Nonbinary Wiki

Module:Citation/CS1: Difference between revisions

Module Discussion

Module:Citation/CS1 (edit)

Revision as of 11:41, 21 May 2021

28,190 bytes added ,  2 years ago
m
21 revisions imported from wikipedia:Module:Citation/CS1: see Topic:Vtixlm0q28eo6jtf
m>Trappist the monk
(Synch from sandbox;)
m (21 revisions imported from wikipedia:Module:Citation/CS1: see Topic:Vtixlm0q28eo6jtf)
 
(47 intermediate revisions by 9 users not shown)
Line 1: Line 1:


local z = {
require('Module:No globals');
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 >--------------------------------------
each of these counts against the Lua upvalue limit
]]
]]
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 validation; -- 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 utilities; -- functions in Module:Citation/CS1/Utilities
local z ={}; -- table of tables in Module:Citation/CS1/Utilities


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 identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
This function is global because it is called from both this module and from Date validation
local metadata; -- functions in Module:Citation/CS1/COinS
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist


--[[------------------< P A G E  S C O P E  V A R I A B L E S >---------------
declare variables here that have page-wide scope that are not brought in from
other modules; that are created here and used here
]]
]]
function is_set( var )
local added_deprecated_cat; -- Boolean flag so that the category is added only once
return not (var == nil or var == '');
local added_discouraged_cat; -- Boolean flag so that the category is added only once
end
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category
local Frame; -- holds the module's frame table


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


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


Whether needle is in haystack
--[[--------------------------< 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.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 
added_vanc_errs is a Boolean declared in page scope variables above


]]
]]


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


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


Populates numbered arguments in a message string using an argument table.
--[[--------------------------< 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 substitute( msg, args )
local function is_scheme (scheme)
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
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 _ D O M A I N _ N A M E >--------------------------------------------------
 
Does this thing that purports to be a domain name seem to be a valid domain name?


]]
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
local function error_comment( content, hidden )
BNF defined here: https://tools.ietf.org/html/rfc4234
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
end
see also [[Single-letter second-level domain]]
list of TLDs: https://www.iana.org/domains/root/db
 
RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit. Between
the first and last characters the name may use letters, digits, and the hyphen.


--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
Also allowed are IPv4 addresses. IPv6 not supported


Sets an error condition and returns the appropriate error message.  The actual placement of the error message in the output is
domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
the responsibility of the calling function.
is two or more alpha characters.  Any preceding '//' (from splitting a URL with a scheme) will be stripped
here.  Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal.


]]
There are several tests:
local function set_error( error_id, arguments, raw, prefix, suffix )
the first character of the whole domain name including subdomains must be a letter or a digit
local error_state = cfg.error_conditions[ error_id ];
internationalized domain name (ASCII characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the TLD) see https://tools.ietf.org/html/rfc3490
single-letter/digit second-level domains in the .org, .cash, and .today TLDs
prefix = prefix or "";
q, x, and z SL domains in the .com TLD
suffix = suffix or "";
i and q SL domains in the .net TLD
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
if error_state == nil then
two-character SL domains in gTLDs (where the gTLD is two or more letters)
error( cfg.messages['undefined_error'] );
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
elseif is_set( error_state.category ) then
IPv4 dot-decimal address format; TLD not allowed
table.insert( z.error_categories, error_state.category );
 
returns true if domain appears to be a proper name and TLD or IPv4 address, else false
 
]=]
 
local function is_domain_name (domain)
if not domain then
return false; -- if not set, abandon
end
end
local message = substitute( error_state.message, arguments );
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
message = message .. " ([[" .. cfg.messages['help page link'] ..
if not domain:match ('^[%w]') then -- first character must be letter or digit
"#" .. error_state.anchor .. "|" ..
return false;
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
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 >------------------------------------------------------
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
return false;
end


Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
local patterns = { -- patterns that look like URLs
To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
'%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars)
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}


]]
for _, pattern in ipairs (patterns) do -- loop through the patterns list
if domain:match (pattern) then
return true; -- if a match then we think that this thing that purports to be a URL is a URL
end
end


local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats
for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
local function add_maint_cat (key, arguments)
if domain:match ('%f[%w][%w]%.' .. d) then
if not added_maint_cats [key] then
return true
added_maint_cats [key] = true; -- note that we've added this category
end
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
end
end
return false; -- no matches, we don't know what this thing is
end
end


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


Adds a category to z.properties_cats using names from the configuration file with additional text if any.
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
 
returns true if the scheme and domain parts of a URL appear to be a valid URL; else false.
 
This function is the last step in the validation process.  This function is separate because there are cases that
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.


]]
]]


local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
local function is_url (scheme, domain)
local function add_prop_cat (key, arguments)
if utilities.is_set (scheme) then -- if scheme is set check it and domain
if not added_prop_cats [key] then
return is_scheme (scheme) and is_domain_name (domain);
added_prop_cats [key] = true; -- note that we've added this category
else
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
return is_domain_name (domain); -- scheme not set when URL is protocol-relative
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.
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
To prevent duplication, added_vanc_errs is nil until an error message is emitted.


]]
Split a URL into a scheme, authority indicator, and domain.


local added_vanc_errs; -- flag so we only emit one Vancouver error / category
First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#).
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


If protocol-relative URL, return nil scheme and domain else return nil for both scheme and domain.


--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
When not protocol-relative, get scheme, authority indicator, and domain.  If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.


does this thing that purports to be a uri scheme seem to be a valid scheme?  The scheme is checked to see if it
Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
like news: that don't use authority indicator?
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;
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (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
if utilities.is_set (authority) then
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
return scheme; -- return scheme only making domain nil which will cause an error message
end
else
if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test?
return scheme; -- return scheme only making domain nil which will cause an error message
end
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
end
end




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


Does this thing that purports to be a domain name seem to be a valid domain name?
checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs


rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
the first and last characters the name may use letters, digits, and the hyphen. Single character names are not allowed.
# < > [ ] | { } _
except the underscore which is used as a space in wiki URLs and # which is used for section links


Also allowed are IPv4 addresses. IPv6 not supported
returns false when the value contains any of these characters.


There are three tests: the first is looking for a hostname that is 2 to n letters or digits followed by a dot and a
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid URL (the
letter (tld); the second looks for a hostname that is 3 to n characters where the first and last are letters or
|<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
digits and the middle characters are letters, digits, or the hyphen; the whole followed by a dot and a letter or digit.
The third test is for IPv4 dot-decimal address format; tld not allowed.
 
returns true if domain appears to be a proper name and tld or IPv4 address, else false


]]
]]


local function is_domain_name (domain)
local function link_param_ok (value)
if not domain then
local scheme, domain;
return false; -- if not set, abandon
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if domain:match ('^[%a%d][%a%d]+%.%a') then -- two character hostname and tld
return true;
elseif domain:match ('^[%a%d][%a%d%-]+[%a%d]%.[%a%d]') 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;
return false;
end
end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from URL;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL
end
end




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


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


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


]]
]]


local function is_url (scheme, domain)
local function link_title_ok (link, lorig, title, torig)
if is_set (scheme) then -- if scheme is set check it and domain
local orig;
return is_scheme (scheme) and is_domain_name (domain);
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value
else
if not link_param_ok (link) then -- check |<param>-link= markup
return is_domain_name (domain); -- scheme not set when url is protocol relative
orig = lorig; -- identify the failing link parameter
elseif title:find ('%[%[') then -- check |title= for wikilink markup
orig = torig; -- identify the failing |title= parameter
elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki
local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix
 
if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon
orig = lorig; -- flag as error
end
end
end
 
if utilities.is_set (orig) then
link = ''; -- unset
table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)}); -- URL or wikilink in |title= with |title-link=;
end
end
return link; -- link if ok, empty string else
end
end




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


Split a url into a scheme and domain pair and return both parts.  If protocol relative url, return nil for scheme
Determines whether a URL string appears to be valid.
and domain else return nil for both scheme and domain.


]]
First we test for space characters.  If any are found, return false.  Then split the URL into scheme and domain
portions, or for protocol-relative (//example.com) URLs, just the domain.  Use is_url() to validate the two
portions of the URL.  If both are valid, or for protocol-relative if domain is valid, return true, else false.


local function split_url (url_str)
Because it is different from a standard URL, and because this module used external_link() to make external links
that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
 
]]
 
local function check_url( url_str )
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL
return false;
end
local scheme, domain;
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
if url_str:match ('%S-:%S+') then -- if there is what appears to be a scheme domain pair
if 'news:' == scheme then -- special case for newsgroups
scheme, domain = url_str:match ('(%S-:)(%S+)'); -- extract the scheme and domain portions
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
elseif url_str:match ('//%S*') then -- if there is what appears to be a protocol relative url
domain = url_str:match ('//(%S*)')
end
end
return scheme, domain;
return is_url (scheme, domain); -- return true if value appears to be a valid URL
end
end




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


checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
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.


Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs.  The tests that
# < > [ ] | { } _
find bracketed URLs are required because the parameters that call this test (currently |title=, |chapter=, |work=,
returns false when the value contains any of these characters.
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
is possible as might be [[en://Hus]].


When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
]=]
|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).


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


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


scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
return is_url (scheme, domain); -- return true if value appears to be a valid URL
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 >------------------------------------------------------------
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------


Determines whether a URL string appears to be valid.
loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
 
First we test for space characters.  If any are found, return false.  Then split the url into scheme and domain
portions, or for protocol relative (//example.com) urls, just the domain.  Use is_scheme() and is_domain() 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 check_for_url (parameter_list)
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
local error_message = '';
return false;
for k, v in pairs (parameter_list) do -- for each parameter in the list
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a URL add an error message
if utilities.is_set(error_message) then -- once we've added the first portion of the error message ...
error_message = error_message .. ", "; -- ... add a comma space separator
end
error_message = error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
if utilities.is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { utilities.set_message ( 'err_param_has_ext_link', {error_message}, true ) } );
end
end
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
end




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


Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
Escape sequences for content that will be used for URL descriptions
characters following the opening bracket obey the rules of a uri scheme (see check_url()).  The test will also find
external wikilinks that use protocol relative urls. Also finds bare urls.


The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls.  The tests that
]]
find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, and
|work=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]] is
possible as might be [[en://Hus]].


]=]
local function safe_for_url( str )
 
if str:match( "%[%[.-%]%]" ) ~= nil then  
local function is_parameter_ext_wikilink (value)
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } );
local scheme, domain;
 
if value:match ('%f[%[]%[%a%S*:%S.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S.*)%]')
elseif value:match ('%f[%[]%[//%S*%.%S*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
domain = value:match ('%f[%[]%[//(%S*%.%S*)%]');
else
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;  
end
end
 
return is_url (scheme, domain); -- return true if value appears to be a valid url
return str:gsub( '[%[%]\n]', {
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
end




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


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


]]
]]


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




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


Protects a string that will be wrapped in wiki italic markup '' ... ''
Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the
offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated
parameters in the citation.


Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
added_deprecated_cat is a Boolean declared in page scope variables above
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
poorly under Mediawiki's HTML tidy.


]]
]]


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


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


Escape sequences for content that will be used for URL descriptions
--[[--------------------------< D I S C O U R A G E D _ P A R A M E T E R >------------------------------------
 
Categorize and emit an maintenance message when the citation contains one or more discouraged parameters.  Only
one error message is emitted regardless of the number of discouraged parameters in the citation.
 
added_discouraged_cat is a Boolean declared in page scope variables above


]]
]]


local function safe_for_url( str )
local function discouraged_parameter(name)
if str:match( "%[%[.-%]%]" ) ~= nil then
if not added_discouraged_cat then
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
added_discouraged_cat = true; -- note that we've added this category
table.insert( z.message_tail, { utilities.set_message ( 'maint_discouraged', {name}, true ) } ); -- add maint message
end
end
end
return str:gsub( '[%[%]\n]', {
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end


--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------


Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
argument; protects italic styled parameters.  Additional text taken from citation_config.presentation - the reason
this function is similar to but separate from wrap_msg().


]]
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.


local function wrap_style (key, str)
This function will positive kern either single or double quotes:
if not is_set( str ) then
"'Unkerned title with leading and trailing single quote marks'"
return "";
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
Double single quotes (italic or bold wiki-markup) are not kerned.
str = safe_for_italics( str );
end


return substitute( cfg.presentation[key], {str} );
Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
end
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.


--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
Call this function for chapter titles, for website titles, etc.; not for book titles.


Format an external link with error checking
]=]


]]
local function kern_quotes (str)
local cap = '';
local cap2 = '';
local wl_type, label, link;


local function external_link( URL, label, source )
wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
local error_str = "";
if not is_set( label ) then
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
label = URL;
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
if is_set( source ) then
str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
else
str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
error( cfg.messages["bare_url_no_origin"] );
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
end
str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
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 >----------------------------------------------
else -- plain text or [[L|D]]; text in label variable
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)


Formats a wiki style external link
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
 
if utilities.is_set (cap) then
]]
label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
 
end
local function external_link_id(options)
local url_string = options.id;
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if options.encode == true or options.encode == nil then
if utilities.is_set (cap) then
url_string = mw.uri.encode( url_string );
label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
end
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
return str;
options.link, options.label, options.separator or "&nbsp;",
options.prefix, url_string, options.suffix or "",
mw.text.nowiki(options.id)
);
end
end


--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------


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


]]
|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.


local page_in_deprecated_cat; -- sticky flag so that the category is added only once
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate RTL languages from the English left to right.
local function 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 >--------------------------------------------------------
|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO 639-1 language code and a colon:
|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
|script-title=ja : *** ***
|script-title=ja: *** ***
|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***


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.
The prefix is checked for validity.  If it is a valid ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
This function will positive kern either single or double quotes:
know the language the tag contains. This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
"'Unkerned title with leading and trailing single quote marks'"
is not added.  At this time there is no error message for this condition.
" '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.
Supports |script-title=, |script-chapter=, |script-<periodical>=


]]
]]


local function kern_quotes (str)
local function format_script_value (script_value, script_param)
local cap='';
local lang=''; -- initialize to empty string
local cap2='';
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if is_set (cap) then
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
end
 
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
if is_set (cap) then
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
return str;
end
 
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
 
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
not be italicized and may be written right-to-left.  The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.
 
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.
 
|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
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 format_script_value (script_value)
local lang=''; -- initialize to empty string
local name;
local name;
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not is_set (lang) then
if not utilities.is_set (lang) then
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
return ''; -- script_value was just the prefix so return empty string
return ''; -- script_value was just the prefix so return empty string
end
end
-- if we get this far we have prefix and script
-- 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
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
if utilities.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
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
-- is prefix one of these language codes?
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
if utilities.in_array (lang, cfg.script_lang_codes) then
add_prop_cat ('script_with_name', {name, lang})
utilities.add_prop_cat ('script_with_name', {name, lang})
else
else
add_prop_cat ('script')
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
end
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
else
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
lang = ''; -- invalid so set lang to empty string
end
end
else
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL


return script_value;
return script_value;
end
end


--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Line 555: Line 578:
]]
]]


local function script_concatenate (title, script)
local function script_concatenate (title, script, script_param)
if is_set (script) then
if utilities.is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error
if is_set (script) then
if utilities.is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
title = title .. ' ' .. script; -- concatenate title and script title
end
end
Line 575: Line 598:


local function wrap_msg (key, str, lower)
local function wrap_msg (key, str, lower)
if not is_set( str ) then
if not utilities.is_set ( str ) then
return "";
return "";
end
end
Line 581: Line 604:
local msg;
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before  
msg = cfg.messages[key]:lower(); -- set the message to lower case before  
return substitute( msg, str ); -- including template text
return utilities.substitute ( msg, str ); -- including template text
else
else
return substitute( cfg.messages[key], str );
return utilities.substitute ( cfg.messages[key], str );
end
end
end
end




--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------
--[[----------------< W I K I S O U R C E _ U R L _ M A K E >-------------------


This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
Makes a Wikisource URL from Wikisource interwiki-link.  Returns the URL and appropriate
provided by the template.
label; nil else.


Input:
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
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 wikisource_url_make (str)
if enumerated then -- is this a test for an enumerated parameters?
local wl_type, D, L;
alias = alias:gsub ('#', index); -- replace '#' with the value in index
local ws_url, ws_label;
else
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
alias = alias:gsub ('#', ''); -- remove '#' if it exists
 
end
wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)


if is_set(args[alias]) then -- alias is in the template's argument list
if 0 == wl_type then -- not a wikilink; might be from |title-link=
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
local skip;
if utilities.is_set (str) then
for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias
ws_url = table.concat ({ -- build a Wikisource URL
if v == alias then
wikisource_prefix, -- prefix
skip = true;
str, -- article title
break; -- has been added so stop looking
});
end
ws_label = str; -- label for the URL
end
end
if not skip then -- has not been added so
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
table.insert( error_list, alias ); -- add error alias to the error list
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
end
if utilities.is_set (str) then
else
ws_url = table.concat ({ -- build a Wikisource URL
value = args[alias]; -- not yet selected an alias, so select this one
wikisource_prefix, -- prefix
selected = alias;
str, -- article title
});
ws_label = str; -- label for the URL
end
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if utilities.is_set (str) then
ws_label = D; -- get ws article name from display portion of interwiki link
ws_url = table.concat ({ -- build a Wikisource URL
wikisource_prefix, -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
end
end
return value, selected; -- return newly selected alias, or previously selected alias
end


if ws_url then
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker
end


--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil
end


Chooses one matching parameter from a list of parameters to consider.  The list of parameters to consider is just
names.  For parameters that may be enumerated, the position of the numerator in the parameter name is identified
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.


Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
--[[----------------< F O R M A T _ P E R I O D I C A L >-----------------------


Format the three periodical parameters: |script-<periodical>=, |<periodical>=,
and |trans-<periodical>= into a single Periodical meta-parameter.


Generates an error if more than one match is present.
]]


]]
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
local periodical_error = '';


local function select_one( args, aliases_list, error_condition, index )
if not utilities.is_set (periodical) then
local value = nil; -- the value assigned to the selected parameter
periodical = ''; -- to be safe for concatenation
local selected = ''; -- the name of the parameter we have chosen
else
local error_list = {};
periodical = utilities.wrap_style ('italic-title', periodical); -- style
end


if index ~= nil then index = tostring(index); end
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped


for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list
if utilities.is_set (trans_periodical) then
if alias:match ('#') then -- if this alias can be enumerated
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases
if utilities.is_set (periodical) then
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias
periodical = periodical .. ' ' .. trans_periodical;
end
else -- here when trans-periodical without periodical or script-periodical
value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias
periodical = trans_periodical;
else
periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'});
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias
end
end
end
end


if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
return periodical .. periodical_error;
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 >--------------------------------------
--[[------------------< F O R M A T _ C H A P T E R _ T I T L E >---------------


Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
parameter (chapter_url_source used for error messages).
and |chapter-url= into a single chapter meta- parameter (chapter_url_source used
for error messages).


]]
]]


local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access)
local chapter_error = '';
local chapter_error = '';
 
if not is_set (chapter) then
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link
if ws_url then
ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters
chapter = ws_label;
end
 
if not utilities.is_set (chapter) then
chapter = ''; -- to be safe for concatenation
chapter = ''; -- to be safe for concatenation
else
else
if false == no_quotes then
if false == no_quotes then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
chapter = wrap_style ('quoted-title', chapter);
chapter = utilities.wrap_style ('quoted-title', chapter);
end
end
end
end


chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped


if is_set (transchapter) then
if utilities.is_set (chapter_url) then
transchapter = wrap_style ('trans-quoted-title', transchapter);
chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
if is_set (chapter) then
elseif ws_url then
chapter = chapter .. ' ' .. transchapter;
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
else -- here when transchapter without chapter or script-chapter
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
chapter = transchapter; --
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end
end


if is_set (chapterurl) then
if utilities.is_set (trans_chapter) then
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter);
if utilities.is_set (chapter) then
chapter = chapter .. ' ' .. trans_chapter;
else -- here when trans_chapter without chapter or script-chapter
chapter = trans_chapter;
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>
chapter_error = ' ' .. utilities.set_message ('err_trans_missing_title', {chapter_source});
end
end
end


Line 725: Line 747:




--[[
--[[----------------< H A S _ I N V I S I B L E _ C H A R S >-------------------
Argument wrapper.  This function provides support for argument
 
mapping defined in the configuration file so that multiple names
This function searches a parameter's value for non-printable or invisible characters.
can be transparently aliased to single internal variable.
The search stops at the first match.
]]


local function argument_wrapper( args )
This function will detect the visible replacement character when it is part of the Wikisource.
 
Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers
(gallery, math, pre, ref) and identifies them with a slightly different error message.
See also coins_cleanup().
 
Output of this function is an error message that identifies the character or the
Unicode group, or the stripmarker that was detected along with its position (or,
for multi-byte characters, the position of its first byte) in the parameter value.
 
]]
 
local function has_invisible_chars (param, v)
local position = ''; -- position of invisible char or starting position of stripmarker
local capture; -- used by stripmarker detection to hold name of the stripmarker
local stripmarker; -- boolean set true when a stripmarker is found
 
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
if capture == v then -- if same there are no Unicode characters
return;
end
 
for _, invisible_char in ipairs (cfg.invisible_chars) do
local char_name = invisible_char[1]; -- the character or group name
local pattern = invisible_char[2]; -- the pattern used to find it
position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern
if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
position = nil; -- unset position
elseif cfg.emoji[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
position = nil; -- unset position
end
end
if position then
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
stripmarker = true; -- set a flag
elseif true == stripmarker and cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
position = nil; -- unset
else
local err_msg;
if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
err_msg = capture .. ' ' .. char_name;
else
err_msg = char_name .. ' ' .. 'character';
end
 
table.insert (z.message_tail, {utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true)}); -- add error message
return; -- and done with this parameter
end
end
end
end
 
 
--[[-------------------< A R G U M E N T _ W R A P P E R >----------------------
 
Argument wrapper.  This function provides support for argument mapping defined
in the configuration file so that multiple names can be transparently aliased to
single internal variable.
 
]]
 
local function argument_wrapper ( args )
local origin = {};
local origin = {};
return setmetatable({
return setmetatable({
ORIGIN = function( self, k )
ORIGIN = function ( self, k )
local dummy = self[k]; --force the variable to be loaded.
local dummy = self[k]; -- force the variable to be loaded.
return origin[k];
return origin[k];
end
end
Line 749: Line 835:
if type( list ) == 'table' then
if type( list ) == 'table' then
v, origin[k] = select_one( args, list, 'redundant_parameters' );
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
if origin[k] == nil then
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
origin[k] = ''; -- Empty string, not nil
end
end
elseif list ~= nil then
elseif list ~= nil then
Line 758: Line 844:
-- maybe let through instead of raising an error?
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
end
end
-- Empty strings, not nil;
-- Empty strings, not nil;
if v == nil then
if v == nil then
v = cfg.defaults[k] or '';
v = '';
origin[k] = '';
origin[k] = '';
end
end
Line 773: Line 859:
end
end


--[[
 
Looks for a parameter's name in the whitelist.
--[[--------------------------< N O W R A P _ D A T E >-------------------------
 
 
Parameters in the whitelist can have three values:
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
true - active, supported parameters
When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
false - deprecated, supported parameters
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
nil - unsupported parameters
]]
 
local function validate( name )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
-- Normal arguments
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- Not supported because not found or name is set to nil
end
 
 
-- Formats a wiki style internal link
local function internal_link_id(options)
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
options.link, options.label, options.separator or "&nbsp;",
options.prefix, options.id, options.suffix or "",
mw.text.nowiki(options.id)
);
end
 
 
--[[--------------------------< 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


DOES NOT yet support MMMM YYYY or any of the date ranges.
DOES NOT yet support MMMM YYYY or any of the date ranges.
Line 826: Line 871:


local function nowrap_date (date)
local function nowrap_date (date)
local cap='';
local cap = '';
local cap2='';
local cap2 = '';


if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
date = substitute (cfg.presentation['nowrap1'], date);
date = utilities.substitute (cfg.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
end
Line 840: Line 885:
end
end


--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------


ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------
If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes,
 
spaces and other non-isxn characters.
This function sets default title types (equivalent to the citation including
|type=<default value>) for those templates that have defaults. Also handles the
special case where it is desirable to omit the title type from the rendered citation
(|type=none).


]]
]]


local function is_valid_isxn (isxn_str, len)
local function set_titletype (cite_class, title_type)
local temp = 0;
if utilities.is_set (title_type) then
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
if 'none' == cfg.keywords_xlate[title_type] then
len = len+1; -- adjust to be a loop counter
title_type = ''; -- if |type=none then type parameter not displayed
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 title_type; -- if |type= has been set to any other value use that value
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
 
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
end




--[[--------------------------< IS _ V A L I D _ I S X N  _ 1 3 >----------------------------------------------
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
 
Converts a hyphen to a dash under certain conditions.  The hyphen must separate
like items; unlike items are returned unmodified.  These forms are modified:
letter - letter (A - B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and
digit is supported – a.1-a.5 or a-1-a-5)
digitletter - digitletter (5a - 5d) (an optional separator between letter and
digit is supported – 5.a-5.d or 5-a-5-d)


ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
any other forms are returned unmodified.
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.
str may be a comma- or semicolon-separated list


]]
]]


local function is_valid_isxn_13 (isxn_str)
local function hyphen_to_dash( str )
local temp=0;
if not utilities.is_set (str) then
return str;
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
for i, v in ipairs( isxn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
end
end
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
end


--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
local accept; -- Boolean


Determines whether an ISBN string is valid
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split
str = str:gsub ('&#45;', '-'); -- replace HTML numeric entity with hyphen character


]]
str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character
local out = {};
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any


local function check_isbn( isbn_str )
for _, item in ipairs (list) do -- for each item in the list
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
item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
local len = isbn_str:len();
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
if len ~= 10 and len ~= 13 then
item:match ('^%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+$') or -- digit separator digit hyphen digit separator digit
return false;
item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit
item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace
end
end
table.insert (out, item); -- add the (possibly modified) item to the output table
end
end


if len == 10 then
local temp_str = ''; -- concatenate the output table into a comma separated string
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out
return is_valid_isxn(isbn_str, 10);
if accept then
temp_str = utilities.has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value
return temp_str;
else
else
local temp = 0;
return temp_str; -- else, return assembled temp_str
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
return is_valid_isxn_13 (isbn_str);
end
end
end
end


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


Determines whether an ISMN string is valid.  Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
--[[--------------------------< S A F E _ J O I N >-----------------------------
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
section 2, pages 9–12.


]]
Joins a sequence of strings together while checking for duplicate separation characters.
 
local function ismn (id)
local handler = cfg.id_handlers['ISMN'];
local text;
local valid_ismn = true;
 
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn
 
if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
valid_ismn = false;
else
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
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;
end
 
--[[--------------------------< I S S N >----------------------------------------------------------------------
 
Validate and format an issn.  This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
digits with a space.  When that condition occurred, the resulting link looked like this:
 
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327]  -- can't have spaces in an external link
This code now prevents that by inserting a hyphen at the issn midpoint.  It also validates the issn for length and makes sure that the checkdigit agrees
with the calculated value.  Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn
error message.  The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.


]]
]]


local function issn(id)
local function safe_join( tbl, duplicate_char )
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local f = {}; -- create a function table appropriate to type of 'duplicate character'
local handler = cfg.id_handlers['ISSN'];
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
local text;
f.gsub = string.gsub
local valid_issn = true;
f.match = string.match
f.sub = string.sub
else -- for multi-byte characters use the ustring library functions
f.gsub = mw.ustring.gsub
f.match = mw.ustring.match
f.sub = mw.ustring.sub
end


id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
local str = ''; -- the output string
 
local comp = ''; -- what does 'comp' mean?
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
local end_chr = '';
valid_issn=false; -- wrong length or improper character
local trim;
else
for _, value in ipairs( tbl ) do
valid_issn=is_valid_isxn(id, 8); -- validate issn
if value == nil then value = ''; end
end
 
if str == '' then -- if output string is empty
if true == valid_issn then
str = value; -- assign value to it (first time through the loop)
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
elseif value ~= '' then
else
if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup.
id = issn_copy; -- if not valid, use the show the invalid issn with error message
comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string)
end
else
comp = value;
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 >------------------------------------------------------------------
 
Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
characters.  If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
 
]]
 
local function amazon(id, domain)
local err_cat = ""
 
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") 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
end
elseif not id:match("^%u[%d%u]+$") then
-- typically duplicate_char is sepc
err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
--  Because individual string segments often (always?) begin with terminal punct for the
--  preceding segment: 'First element' .. 'sepc next element' .. etc.?
trim = false;
end_chr = f.sub(str, -1, -1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = f.sub(str, 1, -2); -- remove it
elseif end_chr == "'" then -- if it might be wiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
trim = true;
elseif  f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = f.sub(str, 1, -3); -- remove them both
end
end
 
if trim then
if value ~= comp then -- value does not equal comp when value contains HTML markup
local dup2 = duplicate_char;
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup
else
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; -- add it to the output string
end
end
end
end
if not is_set(domain) then
return str;
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
end


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


See: http://arxiv.org/help/arxiv_identifier
--[[--------------------------< I S _ S U F F I X >-----------------------------


format and error check arXiv identifier.  There are three valid forms of the identifier:
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
the first form, valid only between date codes 9108 and 0703 is:
Puncutation not allowed.
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:
arXiv:<date code>.<number><version>
where:
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
<number> is a four-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces


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


local function arxiv (id, class)
local function is_suffix (suffix)
local handler = cfg.id_handlers['ARXIV'];
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
local year, month, version;
return true;
local err_cat = '';
local text;
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
end
return false;
end


text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;


if is_set (class) then
--[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
 
else
For Vancouver style, author/editor names are supposed to be rendered in Latin
class = ''; -- empty string for concatenation
(read ASCII) characters.  When a name uses characters that contain diacritical
end
marks, those characters are to be converted to the corresponding Latin
character. When a name is written using a non-Latin alphabet or logogram, that
return text .. class;
name is to be transliterated into Latin characters. The module doesn't do this
end
so editors may/must.


--[[
This test allows |first= and |last= names to contain any of the letters defined
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
in the four Unicode Latin character sets
1. Remove all blanks.
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
3. If there is a hyphen in the string:
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
a. Remove it.
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
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.
|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


local function normalize_lccn (lccn)
This original test:
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$")
or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
was written outside of the code editor and pasted here because the code editor
gets confused between character insertion point and cursor position. The test has
been rewritten to use decimal character escape sequence for the individual bytes
of the Unicode characters so that it is not necessary to use an external editor
to maintain this code.


if nil ~= string.find (lccn,'/') then
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
\195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
end
\195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)


local 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 is_good_vanc_name (last, first, suffix, position)
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 suffix then
lccn=prefix..suffix; -- reassemble the lccn
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
first = first:match ('(.-)[,%s]+'); -- get name/initials
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
end
end
end
if utilities.is_set (suffix) then
return lccn;
if not is_suffix (suffix) then
add_vanc_error (cfg.err_msg_supl.suffix, position);
return false; -- not a name with an appropriate suffix
end
end
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
add_vanc_error (cfg.err_msg_supl['non-Latin char'], position);
return false; -- not a string of Latin characters; Vancouver requires Romanization
end;
return true;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-style=vanc. 
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period.
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.


--[[
Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered
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
as Jr, 2nd, 3rd, etc.  See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
This code only accepts and understands generational suffix in the Vancouver format
because Roman numerals look like, and can be mistaken for, initials.


length = 8 then all digits
This function uses ustring functions because firstname initials may be any of the
length = 9 then lccn[1] is lower case alpha
Unicode Latin characters accepted by is_good_vanc_name ().
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 reduce_to_initials(first, position)
local handler = cfg.id_handlers['LCCN'];
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
local err_cat =  ''; -- presume that LCCN is valid
local id = lccn; -- local copy of the lccn


id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
if not name then -- if not initials and a suffix
local len = id:len(); -- get the length of the lccn
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
end


if 8 == len then
if name then -- if first is initials with or without suffix
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
if 3 > mw.ustring.len (name) then -- if one or two initials
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
if suffix then -- if there is a suffix
end
if is_suffix (suffix) then -- is it legitimate?
elseif 9 == len then -- LCCN should be adddddddd
return first; -- one or two initials and a valid suffix so nothing to do
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
add_vanc_error (cfg.err_msg_supl.suffix, position); -- one or two initials with invalid suffix so error message
end
return first; -- and return first unmolested
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
end
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
else
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
return first; -- one or two initials without suffix; nothing to do
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
end -- if here then name has 3 or more uppercase letters so treat them as a word
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
local initials, names = {}, {}; -- tables to hold name parts and initials
local i = 1; -- counter for number of initials
 
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
 
while names[i] do -- loop through the table
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
if is_suffix (names[i]) then -- if a legitimate suffix
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
break; -- and done because suffix must fall at the end of a name
end -- no error message if not a suffix; possibly because of Romanization
end
end
elseif 12 == len then -- LCCN should be aadddddddddd
if 3 > i then
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
else
i = i + 1; -- bump the counter
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 table.concat(initials) -- Vancouver format does not include spaces.
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


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


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


--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
Formats a list of people (authors, contributors, editors, interviewers, translators)


Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.  If embargo date is
names in the list will be linked when
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
|<name>-link= has a value
|embargo= was not set in this cite.
|<name>-mask- does NOT have a value; masked names are presumed to have been
rendered previously so should have been linked there


]]
when |<name>-mask=0, the associated name is not rendered
 
local function is_embargoed (embargo)
if is_set (embargo) then
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
 
--[[--------------------------< P M C >------------------------------------------------------------------------
 
Format a PMC, do simple error checking, and check for embargoed articles.
 
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
be linked to the article.  If the embargo date is today or in the past, or if it is empty or omitted, then the
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 link.  Function 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 list_people (control, people, etal)
local test_limit = 5000000; -- update this value as PMCs approach
local sep;
local handler = cfg.id_handlers['PMC'];
local namesep;
local err_cat = ''; -- presume that PMC is valid
local format = control.format;
local maximum = control.maximum;
local text;
local name_list = {};


if id:match("[^%d]") then -- if PMC has anything but digits
if 'vanc' == format then -- Vancouver-like name styling?
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
else -- PMC is only digits
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
local id_num = tonumber(id); -- convert id to a number for range testing
else
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
end
end
end
if is_set (embargo) then -- is PMC is still embargoed?
if sep:sub (-1, -1) ~= " " then sep = sep .. " " end
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
for i, person in ipairs (people) do
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
if utilities.is_set (person.last) then
local mask = person.mask;
local one;
local sep_one = sep;
 
if utilities.is_set (maximum) and i > maximum then
etal = true;
break;
end
if mask then
local n = tonumber (mask); -- convert to a number if it can be converted; nil else
if n then
one = 0 ~= n and string.rep("&mdash;", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
else
one = mask; -- replace name with mask text (must include name-list separator)
sep_one = " "; -- modify name-list separator
end
else
one = person.last; -- get surname
local first = person.first -- get given name
if utilities.is_set (first) then
if ("vanc" == format) then -- if Vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first, nil, i) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first;
end
end
if utilities.is_set (person.link) then
one = utilities.make_wikilink (person.link, one); -- link author/editor
end
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
table.insert (name_list, one); -- add it to the list of names
table.insert (name_list, sep_one); -- add the proper name-list separator
end
end
end
 
local count = #name_list / 2; -- (number of names + number of separators) divided by 2
if 0 < count then
if 1 < count and not etal then
if 'amp' == format then
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
elseif 'and' == format then
if 2 == count then
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
else
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
end
end
end
name_list[#name_list] = nil; -- erase the last separator
end
 
local result = table.concat (name_list); -- construct list
if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al.
end
end
return text;
return result, count; -- return name-list string and count of number of names (count used for editor names only)
end
end


-- Formats a DOI and checks for DOI errors.
--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------


-- DOI names contain two parts: prefix and suffix separated by a forward slash.
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise
-- Prefix: directory indicator '10.' followed by a registrant code
returns an empty string.
--  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,
namelist is one of the contributor-, author-, or editor-name lists chosen in that
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
order.  year is Year or anchor_year.


-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
]]
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.


local function doi(id, inactive)
local function make_citeref_id (namelist, year)
local cat = ""
local names={}; -- a table for the one to four names and year
local handler = cfg.id_handlers['DOI'];
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
names[i] = v.last
local text;
if i == 4 then break end -- if four then done
if is_set(inactive) then
end
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
table.insert (names, year); -- add the year at the end
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
local id = table.concat(names); -- concatenate names and year for CITEREF id
if is_set(inactive_year) then
if utilities.is_set (id) then -- if concatenation is not an empty string
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
return "CITEREF" .. id; -- add the CITEREF portion
else
else
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
else  
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
inactive = ""
end
end
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
cat = ' ' .. set_error( 'bad_doi' );
end
return text .. inactive .. cat
end


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


--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
Evaluates the content of name parameters (author, editor, etc.) for variations on
the theme of et al.  If found, the et al. is removed, a flag is set to true and
the function returns the modified name and the flag.


Formats an OpenLibrary link, and checks for associated errors.
This function never sets the flag to false but returns its previous state because
it may have been set by previous passes through this function or by the associated
|display-<names>=etal parameter


]]
]]
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 name_has_etal (name, etal, nocat, param)
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'authors/OL',
if utilities.is_set (name) then -- name can be nil in which case just return
id=id, separator=handler.separator, encode = handler.encode})
local patterns = cfg.et_al_patterns; -- get patterns from configuration
elseif ( code == "M" ) then
return external_link_id({link=handler.link, label=handler.label,
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
prefix=handler.prefix .. 'books/OL',
if name:match (pattern) then -- if this 'et al' pattern is found in name
id=id, separator=handler.separator, encode = handler.encode})
name = name:gsub (pattern, ''); -- remove the offending text
elseif ( code == "W" ) then
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
return external_link_id({link=handler.link, label=handler.label,
if not nocat then -- no categorization for |vauthors=
prefix=handler.prefix .. 'works/OL',
table.insert( z.message_tail, {utilities.set_message ('err_etal', {param})}); -- and set an error if not added
id=id, separator=handler.separator, encode = handler.encode})
end
else
end
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 name, etal;
end
end




--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
--[[---------------------< N A M E _ I S _ N U M E R I C >----------------------


Validate and format a usenet message id.  Simple error checking, looks for 'id-left@id-right' not enclosed in
Add maint cat when name parameter value does not contain letters.  Does not catch
'<' and/or '>' angle brackets.
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
current version of this test but |first=(1888) is caught.
 
returns nothing


]]
]]


local function message_id (id)
local function name_is_numeric (name, list_name)
local handler = cfg.id_handlers['USENETID'];
if utilities.is_set (name) then
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
end
end
end
 


text = external_link_id({link = handler.link, label = handler.label,
--[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
end
return text
end


--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
Evaluates the content of author and editor parameters for extraneous editor annotations:
ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and
are redundant in editor parameters.  If found, the function adds the editor markup
maintenance category.


This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
returns nothing
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).


]]
]]


local function set_titletype (cite_class, title_type)
local function name_has_ed_markup (name, list_name)
if is_set(title_type) then
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
if "none" == title_type then
 
title_type = ""; -- if |type=none then type parameter not displayed
if utilities.is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
utilities.set_message ('maint_extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
end
end
return title_type; -- if |type= has been set to any other value use that value
end
end
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
end


--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------


Removes irrelevant text and dashes from ISBN number
--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
Similar to that used for Special:BookSources


]]
Evaluates the content of last/surname (authors etc.) parameters for multiple names.
Multiple names are indicated if there is more than one comma or any "unescaped"
semicolons. Escaped semicolons are ones used as part of selected HTML entities.
If the condition is met, the function adds the multiple name maintenance category.


local function clean_isbn( isbn_str )
returns nothing
return isbn_str:gsub( "[^-0-9X]", "" );
end


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


Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
local function name_has_mult_names (name, list_name)
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
local _, commas, semicolons, nbsps;
]]
if utilities.is_set (name) then
local function escape_lua_magic_chars (argument)
_, commas = name:gsub (',', ''); -- count the number of commas
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
-- nbsps probably should be its own separate count rather than merged in
return argument;
-- some way with semicolons because Lua patterns do not support the
-- grouping operator that regex does, which means there is no way to add
-- more entities to escape except by adding more counts with the new
-- entities
_, nbsps = name:gsub ('&nbsp;',''); -- count nbsps
-- There is exactly 1 semicolon per &nbsp; entity, so subtract nbsps
-- from semicolons to 'escape' them. If additional entities are added,
-- they also can be subtracted.
if 1 < commas or 0 < (semicolons - nbsps) then
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
end
end
end
end


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


Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
--[[------------------------< N A M E _ C H E C K S >---------------------------
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.
This function calls various name checking functions used to validate the content
of the various name-holding parameters.


]]
]]


local function strip_apostrophe_markup (argument)
local function name_checks (last, first, list_name)
if not is_set (argument) then return argument; end
local accept_name;


while true do
if utilities.is_set (last) then
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
if not accept_name then -- <last> not wrapped in accept-as-written markup
argument=argument:gsub("%'%'%'%'", "");
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
elseif argument:match ("%'%'%'") then -- bold (3)
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
argument=argument:gsub("%'%'%'", "");
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
elseif argument:match ("%'%'") then -- italic (2)
argument=argument:gsub("%'%'", "");
else
break;
end
end
end
end
return argument; -- done
end


--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
if utilities.is_set (first) then
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>


Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
if not accept_name then -- <first> not wrapped in accept-as-written markup
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
end
end


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


local function make_coins_title (title, script)
if is_set (title) then
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
else
title=''; -- if not set, make sure title is an empty string
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)
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
else
script=''; -- if not set, make sure script is an empty string
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
return title .. script; -- return the concatenation
end


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


Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
Searches through args in sequential order to find |lastn= and |firstn= parameters
(or their aliases), and their matching link and mask parameters. Stops searching
when both |lastn= and |firstn= are not found in args after two sequential attempts:
found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the
search is done.


]]
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 get_coins_pages (pages)
When an author or editor parameter contains some form of 'et al.', the 'et al.'
local pattern;
is stripped from the parameter and a flag (etal) returned that will cause list_people()
if not is_set (pages) then return pages; end -- if no page numbers then we're done
to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps
'et al.' out of the template's metadata.  When this occurs, an error is emitted.
while true do
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
if nil == pattern then break; end -- no more urls
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
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


-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
]]
local function remove_wiki_link( str )
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end));
end


-- Converts a hyphen to a dash
local function extract_names(args, list_name)
local function hyphen_to_dash( str )
local names = {}; -- table of names
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
local last; -- individual name components
return str;
local first;
end
local link;
return str:gsub( '-', '–' );
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal = false; -- return value set to true when we find some form of et al. in an author parameter
 
local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging
while true do
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
 
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last, first = name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks
if first and not last then -- if there is a firstn without a matching lastn
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias
table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', {
first_alias, -- param name of alias missing its mate
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
if 2 <= count then -- two missing names and we give up
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
local result;
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
if first then
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup
end
 
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { utilities.set_message ( 'err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
return names, etal; -- all done, return our list of names and the etal flag
end
end


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


Joins a sequence of strings together while checking for duplicate separation characters.
--[[---------------------< G E T _ I S O 6 3 9 _ C O D E >----------------------
 
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
 
Returns the language name and associated two- or three-character 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.


]]
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of
languages that in some cases may include extensions. For example, code 'cbk-zam'
and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
code 'cbk' or name 'Chavacano'.  Most (all?) of these languages are not used a
'language' codes per se, rather they are used as sub-domain names: cbk-zam.wikipedia.org.
A list of language names and codes supported by fetchLanguageNames() can be found
at Template:Citation Style documentation/language/doc


local function safe_join( tbl, duplicate_char )
Names that are included in the list will be found if that name is provided in the
--[[
|language= parameter.  For example, if |language=Chavacano de Zamboanga, that name
Note: we use string functions here, rather than ustring functions.
will be found with the associated code 'cbk-zam'.  When names are found and the
associated code is not two or three characters, this function returns only the
WikiMedia language name.
 
Some language names have multiple entries under different codes:
Aromanian has code rup and code roa-rup
When this occurs, this function returns the language name and the 2- or 3-character code
 
Adapted from code taken from Module:Check ISO 639-1.
 
]]
 
local function get_iso639_code (lang, this_wiki_code)
if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
end
 
local ietf_code; -- because some languages have both IETF-like codes and ISO 639-like codes
local ietf_name;
This has considerably faster performance and should work correctly as
local langlc = mw.ustring.lower (lang); -- lower-case version for comparisons
long as the duplicate_char is strict ASCII. The strings
 
in tbl may be ASCII or UTF8.
for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language
]]
if langlc == mw.ustring.lower (name) then
if 2 == #code or 3 == #code then -- two- or three-character codes only; IETF extensions not supported
local str = ''; -- the output string
return name, code; -- so return the name and the code
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
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
else
comp = value;
end
end
-- typically duplicate_char is sepc
ietf_code = code; -- remember that we found an IETF-like code and save its name
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
ietf_name = name; -- but keep looking for a 2- or 3-char code
--   Because individual string segments often (always?) begin with terminal punct for th
end
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
end
trim = false;
-- didn't find name with 2- or 3-char code; if IETF-like code found return
end_chr = str:sub(-1,-1); -- get the last character of the output string
return ietf_code and ietf_name or lang; -- associated name; return original language text else
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
end
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
--[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------
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 >--------------------------------------------
Gets language name from a provided two- or three-character ISO 639 code.  If a code
is recognized by MediaWiki, use the returned name; if not, then use the value that
was provided with the language parameter.


For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
When |language= contains a recognized language (either code or name), the page is
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
assigned to the category for that code: Category:Norwegian-language sources (no).
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
For valid three-character code languages, the page is assigned to the single category
These things are not currently possible in this module so are left to the editor to do.
for '639-2' codes: Category:CS1 ISO 639-2 language sources.


This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
Languages that are the same as the local wiki are not categorized. MediaWiki does
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
not recognize three-character equivalents of two-character codes: code 'ar' is
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
recognized but code 'ara' is not.
[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/)
This function supports multiple languages in the form |language=nb, French, th
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
where the language names or codes are separated from each other by commas with
 
optional space characters.
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
because the code editor gets confused between character insertion point and cursor position.


]]
]]


local function is_good_vanc_name (last, first)
local function language_parameter (lang)
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 code; -- the two- or three-character language code
add_vanc_error ();
local name; -- the language name
return false; -- not a string of latin characters; Vancouver required Romanization
local language_list = {}; -- table of language names to be rendered
end;
local names_table = {}; -- table made from the value assigned to |language=
return true;
end


--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name


Attempts to convert names to initials in support of |name-list-format=vanc. 
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list


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/.
for _, lang in ipairs (names_table) do -- reuse lang
name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap


Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
if name then -- there was a remapped code so
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 not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private IETF tag
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip IETF tags from code
end
else
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any IETF-like tags from code
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
end
end


This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
if utilities.is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if utilities.is_set (code) then -- only 2- or 3-character codes
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names


]]
if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if 2 == code:len() then -- and is a two-character code
utilities.add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character code)
utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support multiple three-character code categories per cs1|2 template
end
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled
utilities.add_prop_cat ('local_lang_source', {name, code}); -- categorize it
end
else
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
name = utilities.make_sep_list (#language_list, language_list);


local function reduce_to_initials(first)
if this_wiki_name == name then
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
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.
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
--[[ TODO: should only return blank or name rather than full list
so we can clean up the bunched parenthetical elements Language, Type, Format
]]
end
end


--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
 
Gets the default CS style configuration for the given mode.
Formats a list of people (e.g. authors / editors)
Returns default separator and either postscript as passed in or the default.
 
In CS1, the default postscript and separator are '.'.
In CS2, the default postscript is the empty string and the default separator is ','.
]]
]]
 
local function set_cs_style (postscript, mode)
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
if utilities.is_set(postscript) then
-- emit a maintenance message if user postscript is the default cs1 postscript
-- we catch the opposite case for cs2 in set_style
if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then
utilities.set_message ('maint_postscript');
end
else
postscript = cfg.presentation['ps_' .. mode];
end
return cfg.presentation['sep_' .. mode], postscript;
end
 
--[[--------------------------< S E T _ S T Y L E >-----------------------------
Sets the separator and postscript styles. Checks the |mode= first and the
#invoke CitationClass second. Removes the postscript if postscript == none.
]]
local function set_style (mode, postscript, cite_class)
local sep;
local sep;
local namesep;
if 'cs2' == mode then
local format = control.format
sep, postscript = set_cs_style (postscript, 'cs2');
local maximum = control.maximum
elseif 'cs1' == mode then
local lastauthoramp = control.lastauthoramp;
sep, postscript = set_cs_style (postscript, 'cs1');
local text = {}
elseif 'citation' == cite_class then
 
sep, postscript = set_cs_style (postscript, 'cs2');
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = ','; -- name-list separator between authors is a comma
namesep = ' '; -- last/first separator is a space
else
else
sep = ';' -- name-list separator between authors is a semicolon
sep, postscript = set_cs_style (postscript, 'cs1');
namesep = ', ' -- last/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
end


local count = #text / 2; -- (number of names + number of separators) divided by 2
if cfg.keywords_xlate[postscript:lower()] == 'none' then
if count > 0 then
-- emit a maintenance message if user postscript is the default cs2 postscript
if count > 1 and is_set(lastauthoramp) and not etal then
-- we catch the opposite case for cs1 in set_cs_style
text[#text-2] = " & "; -- replace last separator with ampersand text
if 'cs2' == mode or 'citation' == cite_class then
utilities.set_message ('maint_postscript');
end
end
text[#text] = nil; -- erase the last separator
postscript = '';
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
end
return result, count
return sep, postscript
end
end


--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
--[=[-------------------------< I S _ P D F >-----------------------------------


Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
Determines if a URL has the file extension that is one of the PDF file extensions
used by [[MediaWiki:Common.css]] when applying the PDF icon to external links.


namelist is one of the contributor-, author-, or editor-name lists chosen in that order.  year is Year or anchor_year.
returns true if file extension is one of the recognized extensions, else false


]]
]=]
local function anchor_id (namelist, year)
 
local names={}; -- a table for the one to four names and year
local function is_pdf (url)
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
return url:match ('%.pdf$') or url:match ('%.PDF$') or
names[i] = v.last
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
if i == 4 then break end -- if four then done
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end
table.insert (names, year); -- add the year at the end
local id = table.concat(names); -- concatenate names and year for CITEREF id
if is_set (id) then -- if concatenation is not an empty string
return "CITEREF" .. id; -- add the CITEREF portion
else
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end
end




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


Evaluates the content of author and editor name parameters for variations on the theme of et al.  If found,
Applies CSS style to |format=, |chapter-format=, etc.  Also emits an error message
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
if the format parameter does not have a matching URL parameter.  If the format parameter
 
is not set and the URL contains a file extension that is recognized as a PDF document
This function never sets the flag to false but returns it's previous state because it may have been set by
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
the appropriate styling.


]]
]]


local function name_has_etal (name, etal, nocat)
local function style_format (format, url, fmt_param, url_param)
 
if utilities.is_set (format) then
if is_set (name) then -- name can be nil in which case just return
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
if not utilities.is_set (url) then
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} ); -- add an error message
if name:match (etal_pattern) then -- variants on et al.
name = name:gsub (etal_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
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
elseif is_pdf (url) then -- format is not set so if URL is a PDF file then
format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF
else
format = ''; -- empty string for concatenation
end
end
return name, etal; --
return format;
end
end


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


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


This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
Returns a number that defines the number of names displayed for author and editor
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
name lists and a Boolean flag to indicate when et al. should be appended to the name list.


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
When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps 'et al.' out of the
return the number and the previous state of the 'etal' flag (false by default
template's metadata.  When this occurs, the page is added to a maintenance category.
but may have been set to true if the name list contains some variant of the text 'et al.').


]]
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number
that is one greater than the 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 extract_names(args, list_name)
In all other cases, returns nil and the previous state of the 'etal' flag.
local names = {}; -- table of names
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal=false; -- return value set to true when we find some form of et al. in an author parameter


local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
inputs:
while true do
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
count: #a or #e
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
list_name: 'authors' or 'editors'
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
etal: author_etal or editor_etal
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.
]]
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
local function get_display_names (max, count, list_name, etal, param)
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
if utilities.is_set (max) then
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
count = count + 1; -- number of times we haven't found last and first
max = count + 1; -- number of authors + 1 so display all author name plus et al.
if 2 <= count then -- two missing names and we give up
etal = true; -- overrides value set by extract_names()
break; -- normal exit or there is a two-name hole in the list; can't tell which
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
max = nil;
end
end
else -- we have last with or without a first
else -- not a valid keyword or number
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, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link;
max = nil; -- unset; as if |display-xxxxors= had not been set
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
end
end
return names, etal; -- all done, return our list of names
return max, etal;
end
end


--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------


Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for
--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
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
Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be
some form of p. or pp. abbreviation in the first characters of the parameter content.
 
check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value:
good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px
      where x and X are letters and # is a digit
bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG


]]
]]


local function extract_ids( args )
local function extra_text_in_page_check (val, name)
local id_list = {}; -- list of identifiers found in args
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
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
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
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 val:match (pattern) then -- when a match, error so
if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list
table.insert (z.message_tail, {utilities.set_message ('err_extra_text_pages', {name}, true)}); -- add error message
end
return; -- and done
return id_list;
end
end
end
end
end


--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------


Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------


inputs:
Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
id_list – table of identifiers built by extract_ids()
options – table of various template parameter values used to modify some manually handled identifiers


]]
For |volume=:
 
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
local function build_id_list( id_list, options )
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
local new_list, handler = {};
are allowed.


function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
For |issue=:
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
parameter content (all case insensitive).
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
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
-- fallback to read-only cfg
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
handler = setmetatable( { ['id'] = v }, fallback(k) );
if handler.mode == 'external' then
table.insert( new_list, {handler.label, external_link_id( handler ) } );
elseif handler.mode == 'internal' then
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
elseif handler.mode ~= 'manual' then
error( cfg.messages['unknown_ID_mode'] );
elseif k == 'DOI' then
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
elseif k == 'ARXIV' then
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
elseif k == 'ASIN' then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' or k == 'OLA' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISMN' then
table.insert( new_list, {handler.label, ismn( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
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()
<val> is |volume= or |issue= parameter value
return a[1] < b[1];
<name> is |volume= or |issue= parameter name for error message
<selector> is 'v' for |volume=, 'i' for |issue=
 
sets error message on failure; returns nothing
 
]]
 
local function extra_text_in_vol_iss_check (val, name, selector)
if not utilities.is_set (val) then
return;
end
end
table.sort( new_list, comp );
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;
for k, v in ipairs( new_list ) do
 
new_list[k] = v[2];
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
val = val:lower(); -- force parameter value to lower case
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
if val:match (pattern) then -- when a match, error so
table.insert (z.message_tail, {utilities.set_message (handler, {name}, true)}); -- add error message
return; -- and done
end
end
end
return new_list;
end
end
 


--[[--------------------------< C O I N S >--------------------------------------------------------------------


COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------


]]
split apart a |vauthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
rendered citation and in the metadata.  Individual author names may be wikilinked


local function COinS(data, class)
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
if 'table' ~= type(data) or nil == next(data) then
 
return '';
]=]
end
 
local function get_v_name_table (vparam, output_table, output_link_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local wl_type, label, link; -- wl_type not used here; just a placeholder
local ctx_ver = "Z39.88-2004";
local i = 1;
-- treat table strictly as an array with only set values.
while name_table[i] do
local OCinSoutput = setmetatable( {}, {
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
__newindex = function(self, key, value)
local name = name_table[i];
if is_set(value) then
i = i + 1; -- bump indexer to next segment
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses
break; -- and done reassembling so
end
i = i + 1; -- bump indexer
end
end
end
table.insert (output_table, name); -- and add corporate name to the output table
});
table.insert (output_link_table, ''); -- no wikilink
else
if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or
wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then
table.insert (output_table, label); -- add this name
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier
if 1 == wl_type then
if 'arxiv' == class then -- set genre according to the type of citation template we are rendering
table.insert (output_link_table, label); -- simple wikilink [[D]]
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
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only
end
if is_set (data.Map) then
i = i + 1;
OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical
end
else
return output_table;
OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles
end
end
-- these used onlu for periodicals
OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall
OCinSoutput["rft.chron"] = data.Chron; -- free-form date components
OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata


elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier
if 'report' == class or 'techreport' == class then -- cite report and cite techreport
OCinSoutput["rft.genre"] = "report";
elseif 'conference' == class then -- cite conference when Periodical not set
OCinSoutput["rft.genre"] = "conference";
elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then
if is_set (data.Chapter) then
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title
else
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
OCinSoutput["rft.btitle"] = data.Title; -- book only
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
OCinSoutput["rft.series"] = data.Series; -- book only
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
OCinSoutput["rft.edition"] = data.Edition; -- book only
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
end
-- and now common parameters (as much as possible)
OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
if k == 'ISBN' then v = clean_isbn( v ) end
local id = cfg.id_handlers[k].COinS;
if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
elseif string.sub (id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords
OCinSoutput[ id ] = v;
elseif id then -- when cfg.id_handlers[k].COinS is not nil
OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v }; -- others; provide a url
end
end


--[[
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
local id, value = cfg.id_handlers[k].COinS;
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
OCinSoutput[ id ] = value;
end
end
]]
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = v.last, v.first;
if k == 1 then -- for the first author name only
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name
end
else -- for all other authors
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation
end
end
end


OCinSoutput.rft_id = data.URL;
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end


Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.


--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.


Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.


Returns the language name and associated ISO639-1 code.  Because case of the source may be incorrect or different from the case that Wikimedia
]]
uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along
with the code.  When there is no match, we return the original language name string.


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 function parse_vauthors_veditors (args, vparam, list_name)
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 names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
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 v_name_table = {};
returns only the Wikimedia language name.
local v_link_table = {}; -- when name is wikilinked, targets go in this table
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
local corporate = false;


Adapted from code taken from Module:Check ISO 639-1.
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas


]]
for i, v_name in ipairs(v_name_table) do
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
local accept_name;
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>


local function get_iso639_code (lang)
if accept_name then
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
last = v_name;
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
corporate = true; -- flag used in list_people()
end
elseif string.find(v_name, "%s") then
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
add_vanc_error (cfg.err_msg_supl.punctuation, i);
-- ('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
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
local lastfirstTable = {}
end
lastfirstTable = mw.text.split(v_name, "%s+")
end
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end


--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
 
suffix = first; -- not initials so assume that whatever we got is a generational suffix
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.
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
if not utilities.is_set (last) then
first = ''; -- unset
last = v_name; -- last empty because something wrong with first
add_vanc_error (cfg.err_msg_supl.name, i);
end
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error (cfg.err_msg_supl.initials, i); -- matches a space between two initials
end
else
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
end
if utilities.is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error (cfg.err_msg_supl.initials, i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit
if utilities.is_set (suffix) then
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
suffix = ''; -- unset so we don't add this suffix to all subsequent names
end
else
if not corporate then
is_good_vanc_name (last, '', nil, i);
end
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
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
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
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
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.
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


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.


See Help talk:Citation Style_1#An ISO 639-1 language name test
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------


When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
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.
select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.


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.
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest;
|editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn)


]]
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
way to do this, I just haven't discovered what that way is.


local function language_parameter (lang)
Emits an error message when more than one xxxxor name source is provided.
local code; -- the ISO639-1 two character code
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_table = {}; -- table made from the value assigned to |language=


names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.


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


if lang:match ('^%a%a%-') then -- strip ietf language tags from code
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
local lastfirst = false;
end
if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ...
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
end
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
lastfirst = true;
if is_set (name) then -- if Language specified a valid ISO639-1 code
end
code = lang:lower(); -- save it
 
else
if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
end
(true == lastfirst and utilities.is_set (xxxxors)) then
local err_name;
if is_set (code) then
if 'AuthorList' == list_name then -- figure out which name should be used in error message
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
err_name = 'author';
if 'en' ~= code then -- English not the language
else
add_prop_cat ('foreign_lang_source', {name, code})
err_name = 'editor';
end
end
else
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters',
add_maint_cat ('unknown_lang'); -- add maint category if not already added
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
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 true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if 2 >= code then
if utilities.is_set (vxxxxors) then return 2 end;
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
if utilities.is_set (xxxxors) then return 3 end;
elseif 2 < code then
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
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
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
end


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


Set style settings for CS1 citation templates. Returns separator and postscript settings
--[[--------------------------< 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, live, dead, etc.).  When the parameter value has not been assigned a value (missing
or empty in the source template) the function returns the value specified by ret_val.  If the parameter value is one
of the list of allowed values returns the translated value; else, emits an error message and returns the value
specified by ret_val.


]]
]]


local function set_cs1_style (ps)
local function is_valid_parameter_value (value, name, possible, ret_val)
if not is_set (ps) then -- unless explicitely set to something
if not utilities.is_set (value) then
ps = '.'; -- terminate the rendered citation with a period
return ret_val; -- an empty parameter is ok
elseif utilities.in_array (value, possible) then
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
else
table.insert( z.message_tail, { utilities.set_message ( 'err_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return ret_val;
end
end
return '.', ps; -- separator is a full stop
end
end


--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------


Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------


]]
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
when the last character is not a sepc character or when the last three characters are not sepc followed by two
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
single space character.
 
]]


local function set_cs2_style (ps, ref)
local function terminate_name_list (name_list, sepc)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
ps = ''; -- make sure it isn't nil
return name_list; -- just return the name list
end
elseif (string.sub (name_list, -1, -1) == sepc) or (string.sub (name_list, -3, -1) == sepc .. ']]') then -- if last name in list ends with sepc char
if not is_set (ref) then -- if |ref= is not set
return name_list .. " "; -- don't add another
ref = "harv"; -- set default |ref=harv
else
return name_list .. sepc .. ' '; -- otherwise terminate the name list
end
end
return ',', ps, ref; -- separator is a comma
end
end


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


When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
rendered style.
 
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)
if not utilities.is_set (volume) and not utilities.is_set (issue) then
return '';
end
if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, hyphen_to_dash (volume), issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, hyphen_to_dash (volume)}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end


local function get_settings_from_cite_class (ps, ref, cite_class)
if 'podcast' == cite_class and utilities.is_set (issue) then
local sep;
return wrap_msg ('issue', {sepc, issue}, lower);
if (cite_class == "citation") then -- for citation templates (CS2)
sep, ps, ref = set_cs2_style (ps, ref);
else -- not a citation template so CS1
sep, ps = set_cs1_style (ps);
end
end


return sep, ps, ref -- return them all
local vol = ''; -- here for all cites except magazine
if utilities.is_set (volume) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)}); -- not bold
utilities.add_prop_cat ('long_vol');
else -- four or less characters
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold
end
end
if utilities.is_set (issue) then
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
end
return vol;
end
end


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


Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
config.CitationClass from the template's #invoke: to establish style.


]]
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
 
Singular has priority over plural when both are provided.
 
]]


local function set_style (mode, ps, ref, cite_class)
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
local sep;
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
if utilities.is_set (sheet) then
sep, ps, ref = set_cs2_style (ps, ref);
if 'journal' == origin then
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
sep, ps = set_cs1_style (ps);
else
else -- anything but cs1 or cs2
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
elseif utilities.is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
end
if 'none' == ps:lower() then -- if assigned value is 'none' then
 
ps = ''; -- set to empty string
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
if utilities.is_set (page) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif utilities.is_set (pages) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
end
return sep, ps, ref
return '', '', '', ''; -- return empty strings
end
end


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


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


returns true if file extension is one of the recognized extension, else false
returns one of the in-source locators: page, pages, or at.


]=]
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
for use in COinS.  This COinS thing is done because here we convert an interwiki-link to an external link and
add an icon span around that; get_coins_pages() doesn't know about the span.  TODO: should it? 
 
TODO: add support for sheet and sheets?; streamline;
 
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
to a new name)?


local function is_pdf (url)
]]
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
end


--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
local function insource_loc_get (page, page_orig, pages, pages_orig, at)
local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)


Applies css style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
if utilities.is_set (page) then
not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
if utilities.is_set (pages) or utilities.is_set (at) then
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
pages = ''; -- unset the others
the appropriate styling.
at = '';
end
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.


]]
ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label
if ws_url then
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
coins_pages = ws_label;
end
elseif utilities.is_set (pages) then
if utilities.is_set (at) then
at = ''; -- unset
end
extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.


local function style_format (format, url, fmt_param, url_param)
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label
if is_set (format) then
if ws_url then
format = wrap_style ('format', format); -- add leading space, parenthases, resize
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
if not is_set (url) then
pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
coins_pages = ws_label;
end
elseif utilities.is_set (at) then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label
if ws_url then
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
end
return format;
return page, pages, at, coins_pages;
end
end


--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
 
Returns a number that may or may not limit the length of the author or editor name lists.
 
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
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.').
 
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
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.'


In all other cases, returns nil and the previous state of the 'etal' flag.
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value


]]
]]


local function get_display_authors_editors (max, count, list_name, etal)
local function is_unique_archive_url (archive, url, c_url, source, date)
if is_set (max) then
if utilities.is_set (archive) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
if archive == url or archive == c_url then
max = count + 1; -- number of authors + 1 so display all author name plus et al.
table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)}); -- add error message
etal = true; -- overrides value set by extract_names()
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
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
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;
return archive, date;
end
end


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


Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
abbreviation in the first characters of the parameter content.


check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the
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
save snapshot URL or to calendar pages. When the archive URL is 'https://web.archive.org/save/' (or http://...)
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
archive.org saves a snapshot of the target page in the URL.  That is something that Wikipedia should not allow
unwitting readers to do.


]]
When the archive.org URL does not have a complete timestamp, archive.org chooses a snapshot according to its own
algorithm or provides a calendar 'search' result.  [[WP:ELNO]] discourages links to search results.


local function extra_text_in_page_check (page)
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
-- local good_pattern = '^P[^%.P%l]';
|archive-date= and an error message when:
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?
|archive-url= holds an archive.org save command URL
-- local bad_pattern = '^[Pp][Pp]';
|archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
correct place
otherwise returns |archive-url= and |archive-date=


if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
There are two mostly compatible archive.org URLs:
add_maint_cat ('extra_text');
//web.archive.org/<timestamp>... -- the old form
end
//web.archive.org/web/<timestamp>... -- the new form
-- 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


The old form does not support or map to the new form when it contains a display flag.  There are four identified flags
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
we don't check for these specific flags but we do check the form.


--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
This function supports a preview mode.  When the article is rendered in preview mode, this function may return a modified
archive URL:
for save command errors, return undated wildcard (/*/)
for timestamp errors when the timestamp has a wildcard, return the URL unmodified
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)


This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
]=]
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.


Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
local function archive_url_check (url, date)
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
local err_msg = ''; -- start with the error message empty
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
local path, timestamp, flag; -- portions of the archive.org URL
 
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
 
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
]]
 
local function parse_vauthors_veditors (args, vparam, list_name)
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local 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;
 
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
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 url:match('//web%.archive%.org/save/') then -- if a save command URL, we don't want to allow saving of the target page
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
err_msg = cfg.err_msg_supl.save;
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
last = v_name:match ('^%(%((.+)%)%)$')
elseif url:match('//liveweb%.archive%.org/') then
corporate = true;
err_msg = cfg.err_msg_supl.liveweb;
elseif string.find(v_name, "%s") then
else
    lastfirstTable = {}
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation
    lastfirstTable = mw.text.split(v_name, "%s")
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
err_msg = cfg.err_msg_supl.timestamp;
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
if '*' ~= flag then
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
end
elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element
err_msg = cfg.err_msg_supl.path;
elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element)
err_msg = cfg.err_msg_supl.flag;
elseif utilities.is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = cfg.err_msg_supl.flag;
else
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
return url, date; -- return ArchiveURL and ArchiveDate
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
end
end
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") 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
end
return names, etal; -- all done, return our list of names
-- if here, something not right so
table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } ); -- add error message and
if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
else
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
end
end
end


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


Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
--[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
 
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
similarly, |editorn= (and aliases) highest and |editors= lowest
 
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
way to do this, I just haven't discovered what that way is.


Emits an error message when more than one xxxxor name source is provided.
check |place=, |publication-place=, |location= to see if these params include digits.  This function added because
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)


In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
returns the original parameter value without modification; added maint cat when parameter value contains digits


]]
]]


local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local function place_check (param_val)
local lastfirst = false;
if not utilities.is_set (param_val) then -- parameter empty or omitted
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
return param_val; -- return that empty state
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
lastfirst=true;
end
end
 
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
(is_set (vxxxxors) and is_set (xxxxors)) or
utilities.set_message ('maint_location'); -- yep, add maint cat
(true == lastfirst and is_set (xxxxors)) then
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
end
return param_val; -- and done
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;
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


--[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------


--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
compares |title= value against list of known generic title patterns.  Returns true when pattern matches; nil else


This function is used to validate a parameter's assigned value for those parameters that have only a limited number
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
index [1].  index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
true; else, emits an error message and returns false.
or a pattern search (false).  The intent of all this complexity is to make these searches as fast as possible so
that we don't run out of processing time on very large articles.


]]
]]


local function is_valid_parameter_value (value, name, possible)
local function is_generic_title (title)
if not is_set (value) then
title = mw.ustring.lower(title); -- switch title to lower case
return true; -- an empty parameter is ok
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments
elseif in_array(value:lower(), possible) then
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
return true;
return true; -- found English generic title so done
else
elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script
return false
return true; -- found local generic title so done
end
end
end
end
end
end




--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
 
 
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else
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)
local function is_archived_copy (title)
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
title = mw.ustring.lower(title); -- switch title to lower case
return name_list .. " "; -- don't add another
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
else
return true;
return name_list .. sepc .. ' '; -- otherwise terninate the name list
elseif cfg.special_case_translation.archived_copy['local'] then
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
return true;
end
end
end
end
end




--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------


returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
This is the main function doing the majority of the citation formatting.
or formatted issue, or an empty string if neither are set.


]]
]]
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not is_set (volume) and not is_set (issue) then
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 vol = '';
if is_set (volume) then
if (4 < mw.ustring.len(volume)) then
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
else
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end


local function citation0( config, args )
--[[
Load Input Parameters
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
]]
local A = argument_wrapper ( args );
local i


--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
-- Pick out the relevant fields from the arguments.  Different citation templates
-- define different field names for the same underlying things.


adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
local author_etal;
The return order is:
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
page, pages, sheet, sheets
local Authors;
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
local Collaboration = A['Collaboration'];


Singular has priority over plural when both are provided.
do -- to limit scope of selected
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
if 1 == selected then
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
utilities.set_message ('maint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
end
if utilities.is_set (Collaboration) then
author_etal = true; -- so that |display-authors=etal not required
end
end


]]
local editor_etal;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=


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


local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
local Title = A['Title'];
local TitleLink = A['TitleLink'];


if is_set (page) then
local auto_select = ''; -- default is auto
if is_journal then
local accept_link;
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup
elseif not nopp then
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
auto_select = TitleLink; -- remember selection for later
else
TitleLink = ''; -- treat as if |title-link= would have been empty
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
end
 
elseif is_set(pages) then
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
if is_journal then
 
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
if 'map' == config.CitationClass and 'section' == Chapter_origin then
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
elseif not nopp then
Chapter = ''; -- unset for now; will be reset later from |map= if present
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
end
else
 
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
local Periodical = A['Periodical'];
local Periodical_origin = '';
if utilities.is_set (Periodical) then
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local i;
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {Periodical_origin}, true)});
end
end
end
end
return '', '', '', ''; -- return empty strings
end


--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error
table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
end


This is the main function doing the majority of the citation formatting.
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
Periodical_origin = A:ORIGIN('MailingList');
end


]]
local ScriptPeriodical = A['ScriptPeriodical'];


local function citation0( config, args)
-- web and news not tested for now because of
--[[  
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
Load Input Parameters
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
]]
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
local A = argument_wrapper( args );
if p[config.CitationClass]  then
local i
table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
end
end
local Volume;
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
if 'citation' == config.CitationClass then
if utilities.is_set (Periodical) then
if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif utilities.is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
end
else
Volume = A['Volume']; -- and does for non-'periodical' cites
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
Volume = A['Volume'];
end
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v');


-- Pick out the relevant fields from the arguments.  Different citation templates
local Issue;
-- define different field names for the same underlying things.
if 'citation' == config.CitationClass then
local author_etal;
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
local Authors;
Issue = hyphen_to_dash (A['Issue']);
local NameListFormat = A['NameListFormat'];
end
 
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
do -- to limit scope of selected
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
Issue = hyphen_to_dash (A['Issue']);
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
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');


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


local editor_etal;
local Edition = A['Edition'];
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
local Editors;
local Place = place_check (A['Place'], A:ORIGIN('Place'));
 
do -- to limit scope of selected
local PublisherName = A['PublisherName'];
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
local PublisherName_origin = A:ORIGIN('PublisherName');
if 1 == selected then
if utilities.is_set (PublisherName) then
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
local i = 0;
elseif 2 == selected then
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
if i then -- non-zero when markup was stripped so emit an error message
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
end
end
end
end


local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
local Translators; -- assembled translators name list
local Newsgroup_origin = A:ORIGIN('Newsgroup');
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 
if 'newsgroup' == config.CitationClass then
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
local Contributors; -- assembled contributors name list
local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
local Contribution = A['Contribution'];
if utilities.is_set (error_text) then
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
table.insert( z.message_tail, {error_text, error_state} );
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
end
if 0 < #c then
if not is_set (Contribution) then -- |contributor= requires |contribution=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
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
end
Contribution = nil; -- unset
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'
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
NameListFormat = ''; -- anything else, set to empty string
end
end


local Year = A['Year'];
local URL = A['URL']
local PublicationDate = A['PublicationDate'];
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
local OrigYear = A['OrigYear'];
local Date = A['Date'];
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
local LayDate = A['LayDate'];
UrlAccess = nil;
------------------------------------------------- Get title data
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
local Title = A['Title'];
end
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local ChapterURL = A['ChapterURL'];
local Conference = A['Conference'];
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
local TransTitle = A['TransTitle'];
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
local TitleNote = A['TitleNote'];
ChapterUrlAccess = nil;
local TitleLink = A['TitleLink'];
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
end
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
 
end
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
MapUrlAccess = nil;
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'map-url'}, true ) } );
end


local Chapter = A['Chapter'];
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local ScriptChapter = A['ScriptChapter'];
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
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'];
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
local Volume;
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
local Issue;
no_tracking_cats = "true"; -- set no_tracking_cats
local Page;
end
local Pages;
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
local At;
if this_page.text:match (v) then -- test page name against each pattern
 
no_tracking_cats = "true"; -- set no_tracking_cats
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
break; -- bail out if one is found
Volume = A['Volume'];
end
end
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
end
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category


local Edition = A['Edition'];
local coins_pages;
local PublicationPlace = A['PublicationPlace']
local Place = A['Place'];
local PublisherName = A['PublisherName'];
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
local RegistrationRequired = A['RegistrationRequired'];
 
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end


local Via = A['Via'];
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
local AccessDate = A['AccessDate'];
utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
local ArchiveDate = A['ArchiveDate'];
if PublicationPlace == Place then
local Agency = A['Agency'];
Place = ''; -- unset; don't need both if they are the same
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
end
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end


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


local ID_list = extract_ids( args );
|trans-title= maps to |trans-chapter= when |title= is re-mapped
|url= maps to |chapter-url= when |title= is remapped
All other combinations of |encyclopedia=, |title=, and |article= are not modified
]]


local Quote = A['Quote'];
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS


local LayFormat = A['LayFormat'];
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
local LayURL = A['LayURL'];
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
local LaySource = A['LaySource'];
table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
local Transcript = A['Transcript'];
Encyclopedia = nil; -- unset because not supported by this template
local TranscriptFormat = A['TranscriptFormat'];
end
local TranscriptURL = A['TranscriptURL']
end
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL


local LastAuthorAmp = A['LastAuthorAmp'];
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error
LastAuthorAmp = nil; -- set to empty string
table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
end
end
local no_tracking_cats = A['NoTracking'];
 
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
if utilities.is_set (Encyclopedia) then
no_tracking_cats = nil; -- set to empty string
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
Periodical_origin = A:ORIGIN ('Encyclopedia');
end
end


--these are used by cite interview
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
local Callsign = A['Callsign'];
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
local City = A['City'];
if not utilities.is_set (Chapter) then
local Program = A['Program'];
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle')
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL_origin = URL_origin;


--local variables that are not cs1 parameters
ChapterUrlAccess = UrlAccess;
local use_lowercase; -- controls capitalization of certain static text
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


-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
local Mode = A['Mode'];
Chapter = utilities.make_wikilink (TitleLink, Chapter);
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
end
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
 
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
break; -- bail out if one is found
end
end
end
 
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
 
local NoPP = A['NoPP']
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 is_set(Page) then
if is_set(Pages) or is_set(At) then
Pages = ''; -- unset the others
At = '';
end
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
elseif is_set(Pages) then
if is_set(At) then
At = ''; -- unset
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
 
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
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
 
|trans_title maps to |trans_chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped
 
All other combinations of |encyclopedia, |title, and |article are not modified
 
]]
 
local Encyclopedia = A['Encyclopedia'];
 
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
if is_set(Title) or is_set (ScriptTitle) then
if not is_set(Chapter) then
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
ScriptChapter = ScriptTitle;
TransChapter = TransTitle;
ChapterURL = URL;
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
end
Title = Periodical;
Title = Periodical;
ChapterFormat = Format;
ChapterFormat = Format;
Line 2,843: Line 2,717:
ScriptTitle = '';
ScriptTitle = '';
end
end
else -- |title not set
elseif utilities.is_set (Chapter) then -- |title= not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
Periodical = ''; -- redundant so unset
Periodical = ''; -- redundant so unset
end
end
Line 2,850: Line 2,724:
end
end


-- Special case for cite techreport.
-- special case for cite techreport.
local ID = A['ID'];
if (config.CitationClass == "techreport") then -- 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 utilities.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"?
if not utilities.is_set (ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
else -- ID has a value so emit error message
-- ID = ID .. " " .. set_error('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
end
end
end
end
end
end


-- special case for cite interview
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if (config.CitationClass == "interview") then
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
if is_set(Program) then
local Conference = A['Conference'];
ID = ' ' .. Program;
local BookTitle = A['BookTitle'];
end
local TransTitle_origin = A:ORIGIN ('TransTitle');
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 'conference' == config.CitationClass then
if is_set(BookTitle) then
if utilities.is_set (BookTitle) then
Chapter = Title;
Chapter = Title;
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
Chapter_origin = 'title';
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
ChapterURL = URL;
ChapterURL = URL;
ChapterURLorigin = URLorigin;
ChapterUrlAccess = UrlAccess;
URLorigin = '';
ChapterURL_origin = URL_origin;
URL_origin = '';
ChapterFormat = Format;
ChapterFormat = Format;
TransChapter = TransTitle;
TransChapter = TransTitle;
TransChapter_origin = TransTitle_origin;
Title = BookTitle;
Title = BookTitle;
Format = '';
Format = '';
-- TitleLink = '';
-- TitleLink = '';
TransTitle = '';
TransTitle = '';
URL = '';
URL = '';
Line 2,920: Line 2,762:
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
end
 
-- cite map oddities
-- CS1/2 mode
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
-- separator character and postscript
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
-- controls capitalization of certain static text
local use_lowercase = ( sepc == ',' );
-- cite map oddities
local Cartography = "";
local Cartography = "";
local Scale = "";
local Scale = "";
Line 2,927: Line 2,776:
local Sheets = A['Sheets'] or '';
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
if config.CitationClass == "map" then
if utilities.is_set (Chapter) then
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
end
Chapter = A['Map'];
Chapter = A['Map'];
Chapter_origin = A:ORIGIN('Map');
ChapterURL = A['MapURL'];
ChapterURL = A['MapURL'];
ChapterURL_origin = A:ORIGIN('MapURL');
TransChapter = A['TransMap'];
TransChapter = A['TransMap'];
ChapterURLorigin = A:ORIGIN('MapURL');
ScriptChapter = A['ScriptMap']
ScriptChapter_origin = A:ORIGIN('ScriptMap')
 
ChapterUrlAccess = MapUrlAccess;
ChapterFormat = A['MapFormat'];
ChapterFormat = A['MapFormat'];
 
Cartography = A['Cartography'];
Cartography = A['Cartography'];
if is_set( Cartography ) then
if utilities.is_set ( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
end
Scale = A['Scale'];
Scale = A['Scale'];
if is_set( Scale ) then
if utilities.is_set ( Scale ) then
Scale = sepc .. " " .. Scale;
Scale = sepc .. " " .. Scale;
end
end
end
end


-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
local Series = A['Series'];
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local SeriesLink = A['SeriesLink'];
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'))});
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set
end
 
local Network = A['Network'];
local Network = A['Network'];
local Station = A['Station'];
local Station = A['Station'];
local s, n = {}, {};
local s, n = {}, {};
-- do common parameters first
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
if utilities.is_set (Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
if utilities.is_set (Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
Date = AirDate;
end
 
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
local SeriesNumber = A['SeriesNumber'];


if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
end
-- assemble a table of parts concatenated later into Series
-- 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 utilities.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 utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Issue = ''; -- unset because this is not a unique parameter
Chapter = Title; -- promote title parameters to chapter
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ScriptChapter = ScriptTitle;
ChapterLink = TitleLink; -- alias episodelink
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
ChapterLink = TitleLink; -- alias |episode-link=
TransChapter = TransTitle;
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL = URL;
ChapterURLorigin = A:ORIGIN('URL');
ChapterUrlAccess = UrlAccess;
ChapterURL_origin = URL_origin;
Title = Series; -- promote series to title
Title = Series; -- promote series to title
Line 2,987: Line 2,842:
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
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
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
Series = utilities.make_wikilink (ChapterLink, Series);
end
end
URL = ''; -- unset
URL = ''; -- unset
Line 2,999: Line 2,854:
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of 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?
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
Series = utilities.make_wikilink (SeriesLink, Series);
end
end
Series = wrap_style ('italic-title', Series); -- series is italicized
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
end
end
end
end
-- end of {{cite episode}} stuff
-- end of {{cite episode}} stuff


-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
-- handle type parameter for those CS1 citations that have default values
if 'arxiv' == config.CitationClass then
local TitleType = A['TitleType'];
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
local Degree = A['Degree'];
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
elseif is_set (Series) then -- series is an alias of version
TitleType = set_titletype (config.CitationClass, TitleType);
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis
Series = ''; -- unset
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
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
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
end


-- handle type parameter for those CS1 citations that have default values
if utilities.is_set (TitleType) then -- if type parameter is specified
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
TitleType = set_titletype (config.CitationClass, TitleType);
-- TODO: Hack on TitleType to fix bunched parentheses problem
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
end
end
end


if is_set(TitleType) then -- if type parameter is specified
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
local Date = A['Date'];
end
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
local PublicationDate = A['PublicationDate'];
local Year = A['Year'];


-- 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 utilities.is_set (Date) then
if not is_set (Date) then
Date = Year; -- promote Year to Date
Date = Year; -- promote Year to Date
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
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
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promote PublicationDate to Date
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
PublicationDate = ''; -- unset, no longer needed
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
else
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
end
end
else
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
end
end


if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
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
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.
we get the date used in the metadata.
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]


Date validation supporting code is in Module:Citation/CS1/Date_validation
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
]]
if not utilities.is_set (DF) then
do -- create defined block to contain local variables error_message and mismatch
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
local error_message = '';
end
-- 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 ArchiveURL;
local mismatch = year_date_check (Year, Date)
local ArchiveDate;
if 0 == mismatch then -- |year= does not match a year-value in |date=
local ArchiveFormat = A['ArchiveFormat'];
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
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
end
end -- end of do
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL
 
local AccessDate = A['AccessDate'];
local LayDate = A['LayDate'];
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
local DoiBroken = A['DoiBroken'];
local Embargo = A['Embargo'];
local anchor_year; -- used in the CITEREF identifier
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
['date'] = {val = Date, name = Date_origin},
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')},
['lay-date'] = {val = LayDate, name = A:ORIGIN ('LayDate')},
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')},
['year'] = {val = Year, name = A:ORIGIN ('Year')},
};
 
local error_list = {};
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);


-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
-- start temporary Julian / Gregorian calendar uncertainty categorization
-- 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
if COinS_date.inter_cal_cat then
Embargo = is_embargoed (Embargo); --  
utilities.add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization


if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
if not is_set (Embargo) then -- if not embargoed or embargo has expired
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
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
end
if 0 == #error_list then -- error free dates only; 0 when error_list is empty
local modified = false; -- flag
if validation.edtf_transform (date_parameters_list) then -- edtf dates to MOS compliant format
modified = true;
end


-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
if utilities.is_set (DF) then -- if we need to reformat dates
-- Test if citation has no title
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate
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
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
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
['title']=Title,
modified = true;
[A:ORIGIN('Chapter')]=Chapter,
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
[A:ORIGIN('Periodical')]=Periodical,
end
[A:ORIGIN('PublisherName')] = PublisherName,
});
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment the next three lines.  Not supported by en.wiki (for obvious reasons)
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
-- if validation.date_name_xlate (date_parameters_list, false) then
-- modified = true;
-- end


-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
if modified then -- if the date_parameters_list values were modified
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
ArchiveDate = date_parameters_list['archive-date'].val;
-- is the article title, and Chapter is a section within the article.  So, we remap  
Date = date_parameters_list['date'].val;
DoiBroken = date_parameters_list['doi-broken-date'].val;
LayDate = date_parameters_list['lay-date'].val;
PublicationDate = date_parameters_list['publication-date'].val;
end
else
table.insert (z.message_tail, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)}); -- add this error message
end
end -- end of do
 
local ID_list = {}; -- sequence table of rendered identifiers
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
local Class = A['Class']; -- arxiv class identifier
local ID_support = {
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')},
}
 
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- add error message
end
 
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
end
 
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
 
if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
if identifiers.auto_link_urls[auto_select] then -- manual selection
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
URL = identifiers.auto_link_urls['doi'];
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
end
 
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url=
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message
AccessDate = ''; -- unset
end
end
 
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- Test if citation has no title
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
end
 
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Title = ''; -- set title to empty string
utilities.set_message ('maint_untitled'); -- add maint cat
end
 
check_for_url ({ -- add error message when any of these parameters hold a URL
['title'] = Title,
[A:ORIGIN('Chapter')] = Chapter,
[Periodical_origin] = Periodical,
[PublisherName_origin] = PublisherName
});
 
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
-- is the article title, and Chapter is a section within the article.  So, we remap  
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_title = Title; -- et tu
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_chapter = Title; -- remap
coins_title = Periodical;
coins_title = Periodical;
Line 3,138: Line 3,071:
coins_author = c; -- use that instead
coins_author = c; -- use that instead
end
end
local QuotePage = A['QuotePage'];
local QuotePages = hyphen_to_dash (A['QuotePages']);


-- this is the function call to COinS()
-- this is the function call to COinS()
local OCinSoutput = COinS({
local OCinSoutput = metadata.COinS({
['Periodical'] = Periodical,
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
['Encyclopedia'] = Encyclopedia,
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wiki-markup
['Map'] = Map,
['Degree'] = Degree; -- cite thesis only
['Degree'] = Degree; -- cite thesis only
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wiki-markup
['PublicationPlace'] = PublicationPlace,
['PublicationPlace'] = PublicationPlace,
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Season'] = COinS_date.rftssn,
['Season'] = COinS_date.rftssn,
['Quarter'] = COinS_date.rftquarter,
['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
['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,
['Series'] = Series,
['Volume'] = Volume,
['Volume'] = Volume,
['Issue'] = Issue,
['Issue'] = Issue,
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links
['Edition'] = Edition,
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
['URL'] = first_set ({ChapterURL, URL}, 2),
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['Authors'] = coins_author,
['ID_list'] = ID_list,
['ID_list'] = ID_list_coins,
['RawPage'] = this_page.prefixedText,
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
}, config.CitationClass);


-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} 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
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
end
end


-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
-- 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 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
if is_set (PublisherName) then
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
end
end
end


 
local Editors;
 
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
local Contributors; -- assembled contributors name list
local contributor_etal;
local Translators; -- assembled translators name list
local translator_etal;
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
local Interviewers;
local interviewers_list = {};
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
local interviewer_etal;
-- Now perform various field substitutions.
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
-- 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
do
local last_first_list;
local last_first_list;
local maximum;
local control = {  
local control = {  
format = NameListFormat, -- empty string or 'vanc'
format = NameListStyle, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
mode = Mode
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
do -- do editor name list first because the now unsupported coauthors used to modify control table
maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
-- Preserve old-style implicit et al.
Editors, EditorCount = list_people (control, e, editor_etal);
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  
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
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
end
do -- now do interviewers
control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal, A:ORIGIN ('DisplayInterviewers'));
Interviewers = list_people (control, interviewers_list, interviewer_etal);
end
end
do -- now do translators
do -- now do translators
control.maximum = #t; -- number of translators
control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators'));
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
Translators = list_people (control, t, translator_etal);
end
end
do -- now do contributors
do -- now do contributors
control.maximum = #c; -- number of contributors
control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
Contributors = list_people (control, c, contributor_etal);
end
end
do -- now do authors
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));


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


if is_set (Authors) then
if utilities.is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Line 3,245: Line 3,167:
end
end
end -- end of do
end -- end of do
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
end


if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
end


-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
local ConferenceFormat = A['ConferenceFormat'];
-- an error message if the associated url is not set, or an empty string for concatenation
local ConferenceURL = A['ConferenceURL'];
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', '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
-- 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
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
end


if not is_set(URL) then --and
if not utilities.is_set (URL) then
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
table.insert( z.message_tail, { utilities.set_message ( 'err_cite_web_url', {}, true ) } );
end
end
-- Test if accessdate is given without giving a URL
-- do we have |accessdate= without either |url= or |chapter-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?
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } );
AccessDate = '';
AccessDate = '';
end
end
end
end


local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
DeadURL = DeadURL:lower(); -- used later when assembling archived text
local OriginalURL
if is_set( ArchiveURL ) then
local OriginalURL_origin
if is_set (URL) then
local OriginalFormat
OriginalURL = URL; -- save copy of original source URL
local OriginalAccess;
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
OriginalFormat = Format; -- and original |format=
if utilities.is_set ( ArchiveURL ) then
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it
URL = ArchiveURL -- swap-in the archive's url
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
OriginalFormat = ChapterFormat; -- and original |chapter-format=
 
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's URL
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs
end
elseif utilities.is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
 
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
URL = ArchiveURL -- swap-in the archive's URL
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs
end
end
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
end
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
end


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


if is_set (chap_param) then -- if we found one
if utilities.is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
TransChapter = '';
Line 3,326: Line 3,256:
else -- otherwise, format chapter / article title
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
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 utilities.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
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
no_quotes = true; -- then render it unquoted
end
end
end
end


Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
if is_set (Chapter) then
if utilities.is_set (Chapter) then
if 'map' == config.CitationClass and is_set (TitleType) then
Chapter = Chapter .. ChapterFormat ;
Chapter = Chapter .. ' ' .. TitleType;
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
end
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
Chapter = Chapter .. sepc .. ' ';
elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
end
end


-- Format main title.
-- Format main title
if is_set(TitleLink) and is_set(Title) then
local plain_title = false;
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
local accept_title;
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
Title = cfg.messages['notitle']; -- replace by predefined "No title" message
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
ScriptTitle = ''; -- just mute for now
TransTitle = ''; -- just mute for now
plain_title = true; -- suppress text decoration for descriptive title
utilities.set_message ('maint_untitled'); -- add maint cat
end
 
if not accept_title then -- <Title> not wrapped in accept-as-written markup
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title=
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
 
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
end
 
if is_generic_title (Title) then
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message
end
end
end


if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = 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 = utilities.wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
else
Title = wrap_style ('italic-title', Title);
Title = utilities.wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
TransTitle = wrap_style ('trans-italic-title', TransTitle);
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
end
end


TransError = "";
local TransError = "";
if is_set(TransTitle) then
if utilities.is_set (TransTitle) then
if is_set(Title) then
if utilities.is_set (Title) then
TransTitle = " " .. TransTitle;
TransTitle = " " .. TransTitle;
else
else
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} );
end
end
end
end
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
if utilities.is_set (TitleLink) and utilities.is_set (URL) then
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both
TitleLink = ''; -- unset
end
Title = Title .. TransTitle;
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format;
if is_set(Title) then
URL = ''; -- unset these because no longer needed
if not is_set(TitleLink) and is_set(URL) then  
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
URL = "";
Format = "";
Format = "";
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
else
Title = Title .. TransError;
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label
if ws_url then
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Title = Title .. TransTitle .. TransError;
end
end
end
else
Title = TransTitle .. TransError;
end
end


if is_set(Place) then
if utilities.is_set (Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
end


if is_set (Conference) then
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
if is_set (ConferenceURL) then
if utilities.is_set (Conference) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
if utilities.is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
end
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
elseif utilities.is_set (ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
end
end


if not is_set(Position) then
local Position = '';
if not utilities.is_set (Position) then
local Minutes = A['Minutes'];
local Minutes = A['Minutes'];
local Time = A['Time'];
local Time = A['Time'];


if is_set(Minutes) then
if utilities.is_set (Minutes) then
if is_set (Time) then
if utilities.is_set (Time) then
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
end
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
else
if is_set(Time) then
if utilities.is_set (Time) then
local TimeCaption = A['TimeCaption']
local TimeCaption = A['TimeCaption']
if not is_set(TimeCaption) then
if not utilities.is_set (TimeCaption) then
TimeCaption = cfg.messages['event'];
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
if sepc ~= '.' then
Line 3,427: Line 3,408:
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
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 "";
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
Position = is_set(Position) and (sepc .. " " .. Position) or "";
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
if config.CitationClass == 'map' then
local Section = A['Section'];
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
local Sections = A['Sections'];
local Inset = A['Inset'];
local Inset = A['Inset'];
if is_set( Inset ) then
if utilities.is_set ( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
end


if is_set( Sections ) then
if utilities.is_set ( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif is_set( Section ) then
elseif utilities.is_set ( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
end
Line 3,446: Line 3,426:
end
end


if is_set (Language) then
local Others = A['Others'];
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
else
if config.CitationClass == "AV-media-notes"
Language=""; -- language not specified so make sure this is an empty string;
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now
utilities.set_message ('maint_others_avm')
else
utilities.set_message ('maint_others');
end
end
end
 
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then
if utilities.is_set (Translators) then
Others = sepc .. ' Translated by ' .. Translators .. Others;  
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
end
end
 
if utilities.is_set (Interviewers) then
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
if is_set (Edition) then
end
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
add_maint_cat ('extra_text', 'edition');
local TitleNote = A['TitleNote'];
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if utilities.is_set (Edition) then
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_edition')}); -- add error
end
end
Edition = " " .. wrap_msg ('edition', Edition);
Edition = " " .. wrap_msg ('edition', Edition);
Line 3,468: Line 3,455:
end
end


Series = is_set(Series) and (sepc .. " " .. Series) or "";
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
local Agency = A['Agency'];
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
 
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);


------------------------------------ totally unrelated data
if utilities.is_set (AccessDate) then
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']
local retrv_text = " " .. cfg.messages['retrieved']


AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
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
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
AccessDate = utilities.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
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
end
if is_set(ID) then ID = sepc .." ".. ID; end
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
   if "thesis" == config.CitationClass and is_set(Docket) then
ID = sepc .." Docket ".. Docket .. ID;
local Docket = A['Docket'];
   if "thesis" == config.CitationClass and utilities.is_set (Docket) then
ID = sepc .. " Docket " .. Docket .. ID;
end
end
   if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
   if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
end


ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
if utilities.is_set (URL) then
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
end


if is_set(URL) then
local Quote = A['Quote'];
URL = " " .. external_link( URL, nil, URLorigin );
local TransQuote = A['TransQuote'];
end
local ScriptQuote = A['ScriptQuote'];
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then


if is_set(Quote) then
if utilities.is_set (Quote) then
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
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
Quote = Quote:sub(2, -2); -- strip them off
end
end
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
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
end
local Archived
if utilities.is_set (ScriptQuote) then
if is_set(ArchiveURL) then
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
if not is_set(ArchiveDate) then
ArchiveDate = set_error('archive_missing_date');
end
end
if "no" == DeadURL then
 
local arch_text = cfg.messages['archived'];
if utilities.is_set (TransQuote) then
if sepc ~= "." then arch_text = arch_text:lower() end
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
TransQuote = TransQuote:sub(2, -2); -- strip them off
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');  
end
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
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
end
elseif is_set (ArchiveFormat) then
 
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
local quote_prefix = '';
if utilities.is_set (QuotePage) then
extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc.
if not NoPP then
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
end
elseif utilities.is_set (QuotePages) then
extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc.
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', '';
elseif not NoPP then
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', '';
end
end
                       
Quote = quote_prefix .. ": " .. Quote;
else
Quote = sepc .. " " .. Quote;
end
 
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
-- We check length of PostScript here because it will have been nuked by
-- the quote parameters. We'd otherwise emit a message even if there wasn't
-- a displayed postscript.
-- TODO: Should the max size (1) be configurable?
-- TODO: Should we check a specific pattern?
if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then
utilities.set_message('maint_postscript')
end
local Archived
if utilities.is_set (ArchiveURL) then
local arch_text;
if not utilities.is_set (ArchiveDate) then
ArchiveDate = utilities.set_message ('err_archive_missing_date');
end
if "live" == UrlStatus then
arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not utilities.is_set (OriginalURL) then
Archived = Archived .. " " .. utilities.set_message ('err_archive_missing_url');  
end
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
arch_text = cfg.messages['archived-unfit'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
if 'bot: unknown' == UrlStatus then
utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added
else
utilities.set_message ('maint_unfit'); -- and add a category if not already added
end
else -- UrlStatus is empty, 'dead'
arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else -- OriginalUrl not set
arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ utilities.set_message ('err_archive_missing_url'), ArchiveDate } );
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
else
Line 3,559: Line 3,588:
local Lay = '';
local Lay = '';
if is_set(LayURL) then
local LaySource = A['LaySource'];
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
local LayURL = A['LayURL'];
if is_set(LaySource) then  
local LayFormat = A['LayFormat'];
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
if utilities.is_set (LayURL) then
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
if utilities.is_set (LaySource) then  
LaySource = " &ndash; ''" .. utilities.safe_for_italics (LaySource) .. "''";
else
else
LaySource = "";
LaySource = "";
end
end
if sepc == '.' then
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
else
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
elseif utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
end
end


if is_set(Transcript) then
local TranscriptURL = A['TranscriptURL']
if is_set(TranscriptURL) then
local TranscriptFormat = A['TranscriptFormat'];
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
local Transcript = A['Transcript'];
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
if utilities.is_set (Transcript) then
if utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
end
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
elseif utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
end
end


local Publisher;
local Publisher;
if is_set(Periodical) and
if utilities.is_set (PublicationDate) then
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
PublicationDate = wrap_msg ('published', PublicationDate);
if is_set(PublisherName) then
end
if is_set(PublicationPlace) then
if utilities.is_set (PublisherName) then
Publisher = PublicationPlace .. ": " .. PublisherName;
if utilities.is_set (PublicationPlace) then
else
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
Publisher = PublisherName; 
else
end
Publisher = sepc .. " " .. PublisherName .. PublicationDate;   
elseif is_set(PublicationPlace) then
end
Publisher= PublicationPlace;
elseif utilities.is_set (PublicationPlace) then  
else
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
Publisher = "";
else  
end
Publisher = PublicationDate;
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
end
local TransPeriodical =  A['TransPeriodical'];
local TransPeriodical_origin =  A:ORIGIN ('TransPeriodical');
-- Several of the above rely upon detecting this as nil, so do it last.
-- Several of the above rely upon detecting this as nil, so do it last.
if is_set(Periodical) then
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
if is_set(Title) or is_set(TitleNote) then  
if utilities.is_set (Title) or utilities.is_set (TitleNote) then  
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
else  
else  
Periodical = wrap_style ('italic-title', Periodical)
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
end
end
end
local Language = A['Language'];
if utilities.is_set (Language) then
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
else
Language=''; -- language not specified so make sure this is an empty string;
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
end


--[[
--[[
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
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).
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
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
TitleNote = " (Speech)"; -- annotate the citation
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter  
if utilities.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
if utilities.is_set (Conference) then -- and if |event= is set
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
end
end
end
Line 3,654: Line 3,679:
local tcommon2; -- used for book cite when |contributor= is set
local tcommon2; -- used for book cite when |contributor= is set
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,  
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
Language, Edition, Publisher, Agency, Volume}, sepc );
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
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
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 );
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Line 3,668: Line 3,691:


elseif 'map' == config.CitationClass then -- special cases for cite map
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
elseif utilities.is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
else -- a sheet or stand-alone map
Line 3,677: Line 3,700:
elseif 'episode' == config.CitationClass then -- special case for cite episode
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
 
else -- all other CS1 templates
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
Line 3,689: Line 3,713:
end
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local Via = A['Via'];
Via = utilities.is_set (Via) and  wrap_msg ('via', Via) or '';
local idcommon;
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc );
else
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
end
local text;
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;


if is_set(Date) then
local OrigDate = A['OrigDate'];
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
if utilities.is_set (Date) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
else -- neither of authors and editors set
else -- neither of authors and editors set
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
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
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
else
else
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
end
end
end
end
end
end
if is_set(Authors) then
if utilities.is_set (Authors) then
if is_set(Coauthors) then
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
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
end
if is_set(Editors) then
if utilities.is_set (Editors) then
local in_text = " ";
local in_text = " ";
local post_text = "";
local post_text = "";
if is_set(Chapter) and 0 == #c then
if utilities.is_set (Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
if (sepc ~= '.') then
in_text = in_text:lower() -- lowercase for cs2
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
else
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editors'] .. ")";
post_text = ", " .. cfg.messages['editor'];
end
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
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
Authors = by_text .. Authors; -- author follows title so tweak it here
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
end
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
end
Line 3,744: Line 3,772:
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
end
elseif is_set(Editors) then
elseif utilities.is_set (Editors) then
if is_set(Date) then
if utilities.is_set (Date) then
if EditorCount <= 1 then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
Editors = Editors .. ", " .. cfg.messages['editor'];
Line 3,760: Line 3,788:
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
else
if config.CitationClass=="journal" and is_set(Periodical) then
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
else
Line 3,767: Line 3,795:
end
end
if is_set(PostScript) and PostScript ~= sepc then
if utilities.is_set (PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc.
text = text:sub(1,-sepc:len()-1);
text = text:sub(1, -sepc:len() - 1);
end
end
text = safe_join( {text, PostScript}, sepc );
text = safe_join( {text, PostScript}, sepc );


-- Now enclose the whole thing in a <cite/> element
-- Now enclose the whole thing in a <cite> element
local options = {};
local options = {};
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
options.class = config.CitationClass;
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref=
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
else
else
options.class = "citation";
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2');
end
 
local Ref = A['Ref'];
if 'harv' == Ref then -- need to check this before setting to default
utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value
elseif not utilities.is_set (Ref) then
Ref = 'harv'; -- set as default when not set externally
end
end
if 'none' ~= cfg.keywords_xlate[Ref:lower()] then
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
local id = Ref
if ('harv' == Ref ) then
local namelist = {}; -- holds selected contributor, author, editor name list
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
-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation


if #c > 0 then -- if there is a contributor list
if #c > 0 then -- if there is a contributor list
namelist = c; -- select it
namelist = c; -- select it
elseif #a > 0 then -- or an author list
elseif #a > 0 then -- or an author list
namelist = a;
namelist = a;
elseif #e > 0 then -- or an editor list
elseif #e > 0 then -- or an editor list
namelist = e;
namelist = e;
end
end
id = anchor_id (namelist, year); -- go make the CITEREF anchor
local citeref_id
if #namelist > 0 then -- if there are names in namelist
citeref_id = make_citeref_id (namelist, year); -- go make the CITEREF anchor
else
citeref_id = ''; -- unset
end
if citeref_id == Ref then
utilities.set_message ('maint_ref_duplicates_default');
end
if 'harv' == Ref then
id = citeref_id
end
end
options.id = id;
options.id = id;
end
end
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then -- remove <span> tags and other HTML-like markup; then get length of what remains
z.error_categories = {};
z.error_categories = {};
text = set_error('empty_citation');
text = utilities.set_message ('err_empty_citation');
z.message_tail = {};
z.message_tail = {};
end
end
if is_set(options.id) then  
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
 
if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
else
text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
end


local empty_span = '<span style="display:none;">&nbsp;</span>';
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
 
-- Note: Using display: none on the COinS span breaks some clients.
if 0 ~= #z.message_tail then
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
table.insert (render, ' ');
text = text .. OCinS;
if #z.message_tail ~= 0 then
text = text .. " ";
for i,v in ipairs( z.message_tail ) do
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if utilities.is_set (v[1]) then
if i == #z.message_tail then
if i == #z.message_tail then
text = text .. error_comment( v[1], v[2] );
table.insert (render, utilities.error_comment ( v[1], v[2] ));
else
else
text = text .. error_comment( v[1] .. "; ", v[2] );
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
end
end
end
end
Line 3,834: Line 3,873:
end
end


if #z.maintenance_cats ~= 0 then
if 0 ~= #z.maintenance_cats then
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
local maint_msgs = {}; -- here we collect all of the maint messages
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
local maint = {}; -- here we assemble a maintenence message
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint, utilities.substitute (cfg.messages[':cat wikilink'], {v})); -- add the link
table.insert (maint, ')'); -- and close it
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
end
end
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
end
end
no_tracking_cats = no_tracking_cats:lower();
if not no_tracking_cats then
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
for _, v in ipairs( z.error_categories ) do -- append error categories
for _, v in ipairs( z.error_categories ) do
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
text = text .. '[[Category:' .. v ..']]';
end
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
end
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
for _, v in ipairs( z.properties_cats ) do -- append properties categories
text = text .. '[[Category:' .. v ..']]';
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
end
end
end
end
 
return text
return table.concat (render);
end
end


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


This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the first match.
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------


Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the
Looks for a parameter's name in one of several whitelists.
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.


Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
]]


local function has_invisible_chars (param, v)
local function validate (name, cite_class, empty)
local position = '';
local name = tostring (name);
local i=1;
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
local state;
local function state_test (state, name) -- local function to do testing of state values
if true == state then return true; end -- valid actively supported parameter
if false == state then
if empty then return nil; end -- empty deprecated parameters are treated as unknowns
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
if 'discouraged' == state then
discouraged_parameter (name); -- parameter is discouraged but still supported
return true;
end
return nil;
end
 
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
return nil;
end
 
if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[name];
if true == state_test (state, name) then return true; end
 
state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
if true == state_test (state, name) then return true; end
 
-- limited enumerated parameters list
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[enum_name];
if true == state_test (state, name) then return true; end
 
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
 
if utilities.in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list
state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
if true == state_test (state, name) then return true; end
end -- if here, fall into general validation
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
if true == state_test (state, name) then return true; end
 
-- all enumerated parameters allowed
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.numbered_arguments[enum_name];
if true == state_test (state, name) then return true; end
 
return false; -- not supported because not found or name is set to nil
end
 
 
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
 
check <value> for inter-language interwiki-link markup.  <prefix> must be a MediaWiki-recognized language
code.  when these values have the form (without leading colon):
[[<prefix>:link|label]] return label as plain-text
[[<prefix>:link]] return <prefix>:link as plain-text
 
return value as is else
 
]=]
 
local function inter_wiki_check (parameter, value)
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
local _;
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
end
return value;
end


while cfg.invisible_chars[i] do
 
local char=cfg.invisible_chars[i][1] -- the character or group name
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
 
position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
if position then
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
table.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('parameter', param), position}, true ) } ); -- add error message
parameter that is missing its pipe.  There are two tests made:
return; -- and done with this parameter
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
end
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
i=i+1; -- bump our index
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc.  To prevent false positives XML/HTML
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 
]]
 
local function missing_pipe_check (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc.
 
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {utilities.set_message ('err_missing_pipe', parameter)});
end
end
 
 
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
 
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
 
]]
 
local function has_extraneous_punc (param, value)
if 'number' == type (param) then
return;
end
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
if cfg.punct_skip[param] then
return; -- parameter name found in the skip table so done
end
if value:match ('[,;:]$') then
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
end
end
end
end




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


This is used by templates such as {{cite book}} to create the actual citation text.
This is used by templates such as {{cite book}} to create the actual citation text.
Line 3,894: Line 4,043:
]]
]]


function z.citation(frame)
local function citation(frame)
Frame = frame; -- save a copy in case we need to display an error message in preview mode
local pframe = frame:getParent()
local pframe = frame:getParent()
local validation;
local styles;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
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 ...
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
 
validation = require ('Module:Citation/CS1/Date_validation/sandbox');
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
styles = 'Module:Citation/CS1/sandbox/styles.css';
else -- otherwise
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code
utilities = require ('Module:Citation/CS1/Utilities');
validation = require ('Module:Citation/CS1/Date_validation');
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
end
end


dates = validation.dates; -- imported functions
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables
year_date_check = validation.year_date_check;
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities


local args = {};
local args = {}; -- table where we store all of the template's arguments
local suggestions = {};
local suggestions = {}; -- table where we store suggestions if we need to loadData them
local error_text, error_state;
local error_text, error_state;


local config = {};
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame
config[k] = v;
config[k] = v;
args[k] = v;  
-- args[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep?
end
end


local capture; -- the single supported capture when matching unknown parameters using patterns
local capture; -- the single supported capture when matching unknown parameters using patterns
for k, v in pairs( pframe.args ) do
local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing
for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame
v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
if v ~= '' then
if v ~= '' then
if not validate( k ) then
if ('string' == type (k)) then
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
end
if not validate( k, config.CitationClass ) then
error_text = "";
error_text = "";
if type( k ) ~= 'string' then
if type( k ) ~= 'string' then
-- Exclude empty numbered parameters
-- exclude empty numbered parameters
if v:match("%S+") ~= nil then
if v:match("%S+") ~= nil then
error_text, error_state = set_error( 'text_ignored', {v}, true );
error_text, error_state = utilities.set_message ( 'err_text_ignored', {v}, true );
end
end
elseif validate( k:lower() ) then  
elseif validate( k:lower(), config.CitationClass ) then  
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter
else
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
Line 3,943: Line 4,110:
end
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match
capture = k:match (pattern); -- the whole match if no capture in pattern else the capture if a match
if capture then -- if the pattern matches  
if capture then -- if the pattern matches  
param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)
param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator)
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
error_text, error_state = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true ); -- suggested param not supported by this template
v = ''; -- unset
end
end
end
end
end
if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion?
if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an explicit suggestion?
if suggestions.suggestions[ k:lower() ] ~= nil then
if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
else
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end
end
Line 3,961: Line 4,134:
end
end
end
end
args[k] = v;
 
elseif args[k] ~= nil or (k == 'postscript') then
args[k] = v; -- save this parameter and its value
args[k] = v;
 
end
elseif not utilities.is_set (v) then -- for empty parameters
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list
end
-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
-- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
-- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
end
end
if 0 ~= #empty_unknowns then -- create empty unknown error message
table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
}, true )});
end


for k, v in pairs( args ) do
for k, v in pairs( args ) do
has_invisible_chars (k, v)
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v); -- look for invisible characters
end
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label
end
end
return citation0( config, args)
 
return table.concat ({
frame:extensionTag ('templatestyles', '', {src=styles}),
citation0( config, args)
});
end
end


return z
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
]]
 
return {citation = citation};
Retrieved from "https://nonbinary.wiki/wiki/Special:MobileDiff/17775...17821"