From World Afropedia
Jump to: navigation, search
*>Trappist the monk
m (is_parameter_ext_wikilink() fix;)
m (1 revision imported)
 
(11 intermediate revisions by 2 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?
local function error_comment( content, hidden )
 
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
 
end
 
  
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
+
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
 +
BNF defined here: https://tools.ietf.org/html/rfc4234
 +
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
 +
see also [[Single-letter second-level domain]]
 +
list of TLDs: https://www.iana.org/domains/root/db
  
Sets an error condition and returns the appropriate error messageThe actual placement of the error message in the output is
+
RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digitBetween
the responsibility of the calling function.
+
the first and last characters the name may use letters, digits, and the hyphen.
  
]]
+
Also allowed are IPv4 addresses. IPv6 not supported
local function set_error( error_id, arguments, raw, prefix, suffix )
+
 
local error_state = cfg.error_conditions[ error_id ];
+
domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
+
is two or more alpha characters.  Any preceding '//' (from splitting a URL with a scheme) will be stripped
prefix = prefix or "";
+
here.  Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal.
suffix = suffix or "";
+
 
+
There are several tests:
if error_state == nil then
+
the first character of the whole domain name including subdomains must be a letter or a digit
error( cfg.messages['undefined_error'] );
+
internationalized domain name (ASCII characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the TLD) see https://tools.ietf.org/html/rfc3490
elseif is_set( error_state.category ) then
+
single-letter/digit second-level domains in the .org, .cash, and .today TLDs
table.insert( z.error_categories, error_state.category );
+
q, x, and z SL domains in the .com TLD
 +
i and q SL domains in the .net TLD
 +
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
 +
two-character SL domains in gTLDs (where the gTLD is two or more letters)
 +
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
 +
IPv4 dot-decimal address format; TLD not allowed
 +
 
 +
returns true if domain appears to be a proper name and TLD or IPv4 address, else false
 +
 
 +
]=]
 +
 
 +
local function is_domain_name (domain)
 +
if not domain then
 +
return false; -- if not set, abandon
 
end
 
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;
end
+
 +
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
  
  
--[=[-------------------------< 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
  
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
+
Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
BNF defined here: https://tools.ietf.org/html/rfc4234
+
# < > [ ] | { } _
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
+
except the underscore which is used as a space in wiki URLs and # which is used for section links
see also [[Single-letter second-level domain]]
 
list of tlds: https://www.iana.org/domains/root/db
 
  
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
+
returns false when the value contains any of these characters.
the first and last characters the name may use letters, digits, and the hyphen.
 
  
Also allowed are IPv4 addresses. IPv6 not supported
+
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid URL (the
 +
|<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
  
domain is expected to be stripped of any path so that the last character in the last character of the tld.  tld
+
]]
is two or more alpha characters.  Any preceding '//' (from splitting a url with a scheme) will be stripped
 
here.  Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
 
  
There are several tests:
+
local function link_param_ok (value)
the first character of the whole domain name including subdomains must be a letter or a digit
+
local scheme, domain;
single-letter/digit second-level domains in the .org TLD
+
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
q, x, and z SL domains in the .com TLD
 
i and q SL domains in the .net TLD
 
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
 
two-character SL domains in gTLDs (where the gTLD is two or more letters)
 
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
 
IPv4 dot-decimal address format; TLD not allowed
 
 
 
returns true if domain appears to be a proper name and tld or IPv4 address, else false
 
 
 
]=]
 
 
 
local function is_domain_name (domain)
 
if not domain then
 
return false; -- if not set, abandon
 
end
 
 
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
 
 
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
 
return false;
 
end
 
 
if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
 
return true;
 
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
 
return true;
 
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
 
return true;
 
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
 
return true;
 
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
 
return true;
 
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
 
return true;
 
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
 
return true;
 
else
 
 
return false;
 
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 processThis function is separate because there are cases that
+
check <link> for inter-language interwiki-link prefixprefix 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 >------------------------------------------------------------
 +
 
 +
Determines whether a URL string appears to be valid.
  
Split a url into a scheme, authority indicator, and domain.
+
First we test for space characters.  If any are found, return false.  Then split the URL into scheme and domain
If protocol relative url, return nil scheme and domain else return nil for both 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.
  
When not protocol relative, get scheme, authority indicator, and domainIf there is an authority indicator (one
+
Because it is different from a standard URL, and because this module used external_link() to make external links
or more '/' characters following the scheme's colon), make sure that there are only 2.
+
that work for standard and news: links, we validate newsgroup names hereThe specification for a newsgroup name
 +
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
  
 
]]
 
]]
  
local function split_url (url_str)
+
local function check_url( url_str )
local scheme, authority, domain;
+
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;
 +
 
 +
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
 
 
url_str = url_str:gsub ('(%a)/.*', '%1'); -- strip path information (the capture prevents false replacement of '//')
+
if 'news:' == scheme then -- special case for newsgroups
 
+
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
 
domain = url_str:match ('^//(%S*)')
 
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
 
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
 
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
 
if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
 
domain = nil; -- set to nil which will cause an error message
 
end
 
 
end
 
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=,
except the underscore which is used as a space in wiki urls and # which is used for section links
+
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]].
  
returns false when the value contains any of these characters.
+
]=]
  
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
+
local function is_parameter_ext_wikilink (value)
|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).
+
local scheme, domain;
  
]]
+
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
 
+
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
local function link_param_ok (value)
+
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz]
local scheme, domain;
+
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
+
elseif value:match ('%a%S*:%S+') then -- if bare URL with scheme; may have leading or trailing plain text
return false;
+
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 valuesLook 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 falseThen split the url into scheme and domain
 
portions, or for protocol relative (//example.com) urls, just the domain.  Use is_url() to validate the two
 
portions of the url.  If both are valid, or for protocol relative if domain is valid, return true, else false.
 
  
 
]]
 
]]
  
local function check_url( url_str )
+
local function 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
non-space characters following the opening bracket appear to be a url.  The test will also find external wikilinks
 
that use protocol relative urls. Also finds bare urls.
 
  
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls.  The tests that
+
]]
find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,
 
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
 
is possible as might be [[en://Hus]].
 
  
]=]
+
local function 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;
 
 
 
value = value:gsub ('([^%s/])/[%a%d].*', '%1'); -- strip path information (the capture prevents false replacement of '//')
 
 
 
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
 
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+).*%]');
 
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
 
scheme, domain = value:match ('(%a%S*:)(%S+)');
 
elseif value:match ('//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text
 
domain = value:match ('//(%S*%.%S+)'); -- what is left should be the domain
 
else
 
return false; -- didn't find anything that is obviously a url
 
 
end
 
end
 
+
return 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
 
return str:gsub( '[%[%]\n]', {
 
['['] = '&#91;',
 
[']'] = '&#93;',
 
['\n'] = ' ' } );
 
 
end
 
end
  
--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------
 
  
Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
+
--[=[-------------------------< 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
+
Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
 +
quote marks regardless of the need for kerning.  Unicode quote marks are not replaced in simple [[D]] wikilinks.
 +
 
 +
Call this function for chapter titles, for website titles, etc.; not for book titles.
  
return substitute( cfg.presentation[key], {str} );
+
]=]
end
 
  
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
+
local function kern_quotes (str)
 +
local cap = '';
 +
local cap2 = '';
 +
local wl_type, label, link;
  
Format an external link with error checking
+
wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
 +
 +
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
 +
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
 +
str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
 +
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
 +
str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
 +
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
 +
str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
 +
end
  
]]
+
else -- plain text or [[L|D]]; text in label variable
 +
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
 +
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
  
local function external_link( URL, label, source )
+
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
local error_str = "";
+
if utilities.is_set (cap) then
if not is_set( label ) then
+
label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
label = URL;
+
end
if is_set( source ) then
+
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
+
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
 +
if utilities.is_set (cap) then
 +
label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
 +
end
 +
 +
if 2 == wl_type then
 +
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
 
else
 
else
error( cfg.messages["bare_url_no_origin"] );
+
str = label;
end
+
end
 
end
 
end
if not check_url( URL ) then
+
return str;
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
 
end
  
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
 
  
Formats a wiki style external link
+
--[[--------------------------< 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.
  
local function external_link_id(options)
+
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 url_string = options.id;
+
 
if options.encode == true or options.encode == nil then
+
|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:
url_string = mw.uri.encode( url_string );
+
|script-title=ja:*** *** (where * represents a Japanese character)
end
+
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
+
|script-title=ja : *** ***
options.link, options.label, options.separator or "&nbsp;",
+
|script-title=ja: *** ***
options.prefix, url_string, options.suffix or "",
+
|script-title=ja :*** ***
mw.text.nowiki(options.id)
+
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
);
 
end
 
  
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
+
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
 +
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.
  
Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
+
Supports |script-title=, |script-chapter=, |script-<periodical>=
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
 
parameters in the citation.
 
  
 
]]
 
]]
  
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
+
local function format_script_value (script_value, script_param)
local function deprecated_parameter(name)
+
local lang=''; -- initialize to empty string
if not page_in_deprecated_cat then
+
local name;
page_in_deprecated_cat = true; -- note that we've added this category
+
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
+
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
 +
if not utilities.is_set (lang) then
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
 +
return ''; -- script_value was just the prefix so return empty string
 +
end
 +
-- if we get this far we have prefix and script
 +
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
 +
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
 +
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
 +
-- is prefix one of these language codes?
 +
if utilities.in_array (lang, cfg.script_lang_codes) then
 +
utilities.add_prop_cat ('script_with_name', {name, lang})
 +
else
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
 +
end
 +
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
 +
else
 +
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
 +
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 = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL
 +
 +
return script_value;
 
end
 
end
  
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
  
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
+
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
This function will positive kern either single or double quotes:
 
"'Unkerned title with leading and trailing single quote marks'"
 
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
 
Double single quotes (italic or bold wikimarkup) are not kerned.
 
 
 
Call this function for chapter titles, for website titles, etc; not for book titles.
 
  
 +
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
 +
wrapped in <bdi> tags.
 
]]
 
]]
  
local function kern_quotes (str)
+
local function script_concatenate (title, script, script_param)
local cap='';
+
if utilities.is_set (script) then
local cap2='';
+
script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error
+
if utilities.is_set (script) then
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
+
title = title .. ' ' .. script; -- concatenate title and script title
if is_set (cap) then
+
end
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
 
 
end
 
end
 
+
return title;
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
 
if is_set (cap) then
 
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
 
end
 
return str;
 
 
end
 
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
+
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
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.
+
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
 +
configuration taking one argument. Supports lower case text for {{citation}} templates. Additional text taken
 +
from citation_config.messages - the reason this function is similar to but separate from wrap_style().
  
|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
+
local function wrap_msg (key, str, lower)
know the language the tag contains.  This may help the browser render the script more correctlyIf the prefix is invalid, the lang attribute
+
if not utilities.is_set ( str ) then
is not added.  At this time there is no error message for this condition.
+
return "";
 +
end
 +
if true == lower then
 +
local msg;
 +
msg = cfg.messages[key]:lower(); -- set the message to lower case before
 +
return utilities.substitute ( msg, str ); -- including template text
 +
else
 +
return utilities.substitute ( cfg.messages[key], str );
 +
end
 +
end
 +
 
 +
 
 +
--[[----------------< W I K I S O U R C E _ U R L _ M A K E >-------------------
 +
 
 +
Makes a Wikisource URL from Wikisource interwiki-linkReturns the URL and appropriate
 +
label; nil else.
  
Supports |script-title= and |script-chapter=
+
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
  
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
 
 
]]
 
]]
  
local function format_script_value (script_value)
+
local function wikisource_url_make (str)
local lang=''; -- initialize to empty string
+
local wl_type, D, L;
local name;
+
local ws_url, ws_label;
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
+
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
+
 
if not is_set (lang) then
+
wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
return ''; -- script_value was just the prefix so return empty string
+
 
 +
if 0 == wl_type then -- not a wikilink; might be from |title-link=
 +
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
 +
if utilities.is_set (str) then
 +
ws_url = table.concat ({ -- build a Wikisource URL
 +
wikisource_prefix, -- prefix
 +
str, -- article title
 +
});
 +
ws_label = str; -- label for the URL
 +
end
 +
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
 +
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
 +
if utilities.is_set (str) then
 +
ws_url = table.concat ({ -- build a Wikisource URL
 +
wikisource_prefix, -- prefix
 +
str, -- article title
 +
});
 +
ws_label = str; -- label for the URL
 
end
 
end
-- if we get this far we have prefix and script
+
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
+
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
+
if utilities.is_set (str) then
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
+
ws_label = D; -- get ws article name from display portion of interwiki link
-- is prefix one of these language codes?
+
ws_url = table.concat ({ -- build a Wikisource URL
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
+
wikisource_prefix, -- prefix
add_prop_cat ('script_with_name', {name, lang})
+
str, -- article title without namespace from link portion of wikilink
else
+
});
add_prop_cat ('script')
 
end
 
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
 
else
 
lang = ''; -- invalid so set lang to empty string
 
 
end
 
end
 
end
 
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
 
  
return script_value;
+
if ws_url then
 +
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL
 +
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker
 +
end
 +
 
 +
return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil
 
end
 
end
  
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
 
  
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
+
--[[----------------< F O R M A T _ P E R I O D I C A L >-----------------------
wrapped in <bdi> tags.
+
 
 +
Format the three periodical parameters: |script-<periodical>=, |<periodical>=,
 +
and |trans-<periodical>= into a single Periodical meta-parameter.
 +
 
 
]]
 
]]
  
local function script_concatenate (title, script)
+
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
if is_set (script) then
+
local periodical_error = '';
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
+
 
if is_set (script) then
+
if not utilities.is_set (periodical) then
title = title .. ' ' .. script; -- concatenate title and script title
+
periodical = ''; -- to be safe for concatenation
 +
else
 +
periodical = utilities.wrap_style ('italic-title', periodical); -- style
 +
end
 +
 
 +
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
 
 +
if utilities.is_set (trans_periodical) then
 +
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
 +
if utilities.is_set (periodical) then
 +
periodical = periodical .. ' ' .. trans_periodical;
 +
else -- here when trans-periodical without periodical or script-periodical
 +
periodical = trans_periodical;
 +
periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'});
 
end
 
end
 
end
 
end
return title;
+
 
 +
return periodical .. periodical_error;
 
end
 
end
  
  
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
+
--[[------------------< F O R M A T _ C H A P T E R _ T I T L E >---------------
  
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
+
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
+
and |chapter-url= into a single chapter meta- parameter (chapter_url_source used
from citation_config.messages - the reason this function is similar to but separate from wrap_style().
+
for error messages).
  
 
]]
 
]]
  
local function wrap_msg (key, str, lower)
+
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)
if not is_set( str ) then
+
local chapter_error = '';
return "";
+
 
 +
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
 
end
if true == lower then
+
 
local msg;
+
if not utilities.is_set (chapter) then
msg = cfg.messages[key]:lower(); -- set the message to lower case before
+
chapter = ''; -- to be safe for concatenation
return substitute( msg, str ); -- including template text
 
 
else
 
else
return substitute( cfg.messages[key], str );
+
if false == no_quotes then
end
+
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
end
+
chapter = utilities.wrap_style ('quoted-title', chapter);
 +
end
 +
end
  
 +
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
  
--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------
+
if utilities.is_set (chapter_url) then
 +
chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
 +
elseif ws_url then
 +
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
 +
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
 +
end
  
This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
+
if utilities.is_set (trans_chapter) then
provided by the template.
+
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
  
Input:
+
return chapter .. chapter_error;
args – pointer to the arguments table from calling template
+
end
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
+
--[[----------------< H A S _ I N V I S I B L E _ C H A R S >-------------------
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
+
This function searches a parameter's value for non-printable or invisible characters.
error_list – list of aliases that are duplicates of the alias already selected
+
The search stops at the first match.
 +
 
 +
This function will detect the visible replacement character when it is part of the Wikisource.
 +
 
 +
Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers
 +
(gallery, math, pre, ref) and identifies them with a slightly different error message.
 +
See also coins_cleanup().
  
Returns:
+
Output of this function is an error message that identifies the character or the
value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected
+
Unicode group, or the stripmarker that was detected along with its position (or,
selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected
+
for multi-byte characters, the position of its first byte) in the parameter value.
  
 
]]
 
]]
  
local function is_alias_used (args, alias, index, enumerated, value, selected, error_list)
+
local function has_invisible_chars (param, v)
if enumerated then -- is this a test for an enumerated parameters?
+
local position = ''; -- position of invisible char or starting position of stripmarker
alias = alias:gsub ('#', index); -- replace '#' with the value in index
+
local capture; -- used by stripmarker detection to hold name of the stripmarker
else
+
local stripmarker; -- boolean set true when a stripmarker is found
alias = alias:gsub ('#', ''); -- remove '#' if it exists
+
 
 +
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
 +
if capture == v then -- if same there are no Unicode characters
 +
return;
 
end
 
end
  
if is_set(args[alias]) then -- alias is in the template's argument list
+
for _, invisible_char in ipairs (cfg.invisible_chars) do
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
+
local char_name = invisible_char[1]; -- the character or group name
local skip;
+
local pattern = invisible_char[2]; -- the pattern used to find it
for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias
+
position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern
if v == alias then
+
skip = true;
+
if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
break; -- has been added so stop looking
+
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
 
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
if not skip then -- has not been added so
 
table.insert( error_list, alias ); -- add error alias to the error list
 
end
 
else
 
value = args[alias]; -- not yet selected an alias, so select this one
 
selected = alias;
 
 
end
 
end
 
end
 
end
return value, selected; -- return newly selected alias, or previously selected alias
 
 
end
 
end
  
  
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
+
--[[-------------------< A R G U M E N T _ W R A P P E R >----------------------
 
 
Chooses one matching parameter from a list of parameters to consider.  The list of parameters to consider is just
 
names.  For parameters that may be enumerated, the position of the numerator in the parameter name is identified
 
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
 
 
 
Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
 
  
 
+
Argument wrapper.  This function provides support for argument mapping defined
Generates an error if more than one match is present.
+
in the configuration file so that multiple names can be transparently aliased to
 +
single internal variable.
  
 
]]
 
]]
  
local function select_one( args, aliases_list, error_condition, index )
+
local function argument_wrapper ( args )
local value = nil; -- the value assigned to the selected parameter
+
local origin = {};
local selected = ''; -- the name of the parameter we have chosen
+
local error_list = {};
+
return setmetatable({
 
+
ORIGIN = function ( self, k )
if index ~= nil then index = tostring(index); end
+
local dummy = self[k]; -- force the variable to be loaded.
 
+
return origin[k];
for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list
+
end
if alias:match ('#') then -- if this alias can be enumerated
+
},
if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases
+
{
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias
+
__index = function ( tbl, k )
 +
if origin[k] ~= nil then
 +
return nil;
 
end
 
end
value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias
+
else
+
local args, list, v = args, cfg.aliases[k];
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias
+
end
+
if type( list ) == 'table' then
end
+
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
 
+
if origin[k] == nil then
if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
+
origin[k] = ''; -- Empty string, not nil
local error_str = "";
+
end
for _, k in ipairs( error_list ) do
+
elseif list ~= nil then
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
+
v, origin[k] = args[list], list;
error_str = error_str .. wrap_style ('parameter', k);
+
else
end
+
-- maybe let through instead of raising an error?
if #error_list > 1 then
+
-- v, origin[k] = args[k], k;
error_str = error_str .. cfg.messages['parameter-final-separator'];
+
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
else
+
end
error_str = error_str .. cfg.messages['parameter-pair-separator'];
+
end
+
-- Empty strings, not nil;
error_str = error_str .. wrap_style ('parameter', selected);
+
if v == nil then
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
+
v = '';
end
+
origin[k] = '';
+
end
return value, selected;
+
end
+
tbl = rawset( tbl, k, v );
 
+
return v;
 
+
end,
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
+
});
 
+
end
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
 
parameter (chapter_url_source used for error messages).
 
 
 
]]
 
  
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
 
local chapter_error = '';
 
 
if not is_set (chapter) then
 
chapter = ''; -- to be safe for concatenation
 
else
 
if false == no_quotes then
 
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
 
chapter = wrap_style ('quoted-title', chapter);
 
end
 
end
 
  
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
--[[--------------------------< N O W R A P _ D A T E >-------------------------
  
if is_set (transchapter) then
+
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
transchapter = wrap_style ('trans-quoted-title', transchapter);
+
When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
if is_set (chapter) then
+
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
chapter = chapter .. ' ' .. transchapter;
 
else -- here when transchapter without chapter or script-chapter
 
chapter = transchapter; --
 
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
 
end
 
end
 
  
if is_set (chapterurl) then
+
DOES NOT yet support MMMM YYYY or any of the date ranges.
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
 
end
 
  
return chapter .. chapter_error;
+
]]
end
 
  
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
+
local function nowrap_date (date)
 +
local cap = '';
 +
local cap2 = '';
  
This function searches a parameter's value for nonprintable or invisible characters. The search stops at the
+
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
first match.
+
date = utilities.substitute (cfg.presentation['nowrap1'], date);
 
+
This function will detect the visible replacement character when it is part of the wikisource.
+
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
 +
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
 +
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
 +
end
 +
 +
return date;
 +
end
  
Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers (gallery, math, pre, ref)
 
and identifies them with a slightly different error message.  See also coins_cleanup().
 
  
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
+
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------
  
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
+
This function sets default title types (equivalent to the citation including
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
+
|type=<default value>) for those templates that have defaults. Also handles the
parameter value.
+
special case where it is desirable to omit the title type from the rendered citation
 +
(|type=none).
  
 
]]
 
]]
  
local function has_invisible_chars (param, v)
+
local function set_titletype (cite_class, title_type)
local position = ''; -- position of invisible char or starting position of stripmarker
+
if utilities.is_set (title_type) then
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
+
if 'none' == cfg.keywords_xlate[title_type] then
local capture; -- used by stripmarker detection to hold name of the stripmarker
+
title_type = ''; -- if |type=none then type parameter not displayed
local i=1;
 
local stripmarker, apostrophe;
 
 
 
while cfg.invisible_chars[i] do
 
local char=cfg.invisible_chars[i][1] -- the character or group name
 
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
 
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
 
 
if position then
 
-- if 'nowiki' == capture or 'math' == capture or ('ref' == capture and 'quote' == param) then -- nowiki, math, or quote param and ref stripmarker (not an error condition)
 
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
 
stripmarker = true; -- set a flag
 
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
 
position = nil; -- unset
 
elseif 'apostrophe' == char then -- apostrophe template uses &zwj;, hair space and zero-width space
 
apostrophe = true;
 
elseif true == apostrophe and in_array (char, {'zero width joiner', 'zero width space', 'hair space'}) then
 
position = nil; -- unset
 
else
 
local err_msg;
 
if capture then
 
err_msg = capture .. ' ' .. char;
 
else
 
err_msg = char .. ' ' .. 'character';
 
end
 
 
 
table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message
 
return; -- and done with this parameter
 
end
 
 
end
 
end
i=i+1; -- bump our index
+
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
  
  
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
+
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
  
Argument wrapperThis function provides support for argument mapping defined in the configuration file so that
+
Converts a hyphen to a dash under certain conditions.  The hyphen must separate
multiple names can be transparently aliased to single internal variable.
+
like items; unlike items are returned unmodifiedThese forms are modified:
 +
letter - letter (A - B)
 +
digit - digit (4-5)
 +
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
 +
letterdigit - letterdigit (A1-A5) (an optional separator between letter and
 +
digit is supported – a.1-a.5 or a-1-a-5)
 +
digitletter - digitletter (5a - 5d) (an optional separator between letter and
 +
digit is supported – 5.a-5.d or 5-a-5-d)
 +
 
 +
any other forms are returned unmodified.
 +
 
 +
str may be a comma- or semicolon-separated list
  
 
]]
 
]]
  
local function argument_wrapper( args )
+
local function hyphen_to_dash( str )
local origin = {};
+
if not utilities.is_set (str) then
 +
return str;
 +
end
 +
 
 +
local accept; -- Boolean
 +
 
 +
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
 
 
return setmetatable({
+
local out = {};
ORIGIN = function( self, k )
+
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any
local dummy = self[k]; --force the variable to be loaded.
+
 
return origin[k];
+
for _, item in ipairs (list) do -- for each item in the list
end
+
item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
},
+
if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
{
+
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
__index = function ( tbl, k )
+
item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
if origin[k] ~= nil then
+
item:match ('^%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+$') or -- digit separator digit hyphen digit separator digit
return nil;
+
item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit
end
+
item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter
+
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
local args, list, v = args, cfg.aliases[k];
 
 
if type( list ) == 'table' then
 
v, origin[k] = select_one( args, list, 'redundant_parameters' );
 
if origin[k] == nil then
 
origin[k] = ''; -- Empty string, not nil
 
end
 
elseif list ~= nil then
 
v, origin[k] = args[list], list;
 
 
else
 
else
-- maybe let through instead of raising an error?
+
item = mw.ustring.gsub (item, '%s*[–—]%s*', ''); -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace
-- v, origin[k] = args[k], k;
 
error( cfg.messages['unknown_argument_map'] );
 
 
end
 
end
+
end
-- Empty strings, not nil;
+
table.insert (out, item); -- add the (possibly modified) item to the output table
if v == nil then
+
end
v = cfg.defaults[k] or '';
+
 
origin[k] = '';
+
local temp_str = ''; -- concatenate the output table into a comma separated string
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
+
if accept then
tbl = rawset( tbl, k, v );
+
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 v;
+
return temp_str;
end,
+
else
});
+
return temp_str; -- else, return assembled temp_str
end
 
 
 
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
 
Looks for a parameter's name in the whitelist.
 
 
 
Parameters in the whitelist can have three values:
 
true - active, supported parameters
 
false - deprecated, supported parameters
 
nil - unsupported parameters
 
 
]]
 
 
 
local function validate( name )
 
local name = tostring( name );
 
local state = whitelist.basic_arguments[ name ];
 
 
-- Normal arguments
 
if true == state then return true; end -- valid actively supported parameter
 
if false == state then
 
deprecated_parameter (name); -- parameter is deprecated but still supported
 
return true;
 
 
end
 
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
 
end
  
  
-- Formats a wiki style internal link
+
--[[--------------------------< S A F E _ J O I N >-----------------------------
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
 
  
 +
Joins a sequence of strings together while checking for duplicate separation characters.
  
--[[--------------------------< 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
+
local function safe_join( tbl, duplicate_char )
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
+
local f = {}; -- create a function table appropriate to type of 'duplicate character'
 +
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
 +
f.gsub = string.gsub
 +
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
  
DOES NOT yet support MMMM YYYY or any of the date ranges.
+
local str = ''; -- the output string
 +
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
 +
-- typically duplicate_char is sepc
 +
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
 +
--  Because individual string segments often (always?) begin with terminal punct for the
 +
--  preceding segment: 'First element' .. 'sepc next element' .. etc.?
 +
trim = false;
 +
end_chr = f.sub(str, -1, -1); -- get the last character of the output string
 +
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff?
 +
if end_chr == duplicate_char then -- if same as separator
 +
str = f.sub(str, 1, -2); -- remove it
 +
elseif end_chr == "'" then -- if it might be wiki-markup
 +
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
 +
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
 +
elseif  f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
 +
trim = true; -- why? why do this and next differently from previous?
 +
elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
 +
trim = true; -- same question
 +
end
 +
elseif end_chr == "]" then -- if it might be wiki-markup
 +
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
 +
trim = true;
 +
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
 +
trim = true;
 +
elseif  f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
 +
trim = true;
 +
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
 +
trim = true;
 +
end
 +
elseif end_chr == " " then -- if last char of output string is a space
 +
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
 +
str = f.sub(str, 1, -3); -- remove them both
 +
end
 +
end
  
]]
+
if trim then
 
+
if value ~= comp then -- value does not equal comp when value contains HTML markup
local function nowrap_date (date)
+
local dup2 = duplicate_char;
local cap='';
+
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
local cap2='';
+
 
+
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
+
else
date = substitute (cfg.presentation['nowrap1'], date);
+
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
+
end
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
+
end
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
+
end
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
+
str = str .. value; -- add it to the output string
 +
end
 
end
 
end
+
return str;
return date;
 
 
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().
+
--[[--------------------------< I S _ S U F F I X >-----------------------------
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.
+
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
 +
Puncutation not allowed.
  
 
]]
 
]]
  
local function is_valid_isxn (isxn_str, len)
+
local function is_suffix (suffix)
local temp = 0;
+
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58
+
return true;
len = len+1; -- adjust to be a loop counter
 
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
 
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
 
temp = temp + 10*( len - i ); -- it represents 10 decimal
 
else
 
temp = temp + tonumber( string.char(v) )*(len-i);
 
end
 
 
end
 
end
return temp % 11 == 0; -- returns true if calculation result is zero
+
return false;
 
end
 
end
  
  
--[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >----------------------------------------------
+
--[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
  
ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
+
For Vancouver style, author/editor names are supposed to be rendered in Latin
If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length
+
(read ASCII) characters. When a name uses characters that contain diacritical
and stripped of dashes, spaces and other non-isxn-13 characters.
+
marks, those characters are to be converted to the corresponding Latin
 +
character. When a name is written using a non-Latin alphabet or logogram, that
 +
name is to be transliterated into Latin characters. The module doesn't do this
 +
so editors may/must.
  
]]
+
This test allows |first= and |last= names to contain any of the letters defined
 +
in the four Unicode Latin character sets
 +
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
 +
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
 +
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
 +
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
  
local function is_valid_isxn_13 (isxn_str)
+
|lastn= also allowed to contain hyphens, spaces, and apostrophes.
local temp=0;
+
(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
+
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
 
for i, v in ipairs( isxn_str ) do
 
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
 
end
 
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
 
end
 
  
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
+
This original test:
 +
if nil == mw.ustring.find (last, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%']*$")
 +
or nil == mw.ustring.find (first, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") 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.
  
Determines whether an ISBN string is valid
+
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
 +
\195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
 +
\195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
 +
\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
  
 
]]
 
]]
  
local function check_isbn( isbn_str )
+
local function is_good_vanc_name (last, first, suffix, position)
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
+
if not suffix then
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
+
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
local len = isbn_str:len();
+
first = first:match ('(.-)[,%s]+'); -- get name/initials
+
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
if len ~= 10 and len ~= 13 then
+
end
return false;
 
 
end
 
end
 
+
if utilities.is_set (suffix) then
if len == 10 then
+
if not is_suffix (suffix) then
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
+
add_vanc_error (cfg.err_msg_supl.suffix, position);
return is_valid_isxn(isbn_str, 10);
+
return false; -- not a name with an appropriate suffix
else
+
end
local temp = 0;
 
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
 
return is_valid_isxn_13 (isbn_str);
 
 
end
 
end
 +
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
 
end
  
--[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
 
  
Determines whether an ISMN string is validSimilar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
+
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
+
 
section 2, pages 9–12.
+
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
 +
as Jr, 2nd, 3rd, etc.  See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
 +
This code only accepts and understands generational suffix in the Vancouver format
 +
because Roman numerals look like, and can be mistaken for, initials.
 +
 
 +
This function uses ustring functions because firstname initials may be any of the
 +
Unicode Latin characters accepted by is_good_vanc_name ().
  
 
]]
 
]]
  
local function ismn (id)
+
local function reduce_to_initials(first, position)
local handler = cfg.id_handlers['ISMN'];
+
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
local text;
 
local valid_ismn = true;
 
  
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn
+
if not name then -- if not initials and a suffix
 +
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
 +
end
  
if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
+
if name then -- if first is initials with or without suffix
valid_ismn = false;
+
if 3 > mw.ustring.len (name) then -- if one or two initials
else
+
if suffix then -- if there is a suffix
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
+
if is_suffix (suffix) then -- is it legitimate?
end
+
return first; -- one or two initials and a valid suffix so nothing to do
 +
else
 +
add_vanc_error (cfg.err_msg_supl.suffix, position); -- one or two initials with invalid suffix so error message
 +
return first; -- and return first unmolested
 +
end
 +
else
 +
return first; -- one or two initials without suffix; nothing to do
 +
end
 +
end
 +
end -- if here then name has 3 or more uppercase letters so treat them as a word
 +
 
 +
local initials, names = {}, {}; -- tables to hold name parts and initials
 +
local i = 1; -- counter for number of initials
  
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
+
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
-- 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
+
while names[i] do -- loop through the table
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
+
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
end  
+
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
+
if is_suffix (names[i]) then -- if a legitimate suffix
return text;
+
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
 +
break; -- and done because suffix must fall at the end of a name
 +
end -- no error message if not a suffix; possibly because of Romanization
 +
end
 +
if 3 > i then
 +
table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table
 +
end
 +
i = i + 1; -- bump the counter
 +
end
 +
 +
return table.concat(initials) -- Vancouver format does not include spaces.
 
end
 
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
+
--[[--------------------------< L I S T _ P E O P L E >--------------------------
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
+
Formats a list of people (authors, contributors, editors, interviewers, translators)
 
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.
 
  
]]
+
names in the list will be linked when
 +
|<name>-link= has a value
 +
|<name>-mask- does NOT have a value; masked names are presumed to have been
 +
rendered previously so should have been linked there
  
local function issn(id)
+
when |<name>-mask=0, the associated name is not rendered
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
 
local handler = cfg.id_handlers['ISSN'];
 
local text;
 
local valid_issn = true;
 
  
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
+
]]
  
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 function list_people (control, people, etal)
valid_issn=false; -- wrong length or improper character
+
local sep;
else
+
local namesep;
valid_issn=is_valid_isxn(id, 8); -- validate issn
+
local format = control.format;
end
+
local maximum = control.maximum;
 +
local name_list = {};
  
if true == valid_issn then
+
if 'vanc' == format then -- Vancouver-like name styling?
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
+
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
 +
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
 
else
 
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
+
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
 +
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
 
end
 
end
 
 
text = external_link_id({link = handler.link, label = handler.label,
+
if sep:sub (-1, -1) ~= " " then sep = sep .. " " end
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
+
if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names
 
if false == valid_issn then
 
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
 
end
 
 
 
return text
+
for i, person in ipairs (people) do
end
+
if utilities.is_set (person.last) then
 +
local mask = person.mask;
 +
local one;
 +
local sep_one = sep;
  
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
+
if utilities.is_set (maximum) and i > maximum then
 
+
etal = true;
Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
+
break;
characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
+
end
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.
+
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
local function amazon(id, domain)
+
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
local err_cat = ""
+
else
 
+
one = mask; -- replace name with mask text (must include name-list separator)
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
+
sep_one = " "; -- modify name-list separator
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
+
end
else
+
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
+
one = person.last; -- get surname
if check_isbn( id ) then -- see if asin value is isbn10
+
local first = person.first -- get given name
add_maint_cat ('ASIN');
+
if utilities.is_set (first) then
elseif not is_set (err_cat) then
+
if ("vanc" == format) then -- if Vancouver format
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not isbn10
+
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
elseif not id:match("^%u[%d%u]+$") then
 
err_cat =  ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
 
 
end
 
end
 
end
 
end
if not is_set(domain) then
 
domain = "com";
 
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
 
domain = "co." .. domain;
 
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
 
domain = "com." .. domain;
 
end
 
local handler = cfg.id_handlers['ASIN'];
 
return external_link_id({link=handler.link,
 
label=handler.label, prefix=handler.prefix .. domain .. "/dp/",
 
id=id, encode=handler.encode, separator = handler.separator}) .. err_cat;
 
end
 
  
--[[--------------------------< A R X I V >--------------------------------------------------------------------
+
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
 +
 +
return result, count; -- return name-list string and count of number of names (count used for editor names only)
 +
end
 +
 
 +
--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------
  
See: http://arxiv.org/help/arxiv_identifier
+
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise
 +
returns an empty string.
  
format and error check arXiv identifier.  There are three valid forms of the identifier:
+
namelist is one of the contributor-, author-, or editor-name lists chosen in that
the first form, valid only between date codes 9108 and 0703 is:
+
order. year is Year or anchor_year.
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 make_citeref_id (namelist, year)
local handler = cfg.id_handlers['ARXIV'];
+
local names={}; -- a table for the one to four names and year
local year, month, version;
+
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
local err_cat = '';
+
names[i] = v.last
local text;
+
if i == 4 then break end -- if four then done
+
end
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
+
table.insert (names, year); -- add the year at the end
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
+
local id = table.concat(names); -- concatenate names and year for CITEREF id
year = tonumber(year);
+
if utilities.is_set (id) then -- if concatenation is not an empty string
month = tonumber(month);
+
return "CITEREF" .. id; -- add the CITEREF portion
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
 
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
+
return ''; -- return an empty string; no reason to include CITEREF id in this citation
 
end
 
end
 +
end
 +
  
text = external_link_id({link = handler.link, label = handler.label,
+
--[[---------------------< N A M E _ H A S _ E T A L >--------------------------
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
 
  
if is_set (class) then
+
Evaluates the content of name parameters (author, editor, etc.) for variations on
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
+
the theme of et al. If found, the et al. is removed, a flag is set to true and
else
+
the function returns the modified name and the flag.
class = ''; -- empty string for concatenation
 
end
 
 
return text .. class;
 
end
 
  
--[[
+
This function never sets the flag to false but returns its previous state because
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
+
it may have been set by previous passes through this function or by the associated
1. Remove all blanks.
+
|display-<names>=etal parameter
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
 
3. If there is a hyphen in the string:
 
a. Remove it.
 
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
 
1. All these characters should be digits, and there should be six or less. (not done in this function)
 
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
 
  
Returns a normalized lccn for lccn() to validate.  There is no error checking (step 3.b.1) performed in this function.
 
 
]]
 
]]
  
local function normalize_lccn (lccn)
+
local function name_has_etal (name, etal, nocat, param)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
 
  
if nil ~= string.find (lccn,'/') then
+
if utilities.is_set (name) then -- name can be nil in which case just return
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
+
local patterns = cfg.et_al_patterns; -- get patterns from configuration
 +
 +
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
 +
if name:match (pattern) then -- if this 'et al' pattern is found in name
 +
name = name:gsub (pattern, ''); -- remove the offending text
 +
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
 +
if not nocat then -- no categorization for |vauthors=
 +
table.insert( z.message_tail, {utilities.set_message ('err_etal', {param})}); -- and set an error if not added
 +
end
 +
end
 +
end
 
end
 
end
  
local prefix
+
return name, etal;
local suffix
+
end
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
+
--[[---------------------< N A M E _ I S _ N U M E R I C >----------------------
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
 
lccn=prefix..suffix; -- reassemble the lccn
 
end
 
 
return lccn;
 
end
 
  
--[[
+
Add maint cat when name parameter value does not contain letters.  Does not catch
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
+
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
+
current version of this test but |first=(1888) is caught.
  
length = 8 then all digits
+
returns nothing
length = 9 then lccn[1] is lower case alpha
 
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
 
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
 
length = 12 then lccn[1] and lccn[2] are both lower case alpha
 
  
 
]]
 
]]
  
local function lccn(lccn)
+
local function name_is_numeric (name, list_name)
local handler = cfg.id_handlers['LCCN'];
+
if utilities.is_set (name) then
local err_cat =  ''; -- presume that LCCN is valid
+
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
local id = lccn; -- local copy of the lccn
+
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
 
 
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
 
local len = id:len(); -- get the length of the lccn
 
 
 
if 8 == len then
 
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
 
end
 
elseif 9 == len then -- LCCN should be adddddddd
 
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
 
end
 
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
 
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
 
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
end
 
end
 
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
 
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
end
 
elseif 12 == len then -- LCCN should be aadddddddddd
 
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
 
end
 
end
else
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
 
end
 
 
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
 
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
 
 
end
 
end
 
return external_link_id({link = handler.link, label = handler.label,
 
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
 
 
end
 
end
  
--[[
 
Format PMID and do simple error checking.  PMIDs are sequential numbers beginning at 1 and counting up.  This code checks the PMID to see that it
 
contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.
 
]]
 
  
local function pmid(id)
+
--[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------
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 >------------------------------------------------------
+
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.
  
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.  If embargo date is
+
returns nothing
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
 
|embargo= was not set in this cite.
 
  
 
]]
 
]]
  
local function is_embargoed (embargo)
+
local function name_has_ed_markup (name, list_name)
if is_set (embargo) then
+
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
local lang = mw.getContentLanguage();
+
 
local good1, embargo_date, good2, todays_date;
+
if utilities.is_set (name) then
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
+
for _, pattern in ipairs (patterns) do -- spin through patterns table and
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
+
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
if good1 and good2 then -- if embargo date and today's date are good dates
+
break;
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
 
end
 
end
 
end
return ''; -- |embargo= not set return empty string
 
 
end
 
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
+
--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
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
+
Evaluates the content of last/surname (authors etc.) parameters for multiple names.
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link. Function is_embargoed ()
+
Multiple names are indicated if there is more than one comma or any "unescaped"
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
+
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.
  
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
+
returns nothing
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 name_has_mult_names (name, list_name)
local test_limit = 5000000; -- update this value as PMCs approach
+
local _, commas, semicolons, nbsps;
local handler = cfg.id_handlers['PMC'];
+
if utilities.is_set (name) then
local err_cat = ''; -- presume that PMC is valid
+
_, commas = name:gsub (',', ''); -- count the number of commas
+
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
local text;
+
-- nbsps probably should be its own separate count rather than merged in
 
+
-- some way with semicolons because Lua patterns do not support the
if id:match("[^%d]") then -- if PMC has anything but digits
+
-- grouping operator that regex does, which means there is no way to add
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
+
-- more entities to escape except by adding more counts with the new
else -- PMC is only digits
+
-- entities
local id_num = tonumber(id); -- convert id to a number for range testing
+
_, nbsps = name:gsub ('&nbsp;',''); -- count nbsps
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
+
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
+
-- 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
 
if is_set (embargo) then -- is PMC is still embargoed?
 
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
 
else
 
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
 
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
 
end
 
return text;
 
 
end
 
end
  
-- Formats a DOI and checks for DOI errors.
 
  
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
+
--[[------------------------< N A M E _ C H E C K S >---------------------------
-- Prefix: directory indicator '10.' followed by a registrant code
 
-- Suffix: character string of any length chosen by the registrant
 
  
-- This function checks a DOI name for: prefix/suffix.  If the doi name contains spaces or endashes,
+
This function calls various name checking functions used to validate the content
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
+
of the various name-holding parameters.
  
-- 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 name_checks (last, first, list_name)
local cat = ""
+
local accept_name;
local handler = cfg.id_handlers['DOI'];
+
 
+
if utilities.is_set (last) then
local text;
+
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
if is_set(inactive) then
+
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
+
if not accept_name then -- <last> not wrapped in accept-as-written markup
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
+
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
if is_set(inactive_year) then
+
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
+
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
else
 
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
 
 
end
 
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
  
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
+
if utilities.is_set (first) then
cat = ' ' .. set_error( 'bad_doi' );
+
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
 +
 
 +
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
 
end
return text .. inactive .. cat
+
 
 +
return last, first; -- done
 
end
 
end
  
  
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
+
--[[----------------------< E X T R A C T _ N A M E S >-------------------------
 
+
Gets name list from the input arguments
Formats an OpenLibrary link, and checks for associated errors.
 
 
 
]]
 
local function openlibrary(id)
 
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
 
local handler = cfg.id_handlers['OL'];
 
 
 
if ( code == "A" ) then
 
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'authors/OL',
 
id=id, separator=handler.separator, encode = handler.encode})
 
elseif ( code == "M" ) then
 
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'books/OL',
 
id=id, separator=handler.separator, encode = handler.encode})
 
elseif ( code == "W" ) then
 
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'works/OL',
 
id=id, separator=handler.separator, encode = handler.encode})
 
else
 
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'OL',
 
id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' );
 
end
 
end
 
  
 +
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.
  
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
+
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=.
  
Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
+
When an author or editor parameter contains some form of 'et al.', the 'et al.'
'<' and/or '>' angle brackets.
+
is stripped from the parameter and a flag (etal) returned that will cause list_people()
 +
to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps
 +
'et al.' out of the template's metadata.  When this occurs, an error is emitted.
  
 
]]
 
]]
  
local function message_id (id)
+
local function extract_names(args, list_name)
local handler = cfg.id_handlers['USENETID'];
+
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
  
text = external_link_id({link = handler.link, label = handler.label,
+
local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
+
while true do
+
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
+
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
+
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
end
+
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
 
return text
 
end
 
  
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
+
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.
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
+
last, first = name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
+
 
+
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
  
local function set_titletype (cite_class, title_type)
+
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
if is_set(title_type) then
+
n = n + 1; -- point to next location in the names table
if "none" == title_type then
+
if 1 == count then -- if the previous name was missing
title_type = ""; -- if |type=none then type parameter not displayed
+
table.insert( z.message_tail, { utilities.set_message ( 'err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}, true ) } ); -- add this error message
 +
end
 +
count = 0; -- reset the counter, we're looking for two consecutive missing names
 
end
 
end
return title_type; -- if |type= has been set to any other value use that value
+
i = i + 1; -- point to next args location
 
end
 
end
 
+
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
+
return names, etal; -- all done, return our list of names and the etal flag
 
end
 
end
  
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
 
  
Removes irrelevant text and dashes from ISBN number
+
--[[---------------------< G E T _ I S O 6 3 9 _ C O D E >----------------------
Similar to that used for Special:BookSources
 
  
]]
+
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
  
local function clean_isbn( isbn_str )
+
Returns the language name and associated two- or three-character code.  Because
return isbn_str:gsub( "[^-0-9X]", "" );
+
case of the source may be incorrect or different from the case that WikiMedia uses,
end
+
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.
  
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
+
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
  
Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
+
Names that are included in the list will be found if that name is provided in the
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
+
|language= parameter. For example, if |language=Chavacano de Zamboanga, that name
]]
+
will be found with the associated code 'cbk-zam'.  When names are found and the
local function escape_lua_magic_chars (argument)
+
associated code is not two or three characters, this function returns only the
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
+
WikiMedia language name.
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
 
return argument;
 
end
 
  
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
+
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
  
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
+
Adapted from code taken from Module:Check ISO 639-1.
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.
 
  
 
]]
 
]]
  
local function strip_apostrophe_markup (argument)
+
local function get_iso639_code (lang, this_wiki_code)
if not is_set (argument) then return argument; end
+
if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
 +
return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
 +
end
 +
 
 +
local ietf_code; -- because some languages have both IETF-like codes and ISO 639-like codes
 +
local ietf_name;
 +
 +
local langlc = mw.ustring.lower (lang); -- lower-case version for comparisons
  
while true do
+
for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
+
if langlc == mw.ustring.lower (name) then
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
+
if 2 == #code or 3 == #code then -- two- or three-character codes only; IETF extensions not supported
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
+
return name, code; -- so return the name and the code
argument=argument:gsub("%'%'%'%'", "");
+
end
elseif argument:match ("%'%'%'") then -- bold (3)
+
ietf_code = code; -- remember that we found an IETF-like code and save its name
argument=argument:gsub("%'%'%'", "");
+
ietf_name = name; -- but keep looking for a 2- or 3-char code
elseif argument:match ("%'%'") then -- italic (2)
 
argument=argument:gsub("%'%'", "");
 
else
 
break;
 
 
end
 
end
 
end
 
end
return argument; -- done
+
-- didn't find name with 2- or 3-char code; if IETF-like code found return
 +
return ietf_code and ietf_name or lang; -- associated name; return original language text else
 
end
 
end
  
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
 
  
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
+
--[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------
 +
 
 +
Gets language name from a provided two- or three-character ISO 639 code.  If a code
 +
is recognized by MediaWiki, use the returned name; if not, then use the value that
 +
was provided with the language parameter.
 +
 
 +
When |language= contains a recognized language (either code or name), the page is
 +
assigned to the category for that code: Category:Norwegian-language sources (no).
 +
For valid three-character code languages, the page is assigned to the single category
 +
for '639-2' codes: Category:CS1 ISO 639-2 language sources.
 +
 
 +
Languages that are the same as the local wiki are not categorized.  MediaWiki does
 +
not recognize three-character equivalents of two-character codes: code 'ar' is
 +
recognized but code 'ara' is not.
 +
 
 +
This function supports multiple languages in the form |language=nb, French, th
 +
where the language names or codes are separated from each other by commas with
 +
optional space characters.
  
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
 
of %27%27...
 
 
]]
 
]]
  
local function make_coins_title (title, script)
+
local function language_parameter (lang)
if is_set (title) then
+
local code; -- the two- or three-character language code
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
+
local name; -- the language name
else
+
local language_list = {}; -- table of language names to be rendered
title=''; -- if not set, make sure title is an empty string
+
local names_table = {}; -- table made from the value assigned to |language=
end
+
 
if is_set (script) then
+
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
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 >------------------------------------------------
+
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
  
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
+
for _, lang in ipairs (names_table) do -- reuse lang
 +
name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap
  
]]
+
if name then -- there was a remapped code so
 +
if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private IETF tag
 +
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip IETF tags from code
 +
end
 +
else
 +
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any IETF-like tags from code
 +
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
 +
name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
 +
end
 +
end
  
local function get_coins_pages (pages)
+
if utilities.is_set (name) then -- if |language= specified a valid code
local pattern;
+
code = lang:lower(); -- save it
if not is_set (pages) then return pages; end -- if no page numbers then we're done
+
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
 
 
while true do
+
if utilities.is_set (code) then -- only 2- or 3-character codes
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
+
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
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
+
if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
+
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
 
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
+
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
+
name = utilities.make_sep_list (#language_list, language_list);
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
+
if this_wiki_name == name then
local function remove_wiki_link( str )
+
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
+
end
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
+
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end));
+
--[[ TODO: should only return blank or name rather than full list
 +
so we can clean up the bunched parenthetical elements Language, Type, Format
 +
]]
 +
end
 +
 
 +
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
 +
Gets the default CS style configuration for the given mode.
 +
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)
 +
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
 
end
  
-- Converts a hyphen to a dash
+
--[[--------------------------< S E T _ S T Y L E >-----------------------------
local function hyphen_to_dash( str )
+
Sets the separator and postscript styles. Checks the |mode= first and the
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
+
#invoke CitationClass second. Removes the postscript if postscript == none.
return str;
+
]]
end
+
local function set_style (mode, postscript, cite_class)
return str:gsub( '-', '' );
+
local sep;
 +
if 'cs2' == mode then
 +
sep, postscript = set_cs_style (postscript, 'cs2');
 +
elseif 'cs1' == mode then
 +
sep, postscript = set_cs_style (postscript, 'cs1');
 +
elseif 'citation' == cite_class then
 +
sep, postscript = set_cs_style (postscript, 'cs2');
 +
else
 +
sep, postscript = set_cs_style (postscript, 'cs1');
 +
end
 +
 
 +
if cfg.keywords_xlate[postscript:lower()] == 'none' then
 +
-- emit a maintenance message if user postscript is the default cs2 postscript
 +
-- we catch the opposite case for cs1 in set_cs_style
 +
if 'cs2' == mode or 'citation' == cite_class then
 +
utilities.set_message ('maint_postscript');
 +
end
 +
postscript = '';
 +
end
 +
 +
return sep, postscript
 +
end
 +
 
 +
--[=[-------------------------< I S _ P D F >-----------------------------------
 +
 
 +
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.
 +
 
 +
returns true if file extension is one of the recognized extensions, else false
 +
 
 +
]=]
 +
 
 +
local function is_pdf (url)
 +
return url:match ('%.pdf$') or url:match ('%.PDF$') or
 +
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
 +
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
 
end
 
end
  
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
 
  
Joins a sequence of strings together while checking for duplicate separation characters.
+
--[[--------------------------< S T Y L E _ F O R M A T >-----------------------
 +
 
 +
Applies CSS style to |format=, |chapter-format=, etc.  Also emits an error message
 +
if the format parameter does not have a matching URL parameter.  If the format parameter
 +
is not set and the URL contains a file extension that is recognized as a PDF document
 +
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
 +
the appropriate styling.
  
 
]]
 
]]
  
local function safe_join( tbl, duplicate_char )
+
local function style_format (format, url, fmt_param, url_param)
--[[
+
if utilities.is_set (format) then
Note: we use string functions here, rather than ustring functions.
+
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
 +
if not utilities.is_set (url) then
 +
format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} ); -- add an error message
 +
end
 +
elseif is_pdf (url) then -- format is not set so if URL is a PDF file then
 +
format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF
 +
else
 +
format = ''; -- empty string for concatenation
 +
end
 +
return format;
 +
end
 +
 
 +
 
 +
--[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------
 +
 
 +
Returns a number that defines the number of names displayed for author and editor
 +
name lists and a Boolean flag to indicate when et al. should be appended to the name list.
 +
 
 +
When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
 +
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-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.'
 +
 
 +
In all other cases, returns nil and the previous state of the 'etal' flag.
 +
 
 +
inputs:
 +
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
 +
count: #a or #e
 +
list_name: 'authors' or 'editors'
 +
etal: author_etal or editor_etal
 +
 
 +
]]
 +
 
 +
local function get_display_names (max, count, list_name, etal, param)
 +
if utilities.is_set (max) then
 +
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
 +
max = count + 1; -- number of authors + 1 so display all author name plus et al.
 +
etal = true; -- overrides value set by extract_names()
 +
elseif max:match ('^%d+$') then -- if is a string of numbers
 +
max = tonumber (max); -- make it a number
 +
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
 +
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
 +
max = nil;
 +
end
 +
else -- not a valid keyword or number
 +
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
 +
max = nil; -- unset; as if |display-xxxxors= had not been set
 +
end
 +
end
 
 
This has considerably faster performance and should work correctly as
+
return max, etal;
long as the duplicate_char is strict ASCII. The strings
+
end
in tbl may be ASCII or UTF8.
+
 
]]
+
 
 +
--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
 +
 
 +
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 extra_text_in_page_check (val, name)
 +
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
 +
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) 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 ('err_extra_text_pages', {name}, true)}); -- add error message
 +
return; -- and done
 +
end
 +
end
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
 +
 
 +
Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
 +
 
 +
For |volume=:
 +
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
 +
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
 +
are allowed.
 +
 
 +
For |issue=:
 +
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
 +
parameter content (all case insensitive).
 +
 +
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
 +
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
 
 
local str = ''; -- the output string
+
<val> is |volume= or |issue= parameter value
local comp = ''; -- what does 'comp' mean?
+
<name> is |volume= or |issue= parameter name for error message
local end_chr = '';
+
<selector> is 'v' for |volume=, 'i' for |issue=
local trim;
+
 
for _, value in ipairs( tbl ) do
+
sets error message on failure; returns nothing
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)
+
local function extra_text_in_vol_iss_check (val, name, selector)
elseif value ~= '' then
+
if not utilities.is_set (val) then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
+
return;
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
+
end
else
+
comp = value;
+
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;
end
 
-- typically duplicate_char is sepc
 
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
 
--  Because individual string segments often (always?) begin with terminal punct for th
 
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
 
trim = false;
 
end_chr = str:sub(-1,-1); -- get the last character of the output string
 
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
 
if end_chr == duplicate_char then -- if same as separator
 
str = str:sub(1,-2); -- remove it
 
elseif end_chr == "'" then -- if it might be wikimarkup
 
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
 
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
 
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
 
trim = true; -- why? why do this and next differently from previous?
 
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
 
trim = true; -- same question
 
end
 
elseif end_chr == "]" then -- if it might be wikimarkup
 
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
 
trim = true;
 
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
 
trim = true;
 
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
 
trim = true;
 
end
 
elseif end_chr == " " then -- if last char of output string is a space
 
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
 
str = str:sub(1,-3); -- remove them both
 
end
 
end
 
  
if trim then
+
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
if value ~= comp then -- value does not equal comp when value contains html markup
+
val = val:lower(); -- force parameter value to lower case
local dup2 = duplicate_char;
+
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
+
if val:match (pattern) then -- when a match, error so
+
table.insert (z.message_tail, {utilities.set_message (handler, {name}, true)}); -- add error message
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
+
return; -- and done
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
 
end
 
end
return str;
+
end
end 
+
 
  
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
+
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
  
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
+
split apart a |vauthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
+
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
+
rendered citation and in the metadata. Individual author names may be wikilinked
These things are not currently possible in this module so are left to the editor to do.
 
  
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
+
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
 
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
 
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
 
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
 
  
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
+
]=]
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
 
  
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
+
local function get_v_name_table (vparam, output_table, output_link_table)
because the code editor gets confused between character insertion point and cursor position.
+
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 i = 1;
 +
 +
while name_table[i] do
 +
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
 +
local name = name_table[i];
 +
i = i + 1; -- bump indexer to next segment
 +
while name_table[i] do
 +
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
 +
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses
 +
break; -- and done reassembling so
 +
end
 +
i = i + 1; -- bump indexer
 +
end
 +
table.insert (output_table, name); -- and add corporate name to the output table
 +
table.insert (output_link_table, ''); -- no wikilink
 +
else
 +
wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
 +
table.insert (output_table, label); -- add this name
 +
if 1 == wl_type then
 +
table.insert (output_link_table, label); -- simple wikilink [[D]]
 +
else
 +
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
 +
end
 +
end
 +
i = i + 1;
 +
end
 +
return output_table;
 +
end
  
]]
 
  
local function is_good_vanc_name (last, first)
+
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
if nil == mw.ustring.find (last, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
 
add_vanc_error ();
 
return false; -- not a string of latin characters; Vancouver required Romanization
 
end;
 
return true;
 
end
 
  
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
+
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.
  
Attempts to convert names to initials in support of |name-list-format=vanc.
+
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
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/.
+
tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.
  
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
+
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
 
  
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
+
This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
  
 
]]
 
]]
  
local function reduce_to_initials(first)
+
local function parse_vauthors_veditors (args, vparam, list_name)
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
+
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local initials = {}
+
local v_name_table = {};
local i = 0; -- counter for number of initials
+
local v_link_table = {}; -- when name is wikilinked, targets go in this table
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
+
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
+
local last, first, link, mask, suffix;
i = i + 1; -- bump the counter
+
local corporate = false;
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
 
end
 
return table.concat(initials) -- Vancouver format does not include spaces.
 
end
 
  
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
+
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
  
Formats a list of people (e.g. authors / editors)  
+
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>
  
]]
+
if accept_name then
 +
last = v_name;
 +
corporate = true; -- flag used in list_people()
 +
elseif string.find(v_name, "%s") then
 +
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
 +
add_vanc_error (cfg.err_msg_supl.punctuation, i);
 +
end
 +
local lastfirstTable = {}
 +
lastfirstTable = mw.text.split(v_name, "%s+")
 +
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix
  
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
+
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
local sep;
+
suffix = first; -- not initials so assume that whatever we got is a generational suffix
local namesep;
+
first = table.remove(lastfirstTable); -- get what should be the initials from the table
local format = control.format
+
end
local maximum = control.maximum
+
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
local lastauthoramp = control.lastauthoramp;
+
if not utilities.is_set (last) then
local text = {}
+
first = ''; -- unset
 +
last = v_name; -- last empty because something wrong with first
 +
add_vanc_error (cfg.err_msg_supl.name, i);
 +
end
 +
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
 +
add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
 +
end
 +
if mw.ustring.match (v_name, ' %u %u$') 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 nameDoesn'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
  
if 'vanc' == format then -- Vancouver-like author/editor name styling?
+
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
sep = ','; -- name-list separator between authors is a comma
+
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
namesep = ' '; -- last/first separator is a space
+
names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list
else
 
sep = ';' -- name-list separator between authors is a semicolon
 
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
 +
return names, etal; -- all done, return our list of names
 +
end
 +
  
local count = #text / 2; -- (number of names + number of separators) divided by 2
+
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
if count > 0 then
 
if count > 1 and is_set(lastauthoramp) and not etal then
 
text[#text-2] = " & "; -- replace last separator with ampersand text
 
end
 
text[#text] = nil; -- erase the last separator
 
end
 
 
local result = table.concat(text) -- construct list
 
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
 
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
 
end
 
 
return result, count
 
end
 
  
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
+
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
 +
select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
  
Generates a CITEREF anchor ID if we have at least one name or a dateOtherwise returns an empty string.
+
Only one of these appropriate three will be usedThe hierarchy is: |authorn= (and aliases) highest and |authors= lowest;
 +
|editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn)
  
namelist is one of the contributor-, author-, or editor-name lists chosen in that orderyear is Year or anchor_year.
+
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 listThere 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.
local function anchor_id (namelist, year)
 
local names={}; -- a table for the one to four names and year
 
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
 
names[i] = v.last
 
if i == 4 then break end -- if four then done
 
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
 
  
 +
In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.
  
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
+
]]
  
Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,
+
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
+
local lastfirst = false;
 +
if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ...
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
 +
lastfirst = true;
 +
end
  
This function never sets the flag to false but returns it's previous state because it may have been set by
+
if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
+
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
 
+
(true == lastfirst and utilities.is_set (xxxxors)) then
]]
+
local err_name;
 
+
if 'AuthorList' == list_name then -- figure out which name should be used in error message
local function name_has_etal (name, etal, nocat)
+
err_name = 'author';
 
+
else
if is_set (name) then -- name can be nil in which case just return
+
err_name = 'editor';
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
 
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
 
 
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
 
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
+
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters',
name = name:gsub (others_pattern, ''); -- if found, remove
+
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
 
if not nocat then -- no categorization for |vauthors=
 
add_maint_cat ('etal'); -- and add a category if not already added
 
end
 
end
 
 
end
 
end
return name, etal; --  
+
 
 +
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
 +
if utilities.is_set (vxxxxors) then return 2 end;
 +
if utilities.is_set (xxxxors) then return 3 end;
 +
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
 
end
 
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.
+
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
 
find |last4= and |last5= then the search is done.
 
  
This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
+
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
+
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_valIf the parameter value is one
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
+
of the list of allowed values returns the translated value; else, emits an error message and returns the value
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/ConfigurationThis keeps 'et al.' out of the  
+
specified by ret_val.
template's metadata.  When this occurs, the page is added to a maintenance category.
 
  
 
]]
 
]]
  
local function extract_names(args, list_name)
+
local function is_valid_parameter_value (value, name, possible, ret_val)
local names = {}; -- table of names
+
if not utilities.is_set (value) then
local last; -- individual name components
+
return ret_val; -- an empty parameter is ok
local first;
+
elseif utilities.in_array (value, possible) then
local link;
+
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
local mask;
+
else
local i = 1; -- loop counter/indexer
+
table.insert( z.message_tail, { utilities.set_message ( 'err_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
local n = 1; -- output table indexer
+
return ret_val;
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)
+
end
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
+
end
  
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
 
while true do
 
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
 
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
 
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
 
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 
  
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
+
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
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
+
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
+
when the last character is not a sepc character or when the last three characters are not sepc followed by two
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
+
closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
count = count + 1; -- number of times we haven't found last and first
+
single space character.
if 2 <= count then -- two missing names and we give up
 
break; -- normal exit or there is a two-name hole in the list; can't tell which
 
end
 
else -- we have last with or without a first
 
if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last
 
table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link;
 
end
 
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
 
n = n + 1; -- point to next location in the names table
 
if 1 == count then -- if the previous name was missing
 
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
 
end
 
count = 0; -- reset the counter, we're looking for two consecutive missing names
 
end
 
i = i + 1; -- point to next args location
 
end
 
 
return names, etal; -- all done, return our list of names
 
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
 
any of the parameters listed in each cfg.id_handlers['...'].parameters.  If found, adds the parameter and value to
 
the identifier list. Emits redundant error message is more than one alias exists in args
 
  
 
]]
 
]]
  
local function extract_ids( args )
+
local function terminate_name_list (name_list, sepc)
local id_list = {}; -- list of identifiers found in args
+
if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
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
+
return name_list; -- just return the name list
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
+
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 is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list
+
return name_list .. " "; -- don't add another
 +
else
 +
return name_list .. sepc .. ' '; -- otherwise terminate the name list
 
end
 
end
return id_list;
 
 
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.
+
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
  
inputs:
+
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
id_list – table of identifiers built by extract_ids()
+
or formatted issue, or an empty string if neither are set.
options – table of various template parameter values used to modify some manually handled identifiers
 
  
 
]]
 
]]
 +
 +
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 build_id_list( id_list, options )
+
if 'podcast' == cite_class and utilities.is_set (issue) then
local new_list, handler = {};
+
return wrap_msg ('issue', {sepc, issue}, lower);
 +
end
  
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
+
local vol = ''; -- here for all cites except magazine
 
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
 
-- fallback to read-only cfg
 
handler = setmetatable( { ['id'] = v }, fallback(k) );
 
 
 
if handler.mode == 'external' then
+
if utilities.is_set (volume) then
table.insert( new_list, {handler.label, external_link_id( handler ) } );
+
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals
elseif handler.mode == 'internal' then
+
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
+
elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters
elseif handler.mode ~= 'manual' then
+
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)}); -- not bold
error( cfg.messages['unknown_ID_mode'] );
+
utilities.add_prop_cat ('long_vol');
elseif k == 'DOI' then
+
else -- four or less characters
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
+
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold
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
 
end
 
end
+
if utilities.is_set (issue) then
function comp( a, b ) -- used in following table.sort()
+
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
return a[1] < b[1];
 
 
end
 
end
+
return vol;
table.sort( new_list, comp );
 
for k, v in ipairs( new_list ) do
 
new_list[k] = v[2];
 
end
 
 
return new_list;
 
 
end
 
end
 
 
  
--[[--------------------------< C O I N S _ C L E A N U P >----------------------------------------------------
 
  
Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities.
+
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
  
2015-12-10: there is a bug in mw.text.unstripNoWiki ().  It replaced math stripmarkers with the appropriate content
+
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
when it shouldn't.  See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29
+
The return order is:
 +
page, pages, sheet, sheets
  
TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible
+
Singular has priority over plural when both are provided.
characters table?
 
]]
 
 
 
local function coins_cleanup (value)
 
value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content
 
value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">&#39;s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s
 
value = value:gsub ('&zwj;\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe
 
value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11)
 
value = value:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with plain space
 
value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space
 
value = value:gsub ('&zwj;', ''); -- remove &zwj; entities
 
value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space
 
value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space
 
return value;
 
end
 
 
 
 
 
--[[--------------------------< C O I N S >--------------------------------------------------------------------
 
 
 
COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
 
  
 
]]
 
]]
  
local function COinS(data, class)
+
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
if 'table' ~= type(data) or nil == next(data) then
+
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
return '';
+
if utilities.is_set (sheet) then
end
+
if 'journal' == origin then
 
+
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
for k, v in pairs (data) do -- spin through all of the metadata parameter values
 
if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed)
 
data[k] = coins_cleanup (v);
 
end
 
end
 
 
 
local ctx_ver = "Z39.88-2004";
 
 
-- treat table strictly as an array with only set values.
 
local OCinSoutput = setmetatable( {}, {
 
__newindex = function(self, key, value)
 
if is_set(value) then
 
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
 
end
 
end
 
});
 
 
if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or
 
('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then
 
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier
 
if 'arxiv' == class then -- set genre according to the type of citation template we are rendering
 
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
 
elseif 'conference' == class then
 
OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set)
 
elseif 'web' == class then
 
OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set)
 
 
else
 
else
OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles
+
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
 
end
 
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only
+
elseif utilities.is_set (sheets) then
if is_set (data.Map) then
+
if 'journal' == origin then
OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical
+
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
 
else
 
else
OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles
+
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
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
 
end
else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
 
OCinSoutput["rft.genre"] = "unknown";
 
 
end
 
end
OCinSoutput["rft.btitle"] = data.Title; -- book only
 
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
 
OCinSoutput["rft.series"] = data.Series; -- book only
 
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
 
OCinSoutput["rft.edition"] = data.Edition; -- book only
 
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
 
 
else -- cite thesis
 
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
 
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
 
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
 
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
 
 
end
 
end
-- and now common parameters (as much as possible)
+
 
OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation
+
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
 
 
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
+
if utilities.is_set (page) then
if k == 'ISBN' then v = clean_isbn( v ) end
+
if is_journal then
local id = cfg.id_handlers[k].COinS;
+
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry
+
elseif not nopp then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
+
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
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
 
 
 
--[[
 
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
 
else
OCinSoutput[ id ] = value;
+
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
 
end
 
end
end
+
elseif utilities.is_set (pages) then
]]
+
if is_journal then
local last, first;
+
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
for k, v in ipairs( data.Authors ) do
+
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers
+
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
if k == 1 then -- for the first author name only
+
elseif not nopp then
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
+
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
+
else
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
+
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
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
 
end
 
end
 
OCinSoutput.rft_id = data.URL;
 
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
 
OCinSoutput = setmetatable( OCinSoutput, nil );
 
 
 
-- sort with version string always first, and combine.
+
return '', '', '', ''; -- return empty strings
table.sort( OCinSoutput );
 
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
 
return table.concat(OCinSoutput, "&");
 
 
end
 
end
  
  
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
+
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
  
Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
+
returns one of the in-source locators: page, pages, or at.  
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
 
  
Returns the language name and associated ISO639-1 codeBecause case of the source may be incorrect or different from the case that Wikimedia
+
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
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
+
for use in COinSThis COinS thing is done because here we convert an interwiki-link to an external link and
with the codeWhen there is no match, we return the original language name string.
+
add an icon span around that; get_coins_pages() doesn't know about the spanTODO: should it? 
  
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
+
TODO: add support for sheet and sheets?; streamline;
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
 
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
 
returns only the Wikimedia language name.
 
  
Adapted from code taken from Module:Check ISO 639-1.
+
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 get_iso639_code (lang)
+
local function insource_loc_get (page, page_orig, pages, pages_orig, at)
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
+
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?)
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
+
 
 +
if utilities.is_set (page) then
 +
if utilities.is_set (pages) or utilities.is_set (at) then
 +
pages = ''; -- unset the others
 +
at = '';
 +
end
 +
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
 +
 
 +
ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label
 +
if ws_url then
 +
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
 +
coins_pages = ws_label;
 +
end
 +
elseif utilities.is_set (pages) then
 +
if utilities.is_set (at) then
 +
at = ''; -- unset
 +
end
 +
extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
 +
 
 +
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label
 +
if ws_url then
 +
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
 +
coins_pages = ws_label;
 +
end
 +
elseif utilities.is_set (at) then
 +
ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label
 +
if ws_url then
 +
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
 +
coins_pages = ws_label;
 +
end
 
end
 
end
 
 
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
+
return page, pages, at, coins_pages;
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
+
end
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
+
 
+
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
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
+
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value
if 2 ~= code:len() then -- ISO639-1 codes only
+
 
return name; -- so return the name but not the code
+
]]
end
+
 
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
+
local function is_unique_archive_url (archive, url, c_url, source, date)
 +
if utilities.is_set (archive) then
 +
if archive == url or archive == c_url then
 +
table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)}); -- add error message
 +
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
 
end
 
end
 
end
 
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
+
 
 +
return archive, date;
 
end
 
end
  
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
 
  
Get language name from ISO639-1 code value providedIf a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
+
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
 +
 
 +
Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the
 +
save snapshot URL or to calendar pagesWhen the archive URL is 'https://web.archive.org/save/' (or http://...)
 +
archive.org saves a snapshot of the target page in the URL.  That is something that Wikipedia should not allow
 +
unwitting readers to do.
  
There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and
+
When the archive.org URL does not have a complete timestamp, archive.org chooses a snapshot according to its own
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
+
algorithm or provides a calendar 'search' result[[WP:ELNO]] discourages links to search results.
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.
 
  
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
+
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them.
+
|archive-date= and an error message when:
 +
|archive-url= holds an archive.org save command URL
 +
|archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
 +
correct place
 +
otherwise returns |archive-url= and |archive-date=
  
See Help talk:Citation Style_1#An ISO 639-1 language name test
+
There are two mostly compatible archive.org URLs:
 +
//web.archive.org/<timestamp>... -- the old form
 +
//web.archive.org/web/<timestamp>... -- the new form
  
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
+
The old form does not support or map to the new form when it contains a display flag.  There are four identified flags
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.
+
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
 +
we don't check for these specific flags but we do check the form.
  
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas.
+
This function supports a preview mode.  When the article is rendered in preview mode, this function may return a modified
 +
archive URL:
 +
for save command errors, return undated wildcard (/*/)
 +
for timestamp errors when the timestamp has a wildcard, return the URL unmodified
 +
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
  
]]
+
]=]
  
local function language_parameter (lang)
+
local function archive_url_check (url, date)
local code; -- the ISO639-1 two character code
+
local err_msg = ''; -- start with the error message empty
local name; -- the language name
+
local path, timestamp, flag; -- portions of the archive.org URL
local language_list = {}; -- table of language names to be rendered
+
local names_table = {}; -- table made from the value assigned to |language=
+
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
 +
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
 +
end
  
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
+
if url:match('//web%.archive%.org/save/') then -- if a save command URL, we don't want to allow saving of the target page
 
+
err_msg = cfg.err_msg_supl.save;
for _, lang in ipairs (names_table) do -- reuse lang
+
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
 
+
elseif url:match('//liveweb%.archive%.org/') then
if lang:match ('^%a%a%-') then -- strip ietf language tags from code
+
err_msg = cfg.err_msg_supl.liveweb;
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
+
else
end
+
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
+
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
+
if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
end
+
err_msg = cfg.err_msg_supl.timestamp;
+
if '*' ~= flag then
if is_set (name) then -- if Language specified a valid ISO639-1 code
+
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)
code = lang:lower(); -- save it
 
else
 
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
 
end
 
 
if is_set (code) then
 
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
 
if 'en' ~= code then -- English not the language
 
add_prop_cat ('foreign_lang_source', {name, code})
 
 
end
 
end
 +
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
add_maint_cat ('unknown_lang'); -- add maint category if not already added
+
return url, date; -- return ArchiveURL and ArchiveDate
 
end
 
end
 
table.insert (language_list, name);
 
name = ''; -- so we can reuse it
 
 
end
 
end
+
-- if here, something not right so
code = #language_list -- reuse code as number of languages in the list
+
table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } ); -- add error message and
if 2 >= code then
+
if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
+
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
elseif 2 < code then
+
else
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
+
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
 
end
 
if 'English' == name then
 
return ''; -- if one language and that language is English return an empty string (no annotation)
 
 
end
 
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
 
 
end
 
end
  
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
 
  
Set style settings for CS1 citation templates. Returns separator and postscript settings
+
--[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------
  
]]
+
check |place=, |publication-place=, |location= to see if these params include digits.  This function added because
 
+
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
local function set_cs1_style (ps)
 
if not is_set (ps) then -- unless explicitely set to something
 
ps = '.'; -- terminate the rendered citation with a period
 
end
 
return '.', ps; -- separator is a full stop
 
end
 
  
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
+
returns the original parameter value without modification; added maint cat when parameter value contains digits
 
 
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
 
  
 
]]
 
]]
  
local function set_cs2_style (ps, ref)
+
local function place_check (param_val)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
+
if not utilities.is_set (param_val) then -- parameter empty or omitted
ps = ''; -- make sure it isn't nil
+
return param_val; -- return that empty state
 
end
 
end
if not is_set (ref) then -- if |ref= is not set
+
ref = "harv"; -- set default |ref=harv
+
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
 +
utilities.set_message ('maint_location'); -- yep, add maint cat
 
end
 
end
return ',', ps, ref; -- separator is a comma
+
 +
return param_val; -- and done
 
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
+
--[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------
rendered style.
 
  
]]
+
compares |title= value against list of known generic title patterns.  Returns true when pattern matches; nil else
 
 
local function get_settings_from_cite_class (ps, ref, cite_class)
 
local sep;
 
if (cite_class == "citation") then -- for citation templates (CS2)
 
sep, ps, ref = set_cs2_style (ps, ref);
 
else -- not a citation template so CS1
 
sep, ps = set_cs1_style (ps);
 
end
 
 
 
return sep, ps, ref -- return them all
 
end
 
 
 
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
 
  
Establish basic style settings to be used when rendering the citationUses |mode= if set and valid or uses
+
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
config.CitationClass from the template's #invoke: to establish style.
+
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
 +
index [1]index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
 +
or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so
 +
that we don't run out of processing time on very large articles.
  
 
]]
 
]]
  
local function set_style (mode, ps, ref, cite_class)
+
local function is_generic_title (title)
local sep;
+
title = mw.ustring.lower(title); -- switch title to lower case
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
+
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments
sep, ps, ref = set_cs2_style (ps, ref);
+
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
+
return true; -- found English generic title so done
sep, ps = set_cs1_style (ps);
+
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
else -- anything but cs1 or cs2
+
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
+
return true; -- found local generic title so done
end
+
end
if 'none' == ps:lower() then -- if assigned value is 'none' then
+
end
ps = ''; -- set to empty string
 
 
end
 
end
 
return sep, ps, ref
 
 
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
 
applying the pdf icon to external links.
 
  
returns true if file extension is one of the recognized extension, else false
+
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
  
]=]
+
compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else
 
 
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 >------------------------------------------------------
 
 
 
Applies css style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
 
not have a matching url parameter.  If the format parameter is not set and the url contains a file extension that
 
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
 
the appropriate styling.
 
  
 
]]
 
]]
  
local function style_format (format, url, fmt_param, url_param)
+
local function is_archived_copy (title)
if is_set (format) then
+
title = mw.ustring.lower(title); -- switch title to lower case
format = wrap_style ('format', format); -- add leading space, parenthases, resize
+
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
if not is_set (url) then
+
return true;
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
+
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
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
 
format = wrap_style ('format', 'PDF'); -- set format to pdf
 
else
 
format = ''; -- empty string for concatenation
 
 
end
 
end
return format;
 
 
end
 
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 >------------------------
 
  
Returns a number that may or may not limit the length of the author or editor name lists.
+
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
  
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
+
This is the main function doing the majority of the citation formatting.
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.
 
  
 
]]
 
]]
  
local function get_display_authors_editors (max, count, list_name, etal)
+
local function citation0( config, args )
if is_set (max) then
+
--[[
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
+
Load Input Parameters
max = count + 1; -- number of authors + 1 so display all author name plus et al.
+
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
etal = true; -- overrides value set by extract_names()
+
]]
elseif max:match ('^%d+$') then -- if is a string of numbers
+
local A = argument_wrapper ( args );
max = tonumber (max); -- make it a number
+
local i
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);
+
-- Pick out the relevant fields from the arguments.  Different citation templates
 +
-- define different field names for the same underlying things.
 +
 
 +
local author_etal;
 +
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
 +
local Authors;
 +
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
 +
local Collaboration = A['Collaboration'];
 +
 
 +
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
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
+
if utilities.is_set (Collaboration) then
max = count + 1; -- number of authors + 1
+
author_etal = true; -- so that |display-authors=etal not required
 +
end
 
end
 
end
 
return max, etal;
 
end
 
  
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
+
local editor_etal;
 +
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
  
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.  
+
do -- to limit scope of selected
abbreviation in the first characters of the parameter content.
+
local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn
 +
if 1 == selected then
 +
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
 +
elseif 2 == selected then
 +
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
 +
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
 +
end
 +
end
 +
 +
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
 +
local Chapter_origin = A:ORIGIN ('Chapter');
 +
local Contribution; -- because contribution is required for contributor(s)
 +
if 'contribution' == Chapter_origin then
 +
Contribution = Chapter; -- get the name of the contribution
 +
end
 +
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
 +
 +
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
 +
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
 +
 +
if 0 < #c then
 +
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
 +
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
 +
if 0 == #a then -- |contributor= requires |author=
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'author')}); -- add missing author error message
 +
c = {}; -- blank the contributors' table; it is used as a flag later
 +
end
 +
end
 +
else -- if not a book cite
 +
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters?
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_ignored')}); -- add contributor ignored error message
 +
end
 +
Contribution = nil; -- unset
 +
end
  
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
+
local Title = A['Title'];
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
+
local TitleLink = A['TitleLink'];
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
 
  
]]
+
local auto_select = ''; -- default is auto
 +
local accept_link;
 +
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup
 +
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
 +
auto_select = TitleLink; -- remember selection for later
 +
TitleLink = ''; -- treat as if |title-link= would have been empty
 +
end
  
local function extra_text_in_page_check (page)
+
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
-- local good_pattern = '^P[^%.P%l]';
 
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
 
-- local bad_pattern = '^[Pp][Pp]';
 
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
 
  
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
+
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
add_maint_cat ('extra_text');
+
if 'map' == config.CitationClass and 'section' == Chapter_origin then
 +
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
 +
Chapter = ''; -- unset for now; will be reset later from |map= if present
 
end
 
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
 
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
 
-- add_maint_cat ('extra_text');
 
-- end
 
end
 
  
 +
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
  
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
+
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
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
+
table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
+
end
  
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
+
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
+
Periodical_origin = A:ORIGIN('MailingList');
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
+
end
  
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
+
local ScriptPeriodical = A['ScriptPeriodical'];
  
]]
+
-- 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?
local function parse_vauthors_veditors (args, vparam, list_name)
+
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
+
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
local v_name_table = {};
+
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
+
if p[config.CitationClass]  then
local last, first, link, mask;
+
table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
local corporate = false;
+
end
 
 
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
 
if 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
+
 
+
local Volume;
for i, v_name in ipairs(v_name_table) do
+
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
+
if 'citation' == config.CitationClass then
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
+
if utilities.is_set (Periodical) then
last = v_name:match ('^%(%((.+)%)%)$')
+
if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
corporate = true;
+
Volume = A['Volume']; -- but does for all other 'periodicals'
elseif string.find(v_name, "%s") then
+
end
    lastfirstTable = {}
+
elseif utilities.is_set (ScriptPeriodical) then
    lastfirstTable = mw.text.split(v_name, "%s")
+
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
+
Volume = A['Volume']; -- but does for all other 'periodicals'
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
 
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
 
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
 
 
end
 
end
 
else
 
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
+
Volume = A['Volume']; -- and does for non-'periodical' cites
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
+
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');
 +
 
 +
local Issue;
 +
if 'citation' == config.CitationClass then
 +
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
 +
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'
 +
Issue = hyphen_to_dash (A['Issue']);
 
end
 
end
+
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
+
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
add_vanc_error ();
+
Issue = hyphen_to_dash (A['Issue']);
 
end
 
end
-- this from extract_names ()
 
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
 
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
 
 
end
 
end
return names, etal; -- all done, return our list of names
+
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
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 >------------------------
+
local Page;
 +
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
  
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
+
local Edition = A['Edition'];
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
+
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
 +
local Place = place_check (A['Place'], A:ORIGIN('Place'));
 +
 +
local PublisherName = A['PublisherName'];
 +
local PublisherName_origin = A:ORIGIN('PublisherName');
 +
if utilities.is_set (PublisherName) then
 +
local i = 0;
 +
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
 +
if i then -- non-zero when markup was stripped so emit an error message
 +
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
 +
end
 +
end
  
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
+
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
similarly, |editorn= (and aliases) highest and |editors= lowest
+
local Newsgroup_origin = A:ORIGIN('Newsgroup');
  
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
+
if 'newsgroup' == config.CitationClass then
test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better
+
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
way to do this, I just haven't discovered what that way is.
+
local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
 +
if utilities.is_set (error_text) then
 +
table.insert( z.message_tail, {error_text, error_state} );
 +
end
 +
end
  
Emits an error message when more than one xxxxor name source is provided.
+
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
 +
end
  
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
+
local URL = A['URL']
 +
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
 +
 +
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
 +
UrlAccess = nil;
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
 +
end
 +
 +
local ChapterURL = A['ChapterURL'];
 +
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
 +
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
 +
ChapterUrlAccess = nil;
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
 +
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
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
+
MapUrlAccess = nil;
local lastfirst = false;
+
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'map-url'}, true ) } );
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
 
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
 
lastfirst=true;
 
 
end
 
end
  
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
+
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
(is_set (vxxxxors) and is_set (xxxxors)) or
+
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
(true == lastfirst and is_set (xxxxors)) then
+
 
local err_name;
+
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if 'AuthorList' == list_name then -- figure out which name should be used in error message
+
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
err_name = 'author';
+
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
else
+
no_tracking_cats = "true"; -- set no_tracking_cats
err_name = 'editor';
+
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
table.insert( z.message_tail, { set_error( 'redundant_parameters',
+
end
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
 
 
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
  
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
+
local coins_pages;
if is_set (vxxxxors) then return 2 end;
+
if is_set (xxxxors) then return 3 end;
+
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
 
end
 
  
 +
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
  
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
+
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
 
+
utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
+
if PublicationPlace == Place then
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
+
Place = ''; -- unset; don't need both if they are the same
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
+
end
true; else, emits an error message and returns false.
+
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
]]
 
 
 
local function is_valid_parameter_value (value, name, possible)
 
if not is_set (value) then
 
return true; -- an empty parameter is ok
 
elseif in_array(value:lower(), possible) then
 
return true;
 
else
 
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
 
return false
 
 
end
 
end
end
 
  
 +
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
 +
 +
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
 +
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
 +
local ScriptChapter = A['ScriptChapter'];
 +
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
 +
local Format = A['Format'];
 +
local ChapterFormat = A['ChapterFormat'];
 +
local TransChapter = A['TransChapter'];
 +
local TransChapter_origin = A:ORIGIN ('TransChapter');
 +
local TransTitle = A['TransTitle'];
 +
local ScriptTitle = A['ScriptTitle'];
 +
 +
--[[
 +
Parameter remapping for cite encyclopedia:
 +
When the citation has these parameters:
 +
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title=
 +
|encyclopedia= and |article= then map |encyclopedia= to |title=
  
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
+
|trans-title= maps to |trans-chapter= when |title= is re-mapped
 
+
|url= maps to |chapter-url= when |title= is remapped
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
+
All other combinations of |encyclopedia=, |title=, and |article= are not modified
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
+
single space character.
+
]]
  
]]
+
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
  
local function terminate_name_list (name_list, sepc)
+
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
+
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
return name_list .. " "; -- don't add another
+
table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
else
+
Encyclopedia = nil; -- unset because not supported by this template
return name_list .. sepc .. ' '; -- otherwise terninate the name list
+
end
 
end
 
end
end
 
  
 +
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
 +
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error
 +
table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
 +
end
 +
 +
if utilities.is_set (Encyclopedia) then
 +
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
 +
Periodical_origin = A:ORIGIN ('Encyclopedia');
 +
end
  
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
+
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
 +
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
 +
if not utilities.is_set (Chapter) then
 +
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;
  
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
+
ChapterUrlAccess = UrlAccess;
or formatted issue, or an empty string if neither are set.
 
  
]]
+
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
+
Chapter = utilities.make_wikilink (TitleLink, Chapter);
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
+
end
if not is_set (volume) and not is_set (issue) then
+
Title = Periodical;
return '';
+
ChapterFormat = Format;
end
+
Periodical = ''; -- redundant so unset
+
TransTitle = '';
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
+
URL = '';
if is_set (volume) and is_set (issue) then
+
Format = '';
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
+
TitleLink = '';
elseif is_set (volume) then
+
ScriptTitle = '';
return wrap_msg ('vol', {sepc, volume}, lower);
+
end
else
+
elseif utilities.is_set (Chapter) then -- |title= not set
return wrap_msg ('issue', {sepc, issue}, lower);
+
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
end
+
Periodical = ''; -- redundant so unset
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
 
end
 
end
if is_set (issue) then
 
return vol .. substitute (cfg.messages['j-issue'], issue);
 
end
 
return vol;
 
end
 
  
 
+
-- special case for cite techreport.
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
+
local ID = A['ID'];
 
+
if (config.CitationClass == "techreport") then -- special case for cite techreport
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
+
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
The return order is:
+
if not utilities.is_set (ID) then -- can we use ID for the "number"?
page, pages, sheet, sheets
+
ID = A['Number']; -- yes, use it
 
+
else -- ID has a value so emit error message
Singular has priority over plural when both are provided.
+
table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
 
+
end
]]
+
end
 
 
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
 
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
 
if is_set (sheet) then
 
if 'journal' == origin then
 
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
 
else
 
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
 
end
 
elseif is_set (sheets) then
 
if 'journal' == origin then
 
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
 
else
 
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
 
end
 
end
 
 
end
 
end
  
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
+
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
 
+
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
if is_set (page) then
+
local Conference = A['Conference'];
if is_journal then
+
local BookTitle = A['BookTitle'];
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
+
local TransTitle_origin = A:ORIGIN ('TransTitle');
elseif not nopp then
+
if 'conference' == config.CitationClass then
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
+
if utilities.is_set (BookTitle) then
else
+
Chapter = Title;
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
+
Chapter_origin = 'title';
end
+
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
elseif is_set(pages) then
+
ChapterURL = URL;
if is_journal then
+
ChapterUrlAccess = UrlAccess;
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
+
ChapterURL_origin = URL_origin;
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
+
URL_origin = '';
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
+
ChapterFormat = Format;
elseif not nopp then
+
TransChapter = TransTitle;
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
+
TransChapter_origin = TransTitle_origin;
else
+
Title = BookTitle;
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
+
Format = '';
 +
-- TitleLink = '';
 +
TransTitle = '';
 +
URL = '';
 
end
 
end
 +
elseif 'speech' ~= config.CitationClass then
 +
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
 
end
 
end
 
 
return '', '', '', ''; -- return empty strings
+
-- CS1/2 mode
end
+
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
 +
-- separator character and postscript
 +
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
 +
-- controls capitalization of certain static text
 +
local use_lowercase = ( sepc == ',' );
 +
 +
-- cite map oddities
 +
local Cartography = "";
 +
local Scale = "";
 +
local Sheet = A['Sheet'] or '';
 +
local Sheets = A['Sheets'] or '';
 +
if config.CitationClass == "map" then
 +
if utilities.is_set (Chapter) then
 +
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
 +
end
 +
Chapter = A['Map'];
 +
Chapter_origin = A:ORIGIN('Map');
 +
ChapterURL = A['MapURL'];
 +
ChapterURL_origin = A:ORIGIN('MapURL');
 +
TransChapter = A['TransMap'];
 +
ScriptChapter = A['ScriptMap']
 +
ScriptChapter_origin = A:ORIGIN('ScriptMap')
  
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
+
ChapterUrlAccess = MapUrlAccess;
 +
ChapterFormat = A['MapFormat'];
  
This is the main function doing the majority of the citation formatting.
+
Cartography = A['Cartography'];
 +
if utilities.is_set ( Cartography ) then
 +
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
 +
end
 +
Scale = A['Scale'];
 +
if utilities.is_set ( Scale ) then
 +
Scale = sepc .. " " .. Scale;
 +
end
 +
end
  
]]
+
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
 +
local Series = A['Series'];
 +
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
 +
local SeriesLink = A['SeriesLink'];
  
local function citation0( config, args)
+
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
--[[
 
Load Input Parameters
 
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
 
]]
 
local A = argument_wrapper( args );
 
local i
 
  
-- Pick out the relevant fields from the arguments.  Different citation templates
+
local Network = A['Network'];
-- define different field names for the same underlying things.
+
local Station = A['Station'];
local author_etal;
+
local s, n = {}, {};
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
+
-- do common parameters first
local Authors;
+
if utilities.is_set (Network) then table.insert(n, Network); end
local NameListFormat = A['NameListFormat'];
+
if utilities.is_set (Station) then table.insert(n, Station); end
 +
ID = table.concat(n, sepc .. ' ');
 +
 +
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
 +
local Season = A['Season'];
 +
local SeriesNumber = A['SeriesNumber'];
  
do -- to limit scope of selected
+
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
+
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
if 1 == selected then
+
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
+
end
elseif 2 == selected then
+
-- assemble a table of parts concatenated later into Series
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
+
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
+
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
elseif 3 == selected then
+
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Authors = A['Authors']; -- use content of |authors=
+
Issue = ''; -- unset because this is not a unique parameter
end
+
 +
Chapter = Title; -- promote title parameters to chapter
 +
ScriptChapter = ScriptTitle;
 +
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
 +
ChapterLink = TitleLink; -- alias |episode-link=
 +
TransChapter = TransTitle;
 +
ChapterURL = URL;
 +
ChapterUrlAccess = UrlAccess;
 +
ChapterURL_origin = URL_origin;
 +
 +
Title = Series; -- promote series to title
 +
TitleLink = SeriesLink;
 +
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 +
 
 +
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
 +
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
 +
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
 +
Series = utilities.make_wikilink (ChapterLink, Series);
 +
end
 +
URL = ''; -- unset
 +
TransTitle = '';
 +
ScriptTitle = '';
 +
 +
else -- now oddities that are cite serial
 +
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
 +
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
 +
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
 +
Series = utilities.make_wikilink (SeriesLink, Series);
 +
end
 +
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
 +
end
 
end
 
end
 +
-- end of {{cite episode}} stuff
  
local Coauthors = A['Coauthors'];
+
-- handle type parameter for those CS1 citations that have default values
local Others = A['Others'];
+
local TitleType = A['TitleType'];
 +
local Degree = A['Degree'];
 +
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
 +
TitleType = set_titletype (config.CitationClass, TitleType);
 +
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis
 +
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
 +
end
 +
end
 +
 
 +
if utilities.is_set (TitleType) then -- if type parameter is specified
 +
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
 +
-- TODO: Hack on TitleType to fix bunched parentheses problem
 +
end
  
local editor_etal;
+
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
+
local Date = A['Date'];
local Editors;
+
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'];
  
do -- to limit scope of selected
+
if not utilities.is_set (Date) then
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
+
Date = Year; -- promote Year to Date
if 1 == selected then
+
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
+
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
elseif 2 == selected then
+
Date = PublicationDate; -- promote PublicationDate to Date
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
+
PublicationDate = ''; -- unset, no longer needed
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
+
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
elseif 3 == selected then
+
else
Editors = A['Editors']; -- use content of |editors=
+
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
  
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
+
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
local Translators; -- assembled translators name list
+
 
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
+
--[[
 +
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.
 
 
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
+
Date validation supporting code is in Module:Citation/CS1/Date_validation
local Contributors; -- assembled contributors name list
+
]]
local Contribution = A['Contribution'];
+
 
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
+
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
+
if not utilities.is_set (DF) then
+
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
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
 
Contribution = nil; -- unset
 
 
end
 
end
  
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
+
local ArchiveURL;
NameListFormat = ''; -- anything else, set to empty string
+
local ArchiveDate;
end
+
local ArchiveFormat = A['ArchiveFormat'];
 +
 
 +
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
 +
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
 +
 +
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL
  
local Year = A['Year'];
+
local PublicationDate = A['PublicationDate'];
+
local AccessDate = A['AccessDate'];
local OrigYear = A['OrigYear'];
 
local Date = A['Date'];
 
 
local LayDate = A['LayDate'];
 
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
+
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
local Title = A['Title'];
+
local DoiBroken = A['DoiBroken'];
local ScriptTitle = A['ScriptTitle'];
+
local Embargo = A['Embargo'];
local BookTitle = A['BookTitle'];
+
local anchor_year; -- used in the CITEREF identifier
local Conference = A['Conference'];
+
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local TransTitle = A['TransTitle'];
+
local error_message = '';
local TitleNote = A['TitleNote'];
+
-- AirDate has been promoted to Date so not necessary to check it
local TitleLink = A['TitleLink'];
+
local date_parameters_list = {
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
+
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
+
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
 +
['date'] = {val = Date, name = Date_origin},
 +
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
 +
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')},
 +
['lay-date'] = {val = LayDate, name = A:ORIGIN ('LayDate')},
 +
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')},
 +
['year'] = {val = Year, name = A:ORIGIN ('Year')},
 +
};
 +
 
 +
local error_list = {};
 +
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
 +
 
 +
-- start temporary Julian / Gregorian calendar uncertainty categorization
 +
if COinS_date.inter_cal_cat then
 +
utilities.add_prop_cat ('jul_greg_uncertainty');
 
end
 
end
 +
-- end temporary Julian / Gregorian calendar uncertainty categorization
  
local Chapter = A['Chapter'];
+
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;  
local ScriptChapter = A['ScriptChapter'];
+
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
+
end
local TransChapter = A['TransChapter'];
+
local TitleType = A['TitleType'];
+
if 0 == #error_list then -- error free dates only; 0 when error_list is empty
local Degree = A['Degree'];
+
local modified = false; -- flag
local Docket = A['Docket'];
+
local ArchiveFormat = A['ArchiveFormat'];
+
if validation.edtf_transform (date_parameters_list) then -- edtf dates to MOS compliant format
local ArchiveURL = A['ArchiveURL'];
+
modified = true;
local URL = A['URL']
+
end
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'];
+
if utilities.is_set (DF) then -- if we need to reformat dates
+
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate
local Volume;
+
end
local Issue;
+
 
local Page;
+
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
local Pages;
+
modified = true;
local At;
+
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
 +
end
 +
 +
-- for those wikis that can and want to have English date names translated to the local language,
 +
-- uncomment the next three lines.  Not supported by en.wiki (for obvious reasons)
 +
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
 +
-- if validation.date_name_xlate (date_parameters_list, false) then
 +
-- modified = true;
 +
-- end
  
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
+
if modified then -- if the date_parameters_list values were modified
Volume = A['Volume'];
+
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
end
+
ArchiveDate = date_parameters_list['archive-date'].val;
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
+
Date = date_parameters_list['date'].val;
Issue = A['Issue'];
+
DoiBroken = date_parameters_list['doi-broken-date'].val;
end
+
LayDate = date_parameters_list['lay-date'].val;
local Position = '';
+
PublicationDate = date_parameters_list['publication-date'].val;
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
+
end
Page = A['Page'];
+
else
Pages = hyphen_to_dash( A['Pages'] );
+
table.insert (z.message_tail, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)}); -- add this error message
At = A['At'];
+
end
end
+
end -- end of do
  
local Edition = A['Edition'];
+
local ID_list = {}; -- sequence table of rendered identifiers
local PublicationPlace = A['PublicationPlace']
+
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
local Place = A['Place'];
+
local Class = A['Class']; -- arxiv class identifier
 
 
local PublisherName = A['PublisherName'];
+
local ID_support = {
local RegistrationRequired = A['RegistrationRequired'];
+
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
+
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
RegistrationRequired=nil;
+
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')},
end
+
}
local SubscriptionRequired = A['SubscriptionRequired'];
+
 
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
+
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
SubscriptionRequired=nil;
+
 
 +
-- 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
 
end
  
local Via = A['Via'];
+
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
local AccessDate = A['AccessDate'];
+
end
local ArchiveDate = A['ArchiveDate'];
+
 
local Agency = A['Agency'];
+
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
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
 
  
local Language = A['Language'];
+
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
local Format = A['Format'];
+
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
local ChapterFormat = A['ChapterFormat'];
+
if identifiers.auto_link_urls[auto_select] then -- manual selection
local DoiBroken = A['DoiBroken'];
+
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
local ID = A['ID'];
+
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=
local ASINTLD = A['ASINTLD'];
+
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
local IgnoreISBN = A['IgnoreISBN'];
+
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
+
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
IgnoreISBN = nil; -- anything else, set to empty string
+
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
end
+
URL = identifiers.auto_link_urls['doi'];
local Embargo = A['Embargo'];
+
URL_origin = cfg.id_handlers['DOI'].parameters[1];
local Class = A['Class']; -- arxiv class identifier
+
end
 
+
end
local ID_list = extract_ids( args );
 
 
 
local Quote = A['Quote'];
 
 
 
local LayFormat = A['LayFormat'];
 
local LayURL = A['LayURL'];
 
local LaySource = A['LaySource'];
 
local Transcript = A['Transcript'];
 
local TranscriptFormat = A['TranscriptFormat'];
 
local TranscriptURL = A['TranscriptURL']
 
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
 
  
local LastAuthorAmp = A['LastAuthorAmp'];
+
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url=
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
+
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message
LastAuthorAmp = nil; -- set to empty string
+
AccessDate = ''; -- unset
end
 
local no_tracking_cats = A['NoTracking'];
 
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
 
no_tracking_cats = nil; -- set to empty string
 
 
end
 
end
 +
end
  
--these are used by cite interview
+
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
local Callsign = A['Callsign'];
+
-- Test if citation has no title
local City = A['City'];
+
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
local Program = A['Program'];
+
table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
 
 
--local variables that are not cs1 parameters
 
local use_lowercase; -- controls capitalization of certain static text
 
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
 
local anchor_year; -- used in the CITEREF identifier
 
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
 
 
 
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
 
local Mode = A['Mode'];
 
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
 
Mode = '';
 
 
end
 
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
 
local PostScript;
 
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 utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
+
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
+
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
no_tracking_cats = "true"; -- set no_tracking_cats
+
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
end
+
Title = ''; -- set title to empty string
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
+
utilities.set_message ('maint_untitled'); -- add maint cat
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
 
end
  
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
+
check_for_url ({ -- add error message when any of these parameters hold a URL
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
+
['title'] = Title,
 +
[A:ORIGIN('Chapter')] = Chapter,
 +
[Periodical_origin] = Periodical,
 +
[PublisherName_origin] = PublisherName
 +
});
  
local NoPP = A['NoPP']
+
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
+
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
NoPP = true;
+
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
else
+
-- is the article title, and Chapter is a section within the article.  So, we remap
NoPP = nil; -- unset, used as a flag later
+
 +
local coins_chapter = Chapter; -- default assuming that remapping not required
 +
local coins_title = Title; -- et tu
 +
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
 +
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then
 +
coins_chapter = Title; -- remap
 +
coins_title = Periodical;
 +
end
 
end
 
end
 
+
local coins_author = a; -- default for coins rft.au
if is_set(Page) then
+
if 0 < #c then -- but if contributor list
if is_set(Pages) or is_set(At) then
+
coins_author = c; -- use that instead
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
 
end
 
 
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
+
local QuotePage = A['QuotePage'];
+
local QuotePages = hyphen_to_dash (A['QuotePages']);
--[[
 
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
+
-- this is the function call to COinS()
|url maps to |chapterurl when |title is remapped
+
local OCinSoutput = metadata.COinS({
 
+
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
All other combinations of |encyclopedia, |title, and |article are not modified
+
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
 
+
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wiki-markup
]]
+
['Degree'] = Degree; -- cite thesis only
 
+
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wiki-markup
local Encyclopedia = A['Encyclopedia'];
+
['PublicationPlace'] = PublicationPlace,
 
+
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
+
['Season'] = COinS_date.rftssn,
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
+
['Quarter'] = COinS_date.rftquarter,
if is_set(Title) or is_set (ScriptTitle) then
+
['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?
if not is_set(Chapter) then
+
['Series'] = Series,
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
+
['Volume'] = Volume,
ScriptChapter = ScriptTitle;
+
['Issue'] = Issue,
TransChapter = TransTitle;
+
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links
ChapterURL = URL;
+
['Edition'] = Edition,
if not is_set (ChapterURL) and is_set (TitleLink) then
+
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
+
['URL'] = first_set ({ChapterURL, URL}, 2),
end
+
['Authors'] = coins_author,
Title = Periodical;
+
['ID_list'] = ID_list_coins,
ChapterFormat = Format;
+
['RawPage'] = this_page.prefixedText,
Periodical = ''; -- redundant so unset
+
}, config.CitationClass);
TransTitle = '';
+
 
URL = '';
+
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
Format = '';
+
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
TitleLink = '';
+
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
ScriptTitle = '';
 
end
 
else -- |title not set
 
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
 
Periodical = ''; -- redundant so unset
 
end
 
end
 
 
end
 
end
  
-- Special case for cite techreport.
+
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
if (config.CitationClass == "techreport") then -- special case for cite techreport
+
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
+
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
if not is_set(ID) then -- can we use ID for the "number"?
 
ID = A['Number']; -- yes, use it
 
else -- ID has a value so emit error message
 
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
 
end
 
end
 
 
end
 
end
  
-- special case for cite interview
+
local Editors;
if (config.CitationClass == "interview") then
+
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
if is_set(Program) then
+
local Contributors; -- assembled contributors name list
ID = ' ' .. Program;
+
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.
 +
-- We also add leading spaces and surrounding markup and punctuation to the
 +
-- various parts of the citation, but only when they are non-nil.
 +
do
 +
local last_first_list;
 +
local control = {
 +
format = NameListStyle, -- empty string or 'vanc'
 +
maximum = nil, -- as if display-authors or display-editors not set
 +
mode = Mode
 +
};
 +
 
 +
do -- do editor name list first because the now unsupported coauthors used to modify control table
 +
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
 +
Editors, EditorCount = list_people (control, e, editor_etal);
 +
 
 +
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
 +
EditorCount = 2; -- spoof to display (eds.) annotation
 +
end
 +
end
 +
do -- now do 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
if is_set(Callsign) then
+
do -- now do translators
if is_set(ID) then
+
control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators'));
ID = ID .. sepc .. ' ' .. Callsign;
+
Translators = list_people (control, t, translator_etal);
else
 
ID = ' ' .. Callsign;
 
end
 
 
end
 
end
if is_set(City) then
+
do -- now do contributors
if is_set(ID) then
+
control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
ID = ID .. sepc .. ' ' .. City;
+
Contributors = list_people (control, c, contributor_etal);
else
 
ID = ' ' .. City;
 
end
 
 
end
 
end
 +
do -- now do authors
 +
control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));
  
if is_set(Others) then
+
last_first_list = list_people (control, a, author_etal);
if is_set(TitleType) then
+
 
Others = ' ' .. TitleType .. ' with ' .. Others;
+
if utilities.is_set (Authors) then
TitleType = '';
+
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
 +
if author_etal then
 +
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
 +
end
 
else
 
else
Others = ' ' .. 'Interview with ' .. Others;
+
Authors = last_first_list; -- either an author name list or an empty string
 
end
 
end
else
+
end -- end of do
Others = '(Interview)';
+
 +
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
 +
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
 
end
 
end
 +
 
end
 
end
  
-- special case for cite mailing list
+
local ConferenceFormat = A['ConferenceFormat'];
if (config.CitationClass == "mailinglist") then
+
local ConferenceURL = A['ConferenceURL'];
Periodical = A ['MailingList'];
+
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
elseif 'mailinglist' == A:ORIGIN('Periodical') then
+
Format = style_format (Format, URL, 'format', 'url');
Periodical = ''; -- unset because mailing list is only used for cite mailing list
+
 
 +
-- special case for chapter format so no error message or cat when chapter not supported
 +
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
 +
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
 +
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
 
end
 
end
  
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
+
if not utilities.is_set (URL) then
if 'conference' == config.CitationClass then
+
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
if is_set(BookTitle) then
+
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
Chapter = Title;
+
table.insert( z.message_tail, { utilities.set_message ( 'err_cite_web_url', {}, true ) } );
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
+
end
ChapterURL = URL;
+
ChapterURLorigin = URLorigin;
+
-- do we have |accessdate= without either |url= or |chapter-url=?
URLorigin = '';
+
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
ChapterFormat = Format;
+
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } );
TransChapter = TransTitle;
+
AccessDate = '';
Title = BookTitle;
 
Format = '';
 
-- TitleLink = '';
 
TransTitle = '';
 
URL = '';
 
 
end
 
end
elseif 'speech' ~= config.CitationClass then
 
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
 
 
end
 
end
  
-- cite map oddities
+
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
local Cartography = "";
+
local OriginalURL
local Scale = "";
+
local OriginalURL_origin
local Sheet = A['Sheet'] or '';
+
local OriginalFormat
local Sheets = A['Sheets'] or '';
+
local OriginalAccess;
if config.CitationClass == "map" then
+
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
Chapter = A['Map'];
+
if utilities.is_set ( ArchiveURL ) then
ChapterURL = A['MapURL'];
+
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it
TransChapter = A['TransMap'];
+
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
ChapterURLorigin = A:ORIGIN('MapURL');
+
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
ChapterFormat = A['MapFormat'];
+
OriginalFormat = ChapterFormat; -- and original |chapter-format=
+
 
Cartography = A['Cartography'];
+
if 'live' ~= UrlStatus then
if is_set( Cartography ) then
+
ChapterURL = ArchiveURL -- swap-in the archive's URL
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
+
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages
end
+
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
Scale = A['Scale'];
+
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs
if is_set( Scale ) then
+
end
Scale = sepc .. " " .. Scale;
+
elseif utilities.is_set (URL) then
end
+
OriginalURL = URL; -- save copy of original source URL
 +
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
 +
OriginalFormat = Format; -- and original |format=
 +
OriginalAccess = UrlAccess;
 +
 
 +
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
 +
URL = ArchiveURL -- swap-in the archive's URL
 +
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages
 +
Format = ArchiveFormat or ''; -- swap in archive's format
 +
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs
 +
end
 +
end
 
end
 
end
  
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
+
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
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
+
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
local AirDate = A['AirDate'];
+
local chap_param;
local SeriesLink = A['SeriesLink'];
+
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then
+
chap_param = A:ORIGIN ('Chapter')
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))});
+
elseif utilities.is_set (TransChapter) then
 +
chap_param = A:ORIGIN ('TransChapter')
 +
elseif utilities.is_set (ChapterURL) then
 +
chap_param = A:ORIGIN ('ChapterURL')
 +
elseif utilities.is_set (ScriptChapter) then
 +
chap_param = ScriptChapter_origin;
 +
else utilities.is_set (ChapterFormat)
 +
chap_param = A:ORIGIN ('ChapterFormat')
 
end
 
end
local Network = A['Network'];
 
local Station = A['Station'];
 
local s, n = {}, {};
 
-- do common parameters first
 
if is_set(Network) then table.insert(n, Network); end
 
if is_set(Station) then table.insert(n, Station); end
 
ID = table.concat(n, sepc .. ' ');
 
 
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
 
Date = AirDate;
 
end
 
  
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
+
if utilities.is_set (chap_param) then -- if we found one
local Season = A['Season'];
+
table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } ); -- add error message
local SeriesNumber = A['SeriesNumber'];
+
Chapter = ''; -- and set them to empty string to be safe with concatenation
 
+
TransChapter = '';
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
+
ChapterURL = '';
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
+
ScriptChapter = '';
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
+
ChapterFormat = '';
 +
end
 +
else -- otherwise, format chapter / article title
 +
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
 +
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
 +
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
 +
no_quotes = true; -- then render it unquoted
 
end
 
end
-- assemble a table of parts concatenated later into Series
+
end
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
 
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
 
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
 
Issue = ''; -- unset because this is not a unique parameter
 
 
Chapter = Title; -- promote title parameters to chapter
 
ScriptChapter = ScriptTitle;
 
ChapterLink = TitleLink; -- alias episodelink
 
TransChapter = TransTitle;
 
ChapterURL = URL;
 
ChapterURLorigin = A:ORIGIN('URL');
 
 
Title = Series; -- promote series to title
 
TitleLink = SeriesLink;
 
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 
  
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
+
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
+
if utilities.is_set (Chapter) then
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
+
Chapter = Chapter .. ChapterFormat ;
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
+
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
 +
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
 
end
 
end
URL = ''; -- unset
+
Chapter = Chapter .. sepc .. ' ';
TransTitle = '';
+
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
ScriptTitle = '';
+
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
+
end
else -- now oddities that are cite serial
+
end
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?
+
-- Format main title
if is_set (Series) and is_set (SeriesLink) then
+
local plain_title = false;
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
+
local accept_title;
end
+
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
Series = wrap_style ('italic-title', Series); -- series is italicized
+
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
end
+
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
 
end
-- end of {{cite episode}} stuff
 
  
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
+
if not accept_title then -- <Title> not wrapped in accept-as-written markup
if 'arxiv' == config.CitationClass then
+
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title=
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
+
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
+
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
elseif is_set (Series) then -- series is an alias of version
+
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
+
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
Series = ''; -- unset
 
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
 
 
end
 
end
 
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
 
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
 
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
 
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
 
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
 
  
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
+
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
+
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
Chapter = '';
 
URL = '';
 
Format = '';
 
Page = ''; Pages = ''; At = '';
 
 
end
 
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
 
end
 
  
-- handle type parameter for those CS1 citations that have default values
+
if is_generic_title (Title) then
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
+
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message
TitleType = set_titletype (config.CitationClass, TitleType);
 
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
 
TitleType = Degree .. " thesis";
 
 
end
 
end
 
end
 
end
  
if is_set(TitleType) then -- if type parameter is specified
+
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
+
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
 +
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article
 +
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks
 +
Title = utilities.wrap_style ('quoted-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
 +
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
 +
else
 +
Title = utilities.wrap_style ('italic-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
 
end
 
end
  
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
+
local TransError = "";
if not is_set (Date) then
+
if utilities.is_set (TransTitle) then
Date = Year; -- promote Year to Date
+
if utilities.is_set (Title) then
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
+
TransTitle = " " .. TransTitle;
if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
+
else
Date = PublicationDate; -- promote PublicationDate to Date
+
TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} );
PublicationDate = ''; -- unset, no longer needed
 
 
end
 
end
 
end
 
end
  
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
+
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
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
+
TitleLink = ''; -- unset
we get the date used in the metadata.
 
 
 
Date validation supporting code is in Module:Citation/CS1/Date_validation
 
]]
 
do -- create defined block to contain local variables error_message and mismatch
 
local error_message = '';
 
-- AirDate has been promoted to Date so not necessary to check it
 
anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
 
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date);
 
 
 
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
 
local mismatch = year_date_check (Year, Date)
 
if 0 == mismatch then -- |year= does not match a year-value in |date=
 
if is_set (error_message) then -- if there is already an error message
 
error_message = error_message .. ', '; -- tack on this additional message
 
end
 
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
 
elseif 1 == mismatch then -- |year= matches year-value in |date=
 
add_maint_cat ('date_year');
 
end
 
 
end
 
end
 
+
if is_set(error_message) then
+
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
+
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format;
 +
URL = ''; -- unset these because no longer needed
 +
Format = "";
 +
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then
 +
local ws_url;
 +
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
 +
if ws_url then
 +
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
 +
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
 +
Title = Title .. TransTitle .. TransError;
 +
else
 +
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
 +
end
 +
else
 +
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
 +
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label
 +
if ws_url then
 +
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
 +
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
 +
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
 +
Title = Title .. TransTitle .. TransError;
 +
else
 +
Title = Title .. TransTitle .. TransError;
 +
end
 
end
 
end
end -- end of do
+
else
 +
Title = TransTitle .. TransError;
 +
end
  
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
+
if utilities.is_set (Place) then
-- 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
+
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
Embargo = is_embargoed (Embargo); --
+
end
  
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
+
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
if not is_set (Embargo) then -- if not embargoed or embargo has expired
+
if utilities.is_set (Conference) then
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
+
if utilities.is_set (ConferenceURL) then
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
+
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
 
end
 
end
 +
Conference = sepc .. " " .. Conference .. ConferenceFormat;
 +
elseif utilities.is_set (ConferenceURL) then
 +
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
 
end
 
end
  
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
+
local Position = '';
-- Test if citation has no title
+
if not utilities.is_set (Position) then
if not is_set(Title) and
+
local Minutes = A['Minutes'];
not is_set(TransTitle) and
+
local Time = A['Time'];
not is_set(ScriptTitle) then
+
 
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
+
if utilities.is_set (Minutes) then
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
+
if utilities.is_set (Time) then
else
+
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
+
end
 +
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
 +
else
 +
if utilities.is_set (Time) then
 +
local TimeCaption = A['TimeCaption']
 +
if not utilities.is_set (TimeCaption) then
 +
TimeCaption = cfg.messages['event'];
 +
if sepc ~= '.' then
 +
TimeCaption = TimeCaption:lower();
 +
end
 +
end
 +
Position = " " .. TimeCaption .. " " .. Time;
 
end
 
end
 +
end
 +
else
 +
Position = " " .. Position;
 +
At = '';
 
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
+
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
['title']=Title,
+
 
[A:ORIGIN('Chapter')]=Chapter,
+
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
[A:ORIGIN('Periodical')]=Periodical,
+
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
[A:ORIGIN('PublisherName')] = PublisherName,
+
if config.CitationClass == 'map' then
});
+
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
 +
local Inset = A['Inset'];
 +
 +
if utilities.is_set ( Inset ) then
 +
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
 +
end
 +
 
 +
if utilities.is_set ( Sections ) then
 +
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
 +
elseif utilities.is_set ( Section ) then
 +
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
 +
end
 +
At = At .. Inset .. Section;
 +
end
  
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
+
local Others = A['Others'];
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
+
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
+
if config.CitationClass == "AV-media-notes"
-- is the article title, and Chapter is a section within the article. So, we remap
+
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')
local coins_chapter = Chapter; -- default assuming that remapping not required
+
else
local coins_title = Title; -- et tu
+
utilities.set_message ('maint_others');
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
 
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
 
coins_chapter = Title; -- remap
 
coins_title = Periodical;
 
 
end
 
end
 
end
 
end
local coins_author = a; -- default for coins rft.au
+
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
if 0 < #c then -- but if contributor list
+
coins_author = c; -- use that instead
+
if utilities.is_set (Translators) then
 +
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
 
end
 
end
 
+
if utilities.is_set (Interviewers) then
-- this is the function call to COinS()
+
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
local OCinSoutput = COinS({
 
['Periodical'] = Periodical,
 
['Encyclopedia'] = Encyclopedia,
 
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
 
['Map'] = Map,
 
['Degree'] = Degree; -- cite thesis only
 
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
 
['PublicationPlace'] = PublicationPlace,
 
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
 
['Season'] = COinS_date.rftssn,
 
['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
 
['Series'] = Series,
 
['Volume'] = Volume,
 
['Issue'] = Issue,
 
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
 
['Edition'] = Edition,
 
['PublisherName'] = PublisherName,
 
['URL'] = first_set ({ChapterURL, URL}, 2),
 
['Authors'] = coins_author,
 
['ID_list'] = ID_list,
 
['RawPage'] = this_page.prefixedText,
 
}, config.CitationClass);
 
 
 
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
 
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
 
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
 
 
end
 
end
 
+
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
+
local TitleNote = A['TitleNote'];
if 'newsgroup' == config.CitationClass then
+
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (PublisherName) then
+
if utilities.is_set (Edition) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
+
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);
 +
else
 +
Edition = '';
 
end
 
end
  
 +
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
 +
local Agency = A['Agency'];
 +
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);
 +
 +
if utilities.is_set (AccessDate) then
 +
local retrv_text = " " .. cfg.messages['retrieved']
  
 +
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
 +
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
 +
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text
  
-- Now perform various field substitutions.
+
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
-- We also add leading spaces and surrounding markup and punctuation to the
+
end
-- 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
+
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
do
+
local last_first_list;
+
local Docket = A['Docket'];
local maximum;
+
  if "thesis" == config.CitationClass and utilities.is_set (Docket) then
local control = {
+
ID = sepc .. " Docket " .. Docket .. ID;
format = NameListFormat, -- empty string or 'vanc'
+
end
maximum = nil, -- as if display-authors or display-editors not set
+
  if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
lastauthoramp = LastAuthorAmp,
+
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
+
end
};
+
 
 +
if utilities.is_set (URL) then
 +
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
 +
end
 +
 
 +
local Quote = A['Quote'];
 +
local TransQuote = A['TransQuote'];
 +
local ScriptQuote = A['ScriptQuote'];
 +
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
  
do -- do editor name list first because coauthors can modify control table
+
if utilities.is_set (Quote) then
maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
+
if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks
-- Preserve old-style implicit et al.
+
Quote = Quote:sub(2, -2); -- strip them off
if not is_set(maximum) and #e == 4 then
 
maximum = 3;
 
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
 
 
end
 
end
 +
end
 +
 +
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
 +
 +
if utilities.is_set (ScriptQuote) then
 +
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
 +
end
  
control.maximum = maximum;
+
if utilities.is_set (TransQuote) then
+
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
+
TransQuote = TransQuote:sub(2, -2); -- strip them off
 +
end
 +
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
 +
end
  
if is_set (Editors) then
+
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
if editor_etal then
+
local quote_prefix = '';
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
+
if utilities.is_set (QuotePage) then
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
+
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
 
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
+
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
else
 
Editors = last_first_list; -- either an author name list or an empty string
 
 
end
 
end
 +
                       
 +
Quote = quote_prefix .. ": " .. Quote;
 +
else
 +
Quote = sepc .. " " .. Quote;
 +
end
  
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then  
+
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
EditorCount = 2; -- spoof to display (eds.) annotation
+
end
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
 
end
do -- now do translators
+
if "live" == UrlStatus then
control.maximum = #t; -- number of translators
+
arch_text = cfg.messages['archived'];
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
+
if sepc ~= "." then arch_text = arch_text:lower() end
end
+
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'],
do -- now do contributors
+
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
control.maximum = #c; -- number of contributors
+
if not utilities.is_set (OriginalURL) then
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
+
Archived = Archived .. " " .. utilities.set_message ('err_archive_missing_url');  
end
 
do -- now do authors
 
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
 
 
 
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
 
control.lastauthoramp = nil;
 
control.maximum = #a + 1;
 
 
end
 
end
+
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
last_first_list = list_people(control, a, author_etal, 'author');
+
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
 
+
arch_text = cfg.messages['archived-unfit'];
if is_set (Authors) then
+
if sepc ~= "." then arch_text = arch_text:lower() end
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
+
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
if author_etal then
+
if 'bot: unknown' == UrlStatus then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
+
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
 
end
else
+
else -- UrlStatus is empty, 'dead'
Authors = last_first_list; -- either an author name list or an empty string
+
arch_text = cfg.messages['archived-dead'];
end
+
if sepc ~= "." then arch_text = arch_text:lower() end
end -- end of do
+
Archived = sepc .. " " .. utilities.substitute ( arch_text,
 
+
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
+
end
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
+
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
 
end
 +
elseif utilities.is_set (ArchiveFormat) then
 +
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
 +
else
 +
Archived = ""
 
end
 
end
 
+
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
+
local Lay = '';
-- an error message if the associated url is not set, or an empty string for concatenation
+
local LaySource = A['LaySource'];
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
+
local LayURL = A['LayURL'];
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
+
local LayFormat = A['LayFormat'];
Format = style_format (Format, URL, 'format', 'url');
 
 
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
 
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
+
if utilities.is_set (LayURL) then
 
+
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
-- special case for chapter format so no error message or cat when chapter not supported
+
if utilities.is_set (LaySource) then  
if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or
+
LaySource = " &ndash; ''" .. utilities.safe_for_italics (LaySource) .. "''";
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
+
else
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
+
LaySource = "";
end
 
 
 
if not is_set(URL) then --and
 
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
 
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
 
end
 
 
-- Test if accessdate is given without giving a URL
 
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test?
 
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
 
AccessDate = '';
 
 
end
 
end
 +
if sepc == '.' then
 +
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
 +
else
 +
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
 +
end
 +
elseif utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
 +
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
 
end
 
end
  
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
+
local TranscriptURL = A['TranscriptURL']
DeadURL = DeadURL:lower(); -- used later when assembling archived text
+
local TranscriptFormat = A['TranscriptFormat'];
if is_set( ArchiveURL ) then
+
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
if is_set (URL) then
+
local Transcript = A['Transcript'];
OriginalURL = URL; -- save copy of original source URL
+
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
+
if utilities.is_set (Transcript) then
OriginalFormat = Format; -- and original |format=
+
if utilities.is_set (TranscriptURL) then
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
+
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
URL = ArchiveURL -- swap-in the archive's url
 
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
 
Format = ArchiveFormat or ''; -- swap in archive's format
 
end
 
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
 
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
 
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
 
OriginalFormat = ChapterFormat; -- and original |format=
 
if 'no' ~= DeadURL then
 
ChapterURL = ArchiveURL -- swap-in the archive's url
 
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
 
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
 
end
 
 
end
 
end
 +
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
 +
elseif utilities.is_set (TranscriptURL) then
 +
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
 
end
 
end
  
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia
+
local Publisher;
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
+
if utilities.is_set (PublicationDate) then
local chap_param;
+
PublicationDate = wrap_msg ('published', PublicationDate);
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
 
chap_param = A:ORIGIN ('Chapter')
 
elseif is_set (TransChapter) then
 
chap_param = A:ORIGIN ('TransChapter')
 
elseif is_set (ChapterURL) then
 
chap_param = A:ORIGIN ('ChapterURL')
 
elseif is_set (ScriptChapter) then
 
chap_param = A:ORIGIN ('ScriptChapter')
 
else is_set (ChapterFormat)
 
chap_param = A:ORIGIN ('ChapterFormat')
 
end
 
 
 
if is_set (chap_param) then -- if we found one
 
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
 
Chapter = ''; -- and set them to empty string to be safe with concatenation
 
TransChapter = '';
 
ChapterURL = '';
 
ScriptChapter = '';
 
ChapterFormat = '';
 
end
 
else -- otherwise, format chapter / article title
 
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
 
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
 
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
 
no_quotes = true; -- then render it unquoted
 
end
 
end
 
 
 
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
 
if is_set (Chapter) then
 
if 'map' == config.CitationClass and is_set (TitleType) then
 
Chapter = Chapter .. ' ' .. TitleType;
 
end
 
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
 
elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
 
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
 
end
 
 
end
 
end
 
+
if utilities.is_set (PublisherName) then
-- Format main title.
+
if utilities.is_set (PublicationPlace) then
if is_set(TitleLink) and is_set(Title) then
+
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
+
else
 +
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
 +
end
 +
elseif utilities.is_set (PublicationPlace) then
 +
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
 +
else
 +
Publisher = PublicationDate;
 
end
 
end
 
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
 
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
 
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
 
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
 
Title = wrap_style ('quoted-title', Title);
 
 
 
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
local TransPeriodical = A['TransPeriodical'];
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
+
local TransPeriodical_origin = A:ORIGIN ('TransPeriodical');
elseif 'report' == config.CitationClass then -- no styling for cite report
+
-- Several of the above rely upon detecting this as nil, so do it last.
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
+
if utilities.is_set (Title) or utilities.is_set (TitleNote) then  
else
+
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
Title = wrap_style ('italic-title', Title);
+
else  
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
TransTitle = wrap_style ('trans-italic-title', TransTitle);
 
end
 
 
 
TransError = "";
 
if is_set(TransTitle) then
 
if is_set(Title) then
 
TransTitle = " " .. TransTitle;
 
else
 
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
 
 
end
 
end
 
end
 
end
 
 
Title = Title .. TransTitle;
+
local Language = A['Language'];
+
if utilities.is_set (Language) then
if is_set(Title) then
+
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
if not is_set(TitleLink) and is_set(URL) then
+
else
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
+
Language=''; -- language not specified so make sure this is an empty string;
URL = "";
+
--[[ TODO: need to extract the wrap_msg from language_parameter
Format = "";
+
so that we can solve parentheses bunching problem with Format/Language/TitleType
else
+
]]
Title = Title .. TransError;
 
end
 
 
end
 
end
  
if is_set(Place) then
+
--[[
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
+
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
end
+
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
 
+
]]
if is_set (Conference) then
+
if "speech" == config.CitationClass then -- cite speech only
if is_set (ConferenceURL) then
+
TitleNote = " (Speech)"; -- annotate the citation
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
+
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
 +
if utilities.is_set (Conference) then -- and if |event= is set
 +
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
 +
end
 
end
 
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
 
elseif is_set(ConferenceURL) then
 
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
 
 
end
 
end
  
if not is_set(Position) then
+
-- Piece all bits together at last.  Here, all should be non-nil.
local Minutes = A['Minutes'];
+
-- We build things this way because it is more efficient in LUA
local Time = A['Time'];
+
-- not to keep reassigning to the same string variable over and over.
  
if is_set(Minutes) then
+
local tcommon;
if is_set (Time) then
+
local tcommon2; -- used for book cite when |contributor= is set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
+
end
+
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
+
if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
 +
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
 +
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
 +
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
 +
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
 +
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 
else
 
else
if is_set(Time) then
+
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
local TimeCaption = A['TimeCaption']
 
if not is_set(TimeCaption) then
 
TimeCaption = cfg.messages['event'];
 
if sepc ~= '.' then
 
TimeCaption = TimeCaption:lower();
 
end
 
end
 
Position = " " .. TimeCaption .. " " .. Time;
 
end
 
 
end
 
end
else
 
Position = " " .. Position;
 
At = '';
 
end
 
  
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
+
elseif 'map' == config.CitationClass then -- special cases for cite map
 
+
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
At = is_set(At) and (sepc .. " " .. At) or "";
+
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
Position = is_set(Position) and (sepc .. " " .. Position) or "";
+
elseif utilities.is_set (Periodical) then -- map in a periodical
if config.CitationClass == 'map' then
+
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
local Section = A['Section'];
+
else -- a sheet or stand-alone map
local Sections = A['Sections'];
+
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
local Inset = A['Inset'];
+
end
 
 
if is_set( Inset ) then
+
elseif 'episode' == config.CitationClass then -- special case for cite episode
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
+
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
end
 
  
if is_set( Sections ) then
+
else -- all other CS1 templates
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
+
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
elseif is_set( Section ) then
+
Volume, Others, Edition, Publisher, Agency}, sepc );
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
 
end
 
At = At .. Inset .. Section;
 
end
 
 
 
if is_set (Language) then
 
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc
 
else
 
Language=""; -- language not specified so make sure this is an empty string;
 
 
end
 
end
 
Others = is_set(Others) and (sepc .. " " .. Others) or "";
 
 
 
if is_set (Translators) then
+
if #ID_list > 0 then
Others = sepc .. ' Translated by ' .. Translators .. Others;
+
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
end
 
 
 
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
 
if is_set (Edition) then
 
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
 
add_maint_cat ('extra_text', 'edition');
 
end
 
Edition = " " .. wrap_msg ('edition', Edition);
 
 
else
 
else
Edition = '';
+
ID_list = ID;
 
end
 
end
 
+
Series = is_set(Series) and (sepc .. " " .. Series) or "";
+
local Via = A['Via'];
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
+
Via = utilities.is_set (Via) and  wrap_msg ('via', Via) or '';
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
+
local idcommon;
 
+
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
+
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc );
 
 
------------------------------------ totally unrelated data
 
if is_set(Via) then
 
Via = " " .. wrap_msg ('via', Via);
 
end
 
 
 
--[[
 
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
 
note is displayed. There are no error messages for this condition.
 
 
 
]]
 
if is_set (SubscriptionRequired) then
 
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
 
elseif is_set (RegistrationRequired) then
 
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
 
 
else
 
else
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
+
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
 
end
 
end
 +
 +
local text;
 +
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
  
if is_set(AccessDate) then
+
local OrigDate = A['OrigDate'];
local retrv_text = " " .. cfg.messages['retrieved']
+
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
 
+
if utilities.is_set (Date) then
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
+
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
+
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
+
else -- neither of authors and editors set
-- neither of these work; don't know why; it seems that substitute() isn't being called
+
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
+
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
end
+
else
+
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
if is_set(ID) then ID = sepc .." ".. ID; end
+
end
  if "thesis" == config.CitationClass and is_set(Docket) then
 
ID = sepc .." Docket ".. Docket .. ID;
 
end
 
  if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
 
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
 
end
 
 
 
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
 
 
 
if is_set(URL) then
 
URL = " " .. external_link( URL, nil, URLorigin );
 
end
 
 
 
if is_set(Quote) then
 
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
 
Quote = Quote:sub(2,-2); -- strip them off
 
 
end
 
end
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
+
end
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
+
if utilities.is_set (Authors) then
end
+
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
+
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
local Archived
 
if is_set(ArchiveURL) then
 
if not is_set(ArchiveDate) then
 
ArchiveDate = set_error('archive_missing_date');
 
 
end
 
end
if "no" == DeadURL then
+
if utilities.is_set (Editors) then
local arch_text = cfg.messages['archived'];
+
local in_text = " ";
if sepc ~= "." then arch_text = arch_text:lower() end
+
local post_text = "";
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
+
if utilities.is_set (Chapter) and 0 == #c then
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
+
in_text = in_text .. cfg.messages['in'] .. " "
if not is_set(OriginalURL) then
+
if (sepc ~= '.') then
Archived = Archived .. " " .. set_error('archive_missing_url');  
+
in_text = in_text:lower() -- lowercase for cs2
 +
end
 +
end
 +
if EditorCount <= 1 then
 +
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
 +
else
 +
post_text = " (" .. cfg.messages['editors'] .. ")";
 
end
 
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
+
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
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 (Contributors) then -- book cite and we're citing the intro, preface, etc.
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
+
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
else
+
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Archived = ""
+
Authors = by_text .. Authors; -- author follows title so tweak it here
end
+
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
local Lay = '';
+
end
if is_set(LayURL) then
+
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
+
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
if is_set(LaySource) then  
+
end
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
+
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
 
else
 
else
LaySource = "";
+
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
 
end
 
end
if sepc == '.' then
+
elseif utilities.is_set (Editors) then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
+
if utilities.is_set (Date) then
 +
if EditorCount <= 1 then
 +
Editors = Editors .. ", " .. cfg.messages['editor'];
 +
else
 +
Editors = Editors .. ", " .. cfg.messages['editors'];
 +
end
 
else
 
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
+
if EditorCount <= 1 then
end
+
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
 
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
 
end
 
 
 
if is_set(Transcript) then
 
if is_set(TranscriptURL) then
 
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
 
end
 
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
 
elseif is_set(TranscriptURL) then
 
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
 
end
 
 
 
local Publisher;
 
if is_set(Periodical) and
 
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
 
if is_set(PublisherName) then
 
if is_set(PublicationPlace) then
 
Publisher = PublicationPlace .. ": " .. PublisherName;
 
 
else
 
else
Publisher = PublisherName; 
+
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
 
end
 
end
elseif is_set(PublicationPlace) then
 
Publisher= PublicationPlace;
 
else
 
Publisher = "";
 
end
 
if is_set(PublicationDate) then
 
if is_set(Publisher) then
 
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
 
else
 
Publisher = PublicationDate;
 
end
 
end
 
if is_set(Publisher) then
 
Publisher = " (" .. Publisher .. ")";
 
 
end
 
end
 +
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
 
else
 
else
if is_set(PublicationDate) then
+
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
+
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
end
+
else
if is_set(PublisherName) then
+
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
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
 
end
 
 
-- Several of the above rely upon detecting this as nil, so do it last.
+
if utilities.is_set (PostScript) and PostScript ~= sepc then
if is_set(Periodical) then
+
text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc.
if is_set(Title) or is_set(TitleNote) then
+
text = text:sub(1, -sepc:len() - 1);
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
+
end
else  
+
Periodical = wrap_style ('italic-title', Periodical)
+
text = safe_join( {text, PostScript}, sepc );
end
+
 
 +
-- Now enclose the whole thing in a <cite> element
 +
local options = {};
 +
 +
if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
 +
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref=
 +
else
 +
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2');
 
end
 
end
  
--[[
+
local Ref = A['Ref'];
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
+
if 'harv' == Ref then -- need to check this before setting to default
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
+
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
if "speech" == config.CitationClass then -- cite speech only
+
Ref = 'harv'; -- set as default when not set externally
TitleNote = " (Speech)"; -- annotate the citation
 
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
 
if is_set (Conference) then -- and if |event= is set
 
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
 
end
 
end
 
 
end
 
end
 +
if 'none' ~= cfg.keywords_xlate[Ref:lower()] then
 +
local id = Ref
 +
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
  
-- Piece all bits together at last.  Here, all should be non-nil.
+
if #c > 0 then -- if there is a contributor list
-- We build things this way because it is more efficient in LUA
+
namelist = c; -- select it
-- not to keep reassigning to the same string variable over and over.
+
elseif #a > 0 then -- or an author list
 
+
namelist = a;
local tcommon;
+
elseif #e > 0 then -- or an editor list
local tcommon2; -- used for book cite when |contributor= is set
+
namelist = e;
+
end
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
+
local citeref_id
if is_set(Others) then Others = Others .. sepc .. " " end
+
if #namelist > 0 then -- if there are names in namelist
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
+
citeref_id = make_citeref_id (namelist, year); -- go make the CITEREF anchor
Language, Edition, Publisher, Agency, Volume}, sepc );
+
else
+
citeref_id = ''; -- unset
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
+
end
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
+
if citeref_id == Ref then
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
+
utilities.set_message ('maint_ref_duplicates_default');
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 
else
 
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 
 
end
 
end
 
+
if 'harv' == Ref then
elseif 'map' == config.CitationClass then -- special cases for cite map
+
id = citeref_id
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
 
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 
elseif is_set (Periodical) then -- map in a periodical
 
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 
else -- a sheet or stand-alone map
 
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
 
 
end
 
end
+
options.id = id;
elseif 'episode' == config.CitationClass then -- special case for cite episode
 
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
 
else -- all other CS1 templates
 
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
 
Volume, Others, Edition, Publisher, Agency}, sepc );
 
 
end
 
end
 
 
if #ID_list > 0 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
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
+
z.error_categories = {};
else
+
text = utilities.set_message ('err_empty_citation');
ID_list = ID;
+
z.message_tail = {};
 
end
 
end
 
 
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
+
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
local text;
 
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 
  
if is_set(Date) then
+
if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
+
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
+
else
else -- neither of authors and editors set
+
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
+
end
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
+
 
else
+
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
+
 
 +
if 0 ~= #z.message_tail then
 +
table.insert (render, ' ');
 +
for i,v in ipairs( z.message_tail ) do
 +
if utilities.is_set (v[1]) then
 +
if i == #z.message_tail then
 +
table.insert (render, utilities.error_comment ( v[1], v[2] ));
 +
else
 +
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
 +
end
 
end
 
end
 
end
 
end
end
+
end
if is_set(Authors) then
+
 
if is_set(Coauthors) then
+
if 0 ~= #z.maintenance_cats then
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
+
local maint_msgs = {}; -- here we collect all of the maint messages
Authors = Authors .. ', ' .. Coauthors;
+
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
else
+
local maint = {}; -- here we assemble a maintenence message
Authors = Authors .. '; ' .. Coauthors;
+
table.insert (maint, v); -- maint msg is the category name
end
+
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
 +
table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
 +
end
 +
 +
if not no_tracking_cats then
 +
for _, v in ipairs( z.error_categories ) do -- append error categories
 +
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
 
end
 
end
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
+
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
+
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
 
end
 
end
if is_set(Editors) then
+
for _, v in ipairs( z.properties_cats ) do -- append properties categories
local in_text = " ";
+
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
local post_text = "";
 
if is_set(Chapter) and 0 == #c then
 
in_text = in_text .. cfg.messages['in'] .. " "
 
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
 
else
 
if EditorCount <= 1 then
 
post_text = ", " .. cfg.messages['editor'];
 
else
 
post_text = ", " .. cfg.messages['editors'];
 
end
 
end
 
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
 
 
end
 
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
+
end
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
+
 
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
+
return table.concat (render);
Authors = by_text .. Authors; -- author follows title so tweak it here
+
end
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
+
 
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
+
 
end
+
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
+
 
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
+
Looks for a parameter's name in one of several whitelists.
end
+
 
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
+
Parameters in the whitelist can have three values:
else
+
true - active, supported parameters
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
+
false - deprecated, supported parameters
 +
nil - unsupported parameters
 +
 +
]]
 +
 
 +
local function validate (name, cite_class, empty)
 +
local name = tostring (name);
 +
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
 +
local state;
 +
local function state_test (state, name) -- local function to do testing of state values
 +
if true == state then return true; end -- valid actively supported parameter
 +
if false == state then
 +
if empty then return nil; end -- 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
 
end
elseif is_set(Editors) then
+
return nil;
if is_set(Date) then
+
end
if EditorCount <= 1 then
+
 
Editors = Editors .. ", " .. cfg.messages['editor'];
+
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
else
+
return nil;
Editors = Editors .. ", " .. cfg.messages['editors'];
+
end
end
+
 
else
+
if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
if EditorCount <= 1 then
+
state = whitelist.limited_basic_arguments[name];
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
+
if true == state_test (state, name) then return true; end
else
+
 
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
+
state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
end
+
if true == state_test (state, name) then return true; end
end
+
 
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
+
-- limited enumerated parameters list
else
+
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
if config.CitationClass=="journal" and is_set(Periodical) then
+
state = whitelist.limited_numbered_arguments[enum_name];
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
+
if true == state_test (state, name) then return true; end
else
 
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
 
end
 
end
 
 
if is_set(PostScript) and PostScript ~= sepc then
 
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
 
text = text:sub(1,-sepc:len()-1);
 
end
 
 
text = safe_join( {text, PostScript}, sepc );
 
  
-- Now enclose the whole thing in a <cite/> element
+
return false; -- not supported because not found or name is set to nil
local options = {};
+
end -- end limited parameter-set templates
 
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
 
options.class = config.CitationClass;
 
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
 
else
 
options.class = "citation";
 
end
 
 
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
 
local id = Ref
 
if ('harv' == Ref ) then
 
local namelist = {}; -- holds selected contributor, author, editor name list
 
-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
 
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
 
  
if #c > 0 then -- if there is a contributor list
+
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
namelist = c; -- select it
+
state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
elseif #a > 0 then -- or an author list
+
if true == state_test (state, name) then return true; end
namelist = a;
+
end -- if here, fall into general validation
elseif #e > 0 then -- or an editor list
+
namelist = e;
+
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
end
+
if true == state_test (state, name) then return true; end
id = anchor_id (namelist, year); -- go make the CITEREF anchor
 
end
 
options.id = id;
 
end
 
 
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
 
z.error_categories = {};
 
text = set_error('empty_citation');
 
z.message_tail = {};
 
end
 
 
if is_set(options.id) then
 
text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
 
else
 
text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
 
end
 
  
local empty_span = '<span style="display:none;">&nbsp;</span>';
+
-- all enumerated parameters allowed
+
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
-- Note: Using display: none on the COinS span breaks some clients.
+
state = whitelist.numbered_arguments[enum_name];
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
+
if true == state_test (state, name) then return true; end
text = text .. OCinS;
 
 
if #z.message_tail ~= 0 then
 
text = text .. " ";
 
for i,v in ipairs( z.message_tail ) do
 
if is_set(v[1]) then
 
if i == #z.message_tail then
 
text = text .. error_comment( v[1], v[2] );
 
else
 
text = text .. error_comment( v[1] .. "; ", v[2] );
 
end
 
end
 
end
 
end
 
  
if #z.maintenance_cats ~= 0 then
+
return false; -- not supported because not found or name is set to nil
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
 
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
 
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
 
end
 
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
 
end
 
 
no_tracking_cats = no_tracking_cats:lower();
 
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
 
for _, v in ipairs( z.error_categories ) do
 
text = text .. '[[Category:' .. v ..']]';
 
end
 
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
 
text = text .. '[[Category:' .. v ..']]';
 
end
 
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
 
text = text .. '[[Category:' .. v ..']]';
 
end
 
end
 
 
return text
 
 
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.
+
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
  
Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the
+
check <value> for inter-language interwiki-link markup<prefix> must be a MediaWiki-recognized language
replacement characterThat replacement character is not detected by this test though it is visible to readers
+
code.  when these values have the form (without leading colon):
of the rendered citationThis function will detect the replacement character when it is part of the wikisource.
+
[[<prefix>:link|label]] return label as plain-text
 +
[[<prefix>:link]] return <prefix>:link as plain-text
  
Output of this function is an error message that identifies the character or the Unicode group that the character
+
return value as is else
belongs to along with its position in the parameter value.
 
  
]]
+
]=]
--[[
 
local function has_invisible_chars (param, v)
 
local position = '';
 
local i=1;
 
  
while cfg.invisible_chars[i] do
+
local function inter_wiki_check (parameter, value)
local char=cfg.invisible_chars[i][1] -- the character or group name
+
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
+
local _;
v = mw.text.unstripNoWiki( v ); -- remove nowiki stripmarkers
+
position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
+
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
if position then
+
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
table.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('parameter', param), position}, true ) } ); -- add error message
+
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
return; -- and done with this parameter
 
end
 
i=i+1; -- bump our index
 
 
end
 
end
 +
return value;
 
end
 
end
 +
 +
 +
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
 +
 +
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
 +
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
 +
parameter that is missing its pipe.  There are two tests made:
 +
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
 +
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
 +
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc.  To prevent false positives XML/HTML
 +
tags are removed before the search.
 +
 +
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 +
 
]]
 
]]
  
--[[--------------------------< Z . C I T A T I O N >----------------------------------------------------------
+
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
 +
 
 +
 
 +
--[[--------------------------< 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 4,027: 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
  
local args = {};
+
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
local suggestions = {};
+
 
 +
local args = {}; -- table where we store all of the template's arguments
 +
local suggestions = {}; -- table where we store suggestions if we need to loadData them
 
local error_text, error_state;
 
local 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 4,076: 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 4,094: 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
 
if 'string' == type (k) then -- don't evaluate positional parameters
 
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v);
+
has_invisible_chars (k, v); -- look for invisible characters
 
end
 
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};

Latest revision as of 23:54, 1 December 2021

Lua error in package.lua at line 80: module 'strict' not found. Lua error in package.lua at line 80: module 'strict' not found. Lua error in package.lua at line 80: module 'strict' not found.

This module and associated sub-modules support the Citation Style 1 and Citation Style 2 citation templates. In general, it is not intended to be called directly, but is called by one of the core CS1 and CS2 templates.

These files comprise the module support for CS1|2 citation templates:

CS2 modules
live sandbox description
Gold padlock Module:Citation/CS1 Module:Citation/CS1/sandbox [edit] Rendering and support functions
Module:Citation/CS1/Configuration Module:Citation/CS1/Configuration/sandbox [edit] Translation tables; error and identifier handlers
Module:Citation/CS1/Whitelist Module:Citation/CS1/Whitelist/sandbox [edit] 2 parameters
Module:Citation/CS1/Date validation Module:Citation/CS1/Date validation/sandbox [edit] Date format validation functions
Module:Citation/CS1/Identifiers Module:Citation/CS1/Identifiers/sandbox [edit] Functions that support the named identifiers (ISBN, DOI, PMID, etc.)
Module:Citation/CS1/Utilities Module:Citation/CS1/Utilities/sandbox [edit] Common functions and tables
Module:Citation/CS1/COinS Module:Citation/CS1/COinS/sandbox [edit] 2 template's metadata
Module:Citation/CS1/styles.css Module:Citation/CS1/sandbox/styles.css [edit] CSS styles applied to the CS1|2 templates
Silver padlock Module:Citation/CS1/Suggestions Module:Citation/CS1/Suggestions/sandbox [edit] List that maps common erroneous parameter names to valid parameter names

Other documentation:

testcases



require('Module:No globals');

--[[--------------------------< F O R W A R D   D E C L A R A T I O N S >--------------------------------------
each of these counts against the Lua upvalue limit
]]

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

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

local identifiers;																-- functions and tables in Module:Citation/CS1/Identifiers
local metadata;																	-- functions in Module:Citation/CS1/COinS
local cfg = {};																	-- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {};															-- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist

--[[------------------< P A G E   S C O P E   V A R I A B L E S >---------------
declare variables here that have page-wide scope that are not brought in from
other modules; that are created here and used here
]]
local added_deprecated_cat;														-- Boolean flag so that the category is added only once
local added_discouraged_cat;													-- Boolean flag so that the category is added only once
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 >------------------------------------------------------------

Locates and returns the first set value in a table of values where the order established in the table,
left-to-right (or top-to-bottom), is the order in which the values are evaluated.  Returns nil if none are set.

This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs.  With the pairs
version the order of evaluation could not be guaranteed.  With the ipairs version, a nil value would terminate
the for-loop before it reached the actual end of the list.

]]

local function first_set (list, count)
	local i = 1;
	while i <= count do															-- loop through all items in list
		if utilities.is_set( list[i] ) then
			return list[i];														-- return the first set list member
		end
		i = i + 1;																-- point to next
	end
end


--[[--------------------------< 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 add_vanc_error (source, position)
	if added_vanc_errs then return end
		
	added_vanc_errs = true;														-- note that we've added this category
	table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source, position}, true ) } );
end


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

does this thing that purports to be a URI scheme seem to be a valid scheme?  The scheme is checked to see if it
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
	Scheme names consist of a sequence of characters beginning with a
   letter and followed by any combination of letters, digits, plus
   ("+"), period ("."), or hyphen ("-").

returns true if it does, else false

]]

local function is_scheme (scheme)
	return scheme and scheme:match ('^%a[%a%d%+%.%-]*:');						-- true if scheme is set and matches the pattern
end


--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------

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

Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
BNF defined here: https://tools.ietf.org/html/rfc4234
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
	see also [[Single-letter second-level domain]]
list of TLDs: https://www.iana.org/domains/root/db

RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
the first and last characters the name may use letters, digits, and the hyphen.

Also allowed are IPv4 addresses. IPv6 not supported

domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
is two or more alpha characters.  Any preceding '//' (from splitting a URL with a scheme) will be stripped
here.  Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal.

There are several tests:
	the first character of the whole domain name including subdomains must be a letter or a digit
	internationalized domain name (ASCII characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the TLD) see https://tools.ietf.org/html/rfc3490
	single-letter/digit second-level domains in the .org, .cash, and .today TLDs
	q, x, and z SL domains in the .com TLD
	i and q SL domains in the .net TLD
	single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
	two-character SL domains in gTLDs (where the gTLD is two or more letters)
	three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
	IPv4 dot-decimal address format; TLD not allowed

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

]=]

local function is_domain_name (domain)
	if not domain then
		return false;															-- if not set, abandon
	end
	
	domain = domain:gsub ('^//', '');											-- strip '//' from domain name if present; done here so we only have to do it once
	
	if not domain:match ('^[%w]') then											-- first character must be letter or digit
		return false;
	end

	if domain:match ('^%a+:') then												-- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
		return false;
	end

	local patterns = {															-- patterns that look like URLs
		'%f[%w][%w][%w%-]+[%w]%.%a%a+$',										-- three or more character hostname.hostname or hostname.tld
		'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$',									-- internationalized domain name with ACE prefix
		'%f[%a][qxz]%.com$',													-- assigned one character .com hostname (x.com times out 2015-12-10)
		'%f[%a][iq]%.net$',														-- assigned one character .net hostname (q.net registered but not active 2015-12-10)
		'%f[%w][%w]%.%a%a$',													-- one character hostname and ccTLD (2 chars)
		'%f[%w][%w][%w]%.%a%a+$',												-- two character hostname and TLD
		'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?',								-- IPv4 address
		}

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

	for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do					-- look for single letter second level domain names for these top level domains
		if domain:match ('%f[%w][%w]%.' .. d) then
			return true
		end
	end
	return false;																-- no matches, we don't know what this thing is
end


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

returns true if the scheme and domain parts of a URL appear to be a valid URL; else false.

This function is the last step in the validation process.  This function is separate because there are cases that
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.

]]

local function is_url (scheme, domain)
	if utilities.is_set (scheme) then											-- if scheme is set check it and domain
		return is_scheme (scheme) and is_domain_name (domain);
	else
		return is_domain_name (domain);											-- scheme not set when URL is protocol-relative
	end
end


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

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

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

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

When not protocol-relative, get scheme, authority indicator, and domain.  If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.

Any URL that does not have news: scheme must have authority indicator (//).  TODO: are there other common schemes
like news: that don't use authority indicator?

Strip off any port and path;

]]

local function split_url (url_str)
	local scheme, authority, domain;
	
	url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1');						-- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')

	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


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

checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs

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

returns false when the value contains any of these characters.

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

]]

local function link_param_ok (value)
	local scheme, domain;
	if value:find ('[<>%[%]|{}]') then											-- if any prohibited characters
		return false;
	end

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


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

Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.

|<title>= may be wiki-linked but not when |<param>-link= has a value.  This function emits an error message when
that condition exists

check <link> for inter-language interwiki-link prefix.  prefix must be a MediaWiki-recognized language
code and must begin with a colon.

]]

local function link_title_ok (link, lorig, title, torig)
local orig;
	if utilities.is_set (link) then 											-- don't bother if <param>-link doesn't have a value
		if not link_param_ok (link) then										-- check |<param>-link= markup
			orig = lorig;														-- identify the failing link parameter
		elseif title:find ('%[%[') then											-- check |title= for wikilink markup
			orig = torig;														-- identify the failing |title= parameter
		elseif link:match ('^%a+:') then										-- if the link is what looks like an interwiki
			local prefix = link:match ('^(%a+):'):lower();						-- get the interwiki prefix

			if cfg.inter_wiki_map[prefix] then									-- if prefix is in the map, must have preceding colon
				orig = lorig;													-- flag as error
			end
		end
	end

	if utilities.is_set (orig) then
		link = '';																-- unset
		table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)});	-- URL or wikilink in |title= with |title-link=;
	end
	
	return link;																-- link if ok, empty string else
end


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

Determines whether a URL string appears to be valid.

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

Because it is different from a standard URL, and because this module used external_link() to make external links
that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4

]]

local function check_url( url_str )
	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;

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


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

Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
non-space characters following the opening bracket appear to be a URL.  The test will also find external wikilinks
that use protocol-relative URLs. Also finds bare URLs.

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

]=]

local function is_parameter_ext_wikilink (value)
local scheme, domain;

	if value:match ('%f[%[]%[%a%S*:%S+.*%]') then								-- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
		scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
	elseif value:match ('%f[%[]%[//%S+.*%]') then								-- if protocol-relative ext. wikilink: [//yyyyy.zzz]
		scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
	elseif value:match ('%a%S*:%S+') then										-- if bare URL with scheme; may have leading or trailing plain text
		scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
	elseif value:match ('//%S+') then											-- if protocol-relative bare URL: //yyyyy.zzz; may have leading or trailing plain text
		scheme, domain = split_url (value:match ('(//%S+)'));					-- what is left should be the domain
	else
		return false;															-- didn't find anything that is obviously a URL
	end

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


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

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

]]

local function check_for_url (parameter_list)
local error_message = '';
	for k, v in pairs (parameter_list) do										-- for each parameter in the list
		if is_parameter_ext_wikilink (v) then									-- look at the value; if there is a URL add an error message
			if utilities.is_set(error_message) then								-- once we've added the first portion of the error message ...
				error_message = error_message .. ", ";							-- ... add a comma space separator
			end
			error_message = error_message .. "&#124;" .. k .. "=";				-- add the failed parameter
		end
	end
	if utilities.is_set (error_message) then									-- done looping, if there is an error message, display it
		table.insert( z.message_tail, { utilities.set_message ( 'err_param_has_ext_link', {error_message}, true ) } );
	end
end


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

Escape sequences for content that will be used for URL descriptions

]]

local function safe_for_url( str )
	if str:match( "%[%[.-%]%]" ) ~= nil then 
		table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } );
	end
	
	return str:gsub( '[%[%]\n]', {	
		['['] = '&#91;',
		[']'] = '&#93;',
		['\n'] = ' ' } );
end


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

Format an external link with error checking

]]

local function external_link( URL, label, source, access)
	local error_str = "";
	local domain;
	local path;
	local base_url;

	if not utilities.is_set ( label ) then
		label = URL;
		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

	base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" });		-- assemble a wiki-markup URL

	if utilities.is_set (access) then											-- access level (subscription, registration, limited)
		base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url});	-- add the appropriate icon
	end
	
	return table.concat ({base_url, error_str});
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
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
parameters in the citation.

added_deprecated_cat is a Boolean declared in page scope variables above

]]

local function deprecated_parameter(name)
	if not added_deprecated_cat then
		added_deprecated_cat = true;											-- note that we've added this category
		table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } );	-- add error message
	end
end


--[[--------------------------< 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 discouraged_parameter(name)
	if not added_discouraged_cat then
		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


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

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

This function will positive kern either single or double quotes:
	"'Unkerned title with leading and trailing single quote marks'"
	" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wiki-markup) are not kerned.

Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning.  Unicode quote marks are not replaced in simple [[D]] wikilinks.

Call this function for chapter titles, for website titles, etc.; not for book titles.

]=]

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

	wl_type, label, link = utilities.is_wikilink (str);							-- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
	
	if 1 == wl_type then														-- [[D]] simple wikilink with or without quote marks
		if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then		-- leading and trailing quote marks
			str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
		elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]')	then			-- leading quote marks
			str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
		elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then				-- trailing quote marks
			str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
		end

	else																		-- plain text or [[L|D]]; text in label variable
		label = mw.ustring.gsub (label, '[“”]', '\"');							-- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
		label = mw.ustring.gsub (label, '[‘’]', '\'');							-- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)

		cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)");				-- match leading double or single quote but not doubled single quotes (italic markup)
		if utilities.is_set (cap) then
			label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
		end
	
		cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$")				-- match trailing double or single quote but not doubled single quotes (italic markup)
		if utilities.is_set (cap) then
			label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
		end
		
		if 2 == wl_type then
			str = utilities.make_wikilink (link, label);						-- reassemble the wikilink
		else
			str = label;
		end
	end
	return str;
end


--[[--------------------------< 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 ISO 639-1 language code and a colon:
	|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
	|script-title=ja : *** ***
	|script-title=ja: *** ***
	|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***

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

Supports |script-title=, |script-chapter=, |script-<periodical>=

]]

local function format_script_value (script_value, script_param)
	local lang='';																-- initialize to empty string
	local name;
	if script_value:match('^%l%l%l?%s*:') then									-- if first 3 or 4 non-space characters are script language prefix
		lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*');						-- get the language prefix or nil if there is no script
		if not utilities.is_set (lang) then
			table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing title part'}, true ) } );		-- prefix without 'title'; add error message
			return '';															-- script_value was just the prefix so return empty string
		end
																				-- if we get this far we have prefix and script
		name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code );	-- get language name so that we can use it to categorize
		if utilities.is_set (name) then											-- is prefix a proper ISO 639-1 language code?
			script_value = script_value:gsub ('^%l+%s*:%s*', '');				-- strip prefix from script
																				-- is prefix one of these language codes?
			if utilities.in_array (lang, cfg.script_lang_codes) then
				utilities.add_prop_cat ('script_with_name', {name, lang})
			else
				table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'unknown language code'}, true ) } );	-- unknown script-language; add error message
			end
			lang = ' lang="' .. lang .. '" ';									-- convert prefix into a lang attribute
		else
			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
		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
	script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value});	-- isolate in case script is RTL

	return script_value;
end


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

Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been 
wrapped in <bdi> tags.
]]

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


--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------

Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
from citation_config.messages - the reason this function is similar to but separate from wrap_style().

]]

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


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

Makes a Wikisource URL from Wikisource interwiki-link.  Returns the URL and appropriate
label; nil else.

str is the value assigned to |chapter= (or aliases) or |title= or |title-link=

]]

local function wikisource_url_make (str)
	local wl_type, D, L;
	local ws_url, ws_label;
	local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});

	wl_type, D, L = utilities.is_wikilink (str);								-- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)

	if 0 == wl_type then														-- not a wikilink; might be from |title-link=
		str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)');		-- article title from interwiki link with long-form or short-form namespace
		if utilities.is_set (str) then
			ws_url = table.concat ({											-- build a Wikisource URL
				wikisource_prefix,												-- prefix
				str,															-- article title
				});
			ws_label = str;														-- label for the URL
		end
	elseif 1 == wl_type then													-- simple wikilink: [[Wikisource:ws article]]
		str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)');		-- article title from interwiki link with long-form or short-form namespace
		if utilities.is_set (str) then
			ws_url = table.concat ({											-- build a Wikisource URL
				wikisource_prefix,												-- prefix
				str,															-- article title
				});
			ws_label = str;														-- label for the URL
		end
	elseif 2 == wl_type then													-- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
		str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)');		-- article title from interwiki link with long-form or short-form namespace
		if utilities.is_set (str) then
			ws_label = D;														-- get ws article name from display portion of interwiki link
			ws_url = table.concat ({											-- build a Wikisource URL
				wikisource_prefix,												-- prefix
				str,															-- article title without namespace from link portion of wikilink
				});
		end
	end

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

	return ws_url, ws_label, L or D;											-- return proper URL or nil and a label or nil
end


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

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

]]

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

	if not utilities.is_set (periodical) then
		periodical = '';														-- to be safe for concatenation
	else
		periodical = utilities.wrap_style ('italic-title', periodical);			-- style 
	end

	periodical = script_concatenate (periodical, script_periodical, script_periodical_source);	-- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped

	if utilities.is_set (trans_periodical) then
		trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
		if utilities.is_set (periodical) then
			periodical = periodical .. ' ' .. trans_periodical;
		else																	-- here when trans-periodical without periodical or script-periodical
			periodical = trans_periodical;
			periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'});
		end
	end

	return periodical .. periodical_error;
end


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

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

]]

local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access)
	local chapter_error = '';

	local ws_url, ws_label, L = wikisource_url_make (chapter);					-- make a wikisource URL and label from a wikisource interwiki link
	if ws_url then
		ws_label = ws_label:gsub ('_', ' ');									-- replace underscore separators with space characters
		chapter = ws_label;
	end

	if not utilities.is_set (chapter) then
		chapter = '';															-- to be safe for concatenation
	else
		if false == no_quotes then
			chapter = kern_quotes (chapter);									-- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
			chapter = utilities.wrap_style ('quoted-title', chapter);
		end
	end

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

	if utilities.is_set (chapter_url) then
		chapter = external_link (chapter_url, chapter, chapter_url_source, access);	-- adds bare_url_missing_title error if appropriate
	elseif ws_url then
		chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter');	-- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
		chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});				
	end

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

	return chapter .. chapter_error;
end


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

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

This function will detect the visible replacement character when it is part of the Wikisource.

Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers
(gallery, math, pre, ref) and identifies them with a slightly different error message.
See also coins_cleanup().

Output of this function is an error message that identifies the character or the
Unicode group, or the stripmarker that was detected along with its position (or,
for multi-byte characters, the position of its first byte) in the parameter value.

]]

local function has_invisible_chars (param, v)
	local position = '';														-- position of invisible char or starting position of stripmarker
	local 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 = {};
	
	return setmetatable({
		ORIGIN = function ( self, k )
			local dummy = self[k];												-- force the variable to be loaded.
			return origin[k];
		end
	},
	{
		__index = function ( tbl, k )
			if origin[k] ~= nil then
				return nil;
			end
			
			local args, list, v = args, cfg.aliases[k];
			
			if type( list ) == 'table' then
				v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
				if origin[k] == nil then
					origin[k] = '';												-- Empty string, not nil
				end
			elseif list ~= nil then
				v, origin[k] = args[list], list;
			else
				-- maybe let through instead of raising an error?
				-- v, origin[k] = args[k], k;
				error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
			end
			
			-- Empty strings, not nil;
			if v == nil then
				v = '';
				origin[k] = '';
			end
			
			tbl = rawset( tbl, k, v );
			return v;
		end,
	});
end


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

When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY

DOES NOT yet support MMMM YYYY or any of the date ranges.

]]

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

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


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

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

]]

local function set_titletype (cite_class, title_type)
	if utilities.is_set (title_type) then
		if 'none' == cfg.keywords_xlate[title_type] then
			title_type = '';													-- if |type=none then type parameter not displayed
		end
		return title_type;														-- if |type= has been set to any other value use that value
	end

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


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

Converts a hyphen to a dash under certain conditions.  The hyphen must separate
like items; unlike items are returned unmodified.  These forms are modified:
	letter - letter (A - B)
	digit - digit (4-5)
	digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
	letterdigit - letterdigit (A1-A5) (an optional separator between letter and
		digit is supported – a.1-a.5 or a-1-a-5)
	digitletter - digitletter (5a - 5d) (an optional separator between letter and
		digit is supported – 5.a-5.d or 5-a-5-d)

any other forms are returned unmodified.

str may be a comma- or semicolon-separated list

]]

local function hyphen_to_dash( str )
	if not utilities.is_set (str) then
		return str;
	end

	local accept; -- Boolean

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

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

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

	local temp_str = '';														-- concatenate the output table into a comma separated string
	temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out
	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
		return temp_str;														-- else, return assembled temp_str
	end
end


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

Joins a sequence of strings together while checking for duplicate separation characters.

]]

local function safe_join( tbl, duplicate_char )
	local f = {};																-- create a function table appropriate to type of 'duplicate character'
		if 1 == #duplicate_char then											-- for single byte ASCII characters use the string library functions
			f.gsub = string.gsub
			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

	local str = '';																-- the output string
	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
																				-- typically duplicate_char is sepc
			if f.sub(comp, 1, 1) == duplicate_char then							-- is first character same as duplicate_char? why test first character?
																				--   Because individual string segments often (always?) begin with terminal punct for the
																				--   preceding segment: 'First element' .. 'sepc next element' .. etc.?
				trim = false;
				end_chr = f.sub(str, -1, -1);									-- get the last character of the output string
				-- str = str .. "<HERE(enchr=" .. end_chr .. ")"				-- debug stuff?
				if end_chr == duplicate_char then								-- if same as separator
					str = f.sub(str, 1, -2);									-- remove it
				elseif end_chr == "'" then										-- if it might be wiki-markup
					if f.sub(str, -3, -1) == duplicate_char .. "''" then		-- if last three chars of str are sepc'' 
						str = f.sub(str, 1, -4) .. "''";						-- remove them and add back ''
					elseif  f.sub(str, -5, -1) == duplicate_char .. "]]''" then	-- if last five chars of str are sepc]]'' 
						trim = true;											-- why? why do this and next differently from previous?
					elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then	-- if last four chars of str are sepc]'' 
						trim = true;											-- same question
					end
				elseif end_chr == "]" then										-- if it might be wiki-markup
					if f.sub(str, -3, -1) == duplicate_char .. "]]" then		-- if last three chars of str are sepc]] wikilink 
						trim = true;
					elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then	-- if last three chars of str are sepc"] quoted external link 
						trim = true;
					elseif  f.sub(str, -2, -1) == duplicate_char .. "]" then	-- if last two chars of str are sepc] external link
						trim = true;
					elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then	-- normal case when |url=something & |title=Title.
						trim = true;
					end
				elseif end_chr == " " then										-- if last char of output string is a space
					if f.sub(str, -2, -1) == duplicate_char .. " " then			-- if last two chars of str are <sepc><space>
						str = f.sub(str, 1, -3);								-- remove them both
					end
				end

				if trim then
					if value ~= comp then 										-- value does not equal comp when value contains HTML markup
						local dup2 = duplicate_char;
						if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end	-- if duplicate_char not a letter then escape it
						
						value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 )		-- remove duplicate_char if it follows HTML markup
					else
						value = f.sub(value, 2, -1 );							-- remove duplicate_char when it is first character
					end
				end
			end
			str = str .. value; 												-- add it to the output string
		end
	end
	return str;
end


--[[--------------------------< I S _ S U F F I X >-----------------------------

returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
Puncutation not allowed.

]]

local function is_suffix (suffix)
	if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
		return true;
	end
	return false;
end


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

For Vancouver style, author/editor names are supposed to be rendered in Latin
(read ASCII) characters.  When a name uses characters that contain diacritical
marks, those characters are to be converted to the corresponding Latin
character. When a name is written using a non-Latin alphabet or logogram, that
name is to be transliterated into Latin characters. The module doesn't do this
so editors may/must.

This test allows |first= and |last= names to contain any of the letters defined
in the four Unicode Latin character sets
	[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
	[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
	[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
	[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F

|lastn= also allowed to contain hyphens, spaces, and apostrophes.
	(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods

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

	\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
	\195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
	\195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
	\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)

]]

local function is_good_vanc_name (last, first, suffix, position)
	if not suffix then
		if first:find ('[,%s]') then											-- when there is a space or comma, might be first name/initials + generational suffix
			first = first:match ('(.-)[,%s]+');									-- get name/initials
			suffix = first:match ('[,%s]+(.+)$');								-- get generational suffix
		end
	end
	if utilities.is_set (suffix) then
		if not is_suffix (suffix) then
			add_vanc_error (cfg.err_msg_supl.suffix, position);
			return false;														-- not a name with an appropriate suffix
		end
	end
	if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
		nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
			add_vanc_error (cfg.err_msg_supl['non-Latin char'], 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
as Jr, 2nd, 3rd, etc.  See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This code only accepts and understands generational suffix in the Vancouver format
because Roman numerals look like, and can be mistaken for, initials.

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

]]

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

	if not name then															-- if not initials and a suffix
		name = mw.ustring.match(first, "^(%u+)$");								-- is it just initials?
	end

	if name then																-- if first is initials with or without suffix
		if 3 > mw.ustring.len (name) then										-- if one or two initials
			if suffix then														-- if there is a suffix
				if is_suffix (suffix) then										-- is it legitimate?
					return first;												-- one or two initials and a valid suffix so nothing to do
				else
					add_vanc_error (cfg.err_msg_supl.suffix, position);			-- one or two initials with invalid suffix so error message
					return first;												-- and return first unmolested
				end
			else
				return first;													-- one or two initials without suffix; nothing to do
			end
		end
	end																			-- if here then name has 3 or more uppercase letters so treat them as a word

	local initials, names = {}, {};												-- tables to hold name parts and initials
	local i = 1;																-- counter for number of initials

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

	while names[i] do															-- loop through the table
		if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then				-- if not the first name, and looks like a suffix (may have trailing dot)
			names[i] = names[i]:gsub ('%.', '');								-- remove terminal dot if present
			if is_suffix (names[i]) then										-- if a legitimate suffix
				table.insert (initials, ' ' .. names[i]);						-- add a separator space, insert at end of initials table
				break;															-- and done because suffix must fall at the end of a name
			end																	-- no error message if not a suffix; possibly because of Romanization
		end
		if 3 > i then
			table.insert (initials, mw.ustring.sub(names[i], 1, 1));			-- insert the initial at end of initials table
		end
		i = i + 1;																-- bump the counter
	end
			
	return table.concat(initials)												-- Vancouver format does not include spaces.
end


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

Formats a list of people (authors, contributors, editors, interviewers, translators) 

names in the list will be linked when
	|<name>-link= has a value
	|<name>-mask- does NOT have a value; masked names are presumed to have been
		rendered previously so should have been linked there

when |<name>-mask=0, the associated name is not rendered

]]

local function list_people (control, people, etal)
	local sep;
	local namesep;
	local format = control.format;
	local maximum = control.maximum;
	local name_list = {};

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

			if utilities.is_set (maximum) and i > maximum then
				etal = true;
				break;
			end
			
			if mask then
				local n = tonumber (mask);										-- convert to a number if it can be converted; nil else
				if n then
					one = 0 ~= n and string.rep("&mdash;", n) or nil;			-- make a string of (n > 0) mdashes, nil else, to replace name
					person.link = nil;											-- don't create link to name if name is replaces with mdash string or has been set nil
				else
					one = mask;													-- replace name with mask text (must include name-list separator)
					sep_one = " ";												-- modify name-list separator
				end
			else
				one = person.last;												-- get surname
				local first = person.first										-- get given name
				if utilities.is_set (first) then
					if ("vanc" == format) then									-- if Vancouver format
						one = one:gsub ('%.', '');								-- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
						if not person.corporate and is_good_vanc_name (one, first, 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
	
	return result, count;														-- return name-list string and count of number of names (count used for editor names only)
end

--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------

Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise
returns an empty string.

namelist is one of the contributor-, author-, or editor-name lists chosen in that
order.  year is Year or anchor_year.

]]

local function make_citeref_id (namelist, year)
	local names={};							-- a table for the one to four names and year
	for i,v in ipairs (namelist) do			-- loop through the list and take up to the first four last names
		names[i] = v.last
		if i == 4 then break end			-- if four then done
	end
	table.insert (names, year);				-- add the year at the end
	local id = table.concat(names);			-- concatenate names and year for CITEREF id
	if utilities.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


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

Evaluates the content of name parameters (author, editor, etc.) for variations on
the theme of et al.  If found, the et al. is removed, a flag is set to true and
the function returns the modified name and the flag.

This function never sets the flag to false but returns 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 name_has_etal (name, etal, nocat, param)

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

	return name, etal;
end


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

Add maint cat when name parameter value does not contain letters.  Does not catch
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
current version of this test but |first=(1888) is caught.

returns nothing

]]

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


--[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------

Evaluates the content of author and editor parameters for extraneous editor annotations:
ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and
are redundant in editor parameters.  If found, the function adds the editor markup
maintenance category.

returns nothing

]]

local function name_has_ed_markup (name, list_name)
	local patterns = cfg.editor_markup_patterns;								-- get patterns from configuration

	if utilities.is_set (name) then
		for _, pattern in ipairs (patterns) do									-- spin through patterns table and
			if name:match (pattern) then
				utilities.set_message ('maint_extra_text_names', cfg.special_case_translation [list_name]);	-- add a maint cat for this template
				break;
			end
		end
	end
end


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

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.

returns nothing

]]

local function name_has_mult_names (name, list_name)
	local _, commas, semicolons, nbsps;
	if utilities.is_set (name) then
		_, commas = name:gsub (',', '');										-- count the number of commas
		_, semicolons = name:gsub (';', '');									-- count the number of semicolons
		-- nbsps probably should be its own separate count rather than merged in
		-- 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


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

This function calls various name checking functions used to validate the content
of the various name-holding parameters.

]]

local function name_checks (last, first, list_name)
	local accept_name;

	if utilities.is_set (last) then
		last, accept_name = utilities.has_accept_as_written (last);				-- remove accept-this-as-written markup when it wraps all of <last>
		
		if not accept_name then													-- <last> not wrapped in accept-as-written markup
			name_has_mult_names (last, list_name);								-- check for multiple names in the parameter (last only)
			name_has_ed_markup (last, list_name);								-- check for extraneous 'editor' annotation
			name_is_numeric (last, list_name);									-- check for names that are composed of digits and punctuation
		end
	end

	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>

		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

	return last, first;															-- done
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. 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=.

When an author or editor parameter contains some form of 'et al.', the 'et al.'
is stripped from the parameter and a flag (etal) returned that will cause list_people()
to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps
'et al.' out of the template's metadata.  When this occurs, an error is emitted.

]]

local function extract_names(args, list_name)
	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 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


--[[---------------------< 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

Names that are included in the list will be found if that name is provided in the
|language= parameter.  For example, if |language=Chavacano de Zamboanga, that name
will be found with the associated code 'cbk-zam'.  When names are found and the
associated code is not two or three characters, this function returns only the
WikiMedia language name.

Some language names have multiple entries under different codes:
	Aromanian has code rup and code roa-rup
When this occurs, this function returns the language name and the 2- or 3-character code

Adapted from code taken from Module:Check ISO 639-1.

]]

local function get_iso639_code (lang, this_wiki_code)
	if cfg.lang_name_remap[lang:lower()] then									-- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
		return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2];	-- for this language 'name', return a possibly new name and appropriate code
	end

	local ietf_code;															-- because some languages have both IETF-like codes and ISO 639-like codes
	local ietf_name;
	
	local langlc = mw.ustring.lower (lang);										-- lower-case version for comparisons

	for code, name in pairs (cfg.languages) do									-- scan the list to see if we can find our language
		if langlc == mw.ustring.lower (name) then
			if 2 == #code or 3 == #code then									-- two- or three-character codes only; IETF extensions not supported
				return name, code;												-- so return the name and the code
			end
			ietf_code = code;													-- remember that we found an IETF-like code and save its name
			ietf_name = name;													-- but keep looking for a 2- or 3-char code
		end
	end
																				-- didn't find name with 2- or 3-char code; if IETF-like code found return
	return ietf_code and ietf_name or lang;										-- associated name; return original language text else
end


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

Gets language name from a provided two- or three-character ISO 639 code.  If a code
is recognized by MediaWiki, use the returned name; if not, then use the value that
was provided with the language parameter.

When |language= contains a recognized language (either code or name), the page is
assigned to the category for that code: Category:Norwegian-language sources (no).
For valid three-character code languages, the page is assigned to the single category
for '639-2' codes: Category:CS1 ISO 639-2 language sources.

Languages that are the same as the local wiki are not categorized.  MediaWiki does
not recognize three-character equivalents of two-character codes: code 'ar' is
recognized but code 'ara' is not.

This function supports multiple languages in the form |language=nb, French, th
where the language names or codes are separated from each other by commas with
optional space characters.

]]

local function language_parameter (lang)
	local code;																	-- the two- or three-character language 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=

	local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code);	-- get this wiki's language name

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

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

		if name then															-- there was a remapped code so
			if not lang:match ('^%a%a%a?%-x%-%a+$') then						-- if not a private IETF tag
				lang = lang:gsub ('^(%a%a%a?)%-.*', '%1');						-- strip IETF tags from code
			end
		else
			lang = lang:gsub ('^(%a%a%a?)%-.*', '%1');							-- strip any IETF-like tags from code
			if 2 == lang:len() or 3 == lang:len() then							-- if two-or three-character code
				name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code);	-- get language name if |language= is a proper code
			end
		end

		if utilities.is_set (name) then											-- if |language= specified a valid code
			code = lang:lower();												-- save it
		else
			name, code = get_iso639_code (lang, cfg.this_wiki_code);			-- attempt to get code from name (assign name here so that we are sure of proper capitalization)
		end
	
		if utilities.is_set (code) then											-- only 2- or 3-character codes
			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);

	if this_wiki_name == name then
		return '';																-- if one language and that language is this wiki's return an empty string (no annotation)
	end
	return (" " .. wrap_msg ('language', name));								-- otherwise wrap with '(in ...)'
	--[[ TODO: should only return blank or name rather than full list
	so we can clean up the bunched parenthetical elements Language, Type, Format
	]]
end

--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
Gets the default CS style configuration for the given mode.
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)
	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;
	if 'cs2' == mode then
		sep, postscript = set_cs_style (postscript, 'cs2');
	elseif 'cs1' == mode then
		sep, postscript = set_cs_style (postscript, 'cs1');
	elseif 'citation' == cite_class	then
		sep, postscript = set_cs_style (postscript, 'cs2');
	else
		sep, postscript = set_cs_style (postscript, 'cs1');
	end

	if cfg.keywords_xlate[postscript:lower()] == 'none' then
		-- emit a maintenance message if user postscript is the default cs2 postscript
		-- we catch the opposite case for cs1 in set_cs_style
		if 'cs2' == mode or 'citation' == cite_class then
			utilities.set_message ('maint_postscript');
		end
		postscript = '';
	end
	
	return sep, postscript
end

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

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.

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

]=]

local function is_pdf (url)
	return url:match ('%.pdf$') or url:match ('%.PDF$') or
		url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
		url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end


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

Applies CSS style to |format=, |chapter-format=, etc.  Also emits an error message
if the format parameter does not have a matching URL parameter.  If the format parameter
is not set and the URL contains a file extension that is recognized as a PDF document
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.

]]

local function style_format (format, url, fmt_param, url_param)
	if utilities.is_set (format) then
		format = utilities.wrap_style ('format', format);						-- add leading space, parentheses, resize
		if not utilities.is_set (url) then
			format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} );	-- add an error message
		end
	elseif is_pdf (url) then													-- format is not set so if URL is a PDF file then
		format = utilities.wrap_style ('format', 'PDF');						-- set format to PDF
	else
		format = '';															-- empty string for concatenation
	end
	return format;
end


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

Returns a number that defines the number of names displayed for author and editor
name lists and a Boolean flag to indicate when et al. should be appended to the name list.

When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
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-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.'

In all other cases, returns nil and the previous state of the 'etal' flag.

inputs:
	max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
	count: #a or #e
	list_name: 'authors' or 'editors'
	etal: author_etal or editor_etal

]]

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


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

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 extra_text_in_page_check (val, name)
	if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
		for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) 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 ('err_extra_text_pages', {name}, true)}); -- add error message
				return;															-- and done
			end
		end
	end		
end


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

Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.

For |volume=:
	'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
	content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
	are allowed.

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

sets error message on failure; returns nothing

]]

local function extra_text_in_vol_iss_check (val, name, selector)
	if not utilities.is_set (val) then
		return;
	end
	
	local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;

	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


--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------

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

	|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))

]=]

local function get_v_name_table (vparam, output_table, output_link_table)
	local name_table = mw.text.split(vparam, "%s*,%s*");						-- names are separated by commas
	local wl_type, label, link;													-- wl_type not used here; just a placeholder
	
	local i = 1;
	
	while name_table[i] do
		if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then						-- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
			local name = name_table[i];
			i = i + 1;															-- bump indexer to next segment
			while name_table[i] do
				name = name .. ', ' .. name_table[i];							-- concatenate with previous segments
				if name_table[i]:match ('^.*%)%)$') then						-- if this table member has the closing doubled parentheses
					break;														-- and done reassembling so
				end
				i = i + 1;														-- bump indexer
			end
			table.insert (output_table, name);									-- and add corporate name to the output table
			table.insert (output_link_table, '');								-- no wikilink
		else
			wl_type, label, link = utilities.is_wikilink (name_table[i]);		-- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
			table.insert (output_table, label);									-- add this name
			if 1 == wl_type then
				table.insert (output_link_table, label);						-- simple wikilink [[D]]
			else
				table.insert (output_link_table, link);							-- no wikilink or [[L|D]]; add this link if there is one, else empty string
			end
		end
		i = i + 1;
	end	
	return output_table;
end


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

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

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

Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.

This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.

]]

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

	vparam, etal = name_has_etal (vparam, etal, true);							-- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
	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>

		if accept_name then
			last = v_name;
			corporate = true;													-- flag used in list_people()
		elseif string.find(v_name, "%s") then
			if v_name:find('[;%.]') then										-- look for commonly occurring punctuation characters; 
				add_vanc_error (cfg.err_msg_supl.punctuation, i);
			end
			local lastfirstTable = {}
			lastfirstTable = mw.text.split(v_name, "%s+")
			first = table.remove(lastfirstTable);								-- removes and returns value of last element in table which should be initials or generational suffix

			if not mw.ustring.match (first, '^%u+$') then						-- mw.ustring here so that later we will catch non-Latin characters
				suffix = first;													-- not initials so assume that whatever we got is a generational suffix
				first = table.remove(lastfirstTable);							-- get what should be the initials from the table
			end
			last = table.concat(lastfirstTable, ' ')							-- returns a string that is the concatenation of all other names that are not initials and generational suffix
			if not utilities.is_set (last) then
				first = '';														-- unset
				last = v_name;													-- last empty because something wrong with first
				add_vanc_error (cfg.err_msg_supl.name, i);
			end
			if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
				add_vanc_error (cfg.err_msg_supl['missing comma'], i);			-- matches last II last; the case when a comma is missing
			end
			if mw.ustring.match (v_name, ' %u %u$') 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

		link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
		mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
		names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate};		-- add this assembled name to our names list
	end
	return names, etal;															-- all done, return our list of names
end


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

Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |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;
|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.

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

In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.

]]

local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
	local lastfirst = false;
	if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or		-- do this twice in case we have a |first1= without a |last1=; this ...
		utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or		-- ... also catches the case where |first= is used with |vauthors=
		utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
		utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
			lastfirst = true;
	end

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

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


--[[--------------------------< 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 is_valid_parameter_value (value, name, possible, ret_val)
	if not utilities.is_set (value) then
		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


--[[--------------------------< 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 terminate_name_list (name_list, sepc)
	if (string.sub (name_list, -3, -1) == sepc .. '. ') then					-- if already properly terminated
		return name_list;														-- just return the name list
	elseif (string.sub (name_list, -1, -1) == sepc) or (string.sub (name_list, -3, -1) == sepc .. ']]') then	-- if last name in list ends with sepc char
		return name_list .. " ";												-- don't add another
	else
		return name_list .. sepc .. ' ';										-- otherwise terminate the name list
	end
end


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

returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
or formatted issue, or an empty string if neither are set.

]]
	
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
	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

	if 'podcast' == cite_class and utilities.is_set (issue) then
		return wrap_msg ('issue', {sepc, issue}, lower);
	end

	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


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

adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
The return order is:
	page, pages, sheet, sheets

Singular has priority over plural when both are provided.

]]

local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
	if 'map' == cite_class then													-- only cite map supports sheet(s) as in-source locators
		if utilities.is_set (sheet) then
			if 'journal' == origin then
				return '', '', wrap_msg ('j-sheet', sheet, lower), '';
			else
				return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
			end
		elseif 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

	local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
	
	if utilities.is_set (page) then
		if is_journal then
			return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
		elseif not nopp then
			return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
		else
			return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
		end
	elseif utilities.is_set (pages) then
		if is_journal then
			return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
		elseif tonumber(pages) ~= nil and not nopp then							-- if pages is only digits, assume a single page number
			return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
		elseif not nopp then
			return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
		else
			return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
		end
	end
	
	return '', '', '', '';														-- return empty strings
end


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

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 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?)

	if utilities.is_set (page) then
		if utilities.is_set (pages) or utilities.is_set (at) then
			pages = '';															-- unset the others
			at = '';
		end
		extra_text_in_page_check (page, page_orig);								-- emit error message when |page= value begins with what looks like p., pp., etc.

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

		ws_url, ws_label, L = wikisource_url_make (pages);						-- make ws URL from |pages= interwiki link; link portion L becomes tooltip label
		if ws_url then
			pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages');	-- space char after label to move icon away from in-source text; TODO: a better way to do this?
			pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
			coins_pages = ws_label;
		end
	elseif utilities.is_set (at) then
		ws_url, ws_label, L = wikisource_url_make (at);							-- make ws URL from |at= interwiki link; link portion L becomes tooltip label
		if ws_url then
			at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at');	-- space char after label to move icon away from in-source text; TODO: a better way to do this?
			at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
			coins_pages = ws_label;
		end
	end
	
	return page, pages, at, coins_pages;
end

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

add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value

]]

local function is_unique_archive_url (archive, url, c_url, source, date)
	if utilities.is_set (archive) then
		if archive == url or archive == c_url then
			table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)});	-- add error message
			return '', '';														-- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
		end
	end

	return archive, date;
end


--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------

Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the 
save snapshot URL or to calendar pages.  When the archive URL is 'https://web.archive.org/save/' (or http://...)
archive.org saves a snapshot of the target page in the URL.  That is something that Wikipedia should not allow
unwitting readers to do.

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

This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
|archive-date= and an error message when:
	|archive-url= holds an archive.org save command URL
	|archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
		correct place
otherwise returns |archive-url= and |archive-date=

There are two mostly compatible archive.org URLs:
	//web.archive.org/<timestamp>...		-- the old form
	//web.archive.org/web/<timestamp>...	-- the new form

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

This function supports a preview mode.  When the article is rendered in preview mode, this function may return a modified
archive URL:
	for save command errors, return undated wildcard (/*/)
	for timestamp errors when the timestamp has a wildcard, return the URL unmodified
	for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)

]=]

local function archive_url_check (url, date)
	local err_msg = '';															-- start with the error message empty
	local path, timestamp, flag;												-- portions of the archive.org URL
	
	if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then		-- also deprecated liveweb Wayback machine URL
		return url, date;														-- not an archive.org archive, return ArchiveURL and ArchiveDate
	end

	if url:match('//web%.archive%.org/save/') then								-- if a save command URL, we don't want to allow saving of the target page 
		err_msg = cfg.err_msg_supl.save;
		url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1);				-- for preview mode: modify ArchiveURL
	elseif url:match('//liveweb%.archive%.org/') then
		err_msg = cfg.err_msg_supl.liveweb;
	else
		path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/');	-- split out some of the URL parts for evaluation
		
		if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then		-- path and flag optional, must have 14-digit timestamp here
			err_msg = cfg.err_msg_supl.timestamp;
			if '*' ~= flag then
				url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1)	-- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
			end
		elseif utilities.is_set (path) and 'web/' ~= path then					-- older archive URLs do not have the extra 'web/' path element
			err_msg = cfg.err_msg_supl.path;
		elseif utilities.is_set (flag) and not utilities.is_set (path) then		-- flag not allowed with the old form URL (without the 'web/' path element)
			err_msg = cfg.err_msg_supl.flag;
		elseif utilities.is_set (flag) and not flag:match ('%a%a_') then		-- flag if present must be two alpha characters and underscore (requires 'web/' path element)
			err_msg = cfg.err_msg_supl.flag;
		else
			return url, date;													-- return ArchiveURL and ArchiveDate
		end
	end
																				-- if here, something not right so
	table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } );	-- add error message and
	if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
		return '', '';															-- return empty strings for ArchiveURL and ArchiveDate
	else
		return url, date;														-- preview mode so return ArchiveURL and ArchiveDate
	end
end


--[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------

check |place=, |publication-place=, |location= to see if these params include digits.  This function added because
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)

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

]]

local function place_check (param_val)
	if not utilities.is_set (param_val) then									-- parameter empty or omitted
		return param_val;														-- return that empty state
	end
	
	if mw.ustring.find (param_val, '%d') then									-- not empty, are there digits in the parameter value
		utilities.set_message ('maint_location');								-- yep, add maint cat
	end
	
	return param_val;															-- and done
end


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

compares |title= value against list of known generic title patterns.  Returns true when pattern matches; nil else

the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
index [1].  index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
or a pattern search (false).  The intent of all this complexity is to make these searches as fast as possible so
that we don't run out of processing time on very large articles.

]]

local function is_generic_title (title)
	title = mw.ustring.lower(title);											-- switch title to lower case
	for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do 	-- spin through the list of known generic title fragments
		if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
			return true;														-- found English generic title so done
		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
			if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then	-- mw.ustring() because might not be Latin script
				return true;													-- found local generic title so done
			end
		end
	end
end


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

compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else

]]

local function is_archived_copy (title)
	title = mw.ustring.lower(title);											-- switch title to lower case
	if title:find (cfg.special_case_translation.archived_copy.en) then			-- if title is 'Archived copy'
		return true;
	elseif cfg.special_case_translation.archived_copy['local'] then
		if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then	-- mw.ustring() because might not be Latin script
			return true;
		end
	end
end


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

This is the main function doing the majority of the citation formatting.

]]

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 

	-- Pick out the relevant fields from the arguments.  Different citation templates
	-- define different field names for the same underlying things.	

	local author_etal;
	local a	= {};																-- authors list from |lastn= / |firstn= pairs or |vauthors=
	local Authors;
	local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
	local Collaboration = A['Collaboration'];

	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=

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

	local Title = A['Title'];
	local TitleLink = A['TitleLink'];

	local auto_select = ''; -- default is auto
	local accept_link;
	TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true);	-- test for accept-this-as-written markup
	if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
		auto_select = TitleLink;												-- remember selection for later
		TitleLink = '';															-- treat as if |title-link= would have been empty
	end

	TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title');	-- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set

	local Section = '';															-- {{cite map}} only; preset to empty string for concatenation if not used
	if 'map' == config.CitationClass and 'section' == Chapter_origin then
		Section = A['Chapter'];													-- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
		Chapter = '';															-- unset for now; will be reset later from |map= if present
	end

	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

	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

		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'];

	-- web and news not tested for now because of 
	-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
	if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then	-- 'periodical' templates require periodical parameter
	--	local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'};	-- for error message
		local p = {['journal'] = 'journal', ['magazine'] = 'magazine'};			-- for error message
		if p[config.CitationClass]  then
			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');	

	local Issue;
	if 'citation' == config.CitationClass then
		if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or	-- {{citation}} renders issue for these 'periodicals'
			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'
				Issue = hyphen_to_dash (A['Issue']);
		end
	elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then	-- conference & map books do not support issue; {{citation}} listed here because included in settings table
		if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
			Issue = hyphen_to_dash (A['Issue']);
		end
	end
	extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');	

	local Page;
	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 Edition = A['Edition'];
	local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
	local Place = place_check (A['Place'], A:ORIGIN('Place'));
	
	local PublisherName = A['PublisherName'];
	local PublisherName_origin = A:ORIGIN('PublisherName');
	if utilities.is_set (PublisherName) then
		local i = 0;
		PublisherName, i = utilities.strip_apostrophe_markup (PublisherName);	-- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
		if i then																-- non-zero when markup was stripped so emit an error message
			table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
		end
	end

	local Newsgroup = A['Newsgroup'];											-- TODO: strip apostrophe markup?
	local Newsgroup_origin = A:ORIGIN('Newsgroup');	

	if 'newsgroup' == config.CitationClass then
		if utilities.is_set (PublisherName) then								-- general use parameter |publisher= not allowed in cite newsgroup
			local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
			if utilities.is_set (error_text) then
				table.insert( z.message_tail, {error_text, error_state} );
			end				
		end

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

	local URL = A['URL']
	local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
	
	if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
		UrlAccess = nil;
		table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
	end
	
	local ChapterURL = A['ChapterURL'];
	local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
	if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
		ChapterUrlAccess = nil;
		table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
	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 this_page = mw.title.getCurrentTitle();								-- also used for COinS and for language
	local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);

	-- 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
		if utilities.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)
	utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters');	-- this is a dummy call simply to get the error message and category

	local coins_pages;
	
	Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);

	local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);

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

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

		|trans-title= maps to |trans-chapter= when |title= is re-mapped
		|url= maps to |chapter-url= when |title= is remapped
	
	All other combinations of |encyclopedia=, |title=, and |article= are not modified
	
	]]

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

	if utilities.is_set (Encyclopedia) then										-- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
		if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
			table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
			Encyclopedia = nil;													-- unset because not supported by this template
		end
	end

	if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
		if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then	-- when both set emit an error
			table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
		end

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

		if utilities.is_set (Periodical) then									-- Periodical is set when |encyclopedia= is set
			if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
				if not utilities.is_set (Chapter) then
					Chapter = Title;											-- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
					ScriptChapter = ScriptTitle;
					ScriptChapter_origin = A:ORIGIN('ScriptTitle')
					TransChapter = TransTitle;
					ChapterURL = URL;
					ChapterURL_origin = URL_origin;

					ChapterUrlAccess = UrlAccess;

					if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
						Chapter = utilities.make_wikilink (TitleLink, Chapter);
					end
					Title = Periodical;
					ChapterFormat = Format;
					Periodical = '';											-- redundant so unset
					TransTitle = '';
					URL = '';
					Format = '';
					TitleLink = '';
					ScriptTitle = '';
				end
			elseif utilities.is_set (Chapter) then								-- |title= not set
				Title = Periodical;												-- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
				Periodical = '';												-- redundant so unset
			end
		end
	end

	-- special case for cite techreport.
	local ID = A['ID'];
	if (config.CitationClass == "techreport") then								-- special case for cite techreport
		if utilities.is_set (A['Number']) then									-- cite techreport uses 'number', which other citations alias to 'issue'
			if not utilities.is_set (ID) then									-- can we use ID for the "number"?
				ID = A['Number'];												-- yes, use it
			else																-- ID has a value so emit error message
				table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
			end
		end	
	end

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

		ChapterUrlAccess = MapUrlAccess;
		ChapterFormat = A['MapFormat'];

		Cartography = A['Cartography'];
		if utilities.is_set ( Cartography ) then
			Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
		end		
		Scale = A['Scale'];
		if utilities.is_set ( Scale ) then
			Scale = sepc .. " " .. Scale;
		end
	end

	-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
	local Series = A['Series'];
	if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
		local SeriesLink = A['SeriesLink'];

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

		local Network = A['Network'];
		local Station = A['Station'];
		local s, n = {}, {};
																				-- do common parameters first
		if utilities.is_set (Network) then table.insert(n, Network); end
		if utilities.is_set (Station) then table.insert(n, Station); end
		ID = table.concat(n, sepc .. ' ');
		
		if 'episode' == config.CitationClass then								-- handle the oddities that are strictly {{cite episode}}
			local Season = A['Season'];
			local SeriesNumber = A['SeriesNumber'];

			if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then	-- these are mutually exclusive so if both are set
				table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } );		-- add error message
				SeriesNumber = '';												-- unset; prefer |season= over |seriesno=
			end
																				-- assemble a table of parts concatenated later into Series
			if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
			if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
			if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
			Issue = '';															-- unset because this is not a unique parameter
	
			Chapter = Title;													-- promote title parameters to chapter
			ScriptChapter = ScriptTitle;
			ScriptChapter_origin = A:ORIGIN('ScriptTitle');
			ChapterLink = TitleLink;											-- alias |episode-link=
			TransChapter = TransTitle;
			ChapterURL = URL;
			ChapterUrlAccess = UrlAccess;
			ChapterURL_origin = URL_origin;
			
			Title = Series;														-- promote series to title
			TitleLink = SeriesLink;
			Series = table.concat(s, sepc .. ' ');								-- this is concatenation of season, seriesno, episode number

			if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then	-- link but not URL
				Chapter = utilities.make_wikilink (ChapterLink, Chapter);
			elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then	-- if both are set, URL links episode;
				Series = utilities.make_wikilink (ChapterLink, Series);
			end
			URL = '';															-- unset
			TransTitle = '';
			ScriptTitle = '';
			
		else																	-- now oddities that are cite serial
			Issue = '';															-- unset because this parameter no longer supported by the citation/core version of cite serial
			Chapter = A['Episode'];												-- TODO: make |episode= available to cite episode someday?
			if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
				Series = utilities.make_wikilink (SeriesLink, Series);
			end
			Series = utilities.wrap_style ('italic-title', Series);				-- series is italicized
		end	
	end
	-- end of {{cite episode}} stuff

	-- handle type parameter for those CS1 citations that have default values
	local TitleType = A['TitleType'];
	local Degree = A['Degree'];
	if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
		TitleType = set_titletype (config.CitationClass, TitleType);
		if utilities.is_set (Degree) and "Thesis" == TitleType then				-- special case for cite thesis
			TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
		end
	end

	if utilities.is_set (TitleType) then										-- if type parameter is specified
		TitleType = utilities.substitute ( cfg.messages['type'], TitleType);	-- display it in parentheses
	-- TODO: Hack on TitleType to fix bunched parentheses problem
	end

	-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
	local Date = A['Date'];
 	local Date_origin;															-- to hold the name of parameter promoted to Date; required for date error messaging
	local PublicationDate = A['PublicationDate'];
	local Year = A['Year'];

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

	if PublicationDate == Date then PublicationDate = ''; end					-- if PublicationDate is same as Date, don't display in rendered citation

	--[[
	Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
	we get the date used in the metadata.
	
	Date validation supporting code is in Module:Citation/CS1/Date_validation
	]]

	local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
	if not utilities.is_set (DF) then
		DF = cfg.global_df;														-- local |df= if present overrides global df set by {{use xxx date}} template
	end

	local ArchiveURL;
	local ArchiveDate;
	local ArchiveFormat = A['ArchiveFormat'];

	ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
	ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
	
	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);

-- start temporary Julian / Gregorian calendar uncertainty categorization
		if COinS_date.inter_cal_cat then
			utilities.add_prop_cat ('jul_greg_uncertainty');
		end
-- end temporary Julian / Gregorian calendar uncertainty categorization

		if utilities.is_set (Year) and utilities.is_set (Date) then				-- both |date= and |year= not normally needed; 
			validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
		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

			if utilities.is_set (DF) then										-- if we need to reformat dates
				modified = validation.reformat_dates (date_parameters_list, DF);	-- reformat to DF format, use long month names if appropriate
			end

			if true == validation.date_hyphen_to_dash (date_parameters_list) then	-- convert hyphens to dashes where appropriate
				modified = true;
				utilities.set_message ('maint_date_format');					-- hyphens were converted so add maint category
			end
			
	-- for those wikis that can and want to have English date names translated to the local language,
	-- uncomment the next three lines.  Not supported by en.wiki (for obvious reasons)
	-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
	--		if validation.date_name_xlate (date_parameters_list, false) then
	--			modified = true;
	--		end

			if modified then													-- if the date_parameters_list values were modified
				AccessDate = date_parameters_list['access-date'].val;			-- overwrite date holding parameters with modified values
				ArchiveDate = date_parameters_list['archive-date'].val;
				Date = date_parameters_list['date'].val;
				DoiBroken = date_parameters_list['doi-broken-date'].val;
				LayDate = date_parameters_list['lay-date'].val;
				PublicationDate = date_parameters_list['publication-date'].val;
			end
		else
			table.insert (z.message_tail, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)});	-- add this error message
		end
	end	-- end of do

	local ID_list = {};															-- 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_title = Title;													-- et tu
	if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
		if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then		-- if all are used then
			coins_chapter = Title;												-- remap
			coins_title = Periodical;
		end
	end
	local coins_author = a;														-- default for coins rft.au 
	if 0 < #c then																-- but if contributor list
		coins_author = c;														-- use that instead
	end
	
	local QuotePage = A['QuotePage'];
	local QuotePages = hyphen_to_dash (A['QuotePages']);

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

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

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

	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.
	-- We also add leading spaces and surrounding markup and punctuation to the
	-- various parts of the citation, but only when they are non-nil.
	do
		local last_first_list;
		local control = { 
			format = NameListStyle,												-- empty string or 'vanc'
			maximum = nil,														-- as if display-authors or display-editors not set
			mode = Mode
		};

		do																		-- do editor name list first because the now unsupported coauthors used to modify control table
			control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
			Editors, EditorCount = list_people (control, e, editor_etal);

			if 1 == EditorCount and (true == editor_etal or 1 < #e) then		-- only one editor displayed but includes etal then 
				EditorCount = 2;												-- spoof to display (eds.) annotation
			end
		end
		do																		-- now do 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
		do																		-- now do translators
			control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators'));
			Translators = list_people (control, t, translator_etal);
		end
		do																		-- now do contributors
			control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
			Contributors = list_people (control, c, contributor_etal);
		end
		do																		-- now do authors
			control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));

			last_first_list = list_people (control, a, author_etal);

			if utilities.is_set (Authors) then
				Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors');	-- find and remove variations on et al.
				if author_etal then
					Authors = Authors .. ' ' .. cfg.messages['et al'];			-- add et al. to authors parameter
				end
			else
				Authors = last_first_list;										-- either an author name list or an empty string
			end
		end																		-- end of do
	
		if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
			Authors = Authors .. ' (' .. Collaboration .. ')';					-- add collaboration after et al.
		end

	end

	local ConferenceFormat = A['ConferenceFormat'];
	local ConferenceURL = A['ConferenceURL'];
	ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
	Format = style_format (Format, URL, 'format', 'url');

	-- special case for chapter format so no error message or cat when chapter not supported
	if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
		('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
			ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
	end

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

	local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
	local OriginalURL
	local OriginalURL_origin
	local OriginalFormat
	local OriginalAccess;
	UrlStatus = UrlStatus:lower();												-- used later when assembling archived text
	if utilities.is_set ( ArchiveURL ) then
		if utilities.is_set (ChapterURL) then 									-- if chapter-url= is set apply archive url to it
			OriginalURL = ChapterURL;											-- save copy of source chapter's url for archive text
			OriginalURL_origin = ChapterURL_origin;								-- name of |chapter-url= parameter for error messages
			OriginalFormat = ChapterFormat;										-- and original |chapter-format=

			if 'live' ~= UrlStatus then
				ChapterURL = ArchiveURL											-- swap-in the archive's URL
				ChapterURL_origin = A:ORIGIN('ArchiveURL')						-- name of |archive-url= parameter for error messages
				ChapterFormat = ArchiveFormat or '';							-- swap in archive's format
				ChapterUrlAccess = nil;											-- restricted access levels do not make sense for archived URLs
			end
		elseif utilities.is_set (URL) then
			OriginalURL = URL;													-- save copy of original source URL
			OriginalURL_origin = URL_origin;									-- name of URL parameter for error messages
			OriginalFormat = Format; 											-- and original |format=
			OriginalAccess = UrlAccess;

			if 'live' ~= UrlStatus then											-- if URL set then |archive-url= applies to it
				URL = ArchiveURL												-- swap-in the archive's URL
				URL_origin = A:ORIGIN('ArchiveURL')								-- name of archive URL parameter for error messages
				Format = ArchiveFormat or '';									-- swap in archive's format
				UrlAccess = nil;												-- restricted access levels do not make sense for archived URLs
			end
 		end
	end

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

			if utilities.is_set (chap_param) then								-- if we found one
				table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } );	-- add error message
				Chapter = '';													-- and set them to empty string to be safe with concatenation
				TransChapter = '';
				ChapterURL = '';
				ScriptChapter = '';
				ChapterFormat = '';
			end
	else																		-- otherwise, format chapter / article title
		local no_quotes = false;												-- default assume that we will be quoting the chapter parameter value
		if utilities.is_set (Contribution) and 0 < #c then						-- if this is a contribution with contributor(s)
			if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then	-- and a generic contribution title
				no_quotes = true;												-- then render it unquoted
			end
		end

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

	-- Format main title
	local plain_title = false;
	local accept_title;
	Title, accept_title = utilities.has_accept_as_written (Title, true);		-- remove accept-this-as-written markup when it wraps all of <Title>
	if accept_title and ('' == Title) then										-- only support forced empty for now "(())"
		Title = cfg.messages['notitle'];										-- replace by predefined "No title" message
			-- TODO: utilities.set_message ( 'err_redundant_parameters', ...);	-- issue proper error message instead of muting	 
			ScriptTitle = '';													-- just mute for now	 
			TransTitle = '';													-- just mute for now
 		plain_title = true;														-- suppress text decoration for descriptive title
		utilities.set_message ('maint_untitled');								-- add maint cat
	end

	if not accept_title then -- <Title> not wrapped in accept-as-written markup
		if '...' == Title:sub (-3) then											-- if ellipsis is the last three characters of |title=
			Title = Title:gsub ('(%.%.%.)%.+$', '%1');							-- limit the number of dots to three
		elseif not mw.ustring.find (Title, '%.%s*%a%.$') and					-- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
			not mw.ustring.find (Title, '%s+%a%.$') then						-- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
				Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', '');			-- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
		end

		if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
			utilities.set_message ('maint_archived_copy');						-- add maintenance category before we modify the content of Title
		end

		if is_generic_title (Title) then
			table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } );	-- set an error message
		end
	end

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

	local TransError = "";
	if utilities.is_set (TransTitle) then
		if utilities.is_set (Title) then
			TransTitle = " " .. TransTitle;
		else
			TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} );
		end
	end

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

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

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

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

		if utilities.is_set (Minutes) then
			if utilities.is_set (Time) then
				table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
			end
			Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
		else
			if utilities.is_set (Time) then
				local TimeCaption = A['TimeCaption']
				if not utilities.is_set (TimeCaption) then
					TimeCaption = cfg.messages['event'];
					if sepc ~= '.' then
						TimeCaption = TimeCaption:lower();
					end
				end
				Position = " " .. TimeCaption .. " " .. Time;
			end
		end
	else
		Position = " " .. Position;
		At = '';
	end

	Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);

	At = utilities.is_set (At) and (sepc .. " " .. At) or "";
	Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
	if config.CitationClass == 'map' then
		local Sections = A['Sections'];											-- Section (singular) is an alias of Chapter so set earlier
		local Inset = A['Inset'];
		
		if utilities.is_set ( Inset ) then
			Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
		end			

		if utilities.is_set ( Sections ) then
			Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
		elseif utilities.is_set ( Section ) then
			Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
		end
		At = At .. Inset .. Section;		
	end	

	local Others = A['Others'];
	if utilities.is_set (Others) and 0 == #a and 0 == #e then					-- add maint cat when |others= has value and used without |author=, |editor=
		if config.CitationClass == "AV-media-notes"
		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
	Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
	
	if utilities.is_set (Translators) then
		Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
	end
	if utilities.is_set (Interviewers) then
		Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
	end
	
	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
		Edition = " " .. wrap_msg ('edition', Edition);
	else
		Edition = '';
	end

	Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or "";	-- not the same as SeriesNum
	local Agency = A['Agency'];
	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);

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

		AccessDate = nowrap_date (AccessDate);									-- wrap in nowrap span if date in appropriate format
		if (sepc ~= ".") then retrv_text = retrv_text:lower() end				-- if mode is cs2, lower case
		AccessDate = utilities.substitute (retrv_text, AccessDate);				-- add retrieved text

		AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate});	-- allow editors to hide accessdates
	end
	
	if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
	
	local Docket = A['Docket'];
   	if "thesis" == config.CitationClass and utilities.is_set (Docket) then
		ID = sepc .. " Docket " .. Docket .. ID;
	end
   	if "report" == config.CitationClass and utilities.is_set (Docket) then		-- for cite report when |docket= is set
		ID = sepc .. ' ' .. Docket;												-- overwrite ID even if |id= is set
	end

	if utilities.is_set (URL) then
		URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
	end

	local Quote = A['Quote'];
	local TransQuote = A['TransQuote'];
	local ScriptQuote = A['ScriptQuote'];
	if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then

		if utilities.is_set (Quote) then
			if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then			-- if first and last characters of quote are quote marks
				Quote = Quote:sub(2, -2);										-- strip them off
			end
		end

		Quote = utilities.wrap_style ('quoted-text', Quote );					-- wrap in <q>...</q> tags
	
		if utilities.is_set (ScriptQuote) then
			Quote = script_concatenate (Quote, ScriptQuote, 'script-quote');	-- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
		end

		if utilities.is_set (TransQuote) then
			if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
				TransQuote = TransQuote:sub(2, -2); -- strip them off
			end
			Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
		end

		if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then	-- add page prefix
			local quote_prefix = '';
			if utilities.is_set (QuotePage) then
				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
	else
		Archived = ""
	end
	
	local Lay = '';
	local LaySource = A['LaySource'];
	local LayURL = A['LayURL'];
	local LayFormat = A['LayFormat'];
	LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
	if utilities.is_set (LayURL) then
		if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
		if utilities.is_set (LaySource) then 
			LaySource = " &ndash; ''" .. utilities.safe_for_italics (LaySource) .. "''";
		else
			LaySource = "";
		end
		if sepc == '.' then
			Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
		else
			Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
		end			
	elseif utilities.is_set (LayFormat) then									-- Test if |lay-format= is given without giving a |lay-url=
		Lay = sepc .. LayFormat;												-- if set and LayURL not set, then LayFormat has error message
	end

	local TranscriptURL = A['TranscriptURL']
	local TranscriptFormat = A['TranscriptFormat'];
	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
		Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
	elseif utilities.is_set (TranscriptURL) then
		Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
	end

	local Publisher;
	if utilities.is_set (PublicationDate) then
		PublicationDate = wrap_msg ('published', PublicationDate);
	end
	if utilities.is_set (PublisherName) then
		if utilities.is_set (PublicationPlace) then
			Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
		else
			Publisher = sepc .. " " .. PublisherName .. PublicationDate;  
		end			
	elseif utilities.is_set (PublicationPlace) then 
		Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
	else 
		Publisher = PublicationDate;
	end
	
	local TransPeriodical =  A['TransPeriodical'];
	local TransPeriodical_origin =  A:ORIGIN ('TransPeriodical');
	-- Several of the above rely upon detecting this as nil, so do it last.
	if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
		if utilities.is_set (Title) or utilities.is_set (TitleNote) then 
			Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
		else 
			Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
		end
	end
	
	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

	--[[
	Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
	the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
	]]
	if "speech" == config.CitationClass then									-- cite speech only
		TitleNote = " (Speech)";												-- annotate the citation
		if utilities.is_set (Periodical) then									-- if Periodical, perhaps because of an included |website= or |journal= parameter 
			if utilities.is_set (Conference) then								-- and if |event= is set
				Conference = Conference .. sepc .. " ";							-- then add appropriate punctuation to the end of the Conference variable before rendering
			end
		end
	end

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

	local tcommon;
	local tcommon2;																-- used for book cite when |contributor= is set
	
	if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
		if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end		-- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
		tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
	elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then		-- special cases for book cites
		if utilities.is_set (Contributors) then									-- when we are citing foreword, preface, introduction, etc.
			tcommon = safe_join( {Title, TitleNote}, sepc );					-- author and other stuff will come after this and before tcommon2
			tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
		else
			tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
		end

	elseif 'map' == config.CitationClass then									-- special cases for cite map
		if utilities.is_set (Chapter) then										-- map in a book; TitleType is part of Chapter
			tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
		elseif utilities.is_set (Periodical) then								-- map in a periodical
			tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
		else																	-- a sheet or stand-alone map
			tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
		end
		
	elseif 'episode' == config.CitationClass then								-- special case for cite episode
		tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );

	else																		-- all other CS1 templates
		tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, 
			Volume, Others, Edition, Publisher, Agency}, sepc );
	end
	
	if #ID_list > 0 then
		ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
	else
		ID_list = ID;
	end
	
	local 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 pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;

	local OrigDate = A['OrigDate'];
	OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
	if utilities.is_set (Date) then
		if utilities.is_set (Authors) or utilities.is_set (Editors) then		-- date follows authors or editors when authors not set
			Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " ";				-- in parentheses
		else																	-- neither of authors and editors set
			if (string.sub(tcommon, -1, -1) == sepc) then						-- if the last character of tcommon is sepc
				Date = " " .. Date .. OrigDate;									-- Date does not begin with sepc
			else
				Date = sepc .. " " .. Date .. OrigDate;							-- Date begins with sepc
			end
		end
	end	
	if utilities.is_set (Authors) then
		if (not utilities.is_set (Date)) then									-- when date is set it's in parentheses; no Authors termination
			Authors = terminate_name_list (Authors, sepc);						-- when no date, terminate with 0 or 1 sepc and a space
		end
		if utilities.is_set (Editors) then
			local in_text = " ";
			local post_text = "";
			if utilities.is_set (Chapter) and 0 == #c then
				in_text = in_text .. cfg.messages['in'] .. " "
				if (sepc ~= '.') then
					in_text = in_text:lower()									-- lowercase for cs2
				end
			end
			if EditorCount <= 1 then
				post_text = " (" .. cfg.messages['editor'] .. ")";				-- be consistent with no-author, no-date case
			else
				post_text = " (" .. cfg.messages['editors'] .. ")";
			end
			Editors = terminate_name_list (in_text .. Editors .. post_text, sepc);	-- terminate with 0 or 1 sepc and a space
		end
		if utilities.is_set (Contributors) then									-- book cite and we're citing the intro, preface, etc.
			local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
			if (sepc ~= '.') then by_text = by_text:lower() end					-- lowercase for cs2
			Authors = by_text .. Authors;										-- author follows title so tweak it here
			if utilities.is_set (Editors) and utilities.is_set (Date) then		-- when Editors make sure that Authors gets terminated
				Authors = terminate_name_list (Authors, sepc);					-- terminate with 0 or 1 sepc and a space
			end
			if (not utilities.is_set (Date)) then								-- when date is set it's in parentheses; no Contributors termination
				Contributors = terminate_name_list (Contributors, sepc);		-- terminate with 0 or 1 sepc and a space
			end
			text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
		else
			text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
		end
	elseif utilities.is_set (Editors) then
		if utilities.is_set (Date) then
			if EditorCount <= 1 then
				Editors = Editors .. ", " .. cfg.messages['editor'];
			else
				Editors = Editors .. ", " .. cfg.messages['editors'];
			end
		else
			if EditorCount <= 1 then
				Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
			else
				Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
			end
		end
		text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
	else
		if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
			text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
		else
			text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
		end
	end
	
	if utilities.is_set (PostScript) and PostScript ~= sepc then
		text = safe_join( {text, sepc}, sepc ); 								-- Deals with italics, spaces, etc.
		text = text:sub(1, -sepc:len() - 1);
	end	
	
	text = safe_join( {text, PostScript}, sepc );

	-- Now enclose the whole thing in a <cite> element
	local options = {};
	
	if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
		options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1');	-- class=citation required for blue highlight when used with |ref=
	else
		options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2');
	end

	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
	if 'none' ~= cfg.keywords_xlate[Ref:lower()] then
		local id = Ref
		local namelist = {};													-- holds selected contributor, author, editor name list
		local year = first_set ({Year, anchor_year}, 2);						-- Year first for legacy citations and for YMD dates that require disambiguation

		if #c > 0 then															-- if there is a contributor list
			namelist = c;														-- select it
		elseif #a > 0 then														-- or an author list
			namelist = a;
		elseif #e > 0 then														-- or an editor list
			namelist = e;
		end
		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
		options.id = id;
	end
	
	if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then	-- remove <span> tags and other HTML-like markup; then get length of what remains
		z.error_categories = {};
		text = utilities.set_message ('err_empty_citation');
		z.message_tail = {};
	end
	
	local render = {};															-- here we collect the final bits for concatenation into the rendered citation

	if utilities.is_set (options.id) then										-- here we wrap the rendered citation in <cite ...>...</cite> tags
		table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text}));	-- when |ref= is set
	else
		table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text}));	-- all other cases
	end		

	table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput}));	-- append metadata to the citation

	if 0 ~= #z.message_tail then
		table.insert (render, ' ');
		for i,v in ipairs( z.message_tail ) do
			if utilities.is_set (v[1]) then
				if i == #z.message_tail then
					table.insert (render, utilities.error_comment ( v[1], v[2] ));
				else
					table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
				end
			end
		end
	end

	if 0 ~= #z.maintenance_cats then
		local maint_msgs = {};													-- here we collect all of the maint messages
		for _, v in ipairs( z.maintenance_cats ) do								-- append maintenance categories
			local maint = {};													-- here we assemble a maintenence message
			table.insert (maint, v);											-- maint msg is the category name
			table.insert (maint, ' (');											-- open the link text
			table.insert (maint, utilities.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
		table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' ')));	-- wrap the group of maint message with proper presentation and save
	end
	
	if not no_tracking_cats then
		for _, v in ipairs( z.error_categories ) do								-- append error categories
			table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
		end
		for _, v in ipairs( z.maintenance_cats ) do								-- append maintenance categories
			table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
		end
		for _, v in ipairs( z.properties_cats ) do								-- append properties categories
			table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
		end
	end

	return table.concat (render);	
end


--[[--------------------------< V A L I D A T E >--------------------------------------------------------------

Looks for a parameter's name in one of several whitelists.

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

local function validate (name, cite_class, empty)
	local name = tostring (name);
	local enum_name;															-- for enumerated parameters, is name with enumerator replaced with '#'
	local state;
	local function state_test (state, name)										-- local function to do testing of state values
		if true == state then return true; end									-- valid actively supported parameter
		if false == state then
			if empty then return nil; end										-- 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


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

Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
parameter that is missing its pipe.  There are two tests made:
	{{cite ... |title=Title access-date=2016-03-17}}	-- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
	{{cite ... |title=access-date=2016-03-17}}			-- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc.  To prevent false positives XML/HTML
tags are removed before the search.

If a missing pipe is detected, this function adds the missing pipe maintenance category.

]]

local function missing_pipe_check (parameter, value)
	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


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

This is used by templates such as {{cite book}} to create the actual citation text.

]]

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

	utilities.set_selected_modules (cfg);										-- so that functions in Utilities can see the selected cfg tables
	identifiers.set_selected_modules (cfg, utilities);							-- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
	validation.set_selected_modules (cfg, utilities);							-- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
	metadata.set_selected_modules (cfg, utilities);								-- so that functions in COinS can see the selected cfg tables and selected Utilities module

	z = utilities.z;															-- table of error and category tables in Module:Citation/CS1/Utilities

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

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

	local capture;																-- the single supported capture when matching unknown parameters using patterns
	local empty_unknowns = {};													-- sequence table to hold empty unknown params for error message listing
	for k, v in pairs( pframe.args ) do											-- get parameters from the parent (template) frame
		v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1');							-- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
		if v ~= '' then
			if ('string' == type (k)) then
				k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits);		-- for enumerated parameters, translate 'local' digits to Western 0-9
			end
			if not validate( k, config.CitationClass ) then			
				error_text = "";
				if type( k ) ~= 'string' then
					-- exclude empty numbered parameters
					if v:match("%S+") ~= nil then
						error_text, error_state = utilities.set_message ( 'err_text_ignored', {v}, true );
					end
				elseif validate( k:lower(), config.CitationClass ) then 
					error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, k:lower()}, true );	-- suggest the lowercase version of the parameter
				else
					if nil == suggestions.suggestions then						-- if this table is nil then we need to load it
						if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then			-- did the {{#invoke:}} use sandbox version?
							suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' );	-- use the sandbox version
						else
							suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );			-- use the live version
						end
					end
					for pattern, param in pairs (suggestions.patterns) do		-- loop through the patterns to see if we can suggest a proper parameter
						capture = k:match (pattern);							-- the whole match if no capture in pattern else the capture if a match
						if capture then											-- if the pattern matches 
							param = utilities.substitute (param, capture);		-- add the capture to the suggested parameter (typically the enumerator)
							if validate (param, config.CitationClass) then		-- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
								error_text, error_state = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true);	-- set the suggestion error message
							else
								error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true );	-- suggested param not supported by this template
								v = '';											-- unset
							end
						end
					end
					if not utilities.is_set (error_text) then					-- couldn't match with a pattern, is there an explicit suggestion?						
						if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
							error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
						else
							error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true );
							v = '';												-- unset value assigned to unrecognized parameters (this for the limited parameter lists)
						end
					end
				end				  
				if error_text ~= '' then
					table.insert( z.message_tail, {error_text, error_state} );
				end				
			end

			args[k] = v;														-- save this parameter and its value

		elseif not utilities.is_set (v) then									-- for empty parameters
			if not validate (k, config.CitationClass, true) then				-- is this empty parameter a valid parameter
				k = ('' == k) and '(empty string)' or k;						-- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
				table.insert (empty_unknowns, utilities.wrap_style ('parameter', k));	-- format for error message and add to the list
			end
																				-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
	--	elseif args[k] ~= nil or (k == 'postscript') then						-- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
	--		args[k] = v;														-- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
		end																		-- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
	end	

	if 0 ~= #empty_unknowns then												-- create empty unknown error message
		table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
			1 == #empty_unknowns and '' or 's',
			utilities.make_sep_list (#empty_unknowns, empty_unknowns)
			}, true )});
	end

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

	return table.concat ({
		frame:extensionTag ('templatestyles', '', {src=styles}),
		citation0( config, args)
	});
end

--[[--------------------------< E X P O R T E D   F U N C T I O N S >------------------------------------------
]]

return {citation = citation};