'];
else -- neither of authors and editors set
local LayDate = A['LayDate'];
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
------------------------------------------------- Get title data
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
local Title = A['Title'];
else
local ScriptTitle = A['ScriptTitle'];
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
local BookTitle = A['BookTitle'];
end
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
end
end
 
end
local Chapter = A['Chapter'];
if is_set(Authors) then
local ScriptChapter = A['ScriptChapter'];
if is_set(Coauthors) then
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
local TransChapter = A['TransChapter'];
Authors = Authors .. ', ' .. Coauthors;
local TitleType = A['TitleType'];
else
local Degree = A['Degree'];
Authors = Authors .. '; ' .. Coauthors;
local Docket = A['Docket'];
end
local ArchiveFormat = A['ArchiveFormat'];
end
local ArchiveURL = A['ArchiveURL'];
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
local URL = A['URL']
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
end
local ChapterURL = A['ChapterURL'];
if is_set(Editors) then
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local in_text = " ";
local ConferenceFormat = A['ConferenceFormat'];
local post_text = "";
local ConferenceURL = A['ConferenceURL'];
if is_set(Chapter) and 0 == #c then
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
in_text = in_text .. cfg.messages['in'] .. " "
local Periodical = A['Periodical'];
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
else
 
if EditorCount <= 1 then
local Series = A['Series'];
post_text = ", " .. cfg.messages['editor'];
else
local Volume;
post_text = ", " .. cfg.messages['editors'];
local Issue;
end
local Page;
end
local Pages;
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
local At;
 
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
Volume = A['Volume'];
end
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = A['Issue'];
end
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = hyphen_to_dash( A['Pages'] );
At = A['At'];
end
 
local Edition = A['Edition'];
local PublicationPlace = A['PublicationPlace']
local Place = A['Place'];
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
end
local SubscriptionRequired = A['SubscriptionRequired'];
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
SubscriptionRequired=nil;
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
end
Authors = by_text .. Authors; -- author follows title so tweak it here
 
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
local Via = A['Via'];
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
local AccessDate = A['AccessDate'];
end
local ArchiveDate = A['ArchiveDate'];
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
local Agency = A['Agency'];
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
local DeadURL = A['DeadURL']
end
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
DeadURL = ''; -- anything else, set to empty string
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
end
 
elseif is_set(Editors) then
local Language = A['Language'];
if is_set(Date) then
local Format = A['Format'];
if EditorCount <= 1 then
local ChapterFormat = A['ChapterFormat'];
Editors = Editors .. ", " .. cfg.messages['editor'];
local DoiBroken = A['DoiBroken'];
else
local ID = A['ID'];
Editors = Editors .. ", " .. cfg.messages['editors'];
local ASINTLD = A['ASINTLD'];
end
local IgnoreISBN = A['IgnoreISBN'];
else
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
if EditorCount <= 1 then
IgnoreISBN = nil; -- anything else, set to empty string
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
end
else
local Embargo = A['Embargo'];
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
local Class = A['Class']; -- arxiv class identifier
end
 
local ID_list = extract_ids( args );
 
local Quote = A['Quote'];
 
local LayFormat = A['LayFormat'];
local LayURL = A['LayURL'];
local LaySource = A['LaySource'];
local Transcript = A['Transcript'];
local TranscriptFormat = A['TranscriptFormat'];
local TranscriptURL = A['TranscriptURL']
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
 
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
end
local no_tracking_cats = A['NoTracking'];
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
else
no_tracking_cats = nil; -- set to empty string
if config.CitationClass=="journal" and is_set(Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
end
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 );


--these are used by cite interview
-- Now enclose the whole thing in a <cite/> element
local Callsign = A['Callsign'];
local options = {};
local City = A['City'];
local Program = A['Program'];
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
 
options.class = config.CitationClass;
--local variables that are not cs1 parameters
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
local use_lowercase; -- controls capitalization of certain static text
else
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
options.class = "citation";
local anchor_year; -- used in the CITEREF identifier
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
 
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local Ref;
local id = Ref
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
if ('harv' == Ref ) then
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
local namelist = {}; -- holds selected contributor, author, editor name list
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation


--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if #c > 0 then -- if there is a contributor list
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
namelist = c; -- select it
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
elseif #a > 0 then -- or an author list
no_tracking_cats = "true"; -- set no_tracking_cats
namelist = a;
end
elseif #e > 0 then -- or an editor list
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
namelist = e;
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
id = anchor_id (namelist, year); -- go make the CITEREF anchor
end
end
options.id = id;
end
end
 
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
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
z.error_categories = {};
 
text = set_error('empty_citation');
local NoPP = A['NoPP']
z.message_tail = {};
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
end
NoPP = true;
if is_set(options.id) then
text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
else
else
NoPP = nil; -- unset, used as a flag later
text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
end
end


if is_set(Page) then
local empty_span = '<span style="display:none;">&nbsp;</span>';
if is_set(Pages) or is_set(At) then
Pages = ''; -- unset the others
-- Note: Using display: none on the COinS span breaks some clients.
At = '';
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
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
end
elseif is_set(Pages) then
 
if is_set(At) then
if #z.maintenance_cats ~= 0 then
At = ''; -- unset
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
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.
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
end
 
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
no_tracking_cats = no_tracking_cats:lower();
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
end
--[[
return text
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


|trans_title maps to |trans_chapter when |title is re-mapped
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
|url maps to |chapterurl when |title is remapped


All other combinations of |encyclopedia, |title, and |article are not modified
This is used by templates such as {{cite book}} to create the actual citation text.


]]
]]


local Encyclopedia = A['Encyclopedia'];
function cs1.citation(frame)
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata;
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 support modules
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');
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
utilities = require ('Module:Citation/CS1/Utilities');
validation = require ('Module:Citation/CS1/Date_validation');
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
end
 
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (utilities); -- so that functions in Date validataion can see 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


if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
year_date_check = validation.year_date_check;
if is_set(Title) or is_set (ScriptTitle) then
reformat_dates = validation.reformat_dates;
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
 
-- 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
 
-- special case for cite interview
if (config.CitationClass == "interview") then
if is_set(Program) then
ID = ' ' .. Program;
end
if is_set(Callsign) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. Callsign;
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
 
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
else
Others = '(Interview)';
end
end
 
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
 
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if 'conference' == config.CitationClass then
if is_set(BookTitle) then
Chapter = Title;
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
ChapterURL = URL;
ChapterURLorigin = URLorigin;
URLorigin = '';
ChapterFormat = Format;
TransChapter = TransTitle;
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
 
-- cite map oddities
local Cartography = "";
local Scale = "";
local Sheet = A['Sheet'] or '';
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
Chapter = A['Map'];
ChapterURL = A['MapURL'];
TransChapter = A['TransMap'];
ChapterURLorigin = A:ORIGIN('MapURL');
ChapterFormat = A['MapFormat'];
Cartography = A['Cartography'];
if is_set( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
Scale = A['Scale'];
if is_set( Scale ) then
Scale = sepc .. " " .. Scale;
end
end
 
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local SeriesLink = A['SeriesLink'];
if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))});
end
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
Date = AirDate;
end
 
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
 
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
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
-- 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
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
 
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
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
 
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-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
 
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 is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
local mismatch = year_date_check (Year, Date)
if 0 == mismatch then -- |year= does not match a year-value in |date=
if is_set (error_message) then -- if there is already an error message
error_message = error_message .. ', '; -- tack on this additional message
end
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
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
 
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
Embargo = is_embargoed (Embargo); --
 
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if not is_set (Embargo) then -- if not embargoed or embargo has expired
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
end
end
 
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- Test if citation has no title
if not is_set(Title) and
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
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
 
check_for_url ({ -- add error message when any of these parameters contains a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[A:ORIGIN('PublisherName')] = PublisherName,
});
 
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
-- is the article title, and Chapter is a section within the article.  So, we remap
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
end
end
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
end
 
-- this is the function call to COinS()
local OCinSoutput = COinS({
['Periodical'] = Periodical,
['Encyclopedia'] = Encyclopedia,
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
['Map'] = Map,
['Degree'] = Degree; -- cite thesis only
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
['PublicationPlace'] = PublicationPlace,
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Season'] = COinS_date.rftssn,
['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = 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
 
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
end
end
 
 
 
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
do
local last_first_list;
local 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
 
control.maximum = maximum;
last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
 
if is_set (Editors) then
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else
Editors = last_first_list; -- either an author name list or an empty string
end
 
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
do -- now do translators
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
end
do -- now do contributors
control.maximum = #c; -- number of contributors
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
 
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal, 'author');
 
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
end
else
Authors = last_first_list; -- either an author name list or an empty string
end
end -- end of do
 
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
 
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
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
 
if  not is_set(URL) then --and
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
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
 
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
DeadURL = DeadURL:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
if is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalFormat = Format; -- and original |format=
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
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalFormat = ChapterFormat; -- and original |format=
if 'no' ~= DeadURL then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
end
end
end
 
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
 
if is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
ScriptChapter = '';
ChapterFormat = '';
end
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
 
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
if is_set (Chapter) then
if 'map' == config.CitationClass and is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType;
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
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
 
-- Format main title.
if is_set(TitleLink) and is_set(Title) then
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
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);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
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
 
TransError = "";
if is_set(TransTitle) then
if is_set(Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
end
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
URL = "";
Format = "";
else
Title = Title .. TransError;
end
end
 
if is_set(Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
 
if is_set (Conference) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
end
 
if not is_set(Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
 
if is_set(Minutes) then
if is_set (Time) then
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if is_set(Time) then
local TimeCaption = A['TimeCaption']
if not is_set(TimeCaption) then
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
TimeCaption = TimeCaption:lower();
end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end
else
Position = " " .. Position;
At = '';
end
 
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
 
At = 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
 
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
 
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then
Others = sepc .. ' Translated by ' .. Translators .. Others;
end
 
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (Edition) then
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
add_maint_cat ('extra_text', 'edition');
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
 
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
 
------------------------------------ totally unrelated data
if is_set(Via) then
Via = " " .. wrap_msg ('via', Via);
end
 
--[[
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.
 
]]
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
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
 
if is_set(AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
 
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
-- neither of these work; don't know why; it seems that substitute() isn't being called
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if is_set(ID) then ID = sepc .." ".. ID; end
  if "thesis" == config.CitationClass and is_set(Docket) then
ID = sepc .." Docket ".. Docket .. ID;
end
  if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
 
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
 
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin );
end
 
if 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
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
local Archived
if is_set(ArchiveURL) then
if not is_set(ArchiveDate) then
ArchiveDate = set_error('archive_missing_date');
end
if "no" == DeadURL then
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
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
elseif is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Archived = ""
end
local Lay = '';
if is_set(LayURL) then
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
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
 
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
end
 
local Publisher;
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = PublicationPlace .. ": " .. PublisherName;
else
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
Publisher = PublicationDate;
end
end
if is_set(Publisher) then
Publisher = " (" .. Publisher .. ")";
end
else
if is_set(PublicationDate) then
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
end
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
end
elseif is_set(PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
end
-- 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
 
--[[
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
if 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
end
 
-- Piece all bits together at last.  Here, all should be non-nil.
-- We build things this way because it is more efficient in LUA
-- not to keep reassigning to the same string variable over and over.
 
local tcommon;
local tcommon2; -- used for book cite when |contributor= is set
if 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
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
end
 
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif 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, Transcript, Language, Edition, Publisher}, sepc );
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume, Others, Edition, Publisher, Agency}, sepc );
end
if #ID_list > 0 then
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
else
ID_list = ID;
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 
if is_set(Date) then
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
else -- neither of authors and editors set
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
else
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
end
end
end
if is_set(Authors) then
if is_set(Coauthors) then
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
Authors = Authors .. ', ' .. Coauthors;
else
Authors = Authors .. '; ' .. Coauthors;
end
end
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
else
if EditorCount <= 1 then
post_text = ", " .. cfg.messages['editor'];
else
post_text = ", " .. cfg.messages['editors'];
end
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if 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
elseif is_set(Editors) then
if is_set(Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
else
Editors = Editors .. ", " .. cfg.messages['editors'];
end
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if config.CitationClass=="journal" and is_set(Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
end
if is_set(PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc );  --Deals with italics, spaces, etc.
text = text:sub(1,-sepc:len()-1);
end
text = safe_join( {text, PostScript}, sepc );
 
-- Now enclose the whole thing in a <cite/> element
local options = {};
if 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
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
local id = Ref
in_array = utilities.in_array;
if ('harv' == Ref ) then
substitute = utilities.substitute;
local namelist = {}; -- holds selected contributor, author, editor name list
error_comment = utilities.error_comment;
-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
set_error = utilities.set_error;
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
select_one = utilities.select_one;
add_maint_cat = utilities.add_maint_cat;
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
remove_wiki_link = utilities.remove_wiki_link;


if #c > 0 then -- if there is a contributor list
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
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
 
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


if #z.maintenance_cats ~= 0 then
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Utilities
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
build_id_list = identifiers.build_id_list;
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
is_embargoed = identifiers.is_embargoed;
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
end
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
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
end
return text
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
end
get_coins_pages = metadata.get_coins_pages;
 
COinS = metadata.COinS;
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the first match.
 
Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the
replacement character.  That replacement character is not detected by this test though it is visible to readers
of the rendered citation.  This function will detect the replacement character when it is part of the wikisource.


Output of this function is an error message that identifies the character or the Unicode group that the character
belongs to along with its position in the parameter value.
]]
--[[
local function has_invisible_chars (param, v)
local position = '';
local i=1;
while cfg.invisible_chars[i] do
local char=cfg.invisible_chars[i][1] -- the character or group name
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
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
if position then
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=i+1; -- bump our index
end
end
]]
--[[--------------------------< Z . C I T A T I O N >----------------------------------------------------------
This is used by templates such as {{cite book}} to create the actual citation text.
]]
function z.citation(frame)
local pframe = frame:getParent()
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
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code
end
dates = validation.dates; -- imported functions
year_date_check = validation.year_date_check;
local args = {};
local args = {};
local suggestions = {};
local suggestions = {};
Line 4,108: Line 3,058:
end
end


return z
return cs1;
Anonymous user