Difference between revisions of "Module:Citation/CS1"

From Timelines
Jump to: navigation, search
m (is_parameter_ext_wikilink() fix;)
(Synch from sandbox;)
 
(16 intermediate revisions by the same user not shown)
Line 1: Line 1:
  
−
local z = {
+
local cs1 ={};
−
error_categories = {}; -- for categorizing citations that contain errors
 
−
error_ids = {};
 
−
message_tail = {};
 
−
maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
 
−
properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance
 
−
}
 
  
 
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
 
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
 
]]
 
]]
−
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation
 
  
−
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
+
local dates, year_date_check, reformat_dates, date_hyphen_to_dash -- functions in Module:Citation/CS1/Date_validation
−
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
 
  
−
--[[--------------------------< I S _ S E T >------------------------------------------------------------------
+
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
 +
add_maint_cat, wrap_style, safe_for_italics, remove_wiki_link;
  
−
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
+
local z ={}; -- tables in Module:Citation/CS1/Utilities
−
This function is global because it is called from both this module and from Date validation
+
 
 +
local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
 +
 
 +
local make_coins_title, get_coins_pages, COinS; -- 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 >--------------------------------------
 +
 
 +
delare variables here that have page-wide scope that are not brought in from other modules; thatare created here
 +
and used here
  
 
]]
 
]]
−
function is_set( var )
+
 
−
return not (var == nil or var == '');
+
local added_deprecated_cat; -- boolean flag so that the category is added only once
−
end
+
local added_prop_cats = {}; -- list of property categories that have been added to z.properties_cats
 +
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 >------------------------------------------------------------
  
−
First set variable or nil if none
+
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(...)
+
local function first_set (list, count)
−
local list = {...};
+
local i = 1;
−
for _, var in pairs(list) do
+
while i <= count do -- loop through all items in list
−
if is_set( var ) then
+
if is_set( list[i] ) then
−
return var;
+
return list[i]; -- return the first set list member
 
end
 
end
 +
i = i + 1; -- point to next
 
end
 
end
 
end
 
end
  
−
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
+
--[[--------------------------< 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.
  
−
Whether needle is in haystack
+
added_prop_cats is a table declared in page scope variables above
  
 
]]
 
]]
  
−
local function in_array( needle, haystack )
+
local function add_prop_cat (key, arguments)
−
if needle == nil then
+
if not added_prop_cats [key] then
−
return false;
+
added_prop_cats [key] = true; -- note that we've added this category
 +
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
 
end
 
end
−
for n,v in ipairs( haystack ) do
 
−
if v == needle then
 
−
return n;
 
−
end
 
−
end
 
−
return false;
 
 
end
 
end
  
−
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
+
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
 +
 
 +
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.
  
−
Populates numbered arguments in a message string using an argument table.
+
added_vanc_errs is a boolean declared in page scope variables above
  
 
]]
 
]]
  
−
local function substitute( msg, args )
+
local function add_vanc_error (source)
−
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
+
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', {source}, true ) } );
 +
end
 
end
 
end
  
−
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------
 
  
−
Wraps error messages with css markup according to the state of hidden.
+
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
  
−
]]
+
does this thing that purports to be a uri scheme seem to be a valid scheme?  The scheme is checked to see if it
−
local function error_comment( content, hidden )
+
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
−
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
+
Scheme names consist of a sequence of characters beginning with a
−
end
+
  letter and followed by any combination of letters, digits, plus
 +
  ("+"), period ("."), or hyphen ("-").
  
−
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
+
returns true if it does, else false
  
−
Sets an error condition and returns the appropriate error message.  The actual placement of the error message in the output is
+
]]
−
the responsibility of the calling function.
 
  
−
]]
+
local function is_scheme (scheme)
−
local function set_error( error_id, arguments, raw, prefix, suffix )
+
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
−
local error_state = cfg.error_conditions[ error_id ];
 
−
 
−
prefix = prefix or "";
 
−
suffix = suffix or "";
 
−
 
−
if error_state == nil then
 
−
error( cfg.messages['undefined_error'] );
 
−
elseif is_set( error_state.category ) then
 
−
table.insert( z.error_categories, error_state.category );
 
−
end
 
−
 
−
local message = substitute( error_state.message, arguments );
 
−
 
−
message = message .. " ([[" .. cfg.messages['help page link'] ..
 
−
"#" .. error_state.anchor .. "|" ..
 
−
cfg.messages['help page label'] .. "]])";
 
−
 
−
z.error_ids[ error_id ] = true;
 
−
if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
 
−
and z.error_ids['citation_missing_title'] then
 
−
return '', false;
 
−
end
 
−
 
−
message = table.concat({ prefix, message, suffix });
 
−
 
−
if raw == true then
 
−
return message, error_state.hidden;
 
−
end
 
−
 
−
return error_comment( message, error_state.hidden );
 
 
end
 
end
  
−
--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
 
−
 
−
Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
 
−
To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats.
 
  
−
]]
+
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
  
−
local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats
+
Does this thing that purports to be a domain name seem to be a valid domain name?
−
local function add_maint_cat (key, arguments)
 
−
if not added_maint_cats [key] then
 
−
added_maint_cats [key] = true; -- note that we've added this category
 
−
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
 
−
end
 
−
end
 
  
−
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
+
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
 +
BNF defined here: https://tools.ietf.org/html/rfc4234
 +
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
 +
see also [[Single-letter second-level domain]]
 +
list of tlds: https://www.iana.org/domains/root/db
  
−
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
+
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between
 +
the first and last characters the name may use letters, digits, and the hyphen.
  
−
]]
+
Also allowed are IPv4 addresses. IPv6 not supported
  
−
local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
+
domain is expected to be stripped of any path so that the last character in the last character of the tld. tld
−
local function add_prop_cat (key, arguments)
+
is two or more alpha characters.  Any preceding '//' (from splitting a url with a scheme) will be stripped
−
if not added_prop_cats [key] then
+
here.  Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
−
added_prop_cats [key] = true; -- note that we've added this category
 
−
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
 
−
end
 
−
end
 
  
−
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
+
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 TLD
 +
q, x, and z SL domains in the .com TLD
 +
i and q SL domains in the .net TLD
 +
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
 +
two-character SL domains in gTLDs (where the gTLD is two or more letters)
 +
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
 +
IPv4 dot-decimal address format; TLD not allowed
  
−
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
+
returns true if domain appears to be a proper name and tld or IPv4 address, else false
−
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 
  
−
]]
+
]=]
  
−
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
+
local function is_domain_name (domain)
−
local function add_vanc_error ()
+
if not domain then
−
if not added_vanc_errs then
+
return false; -- if not set, abandon
−
added_vanc_errs = true; -- note that we've added this category
+
end
−
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
+
 +
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
 +
 +
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
 +
return false;
 +
end
 +
-- Do most common case first
 +
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
 +
return true;
 +
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
 +
return true;
 +
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
 +
return true;
 +
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
 +
return true;
 +
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
 +
return true;
 +
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
 +
return true;
 +
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
 +
return true;
 +
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
 +
return true;
 +
else
 +
return false;
 
end
 
end
 
end
 
end
  
−
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
 
  
−
Determines whether a URL string is valid.
+
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
  
−
At present the only check is whether the string appears to be prefixed with a URI scheme.  It is not determined whether
+
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
−
the URI scheme is valid or whether the URL is otherwise well formed.
 
  
−
The scheme is checked http://tools.ietf.org/html/std66#section-3.1 which says:
+
This function is the last step in the validation process. This function is separate because there are cases that
−
Scheme names consist of a sequence of characters beginning with a
+
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
−
  letter and followed by any combination of letters, digits, plus
+
wikilinks.
−
  ("+"), period ("."), or hyphen ("-").
 
  
−
First we test for space characters.  If any are found, return false.  Then test for the case where the url is
 
−
protocol relative (//example.com).  If the first two characters of the |url= value are //, return true.  Last
 
−
look for what appears to be a scheme according to the definition above.  If the characters preceding the colon
 
−
are in the allowed set, return true, else false
 
 
]]
 
]]
  
−
local function check_url( url_str )
+
local function is_url (scheme, domain)
−
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value
+
if is_set (scheme) then -- if scheme is set check it and domain
−
return false;
+
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
−
return url_str:sub(1,2) == "//" or nil ~= url_str:match ("^%a[%a%d%+%.%-]*:") -- protocol relative or scheme part composed of legitimate characters
 
 
end
 
end
  
−
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
 
  
−
Protects a string that will be wrapped in wiki italic markup '' ... ''
+
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
  
−
Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
+
Split a url into a scheme, authority indicator, and domain.
−
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
 
−
poorly under Mediawiki's HTML tidy.
 
  
−
]]
+
First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#).
  
−
local function safe_for_italics( str )
+
If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
−
if not is_set(str) then
 
−
return str;
 
−
else
 
−
if str:sub(1,1) == "'" then str = "<span />" .. str; end
 
−
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
 
−
 
−
-- Remove newlines as they break italics.
 
−
return str:gsub( '\n', ' ' );
 
−
end
 
−
end
 
  
−
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
+
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.
  
−
Escape sequences for content that will be used for URL descriptions
+
Strip off any port and path;
  
 
]]
 
]]
  
−
local function safe_for_url( str )
+
local function split_url (url_str)
−
if str:match( "%[%[.-%]%]" ) ~= nil then
+
local scheme, authority, domain;
−
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
 
−
end
 
 
 
−
return str:gsub( '[%[%]\n]', {
+
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
−
['['] = '&#91;',
+
 
−
[']'] = '&#93;',
+
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
−
['\n'] = ' ' } );
+
domain = url_str:match ('^//(%S*)')
 +
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
 +
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
 +
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
 +
if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
 +
return scheme; -- return scheme only making domain nil which will cause an error message
 +
end
 +
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
 +
end
 +
 +
return scheme, domain;
 
end
 
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
+
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
−
argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason
+
 
−
this function is similar to but separate from wrap_msg().
+
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 wrap_style (key, str)
+
local function link_param_ok (value)
−
if not is_set( str ) then
+
local scheme, domain;
−
return "";
+
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
−
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
+
return false;
−
str = safe_for_italics( str );
 
 
end
 
end
  
−
return substitute( cfg.presentation[key], {str} );
+
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
  
−
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
+
--[[--------------------------< 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.
  
−
Format an external link with error checking
+
|<title>= may be wikilinked but not when |<param>-link= has a value.  This function emits an error message when
 +
that condition exists
  
 
]]
 
]]
  
−
local function external_link( URL, label, source )
+
local function link_title_ok (link, lorig, title, torig)
−
local error_str = "";
+
local orig;
−
if not is_set( label ) then
+
 
−
label = URL;
+
if is_set (link) then -- don't bother if <param>-link doesn't have a value
−
if is_set( source ) then
+
if not link_param_ok (link) then -- check |<param>-link= markup
−
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
+
orig = lorig; -- identify the failing link parameter
−
else
+
elseif title:find ('%[%[') then -- check |title= for wikilink markup
−
error( cfg.messages["bare_url_no_origin"] );
+
orig = torig; -- identify the failing |title= parameter
−
end
+
end
 
end
 
end
−
if not check_url( URL ) then
+
 
−
error_str = set_error( 'bad_url', {}, false, " " ) .. error_str;
+
if is_set (orig) then
 +
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=;
 
end
 
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
+
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
  
−
]]
+
Determines whether a URL string appears to be valid.
  
−
local function external_link_id(options)
+
First we test for space characters.  If any are found, return false. Then split the url into scheme and domain
−
local url_string = options.id;
+
portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two
−
if options.encode == true or options.encode == nil then
+
portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false.
−
url_string = mw.uri.encode( url_string );
 
−
end
 
−
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
 
−
options.link, options.label, options.separator or "&nbsp;",
 
−
options.prefix, url_string, options.suffix or "",
 
−
mw.text.nowiki(options.id)
 
−
);
 
−
end
 
  
−
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
+
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
  
−
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.
 
  
−
]]
+
local function check_url( url_str )
 +
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
 +
return false;
 +
end
 +
local scheme, domain;
  
−
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
+
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
−
local function deprecated_parameter(name)
+
−
if not page_in_deprecated_cat then
+
if 'news:' == scheme then -- special case for newsgroups
−
page_in_deprecated_cat = true; -- note that we've added this category
+
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
−
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
 
 
end
 
end
 +
 +
return is_url (scheme, domain); -- return true if value appears to be a valid url
 
end
 
end
  
−
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
  
−
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.
+
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
−
This function will positive kern either single or double quotes:
+
 
−
"'Unkerned title with leading and trailing single quote marks'"
+
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
−
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
+
non-space characters following the opening bracket appear to be a url.  The test will also find external wikilinks
−
Double single quotes (italic or bold wikimarkup) are not kerned.
+
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]].
  
−
Call this function for chapter titles, for website titles, etc; not for book titles.
+
]=]
  
−
]]
+
local function is_parameter_ext_wikilink (value)
 +
local scheme, domain;
  
−
local function kern_quotes (str)
+
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
−
local cap='';
+
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
−
local cap2='';
+
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
−
+
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
−
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
+
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
−
if is_set (cap) then
+
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
−
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
+
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
  
−
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
+
return is_url (scheme, domain); -- return true if value appears to be a valid url
−
if is_set (cap) then
+
end
−
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
 
−
end
 
−
return str;
 
−
end
 
  
−
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
 
  
−
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
+
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
−
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.
+
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
−
 
 
−
|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon:
 
−
|script-title=ja:*** *** (where * represents a Japanese character)
 
−
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
 
−
|script-title=ja : *** ***
 
−
|script-title=ja: *** ***
 
−
|script-title=ja :*** ***
 
−
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
 
  
−
The prefix is checked for validity.  If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
 
−
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
 
−
is not added.  At this time there is no error message for this condition.
 
−
 
−
Supports |script-title= and |script-chapter=
 
−
 
−
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
 
 
]]
 
]]
  
−
local function format_script_value (script_value)
+
local function check_for_url (parameter_list)
−
local lang=''; -- initialize to empty string
+
local error_message = '';
−
local name;
+
for k, v in pairs (parameter_list) do -- for each parameter in the list
−
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
+
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
−
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
+
if is_set(error_message) then -- once we've added the first portion of the error message ...
−
if not is_set (lang) then
+
error_message=error_message .. ", "; -- ... add a comma space separator
−
return ''; -- script_value was just the prefix so return empty string
 
−
end
 
−
-- if we get this far we have prefix and script
 
−
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
 
−
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
 
−
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
 
−
-- is prefix one of these language codes?
 
−
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
 
−
add_prop_cat ('script_with_name', {name, lang})
 
−
else
 
−
add_prop_cat ('script')
 
 
end
 
end
−
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
+
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
−
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
+
if is_set (error_message) then -- done looping, if there is an error message, display it
 +
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
 +
end
 +
end
 +
 
  
−
return script_value;
+
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
−
end
 
  
−
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
+
Escape sequences for content that will be used for URL descriptions
  
−
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
 
−
wrapped in <bdi> tags.
 
 
]]
 
]]
  
−
local function script_concatenate (title, script)
+
local function safe_for_url( str )
−
if is_set (script) then
+
if str:match( "%[%[.-%]%]" ) ~= nil then  
−
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
+
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
−
if is_set (script) then
 
−
title = title .. ' ' .. script; -- concatenate title and script title
 
−
end
 
 
end
 
end
−
return title;
+
 +
return str:gsub( '[%[%]\n]', {
 +
['['] = '&#91;',
 +
[']'] = '&#93;',
 +
['\n'] = ' ' } );
 
end
 
end
  
 +
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
  
−
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
+
Format an external link with error checking
−
 
 
−
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)
+
local function external_link( URL, label, source, access)
−
if not is_set( str ) then
+
local error_str = "";
−
return "";
+
local domain;
 +
local path;
 +
local base_url;
 +
 +
if not is_set( label ) then
 +
label = URL;
 +
if is_set( source ) then
 +
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
 +
else
 +
error( cfg.messages["bare_url_no_origin"] );
 +
end
 +
end
 +
if not check_url( URL ) then
 +
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
 
end
 
end
−
if true == lower then
 
−
local msg;
 
−
msg = cfg.messages[key]:lower(); -- set the message to lower case before
 
−
str = substitute( msg, {str} ); -- including template text
 
−
return str;
 
−
else
 
−
return substitute( cfg.messages[key], {str} );
 
−
end
 
−
end
 
−
 
−
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
 
−
 
−
Chooses one matching parameter from a list of parameters to consider
 
−
Generates an error if more than one match is present.
 
−
 
−
]]
 
−
 
−
local function select_one( args, possible, error_condition, index )
 
−
local value = nil;
 
−
local selected = '';
 
−
local error_list = {};
 
−
 
−
if index ~= nil then index = tostring(index); end
 
 
 
−
-- Handle special case of "#" replaced by empty string
+
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path
−
if index == '1' then
+
if path then -- if there is a path portion
−
for _, v in ipairs( possible ) do
+
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
−
v = v:gsub( "#", "" );
+
URL=domain..path; -- and reassemble
−
if is_set(args[v]) then
 
−
if value ~= nil and selected ~= v then
 
−
table.insert( error_list, v );
 
−
else
 
−
value = args[v];
 
−
selected = v;
 
−
end
 
−
end
 
−
end
 
 
end
 
end
 
 
−
for _, v in ipairs( possible ) do
+
base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" });
−
if index ~= nil then
 
−
v = v:gsub( "#", index );
 
−
end
 
−
if is_set(args[v]) then
 
−
if value ~= nil and selected ~=  v then
 
−
table.insert( error_list, v );
 
−
else
 
−
value = args[v];
 
−
selected = v;
 
−
end
 
−
end
 
−
end
 
 
 
−
if #error_list > 0 then
+
if is_set(access) then -- access level (free, paywalled, ...)
−
local error_str = "";
+
base_url = substitute(cfg.presentation[access], base_url);
−
for _, k in ipairs( error_list ) do
 
−
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
 
−
error_str = error_str .. wrap_style ('parameter', k);
 
−
end
 
−
if #error_list > 1 then
 
−
error_str = error_str .. cfg.messages['parameter-final-separator'];
 
−
else
 
−
error_str = error_str .. cfg.messages['parameter-pair-separator'];
 
−
end
 
−
error_str = error_str .. wrap_style ('parameter', selected);
 
−
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
 
 
end
 
end
 
 
−
return value, selected;
+
return table.concat({ base_url, error_str });
 
end
 
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-
+
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
−
parameter (chapter_url_source used for error messages).
+
 
 +
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 format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source)
+
local function deprecated_parameter(name)
−
local chapter_error = '';
+
if not added_deprecated_cat then
−
+
added_deprecated_cat = true; -- note that we've added this category
−
if not is_set (chapter) then
+
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
−
chapter = ''; -- to be safe for concatenation
 
−
else
 
−
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
 
−
chapter = wrap_style ('quoted-title', chapter);
 
 
end
 
end
 +
end
  
−
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
  
−
if is_set (transchapter) then
+
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.
−
transchapter = wrap_style ('trans-quoted-title', transchapter);
+
This function will positive kern either single or double quotes:
−
if is_set (chapter) then
+
"'Unkerned title with leading and trailing single quote marks'"
−
chapter = chapter ..  ' ' .. transchapter;
+
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
−
else -- here when transchapter without chapter or script-chapter
+
Double single quotes (italic or bold wikimarkup) are not kerned.
−
chapter = transchapter; --
 
−
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
 
−
end
 
−
end
 
  
−
if is_set (chapterurl) then
+
Replaces unicode quotemarks with typewriter quote marks regardless of the need for kerning.
−
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
 
−
end
 
−
 
 
−
return chapter .. chapter_error;
 
−
end
 
  
 +
Call this function for chapter titles, for website titles, etc; not for book titles.
  
−
--[[
 
−
Argument wrapper.  This function provides support for argument
 
−
mapping defined in the configuration file so that multiple names
 
−
can be transparently aliased to single internal variable.
 
 
]]
 
]]
  
−
local function argument_wrapper( args )
+
local function kern_quotes (str)
−
local origin = {};
+
local cap='';
 +
local cap2='';
 +
-- TODO: move this elswhere so that all title-holding elements get these quote marks replaced?
 +
str= mw.ustring.gsub (str, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
 +
str= mw.ustring.gsub (str, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
 
 
−
return setmetatable({
+
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
−
ORIGIN = function( self, k )
+
if is_set (cap) then
−
local dummy = self[k]; --force the variable to be loaded.
+
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
−
return origin[k];
+
end
−
end
+
 
−
},
+
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
−
{
+
if is_set (cap) then
−
__index = function ( tbl, k )
+
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
−
if origin[k] ~= nil then
+
end
−
return nil;
+
return str;
−
end
+
end
−
+
 
−
local args, list, v = args, cfg.aliases[k];
+
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
−
+
 
−
if type( list ) == 'table' then
+
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
−
v, origin[k] = select_one( args, list, 'redundant_parameters' );
+
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
−
if origin[k] == nil then
+
in italic markup.
−
origin[k] = ''; -- Empty string, not nil
 
−
end
 
−
elseif list ~= nil then
 
−
v, origin[k] = args[list], list;
 
−
else
 
−
-- maybe let through instead of raising an error?
 
−
-- v, origin[k] = args[k], k;
 
−
error( cfg.messages['unknown_argument_map'] );
 
−
end
 
−
 
−
-- Empty strings, not nil;
 
−
if v == nil then
 
−
v = cfg.defaults[k] or '';
 
−
origin[k] = '';
 
−
end
 
−
 
−
tbl = rawset( tbl, k, v );
 
−
return v;
 
−
end,
 
−
});
 
−
end
 
  
−
--[[
+
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.
−
Looks for a parameter's name in the whitelist.
 
  
−
Parameters in the whitelist can have three values:
+
|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:
−
true - active, supported parameters
+
|script-title=ja:*** *** (where * represents a Japanese character)
−
false - deprecated, supported parameters
+
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
−
nil - unsupported parameters
+
|script-title=ja : *** ***
−
]]
+
|script-title=ja: *** ***
 +
|script-title=ja :*** ***
 +
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
  
−
local function validate( name )
+
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 name = tostring( name );
+
know the language the tag contains.  This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
−
local state = whitelist.basic_arguments[ name ];
+
is not added.  At this time there is no error message for this condition.
−
 
−
-- Normal arguments
 
−
if true == state then return true; end -- valid actively supported parameter
 
−
if false == state then
 
−
deprecated_parameter (name); -- parameter is deprecated but still supported
 
−
return true;
 
−
end
 
−
 
−
-- Arguments with numbers in them
 
−
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
 
−
state = whitelist.numbered_arguments[ name ];
 
−
if true == state then return true; end -- valid actively supported parameter
 
−
if false == state then
 
−
deprecated_parameter (name); -- parameter is deprecated but still supported
 
−
return true;
 
−
end
 
−
 
−
return false; -- Not supported because not found or name is set to nil
 
−
end
 
  
 +
Supports |script-title= and |script-chapter=
  
−
-- Formats a wiki style internal link
+
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
−
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
 
  
 +
local function format_script_value (script_value)
 +
local lang=''; -- initialize to empty string
 +
local name;
 +
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
 +
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
 +
if not is_set (lang) then
 +
return ''; -- script_value was just the prefix so return empty string
 +
end
 +
-- if we get this far we have prefix and script
 +
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
 +
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
 +
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
 +
-- is prefix one of these language codes?
 +
if in_array (lang, cfg.script_lang_codes) then
 +
add_prop_cat ('script_with_name', {name, lang})
 +
else
 +
add_prop_cat ('script')
 +
end
 +
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
 +
else
 +
lang = ''; -- invalid so set lang to empty string
 +
end
 +
end
 +
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
  
−
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
+
return script_value;
 +
end
  
−
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
+
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
−
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.
 
  
 +
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 nowrap_date (date)
+
local function script_concatenate (title, script)
−
local cap='';
+
if is_set (script) then
−
local cap2='';
+
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
−
 
+
if is_set (script) then
−
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
+
title = title .. ' ' .. script; -- concatenate title and script title
−
date = substitute (cfg.presentation['nowrap1'], date);
+
end
−
 
−
elseif date:match("^%a+%s*%d%d?,%s*%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s*%d%d%d%d$") then
 
−
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
 
−
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
 
 
end
 
end
−
+
return title;
−
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().
+
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
−
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.
+
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 is_valid_isxn (isxn_str, len)
+
local function wrap_msg (key, str, lower)
−
local temp = 0;
+
if not is_set( str ) then
−
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
+
return "";
−
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
+
if true == lower then
 +
local msg;
 +
msg = cfg.messages[key]:lower(); -- set the message to lower case before
 +
return substitute( msg, str ); -- including template text
 +
else
 +
return substitute( cfg.messages[key], str );
 +
end
 
end
 
end
  
  
−
--[[--------------------------< IS _ V A L I D _ I S X N  _ 1 3 >----------------------------------------------
+
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
  
−
ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
+
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
−
If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length
+
parameter (chapter_url_source used for error messages).
−
and stripped of dashes, spaces and other non-isxn-13 characters.
 
  
 
]]
 
]]
  
−
local function is_valid_isxn_13 (isxn_str)
+
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
−
local temp=0;
+
local chapter_error = '';
 
 
−
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
+
if not is_set (chapter) then
−
for i, v in ipairs( isxn_str ) do
+
chapter = ''; -- to be safe for concatenation
−
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
+
else
 +
if false == no_quotes then
 +
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
 +
chapter = wrap_style ('quoted-title', chapter);
 +
end
 
end
 
end
−
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
 
−
end
 
  
−
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
+
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
  
−
Determines whether an ISBN string is valid
+
if is_set (transchapter) then
 +
transchapter = wrap_style ('trans-quoted-title', transchapter);
 +
if is_set (chapter) then
 +
chapter = chapter ..  ' ' .. transchapter;
 +
else -- here when transchapter without chapter or script-chapter
 +
chapter = transchapter; --
 +
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
 +
end
 +
end
  
−
]]
+
if is_set (chapterurl) then
−
 
+
chapter = external_link (chapterurl, chapter, chapter_url_source, nil); -- adds bare_url_missing_title error if appropriate
−
local function check_isbn( isbn_str )
 
−
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
 
−
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
 
−
local len = isbn_str:len();
 
−
 
−
if len ~= 10 and len ~= 13 then
 
−
return false;
 
 
end
 
end
  
−
if len == 10 then
+
return chapter .. chapter_error;
−
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
 
−
return is_valid_isxn(isbn_str, 10);
 
−
else
 
−
local temp = 0;
 
−
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
 
−
return is_valid_isxn_13 (isbn_str);
 
−
end
 
 
end
 
end
  
−
--[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
+
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
  
−
Determines whether an ISMN string is valid.  Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
+
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the
−
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
+
first match.
−
section 2, pages 9–12.
 
  
−
]]
+
This function will detect the visible replacement character when it is part of the wikisource.
  
−
local function ismn (id)
+
Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers (gallery, math, pre, ref)
−
local handler = cfg.id_handlers['ISMN'];
+
and identifies them with a slightly different error message.  See also coins_cleanup().
−
local text;
 
−
local valid_ismn = true;
 
  
−
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn
+
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
  
−
if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
+
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
−
valid_ismn = false;
+
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
−
else
+
parameter value.
−
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
 
−
end
 
  
−
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
+
]]
−
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
 
−
 
−
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet
 
  
−
if false == valid_ismn then
+
local function has_invisible_chars (param, v)
−
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
+
local position = ''; -- position of invisible char or starting position of stripmarker
−
end
+
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
 +
local capture; -- used by stripmarker detection to hold name of the stripmarker
 +
local i=1;
 +
local stripmarker, apostrophe;
 
 
−
return text;
+
capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true
−
end
+
if capture == v then -- if same there are no unicode characters
 +
return;
 +
end
  
−
--[[--------------------------< I S S N >----------------------------------------------------------------------
+
while cfg.invisible_chars[i] do
−
 
+
local char=cfg.invisible_chars[i][1] -- the character or group name
−
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
+
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
−
digits with a space. When that condition occurred, the resulting link looked like this:
+
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
−
 
+
−
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
+
if position then
−
+
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
−
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
+
stripmarker = true; -- set a flag
−
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
+
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
−
error message.  The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
+
position = nil; -- unset
−
 
+
else
−
]]
+
local err_msg;
−
 
+
if capture then
−
local function issn(id)
+
err_msg = capture .. ' ' .. char;
−
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
+
else
−
local handler = cfg.id_handlers['ISSN'];
+
err_msg = char .. ' ' .. 'character';
−
local text;
+
end
−
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
 
−
valid_issn=false; -- wrong length or improper character
 
−
else
 
−
valid_issn=is_valid_isxn(id, 8); -- validate issn
 
−
end
 
−
 
 
−
if true == valid_issn then
 
−
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
 
−
else
 
−
id = issn_copy; -- if not valid, use the show the invalid issn with error message
 
−
end
 
−
 
−
text = external_link_id({link = handler.link, label = handler.label,
 
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
 
−
 
−
if false == valid_issn then
 
−
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
 
−
end
 
−
 
−
return text
 
−
end
 
  
−
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
+
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
−
Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
 
−
characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
 
−
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
 
−
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
 
−
 
 
−
]]
 
−
 
 
−
local function amazon(id, domain)
 
−
local err_cat = ""
 
−
 
 
−
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
 
−
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
 
−
else
 
−
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
 
−
if check_isbn( id ) then -- see if asin value is isbn10
 
−
add_maint_cat ('ASIN');
 
−
elseif not is_set (err_cat) then
 
−
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not isbn10
 
 
end
 
end
−
elseif not id:match("^%u[%d%u]+$") then
 
−
err_cat =  ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
 
 
end
 
end
 +
i=i+1; -- bump our index
 
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
 
end
  
−
--[[--------------------------< A R X I V >--------------------------------------------------------------------
 
  
−
See: http://arxiv.org/help/arxiv_identifier
+
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
  
−
format and error check arXiv identifier.  There are three valid forms of the identifier:
+
Argument wrapper.  This function provides support for argument mapping defined in the configuration file so that
−
the first form, valid only between date codes 9108 and 0703 is:
+
multiple names can be transparently aliased to single internal variable.
−
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 argument_wrapper( args )
−
local handler = cfg.id_handlers['ARXIV'];
+
local origin = {};
−
local year, month, version;
 
−
local err_cat = '';
 
−
local text;
 
 
 
−
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
+
return setmetatable({
−
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
+
ORIGIN = function( self, k )
−
year = tonumber(year);
+
local dummy = self[k]; --force the variable to be loaded.
−
month = tonumber(month);
+
return origin[k];
−
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
 
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]*$");
+
{
−
year = tonumber(year);
+
__index = function ( tbl, k )
−
month = tonumber(month);
+
if origin[k] ~= nil then
−
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
+
return nil;
−
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
+
end
−
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
+
−
end
+
local args, list, v = args, cfg.aliases[k];
−
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
+
−
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
+
if type( list ) == 'table' then
−
year = tonumber(year);
+
v, origin[k] = select_one( args, list, 'redundant_parameters' );
−
month = tonumber(month);
+
if origin[k] == nil then
−
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
+
origin[k] = ''; -- Empty string, not nil
−
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
+
end
−
end
+
elseif list ~= nil then
−
else
+
v, origin[k] = args[list], list;
−
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
+
else
−
end
+
-- maybe let through instead of raising an error?
−
 
+
-- v, origin[k] = args[k], k;
−
text = external_link_id({link = handler.link, label = handler.label,
+
error( cfg.messages['unknown_argument_map'] );
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
+
end
−
 
+
−
if is_set (class) then
+
-- Empty strings, not nil;
−
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
+
if v == nil then
−
else
+
v = cfg.defaults[k] or '';
−
class = ''; -- empty string for concatenation
+
origin[k] = '';
−
end
+
end
−
+
−
return text .. class;
+
tbl = rawset( tbl, k, v );
−
end
+
return v;
−
 
+
end,
−
--[[
+
});
−
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
+
end
−
1. Remove all blanks.
 
−
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
 
−
3. If there is a hyphen in the string:
 
−
a. Remove it.
 
−
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
 
−
1. All these characters should be digits, and there should be six or less. (not done in this function)
 
−
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
 
−
 
 
−
Returns a normalized lccn for lccn() to validate.  There is no error checking (step 3.b.1) performed in this function.
 
−
]]
 
−
 
 
−
local function normalize_lccn (lccn)
 
−
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
 
−
 
 
−
if nil ~= string.find (lccn,'/') then
 
−
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
 
−
end
 
  
−
local prefix
+
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
−
local suffix
+
Looks for a parameter's name in the whitelist.
−
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
+
Parameters in the whitelist can have three values:
−
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
+
true - active, supported parameters
−
lccn=prefix..suffix; -- reassemble the lccn
+
false - deprecated, supported parameters
−
end
+
nil - unsupported parameters
 
 
−
return lccn;
 
−
end
 
−
 
−
--[[
 
−
Format LCCN link and do simple error checking.  LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the
 
−
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
 
−
 
−
length = 8 then all digits
 
−
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 validate( name )
−
local handler = cfg.id_handlers['LCCN'];
+
local name = tostring( name );
−
local err_cat =  ''; -- presume that LCCN is valid
+
local state = whitelist.basic_arguments[ name ];
−
local id = lccn; -- local copy of the lccn
+
−
 
+
-- Normal arguments
−
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
+
if true == state then return true; end -- valid actively supported parameter
−
local len = id:len(); -- get the length of the lccn
+
if false == state then
−
 
+
deprecated_parameter (name); -- parameter is deprecated but still supported
−
if 8 == len then
+
return true;
−
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
 
−
end
 
−
elseif 9 == len then -- LCCN should be adddddddd
 
−
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
 
−
end
 
−
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
 
−
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
 
−
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
−
end
 
−
end
 
−
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
 
−
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
−
end
 
−
elseif 12 == len then -- LCCN should be aadddddddddd
 
−
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
 
−
end
 
−
else
 
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
 
 
end
 
end
−
 
+
−
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
+
-- Arguments with numbers in them
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
+
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
 +
state = whitelist.numbered_arguments[ name ];
 +
if true == state then return true; end -- valid actively supported parameter
 +
if false == state then
 +
deprecated_parameter (name); -- parameter is deprecated but still supported
 +
return true;
 
end
 
end
−
 
+
−
return external_link_id({link = handler.link, label = handler.label,
+
return false; -- Not supported because not found or name is set to nil
−
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 O W R A P _ D A T E >--------------------------------------------------------
−
local test_limit = 30000000; -- update this value as PMIDs approach
 
−
local handler = cfg.id_handlers['PMID'];
 
−
local err_cat =  ''; -- presume that PMID is valid
 
−
 
−
if id:match("[^%d]") then -- if PMID has anything but digits
 
−
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
 
−
else -- PMID is only digits
 
−
local id_num = tonumber(id); -- convert id to a number for range testing
 
−
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
 
−
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
 
−
end
 
−
end
 
−
 
−
return external_link_id({link = handler.link, label = handler.label,
 
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
 
−
end
 
  
−
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
+
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
  
−
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.  If embargo date is
+
DOES NOT yet support MMMM YYYY or any of the date ranges.
−
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 nowrap_date (date)
−
if is_set (embargo) then
+
local cap='';
−
local lang = mw.getContentLanguage();
+
local cap2='';
−
local good1, embargo_date, good2, todays_date;
+
 
−
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
+
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
−
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
+
date = substitute (cfg.presentation['nowrap1'], date);
 
 
−
if good1 and good2 then -- if embargo date and today's date are good dates
+
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
−
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
+
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
−
return embargo; -- still embargoed
+
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
−
else
 
−
add_maint_cat ('embargo')
 
−
return ''; -- unset because embargo has expired
 
−
end
 
−
end
 
 
end
 
end
−
return ''; -- |embargo= not set return empty string
+
 +
return date;
 
end
 
end
  
−
--[[--------------------------< P M C >------------------------------------------------------------------------
+
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
  
−
Format a PMC, do simple error checking, and check for embargoed articles.
+
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).
−
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
 
−
be linked to the article.  If the embargo date is today or in the past, or if it is empty or omitted, then the
 
−
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
 
−
 
 
−
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
 
−
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link. Function is_embargoed ()
 
−
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
 
−
 
 
−
PMCs are sequential numbers beginning at 1 and counting up.  This code checks the PMC to see that it contains only digits and is less
 
−
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
 
  
 
]]
 
]]
  
−
local function pmc(id, embargo)
+
local function set_titletype (cite_class, title_type)
−
local test_limit = 5000000; -- update this value as PMCs approach
+
if is_set(title_type) then
−
local handler = cfg.id_handlers['PMC'];
+
if "none" == title_type then
−
local err_cat =  ''; -- presume that PMC is valid
+
title_type = ""; -- if |type=none then type parameter not displayed
−
 
−
local text;
 
−
 
 
−
if id:match("[^%d]") then -- if PMC has anything but digits
 
−
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
 
−
else -- PMC is only digits
 
−
local id_num = tonumber(id); -- convert id to a number for range testing
 
−
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
 
−
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
 
 
end
 
end
 +
return title_type; -- if |type= has been set to any other value use that value
 
end
 
end
−
+
 
−
if is_set (embargo) then -- is PMC is still embargoed?
+
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
−
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.
+
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
−
-- 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,
+
Converts a hyphen to a dash
−
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
 
  
−
-- 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 hyphen_to_dash( str )
−
local cat = ""
+
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
−
local handler = cfg.id_handlers['DOI'];
+
return str;
−
+
end
−
local text;
+
return str:gsub( '-', '–' );
−
if is_set(inactive) then
 
−
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
 
−
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
 
−
if is_set(inactive_year) then
 
−
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
 
−
else
 
−
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
 
−
end
 
−
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
 
−
else
 
−
text = external_link_id({link = handler.link, label = handler.label,
 
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
 
−
inactive = ""
 
−
end
 
−
 
 
−
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
 
−
cat = ' ' .. set_error( 'bad_doi' );
 
−
end
 
−
return text .. inactive .. cat
 
 
end
 
end
  
−
-- 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
+
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
−
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
 
  
−
 
+
Joins a sequence of strings together while checking for duplicate separation characters.
−
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
 
−
 
 
−
Validate and format a usenet message id.  Simple error checking, looks for 'id-left@id-right' not enclosed in
 
−
'<' and/or '>' angle brackets.
 
  
 
]]
 
]]
  
−
local function message_id (id)
+
local function safe_join( tbl, duplicate_char )
−
local handler = cfg.id_handlers['USENETID'];
+
--[[
−
 
+
Note: we use string functions here, rather than ustring functions.
−
text = external_link_id({link = handler.link, label = handler.label,
+
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
+
This has considerably faster performance and should work correctly as
−
   
+
long as the duplicate_char is strict ASCII.  The strings
−
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
+
in tbl may be ASCII or UTF8.
−
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
+
]]
−
end
 
 
 
−
return text
+
local str = ''; -- the output string
−
end
+
local comp = ''; -- what does 'comp' mean?
−
 
+
local end_chr = '';
−
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
+
local trim;
−
 
+
for _, value in ipairs( tbl ) do
−
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
+
if value == nil then value = ''; end
−
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
+
−
 
+
if str == '' then -- if output string is empty
−
]]
+
str = value; -- assign value to it (first time through the loop)
−
 
+
elseif value ~= '' then
−
local function set_titletype (cite_class, title_type)
+
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
−
if is_set(title_type) then
+
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
−
if "none" == title_type then
+
else
−
title_type = ""; -- if |type=none then type parameter not displayed
+
comp = value;
−
end
+
end
−
return title_type; -- if |type= has been set to any other value use that value
+
-- typically duplicate_char is sepc
−
end
+
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
−
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
+
--   preceding segment: 'First element' .. 'sepc next element' .. etc?
−
end
+
trim = false;
−
 
+
end_chr = str:sub(-1,-1); -- get the last character of the output string
−
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
+
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
−
 
+
if end_chr == duplicate_char then -- if same as separator
−
Removes irrelevant text and dashes from ISBN number
+
str = str:sub(1,-2); -- remove it
−
Similar to that used for Special:BookSources
+
elseif end_chr == "'" then -- if it might be wikimarkup
 +
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
 +
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
 +
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
 +
trim = true; -- why? why do this and next differently from previous?
 +
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
 +
trim = true; -- same question
 +
end
 +
elseif end_chr == "]" then -- if it might be wikimarkup
 +
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
 +
trim = true;
 +
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
 +
trim = true;
 +
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
 +
trim = true;
 +
end
 +
elseif end_chr == " " then -- if last char of output string is a space
 +
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
 +
str = str:sub(1,-3); -- remove them both
 +
end
 +
end
  
−
]]
+
if trim then
−
 
+
if value ~= comp then -- value does not equal comp when value contains html markup
−
local function clean_isbn( isbn_str )
+
local dup2 = duplicate_char;
−
return isbn_str:gsub( "[^-0-9X]", "" );
+
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
−
end
+
−
 
+
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
−
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
+
else
 +
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
 +
end
 +
end
 +
end
 +
str = str .. value; --add it to the output string
 +
end
 +
end
 +
return str;
 +
end 
  
−
Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
 
−
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
 
−
]]
 
−
local function escape_lua_magic_chars (argument)
 
−
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
 
−
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 >--------------------------------
+
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
  
−
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
+
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
−
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 is_suffix (suffix)
−
if not is_set (argument) then return argument; end
+
if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then
−
 
+
return true;
−
while true do
 
−
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
 
−
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
 
−
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
 
−
argument=argument:gsub("%'%'%'%'", "");
 
−
elseif argument:match ("%'%'%'") then -- bold (3)
 
−
argument=argument:gsub("%'%'%'", "");
 
−
elseif argument:match ("%'%'") then -- italic (2)
 
−
argument=argument:gsub("%'%'", "");
 
−
else
 
−
break;
 
−
end
 
 
end
 
end
−
return argument; -- done
+
return false;
 
end
 
end
  
−
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
+
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
  
−
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
+
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
 +
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
 +
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
 +
These things are not currently possible in this module so are left to the editor to do.
  
−
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
+
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
−
of %27%27...
+
[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 make_coins_title (title, script)
+
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
−
if is_set (title) then
+
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
−
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
 
−
else
 
−
title=''; -- if not set, make sure title is an empty string
 
−
end
 
−
if is_set (script) then
 
−
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
 
−
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
 
−
else
 
−
script=''; -- if not set, make sure script is an empty string
 
−
end
 
−
if is_set (title) and is_set (script) then
 
−
script = ' ' .. script; -- add a space before we concatenate
 
−
end
 
−
return title .. script; -- return the concatenation
 
−
end
 
  
−
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
+
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 ouside 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.
  
−
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
+
\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 get_coins_pages (pages)
+
local function is_good_vanc_name (last, first)
−
local pattern;
+
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it
−
if not is_set (pages) then return pages; end -- if no page numbers then we're done
+
 
−
+
if is_set (suffix) then
−
while true do
+
if not is_suffix (suffix) then
−
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
+
add_vanc_error ('suffix');
−
if nil == pattern then break; end -- no more urls
+
return false; -- not a name with an appropriate suffix
−
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
+
end
−
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
 
 
end
 
end
−
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
+
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%']*$") or
−
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
+
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
−
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like?
+
add_vanc_error ('non-Latin character');
−
return pages;
+
return false; -- not a string of latin characters; Vancouver requires Romanization
 +
end;
 +
return true;
 
end
 
end
  
−
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
+
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
−
local function remove_wiki_link( str )
+
 
−
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
+
Attempts to convert names to initials in support of |name-list-format=vanc.
−
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
 
−
end));
 
−
end
 
  
−
-- Converts a hyphen to a dash
+
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
−
local function hyphen_to_dash( str )
 
−
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
 
−
return str;
 
−
end
 
−
return str:gsub( '-', '–' );
 
−
end
 
  
−
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
+
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.
  
−
Joins a sequence of strings together while checking for duplicate separation characters.
+
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
  
 
]]
 
]]
  
−
local function safe_join( tbl, duplicate_char )
+
local function reduce_to_initials(first)
−
--[[
+
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
−
Note: we use string functions here, rather than ustring functions.
+
 
−
+
if not name then -- if not initials and a suffix
−
This has considerably faster performance and should work correctly as
+
name = mw.ustring.match(first, "^(%u+)$"); -- is it just intials?
−
long as the duplicate_char is strict ASCII.  The strings
+
end
−
in tbl may be ASCII or UTF8.
+
 
−
]]
+
if name then -- if first is initials with or without suffix
−
+
if 3 > name:len() then -- if one or two initials
−
local str = ''; -- the output string
+
if suffix then -- if there is a suffix
−
local comp = ''; -- what does 'comp' mean?
+
if is_suffix (suffix) then -- is it legitimate?
−
local end_chr = '';
+
return first; -- one or two initials and a valid suffix so nothing to do
−
local trim;
+
else
−
for _, value in ipairs( tbl ) do
+
add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message
−
if value == nil then value = ''; end
+
return first; -- and return first unmolested
−
+
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
 
else
−
comp = value;
+
return first; -- one or two initials without suffix; nothing to do
 
end
 
end
−
-- typically duplicate_char is sepc
+
end
−
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
+
end -- if here then name has 3 or more uppercase letters so treat them as a word
−
--  Because individual string segments often (always?) begin with terminal punct for th
+
 
−
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
+
 
−
trim = false;
+
local initials, names = {}, {}; -- tables to hold name parts and initials
−
end_chr = str:sub(-1,-1); -- get the last character of the output string
+
local i = 1; -- counter for number of initials
−
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
+
 
−
if end_chr == duplicate_char then -- if same as separator
+
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
−
str = str:sub(1,-2); -- remove it
+
 
−
elseif end_chr == "'" then -- if it might be wikimarkup
+
while names[i] do -- loop through the table
−
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
+
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
−
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
+
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
−
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
+
if is_suffix (names[i]) then -- if a legitimate suffix
−
trim = true; -- why? why do this and next differently from previous?
+
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
−
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
+
break; -- and done because suffix must fall at the end of a name
−
trim = true; -- same question
+
end -- no error message if not a suffix; possibly because of Romanization
−
end
+
end
−
elseif end_chr == "]" then -- if it might be wikimarkup
+
if 3 > i then
−
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
+
table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table
−
trim = true;
+
end
−
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
+
i = i+1; -- bump the counter
−
trim = true;
+
end
−
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
+
−
trim = true;
+
return table.concat(initials) -- Vancouver format does not include spaces.
−
end
+
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>
+
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
−
str = str:sub(1,-3); -- remove them both
 
−
end
 
−
end
 
  
−
if trim then
+
Formats a list of people (e.g. authors / editors)  
−
if value ~= comp then -- value does not equal comp when value contains html markup
 
−
local dup2 = duplicate_char;
 
−
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
 
−
 
−
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
 
−
else
 
−
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
 
−
end
 
−
end
 
−
end
 
−
str = str .. value; --add it to the output string
 
−
end
 
−
end
 
−
return str;
 
−
end 
 
  
−
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
+
]]
  
−
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
+
local function list_people(control, people, etal)
−
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
+
local sep;
−
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
+
local namesep;
−
These things are not currently possible in this module so are left to the editor to do.
+
local format = control.format
 +
local maximum = control.maximum
 +
local lastauthoramp = control.lastauthoramp;
 +
local text = {}
  
−
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
+
if 'vanc' == format then -- Vancouver-like author/editor name styling?
−
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
+
sep = ','; -- name-list separator between authors is a comma
−
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
+
namesep = ' '; -- last/first separator is a space
−
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
+
elseif 'mla' == control.mode then
−
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
+
sep = ','; -- name-list separator between authors is a comma
−
 
+
namesep = ', ' -- last/first separator is <comma><space>
−
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
+
else
−
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
+
sep = ';' -- name-list separator between authors is a semicolon
−
 
+
namesep = ', ' -- last/first separator is <comma><space>
−
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
 
−
because the code editor gets confused between character insertion point and cursor position.
 
−
 
 
−
]]
 
−
 
 
−
local function is_good_vanc_name (last, first)
 
−
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
 
−
add_vanc_error ();
 
−
return false; -- not a string of latin characters; Vancouver required Romanization
 
−
end;
 
−
return true;
 
−
end
 
−
 
 
−
--[[--------------------------< 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-format=vanc. 
 
−
 
 
−
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
 
−
 
 
−
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
 
−
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 ().
 
−
 
 
−
]]
 
−
 
 
−
local function reduce_to_initials(first)
 
−
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
 
−
local initials = {}
 
−
local i = 0; -- counter for number of initials
 
−
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
 
−
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
 
−
i = i + 1; -- bump the counter
 
−
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
 
 
end
 
end
−
return table.concat(initials) -- Vancouver format does not include spaces.
+
−
end
+
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
−
 
 
−
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
 
−
 
 
−
Formats a list of people (e.g. authors / editors)
 
−
 
 
−
]]
 
−
 
 
−
local function list_people(control, people, etal)
 
−
local sep;
 
−
local namesep;
 
−
local format = control.format
 
−
local maximum = control.maximum
 
−
local lastauthoramp = control.lastauthoramp;
 
−
local text = {}
 
−
 
 
−
if 'vanc' == format then -- Vancouver-like author/editor name styling?
 
−
sep = ','; -- name-list separator between authors is a comma
 
−
namesep = ' '; -- last/first separator is a space
 
−
else
 
−
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
 
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
 
 
Line 1,452: Line 1,037:
 
one = person.last
 
one = person.last
 
local first = person.first
 
local first = person.first
−
if is_set(first) then  
+
if is_set(first) then
−
if ( "vanc" == format ) then -- if vancouver format
+
if 'mla' == control.mode then
−
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
+
if i == 1 then -- for mla
−
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
+
one = one .. namesep .. first; -- first name last, first
−
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
+
else -- all other names
 +
one = first .. ' ' .. one; -- first last
 +
end
 +
else
 +
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
 
end
 +
one = one .. namesep .. first;
 
end
 
end
−
one = one .. namesep .. first
 
 
end
 
end
 
if is_set(person.link) and person.link ~= control.page_name then
 
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
 
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
 
end
 
end
−
 
−
if is_set(person.link) and ((nil ~= person.link:find("//")) or (nil ~= person.link:find("[%[%]]"))) then
 
−
one = one .. " " .. set_error( 'bad_authorlink' ) end -- url or wikilink in author link;
 
 
end
 
end
 
table.insert( text, one )
 
table.insert( text, one )
Line 1,476: Line 1,066:
 
if count > 0 then  
 
if count > 0 then  
 
if count > 1 and is_set(lastauthoramp) and not etal then
 
if count > 1 and is_set(lastauthoramp) and not etal then
−
text[#text-2] = " & "; -- replace last separator with ampersand text
+
if 'mla' == control.mode then
 +
text[#text-2] = ", and "; -- replace last separator with ', and ' text
 +
else
 +
text[#text-2] = " & "; -- replace last separator with ampersand text
 +
end
 
end
 
end
 
text[#text] = nil; -- erase the last separator
 
text[#text] = nil; -- erase the last separator
Line 1,483: Line 1,077:
 
local result = table.concat(text) -- construct list
 
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
 
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.
+
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
 
end
 
end
 
 
Line 1,492: Line 1,086:
  
 
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.
 
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.
 +
 +
namelist is one of the contributor-, author-, or editor-name lists chosen in that order.  year is Year or anchor_year.
  
 
]]
 
]]
−
 
+
local function anchor_id (namelist, year)
−
local function anchor_id( options )
+
local names={}; -- a table for the one to four names and year
−
local id = table.concat( options ); -- concatenate names and year for CITEREF id
+
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
 
if is_set (id) then -- if concatenation is not an empty string
 
return "CITEREF" .. id; -- add the CITEREF portion
 
return "CITEREF" .. id; -- add the CITEREF portion
Line 1,503: Line 1,104:
 
end
 
end
 
end
 
end
 +
  
 
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
 
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
Line 1,517: Line 1,119:
  
 
if is_set (name) then -- name can be nil in which case just return
 
if is_set (name) then -- name can be nil in which case just return
−
local etal_pattern = "[;,]? *[\"']*%f[Ee][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
+
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
 
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
 
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
 
 
Line 1,535: Line 1,137:
 
end
 
end
 
return name, etal; --  
 
return name, etal; --  
 +
end
 +
 +
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
 +
 +
Evaluates the content of author and editor (surnames only) parameters for multiple names.  Multiple names are
 +
indicated if there is more than one comma and or semicolon.  If found, the function adds the multiple name
 +
(author or editor) maintenance category.
 +
 +
]]
 +
 +
local function name_has_mult_names (name, list_name)
 +
local count, _;
 +
if is_set (name) then
 +
if name:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, ignore
 +
name = name:match ('^%(%((.*)%)%)$'); -- strip parens
 +
else
 +
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
 +
 +
if 1 < count then -- param could be |author= or |editor= so one separactor character is acceptable
 +
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
 +
end
 +
end
 +
end
 +
return name; -- and done
 
end
 
end
  
Line 1,571: Line 1,197:
 
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], '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.
+
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
−
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
+
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
−
 
+
-- last = name_has_mult_names (last, err_msg_list_name); -- check for multiple names in last and its aliases
 +
last = name_has_mult_names (last, list_name); -- check for multiple names in last and its aliases
 +
 
if first and not last then -- if there is a firstn without a matching lastn
 
if first and not last then -- if there is a firstn without a matching lastn
 
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
 
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
Line 1,582: Line 1,210:
 
end
 
end
 
else -- we have last with or without a first
 
else -- we have last with or without a first
 +
link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup
 +
 
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
 
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
 
n = n + 1; -- point to next location in the names table
Line 1,595: Line 1,225:
 
end
 
end
  
−
-- Populates ID table from arguments using configuration settings
+
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
−
local function extract_ids( args )
+
 
−
local id_list = {};
+
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
−
for k, v in pairs( cfg.id_handlers ) do
+
 
−
v = select_one( args, v.parameters, 'redundant_parameters' );
+
Returns the language name and associated two- or three-character code.  Because case of the source may be incorrect
−
if is_set(v) then id_list[k] = v; end
+
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is
−
end
+
found, the Wikimedia version (assumed to be correct) is returned along with the code.  When there is no match, we
−
return id_list;
+
return the original language name string.
−
end
+
 
 +
mw.language.fetchLanguageNames(<local wiki language>, 'all') return 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'.
  
−
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
+
Names but 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.
  
−
Takes a table of IDs and turns it into a table of formatted ID outputs.
+
Adapted from code taken from Module:Check ISO 639-1.
  
 
]]
 
]]
  
−
local function build_id_list( id_list, options )
+
local function get_iso639_code (lang, this_wiki_code)
−
local new_list, handler = {};
+
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
−
 
+
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
−
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
+
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
 
 
−
for k, v in pairs( id_list ) do
+
for code, name in pairs(languages) do -- scan the list to see if we can find our language
−
-- fallback to read-only cfg
+
if langlc == mw.ustring.lower(name) then
−
handler = setmetatable( { ['id'] = v }, fallback(k) );
+
if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported
−
+
return name; -- so return the name but not the code
−
if handler.mode == 'external' then
 
−
table.insert( new_list, {handler.label, external_link_id( handler ) } );
 
−
elseif handler.mode == 'internal' then
 
−
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
 
−
elseif handler.mode ~= 'manual' then
 
−
error( cfg.messages['unknown_ID_mode'] );
 
−
elseif k == 'DOI' then
 
−
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
 
−
elseif k == 'ARXIV' then
 
−
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );  
 
−
elseif k == 'ASIN' then
 
−
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
 
−
elseif k == 'LCCN' then
 
−
table.insert( new_list, {handler.label, lccn( v ) } );
 
−
elseif k == 'OL' then
 
−
table.insert( new_list, {handler.label, openlibrary( v ) } );
 
−
elseif k == 'PMC' then
 
−
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
 
−
elseif k == 'PMID' then
 
−
table.insert( new_list, {handler.label, pmid( v ) } );
 
−
elseif k == 'ISMN' then
 
−
table.insert( new_list, {handler.label, ismn( v ) } );
 
−
elseif k == 'ISSN' then
 
−
table.insert( new_list, {handler.label, issn( v ) } );
 
−
elseif k == 'ISBN' then
 
−
local ISBN = internal_link_id( handler );
 
−
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
 
−
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
 
 
end
 
end
−
table.insert( new_list, {handler.label, ISBN } );
+
return name, code; -- found it, return name to ensure proper capitalization and the the code
−
elseif k == 'USENETID' then
 
−
table.insert( new_list, {handler.label, message_id( v ) } );
 
−
else
 
−
error( cfg.messages['unknown_manual_ID'] );
 
 
end
 
end
 
end
 
end
−
+
return lang; -- not valid language; return language in original case and nil for the code
−
function comp( a, b ) -- used in following table.sort()
 
−
return a[1] < b[1];
 
−
end
 
−
 
−
table.sort( new_list, comp );
 
−
for k, v in ipairs( new_list ) do
 
−
new_list[k] = v[2];
 
−
end
 
−
 
−
return new_list;
 
 
end
 
end
−
 
 
  
−
--[[--------------------------< C O I N S >--------------------------------------------------------------------
+
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
  
−
COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
+
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 bit 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.
  
 
]]
 
]]
  
−
local function COinS(data, class)
+
local function language_parameter (lang)
−
if 'table' ~= type(data) or nil == next(data) then
+
local code; -- the two- or three-character language code
−
return '';
+
local name; -- the language name
−
end
+
local language_list = {}; -- table of language names to be rendered
−
+
local names_table = {}; -- table made from the value assigned to |language=
−
local ctx_ver = "Z39.88-2004";
+
 
−
+
local this_wiki = mw.getContentLanguage(); -- get a language object for this wiki
−
-- treat table strictly as an array with only set values.
+
local this_wiki_code = this_wiki:getCode() -- get this wiki's language code
−
local OCinSoutput = setmetatable( {}, {
+
local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name
−
__newindex = function(self, key, value)
+
 
−
if is_set(value) then
+
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
−
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
+
 
−
end
+
for _, lang in ipairs (names_table) do -- reuse lang
 +
 
 +
if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag?
 +
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
 +
end
 +
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
 +
name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code
 
end
 
end
−
});
 
 
 
−
if in_array (class, {'citation', 'conference', 'interview', 'press release'}) and is_set(data.Periodical) then
+
if is_set (name) then -- if |language= specified a valid code
−
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
+
code = lang:lower(); -- save it
−
OCinSoutput["rft.genre"] = "article";
 
−
OCinSoutput["rft.jtitle"] = data.Periodical;
 
−
OCinSoutput["rft.atitle"] = data.Title;
 
−
elseif in_array (class, {'arxiv', 'journal', 'news'}) then
 
−
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
 
−
if 'arxiv' == class then
 
−
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
 
 
else
 
else
−
OCinSoutput["rft.genre"] = "article";
+
name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
 
end
 
end
−
OCinSoutput["rft.jtitle"] = data.Periodical;
 
−
OCinSoutput["rft.atitle"] = data.Title;
 
−
else
 
−
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
 
−
if is_set (data.Chapter) then
 
−
OCinSoutput["rft.genre"] = "bookitem";
 
−
OCinSoutput["rft.atitle"] = data.Chapter;
 
−
else
 
−
OCinSoutput["rft.genre"] = "book"
 
−
end
 
−
OCinSoutput["rft.btitle"] = data.Title;
 
−
end
 
−
 
−
OCinSoutput["rft.place"] = data.PublicationPlace;
 
−
OCinSoutput["rft.date"] = data.Date;
 
−
OCinSoutput["rft.series"] = data.Series;
 
−
OCinSoutput["rft.volume"] = data.Volume;
 
−
OCinSoutput["rft.issue"] = data.Issue;
 
−
OCinSoutput["rft.pages"] = data.Pages;
 
−
OCinSoutput["rft.edition"] = data.Edition;
 
−
OCinSoutput["rft.pub"] = data.PublisherName;
 
 
 
−
for k, v in pairs( data.ID_list ) do
+
if is_set (code) then -- only 2- or 3-character codes
−
local id, value = cfg.id_handlers[k].COinS;
+
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language
−
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
+
if 2 == code:len() then -- and is a two-character code
−
if string.sub( id or "", 1, 4 ) == 'info' then
+
add_prop_cat ('foreign_lang_source', {name, code}) -- categorize it
−
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
+
else -- or is a recognized language (but has a three-character code)
 +
add_prop_cat ('foreign_lang_source_2', {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
 +
end
 +
end
 
else
 
else
−
OCinSoutput[ id ] = value;
+
add_maint_cat ('unknown_lang'); -- add maint category if not already added
 
end
 
end
 +
 +
table.insert (language_list, name);
 +
name = ''; -- so we can reuse it
 
end
 
end
 
 
−
local last, first;
+
code = #language_list -- reuse code as number of languages in the list
−
for k, v in ipairs( data.Authors ) do
+
if 2 >= code then
−
last, first = v.last, v.first;
+
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
−
if k == 1 then -- for the first author name only
+
elseif 2 < code then
−
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
+
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
−
OCinSoutput["rft.aulast"] = last;
+
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
−
OCinSoutput["rft.aufirst"] = first;
+
end
−
elseif is_set(last) then
+
if this_wiki_name == name then
−
OCinSoutput["rft.au"] = last; -- otherwise use this form for the first name
+
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
−
end
 
−
else -- for all other authors
 
−
if is_set(last) and is_set(first) then
 
−
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
 
−
elseif is_set(last) then
 
−
OCinSoutput["rft.au"] = last;
 
−
end
 
−
end
 
 
end
 
end
−
 
+
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
−
OCinSoutput.rft_id = data.URL;
+
--[[ TODO: should only return blank or name rather than full list
−
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
+
so we can clean up the bunched parenthetical elements Language, Type, Format
−
OCinSoutput = setmetatable( OCinSoutput, nil );
+
]]
−
 
−
-- sort with version string always first, and combine.
 
−
table.sort( OCinSoutput );
 
−
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver );  -- such as "Z39.88-2004"
 
−
return table.concat(OCinSoutput, "&");
 
 
end
 
end
  
 +
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
  
−
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
+
Set style settings for CS1 citation templates. Returns separator and postscript settings
  
−
Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
+
]]
−
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
 
  
−
Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia
+
local function set_cs1_style (ps)
−
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
+
if not is_set (ps) then -- unless explicitely set to something
−
with the code.  When there is no match, we return the original language name string.
+
ps = '.'; -- terminate the rendered citation with a period
 +
end
 +
return '.', ps; -- separator is a full stop
 +
end
  
−
mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included
+
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
−
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.
+
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
  
 
]]
 
]]
  
−
local function get_iso639_code (lang)
+
local function set_cs2_style (ps, ref)
−
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
+
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
−
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
+
ps = ''; -- make sure it isn't nil
 +
end
 +
if not is_set (ref) then -- if |ref= is not set
 +
ref = "harv"; -- set default |ref=harv
 
end
 
end
−
+
return ',', ps, ref; -- separator is a comma
−
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
 
−
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
 
−
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
 
−
 
−
for code, name in pairs(languages) do -- scan the list to see if we can find our language
 
−
if langlc == mw.ustring.lower(name) then
 
−
if 2 ~= code:len() then -- ISO639-1 codes only
 
−
return name; -- so return the name but not the code
 
−
end
 
−
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
 
−
end
 
−
end
 
−
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
 
 
end
 
end
  
−
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
+
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
  
−
Get language name from ISO639-1 code value provided.  If a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
+
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
 +
rendered style.
  
−
There is an exception.  There are three ISO639-1 codes for Norewegian language variants.  There are two official variants: Norwegian Bokmål (code 'nb') and
+
]]
−
Norwegian Nynorsk (code 'nn').  The third, code 'no',  is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless.  However, it appears
 
−
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
+
local function get_settings_from_cite_class (ps, ref, cite_class)
−
return 'Norwegian' when editors use |language=no.  We presume that editors don't know about the variants or can't descriminate between them.
+
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
  
−
See Help talk:Citation Style_1#An ISO 639-1 language name test
+
return sep, ps, ref -- return them all
 +
end
  
−
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
+
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
−
the page is a mainspace page and the ISO639-1 code is not 'en'.  Similarly, if the  parameter is |language=Norwegian, it will be categorized in the same way.
 
  
−
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas.
+
Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
 +
config.CitationClass from the template's #invoke: to establish style.
  
 
]]
 
]]
  
−
local function language_parameter (lang)
+
local function set_style (mode, ps, ref, cite_class)
−
local code; -- the ISO639-1 two character code
+
local sep;
−
local name; -- the language name
+
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
−
local language_list = {}; -- table of language names to be rendered
+
sep, ps, ref = set_cs2_style (ps, ref);
−
local names_table = {}; -- table made from the value assigned to |language=
+
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
 +
sep, ps = set_cs1_style (ps);
 +
elseif 'mla' == mode then -- if this template is to be rendered in mla style use cs1 for bot cs1 & cs2 templates
 +
sep, ps = set_cs1_style (ps);
 +
else -- anything but cs1 or cs2
 +
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
 +
end
 +
if 'none' == ps:lower() then -- if assigned value is 'none' then
 +
ps = ''; -- set to empty string
 +
end
 +
 +
return sep, ps, ref
 +
end
 +
 
 +
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
 +
 
 +
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
 +
applying the pdf icon to external links.
 +
 
 +
returns true if file extension is one of the recognized extension, else false
  
−
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
+
]=]
  
−
for _, lang in ipairs (names_table) do -- reuse lang
+
local function is_pdf (url)
 +
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
 +
end
  
−
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
+
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
−
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
+
 
−
end
+
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
−
if is_set (name) then -- if Language specified a valid ISO639-1 code
+
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
−
code = lang:lower(); -- save it
+
the appropriate styling.
−
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
+
 
−
+
local function style_format (format, url, fmt_param, url_param)
−
if is_set (code) then
+
if is_set (format) then
−
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
+
format = wrap_style ('format', format); -- add leading space, parenthases, resize
−
if 'en' ~= code then -- English not the language
+
if not is_set (url) then
−
add_prop_cat ('foreign_lang_source', {name, code})
+
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
−
end
 
−
else
 
−
add_maint_cat ('unknown_lang'); -- add maint category if not already added
 
 
end
 
end
−
+
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
−
table.insert (language_list, name);
+
format = wrap_style ('format', 'PDF'); -- set format to pdf
−
name = ''; -- so we can reuse it
+
else
 +
format = ''; -- empty string for concatenation
 
end
 
end
−
+
return format;
−
code = #language_list -- reuse code as number of languages in the list
 
−
if 2 >= code then
 
−
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
 
−
elseif 2 < code then
 
−
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
 
−
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
 
−
end
 
−
if 'English' == name then
 
−
return ''; -- if one language and that language is English return an enpty string (no annotation)
 
−
end
 
−
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
 
 
end
 
end
  
−
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
+
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
  
−
Set style settings for CS1 citation templates. Returns separator and postscript settings
+
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.').
  
−
local function set_cs1_style (ps)
+
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the
−
if not is_set (ps) then -- unless explicitely set to something
+
number of authors in the list and set the 'etal' flag true.  This will cause the list_people() to display all of
−
ps = '.'; -- terminate the rendered citation with a period
+
the names in the name list followed by 'et al.'
−
end
 
−
return '.', ps; -- separator is a full stop
 
−
end
 
  
−
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
+
In all other cases, returns nil and the previous state of the 'etal' flag.
  
−
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
+
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 set_cs2_style (ps, ref)
+
local function get_display_authors_editors (max, count, list_name, etal)
−
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
+
if is_set (max) then
−
ps = ''; -- make sure it isn't nil
+
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
 +
add_maint_cat ('disp_auth_ed', cfg.special_case_translation [list_name]);
 +
end
 +
else -- not a valid keyword or number
 +
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
 +
max = nil; -- unset; as if |display-xxxxors= had not been set
 +
end
 
end
 
end
−
if not is_set (ref) then -- if |ref= is not set
+
−
ref = "harv"; -- set default |ref=harv
+
return max, etal;
−
end
 
−
return ',', ps, ref; -- separator is a comma
 
 
end
 
end
  
−
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
+
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
 +
 
 +
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
 +
abbreviation in the first characters of the parameter content.
  
−
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
+
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
−
rendered style.
+
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
 +
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
  
 
]]
 
]]
  
−
local function get_settings_from_cite_class (ps, ref, cite_class)
+
local function extra_text_in_page_check (page)
−
local sep;
+
-- local good_pattern = '^P[^%.P%l]';
−
if (cite_class == "citation") then -- for citation templates (CS2)
+
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?
−
sep, ps, ref = set_cs2_style (ps, ref);
+
-- local bad_pattern = '^[Pp][Pp]';
−
else -- not a citation template so CS1
+
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
−
sep, ps = set_cs1_style (ps);
+
 
 +
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
 +
add_maint_cat ('extra_text');
 
end
 
end
 +
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
 +
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
 +
-- add_maint_cat ('extra_text');
 +
-- end
 +
end
 +
 +
--[[--------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
  
−
return sep, ps, ref -- return them all
+
split apart a |vautthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
−
end
+
parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the
 +
rendered citation and in the metadata.
  
−
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
+
|vauthors=Jones AB, White EB, ((Black, Brown, and Co.))
  
−
Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
+
This code is experimental and may not be retained.
−
config.CitationClass from the template's #invoke: to establish style.
 
  
 
]]
 
]]
−
 
+
local function get_v_name_table (vparam, output_table)
−
local function set_style (mode, ps, ref, cite_class)
+
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
−
local sep;
+
−
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
+
local i = 1;
−
sep, ps, ref = set_cs2_style (ps, ref);
 
−
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
 
−
sep, ps = set_cs1_style (ps);
 
−
else -- anything but cs1 or cs2
 
−
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
 
−
end
 
−
if 'none' == ps:lower() then -- if assigned value is 'none' then
 
−
ps = ''; -- set to empty string
 
−
end
 
 
 
−
return sep, ps, ref
+
while name_table[i] do
 +
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens
 +
local name = name_table[i];
 +
i=i+1; -- bump indexer to next segment
 +
while name_table[i] do
 +
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
 +
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens
 +
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
 +
else
 +
table.insert (output_table, name_table[i]); -- add this name
 +
end
 +
i = i+1;
 +
end
 +
return output_table;
 
end
 
end
  
−
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
+
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
  
−
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
+
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
−
applying the pdf icon to external links.
+
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
  
−
returns true if file extension is one of the recognized extension, else false
+
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
 +
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
 +
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
  
−
]=]
+
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
  
−
local function is_pdf (url)
+
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
−
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
+
local function parse_vauthors_veditors (args, vparam, list_name)
−
not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
+
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
−
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
+
local v_name_table = {};
−
the appropriate styling.
+
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)
−
 
+
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
−
local function style_format (format, url, fmt_param, url_param)
+
add_vanc_error ('wikilink');
−
if is_set (format) then
 
−
format = wrap_style ('format', format); -- add leading space, parenthases, resize
 
−
if not is_set (url) then
 
−
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
 
−
end
 
−
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;
+
v_name_table = get_v_name_table (vparam, v_name_table); -- names are separated by commas
−
end
+
 
 +
for i, v_name in ipairs(v_name_table) do
 +
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
 +
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
 +
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
 +
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 ('punctuation');
 +
end
 +
local lastfirstTable = {}
 +
lastfirstTable = mw.text.split(v_name, "%s")
 +
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
 +
if is_suffix (first) then -- if a valid suffix
 +
suffix = first -- save it as a suffix and
 +
first = table.remove(lastfirstTable); -- get what should be the initials from the table
 +
end -- no suffix error message here because letter combination may be result of Romanization; check for digits?
 +
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+') then
 +
add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing
 +
end
 +
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
 +
add_vanc_error ('name'); -- matches a space between two intiials
 +
end
 +
else
 +
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
 +
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
 +
end
 +
 +
if is_set (first) then
 +
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
 +
add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
 +
end
 +
is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit
 +
if is_set (suffix) then
 +
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
 +
suffix = ''; -- unset so we don't add this suffix to all subsequent names
 +
end
 +
else
 +
if not corporate then
 +
is_good_vanc_name (last, '');
 +
end
 +
end
 +
-- this from extract_names ()
 +
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
 +
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 +
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
 +
end
 +
return names, etal; -- all done, return our list of names
 +
end
  
−
--[[--------------------------< 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.
+
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
  
−
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
+
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
−
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
+
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
−
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
+
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
−
number of authors in the list and set the 'etal' flag true.  This will cause the list_people() to display all of
+
similarly, |editorn= (and aliases) highest and |editors= lowest
−
the names in the name list followed by 'et al.'
 
  
−
In all other cases, returns nil and the previous state of the 'etal' flag.
+
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.
  
−
local function get_display_authors_editors (max, count, list_name, etal)
+
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
−
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
 
−
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 and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
 
−
add_maint_cat ('disp_auth_ed', list_name);
 
−
end
 
−
else -- not a valid keyword or number
 
−
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
 
−
max = nil; -- unset
 
−
end
 
−
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
 
−
max = count + 1; -- number of authors + 1
 
−
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 page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
 
−
abbreviation in the first characters of the parameter content.
 
−
 
 
−
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
 
−
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
 
−
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
 
  
 
]]
 
]]
  
−
local function extra_text_in_page_check (page, nopp)
+
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
−
-- local good_pattern = '^P[^%.P%l]';
+
local lastfirst = false;
−
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
+
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a |first1= without a |last1=; this ...
−
-- local bad_pattern = '^[Pp][Pp]';
+
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
−
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
+
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
−
 
+
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
−
if is_set (nopp) then -- don't bother checking if |nopp= is set
+
lastfirst=true;
−
return;
 
 
end
 
end
  
−
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
+
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
−
add_maint_cat ('extra_text');
+
(is_set (vxxxxors) and is_set (xxxxors)) or
 +
(true == lastfirst and is_set (xxxxors)) then
 +
local err_name;
 +
if 'AuthorList' == list_name then -- figure out which name should be used in error message
 +
err_name = 'author';
 +
else
 +
err_name = 'editor';
 +
end
 +
table.insert( z.message_tail, { set_error( 'redundant_parameters',
 +
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
 
end
 
end
−
-- 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
+
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
−
-- add_maint_cat ('extra_text');
+
if is_set (vxxxxors) then return 2 end;
−
-- end
+
if is_set (xxxxors) then return 3 end;
 +
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
 
end
 
end
  
  
−
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
+
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
  
−
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
+
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
−
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
+
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
−
 
+
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
−
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
+
true; else, emits an error message and returns false.
−
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
 
−
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
 
−
 
 
−
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
 
  
 
]]
 
]]
  
−
local function parse_vauthors_veditors (args, vparam, list_name)
+
local function is_valid_parameter_value (value, name, possible, cite_class)
−
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
+
-- begin hack to limit |mode=mla to a specific set of templates
−
local v_name_table = {};
+
if ('mode' == name) and ('mla' == value) and not in_array (cite_class, {'book', 'journal', 'news'}) then
−
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
+
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
−
local last, first, link, mask;
+
return false
−
local corporate = false;
 
−
 
 
−
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
 
−
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
 
−
add_vanc_error ();
 
 
end
 
end
−
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
+
-- end hack
  
−
for i, v_name in ipairs(v_name_table) do
+
if not is_set (value) then
−
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
+
return true; -- an empty parameter is ok
−
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
+
elseif in_array(value:lower(), possible) then
−
last = v_name:match ('^%(%((.+)%)%)$')
+
return true;
−
corporate = true;
+
else
−
elseif string.find(v_name, "%s") then
+
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
−
    lastfirstTable = {}
+
return false
−
    lastfirstTable = mw.text.split(v_name, "%s")
 
−
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
 
−
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
 
−
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
 
−
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
 
−
end
 
−
else
 
−
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
 
−
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
 
−
end
 
−
 
−
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
 
−
add_vanc_error ();
 
−
end
 
−
-- this from extract_names ()
 
−
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
 
−
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 
−
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
 
 
end
 
end
−
return names, etal; -- all done, return our list of names
 
 
end
 
end
  
−
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
 
  
−
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
+
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
−
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
+
 
 +
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.
 +
 
 +
]]
  
−
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
+
local function terminate_name_list (name_list, sepc)
−
similarly, |editorn= (and aliases) highest and |editors= lowest
+
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
 +
return name_list .. " "; -- don't add another
 +
else
 +
return name_list .. sepc .. ' '; -- otherwise terninate the name list
 +
end
 +
end
  
−
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.
+
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
  
−
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
+
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, mode)
 +
if not is_set (volume) and not is_set (issue) then
 +
return '';
 +
end
 +
 +
if ('mla' == mode) and ('journal' == cite_class) then -- same as cs1 for magazines
 +
lower = true; -- mla 8th edition; force these to lower case
 +
if is_set (volume) and is_set (issue) then
 +
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
 +
elseif is_set (volume) then
 +
return wrap_msg ('vol', {sepc, volume}, lower);
 +
else
 +
return '';
 +
end
 +
end
  
−
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
+
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
−
local lastfirst = false;
+
if is_set (volume) and is_set (issue) then
−
if select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', 1 ) or -- do this twice incase we have a first 1 without a last1
+
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
−
select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', 2 ) then
+
elseif is_set (volume) then
−
lastfirst=true;
+
return wrap_msg ('vol', {sepc, volume}, lower);
 +
else
 +
return wrap_msg ('issue', {sepc, issue}, lower);
 +
end
 
end
 
end
  
−
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
+
local vol = '';
−
(is_set (vxxxxors) and is_set (xxxxors)) or
+
−
(true == lastfirst and is_set (xxxxors)) then
+
if is_set (volume) then
−
local err_name;
+
if (4 < mw.ustring.len(volume)) then
−
if 'AuthorList' == list_name then -- figure out which name should be used in error message
+
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
−
err_name = 'author';
+
else
−
else
+
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)});
−
err_name = 'editor';
+
end
−
end
+
end
−
table.insert( z.message_tail, { set_error( 'redundant_parameters',
+
if is_set (issue) then
−
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
+
return vol .. substitute (cfg.messages['j-issue'], issue);
 
end
 
end
 +
return vol;
 +
end
  
−
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
 
−
if is_set (vxxxxors) then return 2 end;
 
−
if is_set (xxxxors) then return 3 end;
 
−
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
 
−
end
 
  
 +
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
  
−
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
+
not currently used
  
−
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
+
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
−
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
+
returns list unchanged if there are no commas else strips whitespace and then reformats the list
−
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
 
−
true; else, emits an error message and returns false.
 
  
 +
]]
 +
--[[
 +
local function normalize_page_list (list)
 +
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
 +
 +
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
 +
list = table.concat (list, ', '); -- and now make a normalized list
 +
return list;
 +
end
 
]]
 
]]
  
−
local function is_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
 
  
 +
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
  
−
--[[--------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
+
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
  
−
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
+
Singular has priority over plural when both are provided.
−
characters following the opening bracket obey the rules of a uri scheme (see check_url()).  The test will also find
 
−
external wikilinks that use protocol relative urls.
 
  
 
]]
 
]]
  
−
local function is_parameter_ext_wikilink (value)
+
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower, mode)
−
if value:match ("%[%[%a+:") then -- if a wikilink with namespace
+
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
−
return false;
+
if is_set (sheet) then
−
elseif value:match ("%[%a[%a%d%+%.%-]*:.*%]") or value:match ("%[//.*%]") then -- does the param value contain an external wikilink?
+
if 'journal' == origin then
−
return true;
+
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
−
else
+
else
−
return false;
+
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
−
end
 
  
 +
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
 +
 +
if is_journal and 'mla' == mode then
 +
is_journal = false; -- mla always uses p & pp
 +
end
  
−
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
+
if is_set (page) then
−
 
+
if is_journal then
−
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
+
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
−
 
+
elseif not nopp then
−
]]
+
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
−
 
+
else
−
local function check_for_url (parameter_list)
+
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
−
local error_message = '';
+
end
−
for k, v in pairs (parameter_list) do -- for each parameter in the list
+
elseif is_set(pages) then
−
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
+
if is_journal then
−
if is_set(error_message) then -- once we've added the first portion of the error message ...
+
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
−
error_message=error_message .. ", "; -- ... add a comma space separator
+
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
−
end
+
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
−
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
+
elseif not nopp then
 +
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
 +
else
 +
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
 
end
 
end
 
end
 
end
−
if is_set (error_message) then -- done looping, if there is an error message, display it
+
−
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
+
return '', '', '', ''; -- return empty strings
−
end
 
 
end
 
end
  
  
−
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
+
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
  
−
This is the main function doing the majority of the citation formatting.
+
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.
  
−
local function citation0( config, args)
+
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:
−
Load Input Parameters
+
|archive-url= holds an archive.org save command url
−
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
+
|archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
−
]]
+
correct place
−
local A = argument_wrapper( args );
+
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 funct 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 i
+
]=]
−
local PPrefix = A['PPrefix']
 
−
local PPPrefix = A['PPPrefix']
 
−
local NoPP = A['NoPP']
 
−
if is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
 
−
PPPrefix = ''; -- unset these, prefix if used is in |page= or |pages=
 
−
PPrefix = '';
 
−
else
 
−
NoPP = nil; -- unset, used as a flag later
 
−
end
 
−
 
−
-- Pick out the relevant fields from the arguments.  Different citation templates
 
−
-- define different field names for the same underlying things.
 
−
local author_etal;
 
−
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
 
−
local Authors;
 
−
local NameListFormat = A['NameListFormat'];
 
  
−
do -- to limit scope of selected
+
local function archive_url_check (url, date)
−
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
+
local err_msg = ''; -- start with the error message empty
−
if 1 == selected then
+
local path, timestamp, flag; -- portions of the archive.or url
−
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
+
−
elseif 2 == selected then
+
if not url:match('//web%.archive%.org/') then
−
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
+
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
−
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
 
−
elseif 3 == selected then
 
−
Authors = A['Authors']; -- use content of |authors=
 
−
end
 
 
end
 
end
  
−
local Coauthors = A['Coauthors'];
+
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page
−
local Others = A['Others'];
+
err_msg = 'save command';
 +
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
 +
else
 +
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
 +
 +
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
 +
err_msg = '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 is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
 +
err_msg = 'path';
 +
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
 +
err_msg = 'flag';
 +
elseif 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 = 'flag';
 +
else
 +
return url, date; -- return archiveURL and ArchiveDate
 +
end
 +
end
 +
-- if here, something not right so
 +
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
 +
if 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
 +
 
 +
 
 +
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
  
−
local editor_etal;
+
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
−
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
+
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
−
local Editors;
+
parameter that is missing its pipe:
 +
{{cite ... |title=Title access-date=2016-03-17}}
  
−
do -- to limit scope of selected
+
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc.  To prevent false positives xml/html
−
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
+
tags are removed before the search.
−
if 1 == selected then
 
−
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
 
−
elseif 2 == selected then
 
−
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
 
−
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
 
−
elseif 3 == selected then
 
−
Editors = A['Editors']; -- use content of |editors=
 
−
end
 
−
end
 
  
−
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
+
If a missing pipe is detected, this function adds the missing pipe maintenance category.
−
local Translators; -- assembled trnaslators name list
 
−
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 
−
 
−
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
 
−
NameListFormat = ''; -- anything else, set to empty string
 
−
end
 
  
−
local Year = A['Year'];
+
]]
−
local PublicationDate = A['PublicationDate'];
 
−
local OrigYear = A['OrigYear'];
 
−
local Date = A['Date'];
 
−
local LayDate = A['LayDate'];
 
−
------------------------------------------------- Get title data
 
−
local Title = A['Title'];
 
−
local ScriptTitle = A['ScriptTitle'];
 
−
local BookTitle = A['BookTitle'];
 
−
local Conference = A['Conference'];
 
−
local TransTitle = A['TransTitle'];
 
−
local TitleNote = A['TitleNote'];
 
−
local TitleLink = A['TitleLink'];
 
−
local Chapter = A['Chapter'];
 
−
local ScriptChapter = A['ScriptChapter'];
 
−
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
 
−
local TransChapter = A['TransChapter'];
 
−
local TitleType = A['TitleType'];
 
−
local Degree = A['Degree'];
 
−
local Docket = A['Docket'];
 
−
local ArchiveFormat = A['ArchiveFormat'];
 
−
local ArchiveURL = A['ArchiveURL'];
 
−
local URL = A['URL']
 
−
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
 
−
local ChapterURL = A['ChapterURL'];
 
−
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
 
−
local ConferenceFormat = A['ConferenceFormat'];
 
−
local ConferenceURL = A['ConferenceURL'];
 
−
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
 
−
local Periodical = A['Periodical'];
 
  
−
local Series = A['Series'];
+
local function missing_pipe_check (value)
−
local Volume = A['Volume'];
+
local capture;
−
local Issue = A['Issue'];
+
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
−
local Position = '';
 
−
local Page = A['Page'];
 
−
local Pages = hyphen_to_dash( A['Pages'] );
 
−
local At = A['At'];
 
  
−
local Edition = A['Edition'];
+
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
−
local PublicationPlace = A['PublicationPlace']
+
if capture and validate (capture) then -- if the capture is a valid parameter name
−
local Place = A['Place'];
+
add_maint_cat ('missing_pipe');
−
+
end
−
local PublisherName = A['PublisherName'];
+
end
−
local RegistrationRequired = A['RegistrationRequired'];
 
−
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
 
−
registration=nil;
 
−
end
 
−
local SubscriptionRequired = A['SubscriptionRequired'];
 
−
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
 
−
subscription=nil;
 
−
end
 
  
−
local Via = A['Via'];
 
−
local AccessDate = A['AccessDate'];
 
−
local ArchiveDate = A['ArchiveDate'];
 
−
local Agency = A['Agency'];
 
−
local DeadURL = A['DeadURL']
 
−
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
 
−
DeadURL = ''; -- anything else, set to empty string
 
−
end
 
  
−
local Language = A['Language'];
+
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
−
local Format = A['Format'];
 
−
local ChapterFormat = A['ChapterFormat'];
 
−
local DoiBroken = A['DoiBroken'];
 
−
local ID = A['ID'];
 
−
local ASINTLD = A['ASINTLD'];
 
−
local IgnoreISBN = A['IgnoreISBN'];
 
−
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
 
−
IgnoreISBN = nil; -- anything else, set to empty string
 
−
end
 
−
local Embargo = A['Embargo'];
 
−
local Class = A['Class']; -- arxiv class identifier
 
  
−
local ID_list = extract_ids( args );
+
This is the main function doing the majority of the citation formatting.
  
−
local Quote = A['Quote'];
+
]]
  
−
local LayFormat = A['LayFormat'];
+
local function citation0( config, args)
−
local LayURL = A['LayURL'];
+
--[[  
−
local LaySource = A['LaySource'];
+
Load Input Parameters
−
local Transcript = A['Transcript'];
+
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
−
local TranscriptFormat = A['TranscriptFormat'];
+
]]
−
local TranscriptURL = A['TranscriptURL']
+
local A = argument_wrapper( args );
−
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
+
local i
  
−
local LastAuthorAmp = A['LastAuthorAmp'];
+
-- Pick out the relevant fields from the arguments. Different citation templates
−
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
+
-- define different field names for the same underlying things.
−
LastAuthorAmp = nil; -- set to empty string
 
−
end
 
−
local no_tracking_cats = A['NoTracking'];
 
−
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
 
−
no_tracking_cats = nil; -- set to empty string
 
−
end
 
−
 
 
−
--these are used by cite interview
 
−
local Callsign = A['Callsign'];
 
−
local City = A['City'];
 
−
local Program = A['Program'];
 
−
 
 
−
--local variables that are not cs1 parameters
 
−
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; -- used in the COinS metadata
 
  
 
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
 
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
 
local Mode = A['Mode'];
 
local Mode = A['Mode'];
−
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
+
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode'], config.CitationClass) then
 
Mode = '';
 
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
+
local author_etal;
−
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
+
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
−
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
+
local Authors;
−
no_tracking_cats = "true"; -- set no_tracking_cats
+
local NameListFormat = A['NameListFormat'];
 +
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
 +
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
 +
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
 +
elseif 3 == selected then
 +
Authors = A['Authors']; -- use content of |authors=
 +
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
 +
add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
 +
end
 
end
 
end
−
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
+
if is_set (Collaboration) then
−
if this_page.text:match (v) then -- test page name against each pattern
+
author_etal = true; -- so that |display-authors=etal not required
−
no_tracking_cats = "true"; -- set no_tracking_cats
 
−
break; -- bail out if one is found
 
−
end
 
 
end
 
end
 
end
 
end
  
−
-- check for extra |page=, |pages= or |at= parameters.
+
local Coauthors = A['Coauthors'];
−
if is_set(Page) then
+
local Others = A['Others'];
−
if is_set(Pages) or is_set(At) then
 
−
Page = Page .. " " .. set_error('extra_pages'); -- add error message
 
−
Pages = ''; -- unset the others
 
−
At = '';
 
−
end
 
−
extra_text_in_page_check (Page, NoPP); -- 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
 
−
Pages = Pages .. " " .. set_error('extra_pages'); -- add error messages
 
−
At = ''; -- unset
 
−
end
 
−
extra_text_in_page_check (Pages, NoPP); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
 
−
end
 
  
−
-- both |publication-place= and |place= (|location=) allowed if different
+
local editor_etal;
−
if not is_set(PublicationPlace) and is_set(Place) then
+
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
−
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
+
local Editors;
 +
 
 +
do -- to limit scope of selected
 +
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
 +
if 1 == selected then
 +
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
 +
elseif 2 == selected then
 +
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
 +
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
 +
elseif 3 == selected then
 +
Editors = A['Editors']; -- use content of |editors=
 +
add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged
 +
end
 
end
 
end
 +
 +
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
 +
local Translators; -- assembled translators name list
 +
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 
 
−
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
+
local Interviewers = A['Interviewers']
 
 
−
--[[
+
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
−
Parameter remapping for cite encyclopedia:
+
local Contributors; -- assembled contributors name list
−
When the citation has these parameters:
+
local Contribution = A['Contribution'];
−
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
+
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
−
|encyclopedia and |article then map |encyclopedia to |title
+
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
−
|encyclopedia then map |encyclopedia to |title
+
 +
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
  
−
|trans_title maps to |trans_chapter when |title is re-mapped
+
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
−
|url maps to |chapterurl when |title is remapped
+
NameListFormat = ''; -- anything else, set to empty string
 +
end
  
−
All other combinations of |encyclopedia, |title, and |article are not modified
+
local Year = A['Year'];
 +
local PublicationDate = A['PublicationDate'];
 +
local OrigYear = A['OrigYear'];
 +
local Date = A['Date'];
 +
local LayDate = A['LayDate'];
 +
------------------------------------------------- Get title data
 +
local Title = A['Title'];
 +
local ScriptTitle = A['ScriptTitle'];
 +
local BookTitle = A['BookTitle'];
 +
local Conference = A['Conference'];
 +
local TransTitle = A['TransTitle'];
 +
local TitleNote = A['TitleNote'];
 +
local TitleLink = A['TitleLink'];
 +
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
  
−
]]
+
local Chapter = A['Chapter'];
 +
local ScriptChapter = A['ScriptChapter'];
 +
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
 +
local TransChapter = A['TransChapter'];
 +
local TitleType = A['TitleType'];
 +
local Degree = A['Degree'];
 +
local Docket = A['Docket'];
 +
local ArchiveFormat = A['ArchiveFormat'];
  
−
local Encyclopedia = A['Encyclopedia'];
+
local ArchiveDate;
 +
local ArchiveURL;
  
−
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
+
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
−
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
+
−
if is_set(Title) or is_set (ScriptTitle) then
+
local DeadURL = A['DeadURL']
−
if not is_set(Chapter) then
+
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
−
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
+
DeadURL = ''; -- anything else, set to empty string
−
ScriptChapter = ScriptTitle;
 
−
TransChapter = TransTitle;
 
−
ChapterURL = URL;
 
−
if not is_set (ChapterURL) and is_set (TitleLink) then
 
−
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
 
−
end
 
−
Title = Periodical;
 
−
ChapterFormat = Format;
 
−
Periodical = ''; -- redundant so unset
 
−
TransTitle = '';
 
−
URL = '';
 
−
Format = '';
 
−
TitleLink = '';
 
−
ScriptTitle = '';
 
−
end
 
−
else -- |title not set
 
−
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
 
−
Periodical = ''; -- redundant so unset
 
−
end
 
 
end
 
end
−
end
 
  
−
-- Special case for cite techreport.
+
local URL = A['URL']
−
if (config.CitationClass == "techreport") then -- special case for cite techreport
+
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
−
if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue'
+
local ChapterURL = A['ChapterURL'];
−
if not is_set(ID) then -- can we use ID for the "number"?
+
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
−
ID = Issue; -- yes, use it
+
local ConferenceFormat = A['ConferenceFormat'];
−
Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
+
local ConferenceURL = A['ConferenceURL'];
−
else -- can't use ID so emit error message
+
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
−
ID = ID .. " " .. set_error('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
+
local Periodical = A['Periodical'];
−
end
+
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
−
end
+
 
−
end
+
local Series = A['Series'];
−
 
+
−
-- special case for cite interview
+
local Volume;
−
if (config.CitationClass == "interview") then
+
local Issue;
−
if is_set(Program) then
+
local Page;
−
ID = ' ' .. Program;
+
local Pages;
 +
local At;
 +
-- previously conference books did not support volume
 +
-- if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
 +
if in_array (config.CitationClass, cfg.templates_using_volume) then
 +
Volume = A['Volume'];
 +
end
 +
-- conference & map books do not support issue
 +
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
 +
Issue = A['Issue'];
 +
end
 +
local Position = '';
 +
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
 +
Page = A['Page'];
 +
Pages = hyphen_to_dash( A['Pages'] );
 +
At = A['At'];
 +
end
 +
 
 +
local Edition = A['Edition'];
 +
local PublicationPlace = A['PublicationPlace']
 +
local Place = A['Place'];
 +
 +
local PublisherName = A['PublisherName'];
 +
local RegistrationRequired = A['RegistrationRequired'];
 +
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
 +
RegistrationRequired=nil;
 +
end
 +
local SubscriptionRequired = A['SubscriptionRequired'];
 +
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
 +
SubscriptionRequired=nil;
 
end
 
end
−
if is_set(Callsign) then
+
local UrlAccess = A['UrlAccess'];
−
if is_set(ID) then
+
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
−
ID = ID .. sepc .. ' ' .. Callsign;
+
UrlAccess = nil;
−
else
 
−
ID = ' ' .. Callsign;
 
−
end
 
 
end
 
end
−
if is_set(City) then
+
if not is_set(URL) and is_set(UrlAccess) then
−
if is_set(ID) then
+
UrlAccess = nil;
−
ID = ID .. sepc .. ' ' .. City;
+
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } );
−
else
 
−
ID = ' ' .. City;
 
−
end
 
 
end
 
end
  
−
if is_set(Others) then
+
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set
−
if is_set(TitleType) then
+
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message
−
Others = ' ' .. TitleType .. ' with ' .. Others;
+
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription=
−
TitleType = '';
+
end
−
else
+
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set
−
Others = ' ' .. 'Interview with ' .. Others;
+
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message
−
end
+
RegistrationRequired = nil; -- unset; prefer |access= over |registration=
−
else
 
−
Others = '(Interview)';
 
 
end
 
end
−
end
 
  
−
-- special case for cite mailing list
 
−
if (config.CitationClass == "mailinglist") then
 
−
Periodical = A ['MailingList'];
 
−
end
 
  
−
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
+
local Via = A['Via'];
−
if 'conference' == config.CitationClass then
+
local AccessDate = A['AccessDate'];
−
if is_set(BookTitle) then
+
local Agency = A['Agency'];
−
Chapter = Title;
 
−
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
 
−
ChapterURL = URL;
 
−
ChapterURLorigin = URLorigin;
 
−
URLorigin = '';
 
−
ChapterFormat = Format;
 
−
TransChapter = TransTitle;
 
−
Title = BookTitle;
 
−
Format = '';
 
−
-- TitleLink = '';
 
−
TransTitle = '';
 
−
URL = '';
 
−
end
 
−
elseif 'speech' ~= config.CitationClass then
 
−
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
 
−
end
 
  
−
-- cite map oddities
+
local Language = A['Language'];
−
local Cartography = "";
+
local Format = A['Format'];
−
local Scale = "";
+
local ChapterFormat = A['ChapterFormat'];
−
local Sheet = A['Sheet'] or '';
+
local DoiBroken = A['DoiBroken'];
−
local Sheets = A['Sheets'] or '';
+
local ID = A['ID'];
−
if config.CitationClass == "map" then
+
local ASINTLD = A['ASINTLD'];
−
Chapter = A['Map'];
+
local IgnoreISBN = A['IgnoreISBN'];
−
ChapterURL = A['MapURL'];
+
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
−
TransChapter = A['TransMap'];
+
IgnoreISBN = nil; -- anything else, set to empty string
−
ChapterURLorigin = A:ORIGIN('MapURL');
 
−
ChapterFormat = A['MapFormat'];
 
−
 
−
Cartography = A['Cartography'];
 
−
if is_set( Cartography ) then
 
−
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
 
−
end
 
−
Scale = A['Scale'];
 
−
if is_set( Scale ) then
 
−
Scale = sepc .. " " .. Scale;
 
 
end
 
end
−
end
+
local Embargo = A['Embargo'];
 +
local Class = A['Class']; -- arxiv class identifier
 +
 
 +
local ID_list = extract_ids( args );
 +
local ID_access_levels = extract_id_access_levels( args, ID_list );
  
−
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
+
local Quote = A['Quote'];
−
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
 
−
local AirDate = A['AirDate'];
 
−
local SeriesLink = A['SeriesLink'];
 
−
local Network = A['Network'];
 
−
local Station = A['Station'];
 
−
local s, n = {}, {};
 
  
−
-- do common parameters first
+
local LayFormat = A['LayFormat'];
−
if is_set(Network) then table.insert(n, Network); end
+
local LayURL = A['LayURL'];
−
if is_set(Station) then table.insert(n, Station); end
+
local LaySource = A['LaySource'];
−
ID = table.concat(n, sepc .. ' ');
+
local Transcript = A['Transcript'];
−
+
local TranscriptFormat = A['TranscriptFormat'];
−
if not is_set (Date) then -- promote airdate or Began/Ended to date
+
local TranscriptURL = A['TranscriptURL']
−
if is_set (AirDate) then
+
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
−
Date = AirDate;
+
 
−
end
+
local LastAuthorAmp = A['LastAuthorAmp'];
 +
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
 +
LastAuthorAmp = nil; -- set to empty string
 +
end
 +
if 'mla' == Mode then
 +
LastAuthorAmp = 'yes'; -- replaces last author/editor separator with ' and ' text
 +
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
  
−
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
+
--these deprecated parameters are used by cite interview
−
local Season = A['Season'];
+
local Callsign = A['Callsign'];
−
local SeriesNumber = A['SeriesNumber'];
+
local City = A['City'];
 +
local Program = A['Program'];
 +
 
 +
--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
 +
 
 +
local DF = A['DF']; -- date format set in cs1|2 template
 +
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
 +
DF = ''; -- not valid, set to empty string
 +
end
  
−
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
+
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
−
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
+
local PostScript;
−
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
+
local Ref;
−
end
+
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
−
-- assemble a table of parts concatenated later into Series
+
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
−
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
+
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
−
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
+
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
−
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
+
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
−
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
+
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
−
URL = ''; -- unset
+
end
−
TransTitle = '';
 
−
ScriptTitle = '';
 
−
 
−
else -- now oddities that are cite serial
 
−
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
 
−
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
 
−
if is_set (Series) and is_set (SeriesLink) then
 
−
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
 
−
end
 
−
Series = wrap_style ('italic-title', Series); -- series is italicized
 
−
end
 
 
end
 
end
−
-- end of {{cite episode}} stuff
 
  
−
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
+
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
−
if 'arxiv' == config.CitationClass then
+
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
−
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
+
 
−
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
+
local NoPP = A['NoPP']  
−
elseif is_set (Series) then -- series is an alias of version
+
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
−
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
+
NoPP = true;
−
Series = ''; -- unset
+
else
−
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
+
NoPP = nil; -- unset, used as a flag later
−
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']) 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 is_set(Page) then
−
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
+
if is_set(Pages) or is_set(At) then
−
Chapter = '';
+
Pages = ''; -- unset the others
−
URL = '';
+
At = '';
−
Format = '';
+
end
−
Page = ''; Pages = ''; At = '';
+
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
 
end
−
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
+
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
−
end
+
end
  
−
-- handle type parameter for those CS1 citations that have default values
+
-- both |publication-place= and |place= (|location=) allowed if different
−
 
+
if not is_set(PublicationPlace) and is_set(Place) then
−
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
+
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
−
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
 +
 +
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
 +
 +
--[[
 +
Parameter remapping for cite encyclopedia:
 +
When the citation has these parameters:
 +
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
 +
|encyclopedia and |article then map |encyclopedia to |title
 +
|encyclopedia then map |encyclopedia to |title
  
−
if is_set(TitleType) then -- if type parameter is specified
+
|trans_title maps to |trans_chapter when |title is re-mapped
−
TitleType = " (" .. TitleType .. ")"; -- display it in parentheses
+
|url maps to |chapterurl when |title is remapped
−
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.
+
All other combinations of |encyclopedia, |title, and |article are not modified
−
if not is_set (Date) then
 
−
Date = Year; -- promote Year to Date
 
−
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
 
−
if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
 
−
Date = PublicationDate; -- promote PublicationDate to Date
 
−
PublicationDate = ''; -- unset, no longer needed
 
−
end
 
−
end
 
  
−
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
 
−
 
−
--[[
 
−
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
 
−
we get the date used in the metadata.
 
−
 
−
Date validation supporting code is in Module:Citation/CS1/Date_validation
 
 
]]
 
]]
−
do -- create defined block to contain local variables error_message and mismatch
 
−
local error_message = '';
 
−
-- AirDate has been promoted to Date so not necessary to check it
 
−
anchor_year, COinS_date, 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});
 
  
−
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
+
local Encyclopedia = A['Encyclopedia'];
−
local mismatch = year_date_check (Year, Date)
 
−
if 0 == mismatch then -- |year= does not match a year-value in |date=
 
−
if is_set (error_message) then -- if there is already an error message
 
−
error_message = error_message .. ', '; -- tack on this additional message
 
−
end
 
−
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
 
−
elseif 1 == mismatch then -- |year= matches year-value in |date=
 
−
add_maint_cat ('date_year');
 
−
end
 
−
end
 
  
−
if is_set(error_message) then
+
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
−
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
+
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
−
end
+
if is_set(Title) or is_set (ScriptTitle) then
−
end -- end of do
+
if not is_set(Chapter) then
−
 
+
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
−
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
+
ScriptChapter = ScriptTitle;
−
-- 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
+
TransChapter = TransTitle;
−
Embargo = is_embargoed (Embargo); --  
+
ChapterURL = URL;
−
 
+
if not is_set (ChapterURL) and is_set (TitleLink) then
−
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
+
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
−
if not is_set (Embargo) then -- if not embargoed or embargo has expired
+
end
−
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
+
Title = Periodical;
−
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
+
ChapterFormat = Format;
 +
Periodical = ''; -- redundant so unset
 +
TransTitle = '';
 +
URL = '';
 +
Format = '';
 +
TitleLink = '';
 +
ScriptTitle = '';
 +
end
 +
else -- |title not set
 +
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
 +
Periodical = ''; -- redundant so unset
 +
end
 
end
 
end
 
end
 
end
  
−
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
+
-- Special case for cite techreport.
−
-- Test if citation has no title
+
if (config.CitationClass == "techreport") then -- special case for cite techreport
−
if not is_set(Title) and
+
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
−
not is_set(TransTitle) and
+
if not is_set(ID) then -- can we use ID for the "number"?
−
not is_set(ScriptTitle) then
+
ID = A['Number']; -- yes, use it
−
if 'episode' == config.CitationClass then -- special case for cite episode; is there a better way to do this?
+
else -- ID has a value so emit error message
−
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
+
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
−
else
+
end
−
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
+
end
 +
end
 +
 
 +
-- special case for cite interview
 +
-- TODO: make cite interview not need any special cases
 +
--[[
 +
Program, Callsign, City deprecated, so avoid using /Configuration
 +
for reassignment, which would allow these parameters' use outside interview
 +
]]
 +
if (config.CitationClass == "interview") then
 +
if is_set(Program) then
 +
if not is_set(Periodical) then
 +
Periodical = Program;
 +
end
 +
end
 +
if is_set(Callsign) then
 +
if not is_set(PublisherName) then
 +
PublisherName = Callsign;
 +
end
 +
end
 +
if is_set(City) then
 +
if not is_set(PublicationPlace) then
 +
PublicationPlace = City;
 
end
 
end
 +
end
 
end
 
end
−
+
 
−
if 'none' == Title and is_set(Periodical) and not (( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia))) then -- special case
+
-- special case for cite mailing list
−
Title = ''; -- set title to empty string
+
if (config.CitationClass == "mailinglist") then
−
add_maint_cat ('untitled');
+
Periodical = A ['MailingList'];
 +
elseif 'mailinglist' == A:ORIGIN('Periodical') then
 +
Periodical = ''; -- unset because mailing list is only used for cite mailing list
 
end
 
end
  
−
check_for_url ({['title']=Title, ['chapter']=Chapter, ['work']=Periodical}); -- adds error message when any of these parameters contain a URL
+
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
−
 
+
if 'conference' == config.CitationClass then
−
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
+
if is_set(BookTitle) then
−
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
+
Chapter = Title;
−
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
+
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
−
-- is the article title, and Chapter is a section within the article.  So, we remap
+
ChapterURL = URL;
−
+
ChapterURLorigin = URLorigin;
−
local coins_chapter = Chapter; -- default assuming that remapping not required
+
URLorigin = '';
−
local coins_title = Title; -- et tu
+
ChapterFormat = Format;
−
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
+
TransChapter = TransTitle;
−
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
+
Title = BookTitle;
−
coins_chapter = Title; -- remap
+
Format = '';
−
coins_title = Periodical;
+
-- 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
−
+
 
−
-- this is the function call to COinS()
+
-- cite map oddities
−
local OCinSoutput = COinS({
+
local Cartography = "";
−
['Periodical'] = Periodical,
+
local Scale = "";
−
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
+
local Sheet = A['Sheet'] or '';
−
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
+
local Sheets = A['Sheets'] or '';
−
['PublicationPlace'] = PublicationPlace,
+
if config.CitationClass == "map" then
−
['Date'] = first_set(COinS_date, Date), -- COinS_date has correctly formatted date if Date is valid; any reason to keep Date here?  Should we be including invalid dates in metadata?
+
Chapter = A['Map'];
−
['Series'] = Series,
+
ChapterURL = A['MapURL'];
−
['Volume'] = Volume,
+
TransChapter = A['TransMap'];
−
['Issue'] = Issue,
+
ChapterURLorigin = A:ORIGIN('MapURL');
−
['Pages'] = get_coins_pages (first_set(Sheet, Sheets, Page, Pages, At)), -- pages stripped of external links
+
ChapterFormat = A['MapFormat'];
−
['Edition'] = Edition,
+
−
['PublisherName'] = PublisherName,
+
Cartography = A['Cartography'];
−
['URL'] = first_set( URL, ChapterURL ),
+
if is_set( Cartography ) then
−
['Authors'] = a,
+
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
−
['ID_list'] = ID_list,
+
end
−
['RawPage'] = this_page.prefixedText,
+
Scale = A['Scale'];
−
}, config.CitationClass);
+
if is_set( Scale ) then
−
 
+
Scale = sepc .. " " .. Scale;
−
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
 
−
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
 
−
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
 
−
end
 
−
 
 
−
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
 
−
if 'newsgroup' == config.CitationClass then
 
−
if is_set (PublisherName) then
 
−
PublisherName = '[[Usenet newsgroup|Newsgroup]]:&nbsp;' .. external_link( 'news:' .. PublisherName, PublisherName );
 
 
end
 
end
 
end
 
end
  
 +
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
 +
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
 +
local AirDate = A['AirDate'];
 +
local SeriesLink = A['SeriesLink'];
  
 +
link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
  
−
-- Now perform various field substitutions.
+
local Network = A['Network'];
−
-- We also add leading spaces and surrounding markup and punctuation to the
+
local Station = A['Station'];
−
-- various parts of the citation, but only when they are non-nil.
+
local s, n = {}, {};
−
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
+
-- do common parameters first
−
do
+
if is_set(Network) then table.insert(n, Network); end
−
local last_first_list;
+
if is_set(Station) then table.insert(n, Station); end
−
local maximum;
+
ID = table.concat(n, sepc .. ' ');
−
local control = {
+
−
format = NameListFormat, -- empty string or 'vanc'
+
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
−
maximum = nil, -- as if display-authors or display-editors not set
+
Date = AirDate;
−
lastauthoramp = LastAuthorAmp,
+
end
−
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
+
 
−
};
+
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
 +
local Season = A['Season'];
 +
local SeriesNumber = A['SeriesNumber'];
  
−
do -- do editor name list first because coauthors can modify control table
+
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
−
maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
+
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
−
-- Preserve old-style implicit et al.
+
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
−
if not is_set(maximum) and #e == 4 then  
 
−
maximum = 3;
 
−
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
 
 
end
 
end
 +
-- assemble a table of parts concatenated later into Series
 +
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
 +
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
 +
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
 +
Issue = ''; -- unset because this is not a unique parameter
 +
 +
Chapter = Title; -- promote title parameters to chapter
 +
ScriptChapter = ScriptTitle;
 +
ChapterLink = TitleLink; -- alias episodelink
 +
TransChapter = TransTitle;
 +
ChapterURL = URL;
 +
ChapterURLorigin = A:ORIGIN('URL');
 +
 +
Title = Series; -- promote series to title
 +
TitleLink = SeriesLink;
 +
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
  
−
control.maximum = maximum;
+
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
−
+
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
−
last_first_list, EditorCount = list_people(control, e, editor_etal);
+
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
−
 
+
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
−
if is_set (Editors) then
 
−
if editor_etal then
 
−
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
 
−
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
 
−
else
 
−
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
 
−
end
 
−
else
 
−
Editors = last_first_list; -- either an author name list or an empty string
 
−
end
 
−
 
 
−
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
 
−
EditorCount = 2; -- spoof to display (eds.) annotation
 
−
end
 
−
end
 
−
do -- now do translators
 
−
control.maximum = #t; -- number of translators
 
−
Translators = list_people(control, t, false); -- et al not currently supported
 
−
end
 
−
do -- now do authors
 
−
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
 
−
 
 
−
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
 
−
control.lastauthoramp = nil;
 
−
control.maximum = #a + 1;
 
 
end
 
end
 +
URL = ''; -- unset
 +
TransTitle = '';
 +
ScriptTitle = '';
 
 
−
last_first_list = list_people(control, a, author_etal);
+
else -- now oddities that are cite serial
−
 
+
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
−
if is_set (Authors) then
+
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
−
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
+
if is_set (Series) and is_set (SeriesLink) then
−
if author_etal then
+
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
−
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
 +
Series = wrap_style ('italic-title', Series); -- series is italicized
 +
end
 +
end
 +
-- end of {{cite episode}} stuff
  
−
end -- end of do
+
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
−
 
+
if 'arxiv' == config.CitationClass then
−
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
+
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
−
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
+
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
 +
elseif is_set (Series) then -- series is an alias of version
 +
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
 +
Series = ''; -- unset
 +
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
 
end
 
end
−
end
+
 +
if first_set ({AccessDate, At, Authors, 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'], -- TODO: find a better way to do this
 +
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
−
 
+
Authors = '';
−
--[[
+
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
−
do -- do-block to limit scope of last_first_list
+
Chapter = '';
−
local last_first_list;
+
URL = '';
−
local maximum = A['DisplayAuthors'];
+
Format = '';
−
 
+
Page = ''; Pages = ''; At = '';
−
maximum , author_etal = get_display_authors_editors (maximum, #a, 'authors', author_etal);
 
−
 
 
−
local control = {
 
−
format = NameListFormat, -- empty string or 'vanc'
 
−
maximum = maximum,
 
−
lastauthoramp = LastAuthorAmp,
 
−
page_name = this_page.text -- get current page name so that we don't wikilink to it via authorlinkn
 
−
};
 
−
 
−
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
−
+
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
−
last_first_list = list_people(control, a, author_etal);
+
end
  
−
if is_set (Authors) then
+
-- handle type parameter for those CS1 citations that have default values
−
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
+
if in_array(config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
−
if author_etal then
+
TitleType = set_titletype (config.CitationClass, TitleType);
−
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
+
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
−
end
+
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
−
else
 
−
Authors = last_first_list; -- either an author name list or an empty string
 
 
end
 
end
 +
end
  
−
end -- end of do
+
if is_set(TitleType) then -- if type parameter is specified
 +
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
 +
-- TODO: Hack on TitleType to fix bunched parentheses problem
 +
end
  
−
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
+
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
−
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
+
if not is_set (Date) then
 +
Date = Year; -- promote Year to Date
 +
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
 +
if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
 +
Date = PublicationDate; -- promote PublicationDate to Date
 +
PublicationDate = ''; -- unset, no longer needed
 +
end
 
end
 
end
  
−
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
+
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
−
do
+
 
−
local last_first_list;
+
--[[
−
local maximum = A['DisplayEditors'];
+
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.
  
−
maximum , editor_etal = get_display_authors_editors (maximum, #e, 'editors', editor_etal);
+
Date validation supporting code is in Module:Citation/CS1/Date_validation
−
-- Preserve old-style implicit et al.
+
]]
−
if not is_set(maximum) and #e == 4 then
+
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
−
maximum = 3;
+
local error_message = '';
−
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
+
-- AirDate has been promoted to Date so not necessary to check it
−
end
+
local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
 +
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};
  
−
local control = {
+
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
−
format = NameListFormat, -- empty string or 'vanc'
 
−
maximum = maximum,
 
−
lastauthoramp = LastAuthorAmp,
 
−
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
 
−
};
 
  
−
last_first_list, EditorCount = list_people(control, e, editor_etal);
+
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
 +
local mismatch = year_date_check (Year, Date)
 +
if 0 == mismatch then -- |year= does not match a year-value in |date=
 +
if is_set (error_message) then -- if there is already an error message
 +
error_message = error_message .. ', '; -- tack on this additional message
 +
end
 +
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
 +
elseif 1 == mismatch then -- |year= matches year-value in |date=
 +
add_maint_cat ('date_year');
 +
end
 +
end
 +
 +
if not is_set(error_message) then -- error free dates only
 +
local modified = false; -- flag
 +
if is_set (DF) then -- if we need to reformat dates
 +
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
 +
end
  
−
if is_set (Editors) then
+
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
−
if editor_etal then
+
modified = true;
−
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
+
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
−
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
+
end
−
else
+
−
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
+
if modified then -- if the date_parameters_list values were modified
 +
AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with modified values
 +
ArchiveDate = date_parameters_list['archive-date'];
 +
Date = date_parameters_list['date'];
 +
DoiBroken = date_parameters_list['doi-broken-date'];
 +
LayDate = date_parameters_list['lay-date'];
 +
PublicationDate = date_parameters_list['publication-date'];
 
end
 
end
 
else
 
else
−
Editors = last_first_list; -- either an author name list or an empty string
+
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
 
end
 
end
 +
end -- end of do
  
−
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
+
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
−
EditorCount = 2; -- spoof to display (eds.) annotation
+
-- 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
−
end
+
Embargo = is_embargoed (Embargo); --
−
end
 
−
]]
 
  
−
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
+
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
−
-- an error message if the associated url is not set, or an empty string for concatenation
+
if not is_set (Embargo) then -- if not embargoed or embargo has expired
−
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
+
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
−
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
+
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
−
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
+
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
−
Format = style_format (Format, URL, 'format', 'url');
+
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
−
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
+
AccessDate = ''; -- unset
−
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
+
end
  
−
if  not is_set(URL) then --and
 
−
-- not is_set(ArchiveURL) then --and -- prevents format_missing_url error from registering
 
−
-- not is_set(ConferenceURL) and -- TODO: keep this here? conference as part of cite web or cite podcast?
 
−
-- not is_set(TranscriptURL) then -- TODO: remove? |transcript-url= and |transcript= has separate test
 
−
 
−
-- Test if cite web or cite podcast |url= is missing or empty
 
−
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then
 
−
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
 
end
 
end
  
−
local OriginalURL, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
+
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
−
DeadURL = DeadURL:lower(); -- used later when assembling archived text
+
-- Test if citation has no title
−
if is_set( ArchiveURL ) then
+
if not is_set(Title) and
−
if is_set (URL) then
+
not is_set(TransTitle) and
−
OriginalURL = URL; -- save copy of original source URL
+
not is_set(ScriptTitle) then
−
OriginalFormat = Format; -- and original |format=
+
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
−
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
+
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
−
URL = ArchiveURL -- swap-in the archive's url
+
else
−
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
+
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
−
Format = ArchiveFormat or ''; -- swap in archive's format
 
 
end
 
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
 
−
OriginalFormat = ChapterFormat; -- and original |format=
 
−
if 'no' ~= DeadURL then
 
−
ChapterURL = ArchiveURL -- swap-in the archive's url
 
−
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
 
−
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
 
−
end
 
−
end
 
 
end
 
end
−
 
+
−
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", 'arxiv'}) or
+
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
−
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
+
Title = ''; -- set title to empty string
−
if is_set (Chapter) or is_set (TransChapter) or is_set (ChapterURL) or is_set (ScriptChapter) then -- chapter parameters not supported for these citation types
+
add_maint_cat ('untitled');
−
table.insert( z.message_tail, { set_error( 'chapter_ignored', {A:ORIGIN ('Chapter')}, true ) } ); -- add error message
 
−
Chapter = ''; -- set them to empty string to be safe with concatenation
 
−
TransChapter = '';
 
−
ChapterURL = '';
 
−
ScriptChapter = '';
 
−
end
 
−
else -- otherwise, format chapter / article title
 
−
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin);
 
−
if is_set (Chapter) then
 
−
if 'map' == config.CitationClass and is_set (TitleType) then
 
−
Chapter = Chapter .. ' ' .. TitleType;
 
−
end
 
−
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
 
−
end
 
 
end
 
end
  
−
-- Format main title.
+
check_for_url ({ -- add error message when any of these parameters contains a URL
−
if is_set(TitleLink) and is_set(Title) then
+
['title']=Title,
−
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
+
[A:ORIGIN('Chapter')]=Chapter,
−
end
+
[A:ORIGIN('Periodical')]=Periodical,
 +
[A:ORIGIN('PublisherName')] = PublisherName
 +
});
  
−
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", "mailinglist", 'arxiv'}) or
+
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
−
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
+
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
−
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
+
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
−
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
+
-- is the article title, and Chapter is a section within the article.  So, we remap
−
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 coins_chapter = Chapter; -- default assuming that remapping not required
−
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
+
local coins_title = Title; -- et tu
−
elseif 'report' == config.CitationClass then -- no styling for cite report
+
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
−
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
+
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
−
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
+
coins_chapter = Title; -- remap
−
else
+
coins_title = Periodical;
−
Title = wrap_style ('italic-title', Title);
 
−
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 
−
TransTitle = wrap_style ('trans-italic-title', TransTitle);
 
−
end
 
−
 
 
−
TransError = "";
 
−
if is_set(TransTitle) then
 
−
if is_set(Title) then
 
−
TransTitle = " " .. TransTitle;
 
−
else
 
−
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
 
 
end
 
end
 
end
 
end
−
+
local coins_author = a; -- default for coins rft.au
−
Title = Title .. TransTitle;
+
if 0 < #c then -- but if contributor list
−
+
coins_author = c; -- use that instead
−
if is_set(Title) then
 
−
if not is_set(TitleLink) and is_set(URL) then
 
−
Title = external_link( URL, Title ) .. TransError .. Format;
 
−
URL = "";
 
−
Format = "";
 
−
else
 
−
Title = Title .. TransError;
 
−
end
 
 
end
 
end
  
−
if is_set(Place) then
+
-- this is the function call to COinS()
−
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
+
local OCinSoutput = COinS({
 +
['Periodical'] = Periodical,
 +
['Encyclopedia'] = Encyclopedia,
 +
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
 +
['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
  
−
if is_set (Conference) then
+
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
−
if is_set (ConferenceURL) then
+
if 'newsgroup' == config.CitationClass then
−
Conference = external_link( ConferenceURL, Conference );
+
if is_set (PublisherName) then
 +
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil ));
 
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
+
 
−
local Minutes = A['Minutes'];
+
 
−
if is_set(Minutes) then
+
-- Now perform various field substitutions.
−
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
+
-- We also add leading spaces and surrounding markup and punctuation to the
−
else
+
-- various parts of the citation, but only when they are non-nil.
−
local Time = A['Time'];
+
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
−
if is_set(Time) then
+
do
−
local TimeCaption = A['TimeCaption']
+
local last_first_list;
−
if not is_set(TimeCaption) then
+
local control = {
−
TimeCaption = cfg.messages['event'];
+
format = NameListFormat, -- empty string or 'vanc'
−
if sepc ~= '.' then
+
maximum = nil, -- as if display-authors or display-editors not set
−
TimeCaption = TimeCaption:lower();
+
lastauthoramp = LastAuthorAmp,
−
end
+
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn
 +
mode = Mode
 +
};
 +
 
 +
do -- do editor name list first because coauthors can modify control table
 +
control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
 +
last_first_list, EditorCount = list_people(control, e, editor_etal);
 +
 
 +
if is_set (Editors) then
 +
if editor_etal then
 +
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
 +
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
 +
else
 +
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
 
end
 
end
−
Position = " " .. TimeCaption .. " " .. Time;
+
else
 +
Editors = last_first_list; -- either an author name list or an empty string
 
end
 
end
−
end
+
 
−
else
+
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then  
−
Position = " " .. Position;
+
EditorCount = 2; -- spoof to display (eds.) annotation
−
At = '';
 
−
end
 
−
 
−
if not is_set(Page) then
 
−
if is_set(Pages) then
 
−
if is_set(Periodical) and
 
−
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
 
−
Pages = ": " .. Pages;
 
−
elseif tonumber(Pages) ~= nil then
 
−
Pages = sepc .." " .. PPrefix .. Pages;
 
−
else
 
−
Pages = sepc .." " .. PPPrefix .. Pages;
 
 
end
 
end
 
end
 
end
−
else
+
do -- now do translators
−
if is_set(Periodical) and
+
control.maximum = #t; -- number of translators
−
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
+
Translators = list_people(control, t, false); -- et al not currently supported
−
Page = ": " .. Page;
+
end
−
else
+
do -- now do contributors
−
Page = sepc .." " .. PPrefix .. Page;
+
control.maximum = #c; -- number of contributors
 +
Contributors = list_people(control, c, false); -- et al not currently supported
 
end
 
end
−
end
+
do -- now do authors
 +
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
  
−
if 'map' == config.CitationClass then -- cite map oddity done after COinS call (and with other in-source locators)
+
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
−
if is_set (Sheet) or is_set (Sheets) then
+
control.lastauthoramp = nil;
−
local err_msg1 = 'sheet=, &#124;sheets'; -- default error message in case any of page pages or at are set
+
control.maximum = #a + 1;
−
local err_msg2;
 
−
if is_set (Page) or is_set (Pages) or is_set (At) then -- are any set?
 
−
err_msg2 = 'page=, &#124;pages=, &#124;at'; -- a generic error message
 
−
Page = ''; Pages = ''; At = '';
 
−
elseif is_set (Sheet) and is_set (Sheets) then -- if both are set make error message
 
−
err_msg1 = 'sheet';
 
−
err_msg2 = 'sheets';
 
 
end
 
end
−
if is_set (err_msg2) then
+
−
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', err_msg1) .. ' and ' .. wrap_style ('parameter', err_msg2)}, true ) } ); -- add error message
+
last_first_list = list_people(control, a, author_etal);
−
end
+
 
−
if not is_set (Sheet) then -- do sheet static text and formatting; Sheet has priority over Sheets if both provided
+
if is_set (Authors) then
−
if is_set (Sheets) then
+
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
−
if is_set (Periodical) then
+
if author_etal then
−
Sheet = ": Sheets " .. Sheets; -- because Sheet has priority, no need to support both later on
+
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
−
else
 
−
Sheet = sepc .. " Sheets " .. Sheets;
 
−
end
 
 
end
 
end
 
else
 
else
−
if is_set (Periodical) then
+
Authors = last_first_list; -- either an author name list or an empty string
−
Sheet = ": Sheet " .. Sheet;
 
−
else
 
−
Sheet = sepc .. " Sheet " .. Sheet;
 
−
end
 
 
end
 
end
 +
end -- end of do
 +
 +
if is_set (Authors) and is_set (Collaboration) then
 +
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
 +
end
 +
 +
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
 +
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
 
end
 
end
 
end
 
end
  
−
At = is_set(At) and (sepc .. " " .. At) or "";
+
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
−
Position = is_set(Position) and (sepc .. " " .. Position) or "";
+
-- an error message if the associated url is not set, or an empty string for concatenation
−
if config.CitationClass == 'map' then
+
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
−
local Section = A['Section'];
+
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
−
local Sections = A['Sections'];
+
Format = style_format (Format, URL, 'format', 'url');
−
local Inset = A['Inset'];
+
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
−
+
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
−
if is_set( Inset ) then
 
−
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
 
−
end
 
  
−
if is_set( Sections ) then
+
-- special case for chapter format so no error message or cat when chapter not supported
−
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
+
if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or
−
elseif is_set( Section ) then
+
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
−
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
+
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
−
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 not is_set(URL) then
−
+
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- |url= required for cite web, cite podcast, and cite mailinglist
−
if is_set (Translators) then
+
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
−
Others = sepc .. ' Translated by ' .. Translators .. Others;  
+
end
 +
 +
-- do we have |accessdate= without either |url= or |chapter-url=?
 +
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when URL is not set;
 +
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
 +
AccessDate = '';
 +
end
 
end
 
end
  
−
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
+
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess;
−
if is_set (Edition) then
+
DeadURL = DeadURL:lower(); -- used later when assembling archived text
−
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
+
if is_set( ArchiveURL ) then
−
add_maint_cat ('extra_text', 'edition');
+
if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
−
end
+
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
−
Edition = " " .. wrap_msg ('edition', Edition);
+
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
−
else
+
OriginalFormat = ChapterFormat; -- and original |format=
−
Edition = '';
+
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
 +
elseif is_set (URL) then
 +
OriginalURL = URL; -- save copy of original source URL
 +
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
 +
OriginalFormat = Format; -- and original |format=
 +
OriginalAccess = UrlAccess;
 +
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
 +
URL = ArchiveURL -- swap-in the archive's url
 +
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
 +
Format = ArchiveFormat or ''; -- swap in archive's format
 +
UrlAccess = nil; -- restricted access levels do not make sense for archived urls
 +
end
 +
end
 
end
 
end
−
Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
 
−
Series = is_set(Series) and (sepc .. " " .. Series) or "";
 
−
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
 
−
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 
  
−
if is_set(Volume) then
+
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia
−
if ( mw.ustring.len(Volume) > 4 )
+
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
−
  then Volume = sepc .." " .. Volume;
+
local chap_param;
−
  else Volume = " <b>" .. hyphen_to_dash(Volume) .. "</b>";
+
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
 
end
−
end
 
  
−
------------------------------------ totally unrelated data
+
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
−
if is_set(Via) then
+
if is_set (Chapter) then
−
Via = " " .. wrap_msg ('via', Via);
+
Chapter = Chapter .. ChapterFormat ;
 +
if 'map' == config.CitationClass and is_set (TitleType) then
 +
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
 +
end
 +
Chapter = Chapter.. 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
  
−
--[[
+
-- Format main title.
−
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
+
if is_set(TitleLink) and is_set(Title) then
−
note is displayed. There are no error messages for this condition.
+
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
 +
end
  
−
]]
+
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv', 'interview'}) or
−
if is_set (SubscriptionRequired) then
+
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
−
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
+
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
−
elseif is_set (RegistrationRequired) then
+
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
−
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
+
Title = wrap_style ('quoted-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 +
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
 +
elseif 'report' == config.CitationClass then -- no styling for cite report
 +
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 +
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
 
else
 
else
−
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
+
Title = wrap_style ('italic-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 +
TransTitle = wrap_style ('trans-italic-title', TransTitle);
 
end
 
end
  
−
if is_set(AccessDate) then
+
local TransError = "";
−
local retrv_text = " " .. cfg.messages['retrieved']
+
if is_set(TransTitle) then
−
 
+
if is_set(Title) then
−
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
+
TransTitle = " " .. TransTitle;
−
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
+
else
−
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
+
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
−
-- neither of these work; don't know why; it seems that substitute() isn't being called
+
end
−
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
 
 
end
 
end
 
 
−
if is_set(ID) then ID = sepc .." ".. ID; end
+
Title = Title .. TransTitle;
−
  if "thesis" == config.CitationClass and is_set(Docket) then
+
−
ID = sepc .." Docket ".. Docket .. ID;
+
if is_set(Title) then
−
end
+
if not is_set(TitleLink) and is_set(URL) then
−
  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
+
Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransError .. Format;
 +
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
 +
-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive
 +
-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available
 +
-- local err_msg
 +
-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message
 +
-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this
 +
-- Title = Title .. (err_msg or '');
 +
-- end
 +
-- else
 +
-- Title = temp_title;
 +
-- end
 +
 
 +
URL = ''; -- unset these because no longer needed
 +
Format = "";
 +
else
 +
Title = Title .. TransError;
 +
end
 
end
 
end
  
−
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
+
if is_set(Place) then
−
 
+
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
−
if is_set(URL) then
 
−
URL = " " .. external_link( URL, nil, URLorigin );
 
 
end
 
end
  
−
if is_set(Quote) then
+
if is_set (Conference) then
−
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then
+
if is_set (ConferenceURL) then
−
Quote = Quote:sub(2,-2);
+
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil );
 
end
 
end
−
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
+
Conference = sepc .. " " .. Conference .. ConferenceFormat;
−
PostScript = ""; -- CS1 does not supply terminal punctuation when |quote= is set
+
elseif is_set(ConferenceURL) then
 +
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
 
end
 
end
−
+
 
−
local Archived
+
if not is_set(Position) then
−
if is_set(ArchiveURL) then
+
local Minutes = A['Minutes'];
−
if not is_set(ArchiveDate) then
+
local Time = A['Time'];
−
ArchiveDate = set_error('archive_missing_date');
+
 
−
end
+
if is_set(Minutes) then
−
if "no" == DeadURL then
+
if is_set (Time) then
−
local arch_text = cfg.messages['archived'];
+
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
−
if sepc ~= "." then arch_text = arch_text:lower() end
 
−
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
 
−
{ external_link( ArchiveURL, arch_text ) .. ArchiveFormat, ArchiveDate } );
 
−
if not is_set(OriginalURL) then
 
−
Archived = Archived .. " " .. set_error('archive_missing_url');  
 
 
end
 
end
−
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
+
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
−
local arch_text = cfg.messages['archived-dead'];
 
−
if sepc ~= "." then arch_text = arch_text:lower() end
 
−
-- if 'usurped' == DeadURL then -- when original has unsuitable content do not link
 
−
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'] ) .. OriginalFormat, ArchiveDate } ); -- format already styled
 
−
end
 
 
else
 
else
−
local arch_text = cfg.messages['archived-missing'];
+
if is_set(Time) then
−
if sepc ~= "." then arch_text = arch_text:lower() end
+
local TimeCaption = A['TimeCaption']
−
Archived = sepc .. " " .. substitute( arch_text,
+
if not is_set(TimeCaption) then
−
{ set_error('archive_missing_url'), ArchiveDate } );
+
TimeCaption = cfg.messages['event'];
 +
if sepc ~= '.' then
 +
TimeCaption = TimeCaption:lower();
 +
end
 +
end
 +
Position = " " .. TimeCaption .. " " .. Time;
 +
end
 
end
 
end
−
elseif is_set (ArchiveFormat) then
 
−
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
 
 
else
 
else
−
Archived = ""
+
Position = " " .. Position;
 +
At = '';
 
end
 
end
−
+
 
−
local Lay = '';
+
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase, Mode);
−
if is_set(LayURL) then
+
 
−
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
+
At = is_set(At) and (sepc .. " " .. At) or "";
−
if is_set(LaySource) then
+
Position = is_set(Position) and (sepc .. " " .. Position) or "";
−
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
+
if config.CitationClass == 'map' then
−
else
+
local Section = A['Section'];
−
LaySource = "";
+
local Sections = A['Sections'];
−
end
+
local Inset = A['Inset'];
−
if sepc == '.' then
+
−
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'] ) .. LayFormat .. LaySource .. LayDate
+
if is_set( Inset ) then
−
else
+
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
−
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower() ) .. LayFormat .. LaySource .. LayDate
 
 
end
 
end
−
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
 
−
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
 
−
end
 
  
−
if is_set(Transcript) then
+
if is_set( Sections ) then
−
if is_set(TranscriptURL) then
+
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
−
Transcript = external_link( TranscriptURL, Transcript );
+
elseif is_set( Section ) then
 +
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
 
end
 
end
−
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
+
At = At .. Inset .. Section;
−
elseif is_set(TranscriptURL) then
+
end
−
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
+
 
 +
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;
 +
--[[ TODO: need to extract the wrap_msg from language_parameter
 +
so that we can solve parentheses bunching problem with Format/Language/TitleType
 +
]]
 
end
 
end
  
−
local Publisher;
+
Others = is_set(Others) and (sepc .. " " .. Others) or "";
−
if is_set(Periodical) and
+
−
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
+
if is_set (Translators) then
−
if is_set(PublisherName) then
+
if 'mla' == Mode then
−
if is_set(PublicationPlace) then
+
Others = sepc .. ' Trans. ' .. Translators .. Others;
−
Publisher = PublicationPlace .. ": " .. PublisherName;
+
else
−
else
+
Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;
−
Publisher = PublisherName; 
 
−
end
 
−
elseif is_set(PublicationPlace) then
 
−
Publisher= PublicationPlace;
 
−
else
 
−
Publisher = "";
 
 
end
 
end
−
if is_set(PublicationDate) then
+
end
−
if is_set(Publisher) then
+
if is_set (Interviewers) then
−
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
+
Others = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others;
−
else
+
end
−
Publisher = PublicationDate;
+
−
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
 
end
−
if is_set(Publisher) then
+
if 'mla' == Mode then
−
Publisher = " (" .. Publisher .. ")";
+
Edition = '. ' .. Edition .. ' ed.';
 +
else
 +
Edition = " " .. wrap_msg ('edition', Edition);
 
end
 
end
 
else
 
else
−
if is_set(PublicationDate) then
+
Edition = '';
−
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
 
−
end
 
−
if is_set(PublisherName) then
 
−
if is_set(PublicationPlace) then
 
−
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
 
−
else
 
−
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
 
−
end
 
−
elseif is_set(PublicationPlace) then
 
−
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
 
−
else
 
−
Publisher = PublicationDate;
 
−
end
 
 
end
 
end
−
+
 
−
-- Several of the above rely upon detecting this as nil, so do it last.
+
Series = is_set(Series) and (sepc .. " " .. Series) or "";
−
if is_set(Periodical) then
+
if 'mla' == Mode then -- not in brackets for mla
−
if is_set(Title) or is_set(TitleNote) then
+
OrigYear = is_set(OrigYear) and (". " .. OrigYear) or "";
−
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
+
else
−
else
+
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
−
Periodical = wrap_style ('italic-title', Periodical)
+
end
−
end
+
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 +
 
 +
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase, Mode);
 +
 
 +
------------------------------------ totally unrelated data
 +
if is_set(Via) then
 +
Via = " " .. wrap_msg ('via', Via);
 
end
 
end
  
 
--[[
 
--[[
−
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
+
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
−
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
+
note is displayed. There are no error messages for this condition.
 +
 
 
]]
 
]]
−
if "speech" == config.CitationClass then -- cite speech only
+
if is_set (SubscriptionRequired) then
−
TitleNote = " (Speech)"; -- annotate the citation
+
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
−
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
+
elseif is_set (RegistrationRequired) then
−
if is_set (Conference) then -- and if |event= is set
+
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
−
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
+
else
−
end
+
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
−
end
 
 
end
 
end
  
−
-- Piece all bits together at last. Here, all should be non-nil.
+
if is_set(AccessDate) then
−
-- We build things this way because it is more efficient in LUA
+
local retrv_text = " " .. cfg.messages['retrieved']
−
-- not to keep reassigning to the same string variable over and over.
 
  
−
local tcommon
+
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
−
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
+
if 'mla' == Mode then -- retrieved text not used in mla
−
if is_set(Others) then Others = Others .. sepc .. " " end
+
AccessDate = ' ' .. AccessDate;
−
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
+
else
−
Language, Edition, Publisher, Agency, Volume, Issue}, sepc );
+
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
−
+
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
−
elseif 'map' == config.CitationClass then -- special cases for cite map
 
−
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
 
−
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 
−
elseif is_set (Periodical) then -- map in a periodical
 
−
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume, Issue}, sepc );
 
−
else -- a sheet or stand-alone map
 
−
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
 
 
end
 
end
−
+
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
−
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, Issue, Others, Edition, Publisher, Agency}, sepc );
 
 
end
 
end
 
 
−
if #ID_list > 0 then
+
if is_set(ID) then ID = sepc .." ".. ID; end
−
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
+
  if "thesis" == config.CitationClass and is_set(Docket) then
−
else
+
ID = sepc .." Docket ".. Docket .. ID;
−
ID_list = 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, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
 +
 
 +
if is_set(URL) then
 +
URL = " " .. external_link( URL, nil, URLorigin, Access );
 +
end
 +
 
 +
if is_set(Quote) then
 +
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
 +
Quote = Quote:sub(2,-2); -- strip them off
 +
end
 +
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
 +
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
 
end
 
end
 
 
−
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
+
local Archived
−
local text;
+
if is_set(ArchiveURL) then
−
local pgtext = Position .. Sheet .. Page .. Pages .. At;
+
if not is_set(ArchiveDate) then
−
+
ArchiveDate = set_error('archive_missing_date');
−
if is_set(Authors) then
+
end
−
if is_set(Coauthors) then
+
if "no" == DeadURL then
−
local sep = '; ';
+
local arch_text = cfg.messages['archived'];
−
if 'vanc' == NameListFormat then
+
if sepc ~= "." then arch_text = arch_text:lower() end
−
sep = ', ';
+
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
 +
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
 +
if not is_set(OriginalURL) then
 +
Archived = Archived .. " " .. set_error('archive_missing_url');  
 
end
 
end
−
Authors = Authors .. sep .. Coauthors;
+
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
−
end
+
local arch_text = cfg.messages['archived-dead'];
−
if is_set(Date) then
+
if sepc ~= "." then arch_text = arch_text:lower() end
−
Date = " ("..Date..")" .. OrigYear .. sepc .. " "
+
if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then
−
elseif string.sub(Authors,-1,-1) == sepc then
+
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
−
Authors = Authors .. " "
+
if 'bot: unknown' == DeadURL then
 +
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
 +
else
 +
add_maint_cat ('unfit'); -- and add a category if not already added
 +
end
 +
else -- DeadURL is empty, 'yes', 'true', or 'y'
 +
Archived = sepc .. " " .. substitute( arch_text,
 +
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
 +
end
 
else
 
else
−
Authors = Authors .. sepc .. " "
+
local arch_text = cfg.messages['archived-missing'];
 +
if sepc ~= "." then arch_text = arch_text:lower() end
 +
Archived = sepc .. " " .. substitute( arch_text,
 +
{ set_error('archive_missing_url'), ArchiveDate } );
 
end
 
end
−
if is_set(Editors) then
+
elseif is_set (ArchiveFormat) then
−
local in_text = " ";
+
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
−
local post_text = "";
+
else
−
if is_set(Chapter) then
+
Archived = ""
−
in_text = in_text .. cfg.messages['in'] .. " "
+
end
−
else
+
−
if EditorCount <= 1 then
+
local Lay = '';
−
post_text = ", " .. cfg.messages['editor'];
+
if is_set(LayURL) then
−
else
+
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
−
post_text = ", " .. cfg.messages['editors'];
+
if is_set(LaySource) then  
−
end
+
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
−
end
+
else
−
if (sepc ~= '.') then in_text = in_text:lower() end
+
LaySource = "";
−
Editors = in_text .. Editors .. post_text;
 
−
if (string.sub(Editors,-1,-1) == sepc) or (string.sub(Editors,-3,-1) == sepc .. ']]') then -- if last editor name ends with sepc char
 
−
Editors = Editors .. " "; -- don't add another
 
−
else
 
−
Editors = Editors .. sepc .. " " -- otherwise terninate the editor list
 
−
end
 
 
end
 
end
−
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
+
if sepc == '.' then
−
text = safe_join( {text, pgtext, idcommon}, sepc );
+
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
−
elseif is_set(Editors) then
+
else
−
if is_set(Date) then
+
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
−
if EditorCount <= 1 then
+
end
−
Editors = Editors .. ", " .. cfg.messages['editor'];
+
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
−
else
+
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
−
Editors = Editors .. ", " .. cfg.messages['editors'];
+
end
−
end
+
 
−
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
+
if is_set(Transcript) then
−
else
+
if is_set(TranscriptURL) then
−
if EditorCount <= 1 then
+
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil );
−
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
+
end
−
else
+
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
−
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
+
elseif is_set(TranscriptURL) then
−
end
+
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
−
end
+
end
−
text = safe_join( {Editors, Date, Chapter, Place, tcommon}, sepc );
+
 
−
text = safe_join( {text, pgtext, idcommon}, sepc );
+
local Publisher;
−
else
+
if is_set(PublicationDate) then
−
if is_set(Date) then
+
PublicationDate = wrap_msg ('published', PublicationDate);
−
if ( string.sub(tcommon,-1,-1) ~= sepc )
+
end
−
  then Date = sepc .." " .. Date .. OrigYear
+
if is_set(PublisherName) then
−
  else Date = " " .. Date .. OrigYear
+
if is_set(PublicationPlace) then
−
end
+
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
−
end
+
else
−
if config.CitationClass=="journal" and is_set(Periodical) then
+
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
−
text = safe_join( {Chapter, Place, tcommon}, sepc );
+
end
−
text = safe_join( {text, pgtext, Date, idcommon}, sepc );
+
elseif is_set(PublicationPlace) then
−
else
+
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
−
text = safe_join( {Chapter, Place, tcommon, Date}, sepc );
+
else  
−
text = safe_join( {text, pgtext, idcommon}, sepc );
+
Publisher = PublicationDate;
−
end
+
end
−
end
+
−
+
-- Several of the above rely upon detecting this as nil, so do it last.
−
if 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
−
 
+
end
−
-- Now enclose the whole thing in a <cite/> element
+
 
−
local options = {};
+
--[[
−
+
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 is_set(config.CitationClass) and config.CitationClass ~= "citation" then
+
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
−
options.class = config.CitationClass;
+
]]
−
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
+
if "speech" == config.CitationClass then -- cite speech only
−
else
+
TitleNote = " (Speech)"; -- annotate the citation
−
options.class = "citation";
+
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
−
end
+
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
−
if is_set(Ref) and Ref:lower() ~= "none" then
+
end
−
local id = Ref
+
end
−
if ( "harv" == Ref ) then
+
end
−
local names = {} --table of last names & year
+
 
−
if #a > 0 then
+
-- Piece all bits together at last.  Here, all should be non-nil.
−
for i,v in ipairs(a) do
+
-- We build things this way because it is more efficient in LUA
−
names[i] = v.last
+
-- not to keep reassigning to the same string variable over and over.
−
if i == 4 then break end
+
 
−
end
+
local tcommon;
−
elseif #e > 0 then
+
local tcommon2; -- used for book cite when |contributor= is set
−
for i,v in ipairs(e) do
+
−
names[i] = v.last
+
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
−
if i == 4 then break end
+
if is_set(Others) then Others = Others .. sepc .. " " end
−
end
+
if 'mla' == Mode then
−
end
+
tcommon = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
−
names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
+
else
−
id = anchor_id(names)
+
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
−
end
+
Language, Edition, Publisher, Agency, Volume}, sepc );
−
options.id = id;
+
end
−
end
+
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
−
+
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
−
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
+
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
 +
if 'mla' == Mode then
 +
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Edition, Publisher, Agency}, sepc );
 +
else
 +
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 +
end
 +
elseif 'mla' == Mode then
 +
tcommon = safe_join( {TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Publisher, Agency}, sepc );
 +
else
 +
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 +
end
 +
 
 +
elseif 'map' == config.CitationClass then -- special cases for cite map
 +
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
 +
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 +
elseif is_set (Periodical) then -- map in a periodical
 +
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 +
else -- a sheet or stand-alone map
 +
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
 +
end
 +
 +
elseif 'episode' == config.CitationClass then -- special case for cite episode
 +
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
 +
 
 +
elseif ('news' == config.CitationClass) and ('mla' == Mode) then -- special case for cite news in MLA mode
 +
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, Edition, Agency}, sepc );
 +
 
 +
elseif ('web' == config.CitationClass) and ('mla' == Mode) then -- special case for cite web in MLA mode
 +
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language,
 +
Edition, Publisher, Agency}, sepc );
 +
 
 +
else -- all other CS1 templates
 +
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
 +
Volume, Others, Edition, Publisher, Agency}, sepc );
 +
end
 +
 +
if #ID_list > 0 then
 +
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
 +
else
 +
ID_list = ID;
 +
end
 +
 +
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
 +
local text;
 +
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 +
 
 +
if is_set(Date) then
 +
if ('mla' == Mode) then
 +
if in_array (config.CitationClass, {'book', 'news', 'web'}) then
 +
Date = ', ' .. Date; -- origyear follows title in mla
 +
elseif 'journal' == config.CitationClass then
 +
Date = ', (' .. Date .. ')';
 +
end
 +
elseif is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
 +
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
 +
else -- neither of authors and editors set
 +
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
 +
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
 +
else
 +
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
 +
end
 +
end
 +
end
 +
if is_set(Authors) then
 +
if is_set(Coauthors) then
 +
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
 +
Authors = Authors .. ', ' .. Coauthors;
 +
else
 +
Authors = Authors .. '; ' .. Coauthors;
 +
end
 +
end
 +
if (not is_set (Date)) or ('mla' == Mode) then -- when date is set it's in parentheses; no Authors termination
 +
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
 +
end
 +
if is_set(Editors) then
 +
local in_text = " ";
 +
local post_text = "";
 +
if is_set(Chapter) and 0 == #c and 'mla' ~= Mode then
 +
in_text = in_text .. cfg.messages['in'] .. " "
 +
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
 +
elseif is_set(Chapter) and 'mla' == Mode then
 +
if EditorCount <= 1 then
 +
in_text = '. Ed. ';
 +
else
 +
in_text = '. Eds. ';
 +
end
 +
else
 +
if EditorCount <= 1 then
 +
post_text = ", " .. cfg.messages['editor'];
 +
else
 +
post_text = ", " .. cfg.messages['editors'];
 +
end
 +
end
 +
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
 +
end
 +
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
 +
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
 +
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
 +
Authors = by_text .. Authors; -- author follows title so tweak it here
 +
if is_set (Editors) and ('mla' ~= Mode)then -- when Editors make sure that Authors gets terminated
 +
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
 +
end
 +
if (not is_set (Date)) or ('mla' == Mode) 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
 +
if 'mla' == Mode then
 +
text = safe_join( {Contributors, Chapter, tcommon, OrigYear, Authors, Place, Others, Editors, tcommon2, Date, pgtext, idcommon }, sepc );
 +
else
 +
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
 +
end
 +
elseif 'mla' == Mode then
 +
tcommon = tcommon .. Date; -- hack to avoid duplicate separators
 +
text = safe_join( {Authors, Chapter, Title, OrigYear, Others, Editors, Edition, Place, tcommon, pgtext, idcommon }, sepc );
 +
else
 +
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
 +
end
 +
elseif is_set(Editors) then
 +
if is_set(Date) then
 +
if EditorCount <= 1 then
 +
Editors = Editors .. ", " .. cfg.messages['editor'];
 +
else
 +
Editors = Editors .. ", " .. cfg.messages['editors'];
 +
end
 +
else
 +
if EditorCount <= 1 then
 +
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
 +
else
 +
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
 +
end
 +
end
 +
if 'mla' == Mode then
 +
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
 +
text = safe_join( {Editors, Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
 +
else
 +
text = safe_join( {Editors, Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
 +
end
 +
else
 +
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
 +
end
 +
elseif 'mla' == Mode then
 +
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
 +
text = safe_join( {Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
 +
else
 +
text = safe_join( {Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
 +
end
 +
else
 +
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
 +
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
 +
else
 +
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
 +
end
 +
end
 +
 +
if is_set(PostScript) and PostScript ~= sepc then
 +
text = safe_join( {text, sepc}, sepc );  --Deals with italics, spaces, etc.
 +
text = text:sub(1,-sepc:len()-1);
 +
end
 +
 +
text = safe_join( {text, PostScript}, sepc );
 +
 
 +
-- Now enclose the whole thing in a <cite/> element
 +
local options = {};
 +
 +
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
 +
options.class = config.CitationClass;
 +
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
 +
else
 +
options.class = "citation";
 +
end
 +
 +
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
 +
local id = Ref
 +
if ('harv' == Ref ) then
 +
local namelist = {}; -- holds selected contributor, author, editor name list
 +
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
 +
 
 +
if #c > 0 then -- if there is a contributor list
 +
namelist = c; -- select it
 +
elseif #a > 0 then -- or an author list
 +
namelist = a;
 +
elseif #e > 0 then -- or an editor list
 +
namelist = e;
 +
end
 +
if #namelist > 0 then -- if there are names in namelist
 +
id = anchor_id (namelist, year); -- go make the CITEREF anchor
 +
else
 +
id = ''; -- unset
 +
end
 +
end
 +
options.id = id;
 +
end
 +
 +
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>","")) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains
 
z.error_categories = {};
 
z.error_categories = {};
 
text = set_error('empty_citation');
 
text = set_error('empty_citation');
Line 3,505: Line 3,335:
 
end
 
end
 
 
−
if is_set(options.id) then  
+
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
−
text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
+
text = substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text}); -- when |ref= is set
 
else
 
else
−
text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>";
+
text = substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text}); -- all other cases
 
end
 
end
  
−
local empty_span = '<span style="display:none;">&nbsp;</span>';
+
text = text .. substitute (cfg.presentation['ocins'], {OCinSoutput}); -- append metadata to the citation
−
 
−
-- Note: Using display: none on then COinS span breaks some clients.
 
−
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
 
−
text = text .. OCinS;
 
 
 
 
if #z.message_tail ~= 0 then
 
if #z.message_tail ~= 0 then
Line 3,554: Line 3,380:
 
end
 
end
  
−
-- This is used by templates such as {{cite book}} to create the actual citation text.
+
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
−
function z.citation(frame)
+
 
 +
This is used by templates such as {{cite book}} to create the actual citation text.
 +
 
 +
]]
 +
 
 +
function cs1.citation(frame)
 +
Frame = frame; -- save a copy incase we need to display an error message in preview mode
 
local pframe = frame:getParent()
 
local pframe = frame:getParent()
−
local validation;
+
local validation, utilities, identifiers, metadata;
 
 
 
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');
 +
 
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');
 
end
 
end
  
−
dates = validation.dates; -- imported functions
+
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
 +
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
 +
validation.set_selected_modules (utilities); -- so that functions in Date validataion can see the selected Utilities module
 +
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 +
 
 +
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation
 
year_date_check = validation.year_date_check;
 
year_date_check = validation.year_date_check;
 +
reformat_dates = validation.reformat_dates;
 +
date_hyphen_to_dash = validation.date_hyphen_to_dash;
 +
 +
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
 +
in_array = utilities.in_array;
 +
substitute = utilities.substitute;
 +
error_comment = utilities.error_comment;
 +
set_error = utilities.set_error;
 +
select_one = utilities.select_one;
 +
add_maint_cat = utilities.add_maint_cat;
 +
wrap_style = utilities.wrap_style;
 +
safe_for_italics = utilities.safe_for_italics;
 +
remove_wiki_link = utilities.remove_wiki_link;
 +
 +
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 +
 +
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Utilities
 +
build_id_list = identifiers.build_id_list;
 +
is_embargoed = identifiers.is_embargoed;
 +
extract_id_access_levels = identifiers.extract_id_access_levels;
 +
 +
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
 +
get_coins_pages = metadata.get_coins_pages;
 +
COinS = metadata.COinS;
  
 
local args = {};
 
local args = {};
Line 3,617: Line 3,484:
 
end
 
end
 
end
 
end
−
-- if #suggestions == 0 then
 
−
-- suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
 
−
-- end
 
−
-- if suggestions[ k:lower() ] ~= nil then
 
−
-- error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
 
−
-- else
 
−
-- error_text, error_state = set_error( 'parameter_ignored', {k}, true );
 
−
-- end
 
 
end    
 
end    
 
if error_text ~= '' then
 
if error_text ~= '' then
Line 3,630: Line 3,489:
 
end
 
end
 
end
 
end
 +
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe?
 +
 
args[k] = v;
 
args[k] = v;
 
elseif args[k] ~= nil or (k == 'postscript') then
 
elseif args[k] ~= nil or (k == 'postscript') then
Line 3,635: Line 3,496:
 
end
 
end
 
end
 
end
−
+
 
 +
for k, v in pairs( args ) do
 +
if 'string' == type (k) then -- don't evaluate positional parameters
 +
has_invisible_chars (k, v);
 +
end
 +
end
 
return citation0( config, args)
 
return citation0( config, args)
 
end
 
end
  
−
return z
+
return cs1;

Latest revision as of 00:52, 29 October 2016

Documentation for this module may be created at Module:Citation/CS1/doc 


local cs1 ={};

--[[--------------------------< F O R W A R D   D E C L A R A T I O N S >--------------------------------------
]]

local dates, year_date_check, reformat_dates, date_hyphen_to_dash				-- functions in Module:Citation/CS1/Date_validation

local is_set, in_array, substitute, error_comment, set_error, select_one,		-- functions in Module:Citation/CS1/Utilities
	add_maint_cat, wrap_style, safe_for_italics, remove_wiki_link;

local z ={};																	-- tables in Module:Citation/CS1/Utilities

local extract_ids, extract_id_access_levels, build_id_list, is_embargoed;					-- functions in Module:Citation/CS1/Identifiers

local make_coins_title, get_coins_pages, COinS;									-- 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 >--------------------------------------

delare variables here that have page-wide scope that are not brought in from other modules; thatare created here
and used here

]]

local added_deprecated_cat;														-- boolean flag so that the category is added only once
local added_prop_cats = {};														-- list of property categories that have been added to z.properties_cats
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 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 _ 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.

added_prop_cats is a table declared in page scope variables above

]]

local function add_prop_cat (key, arguments)
	if not added_prop_cats [key] then
		added_prop_cats [key] = true;											-- note that we've added this category
		table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments));		-- make name then add to table
	end
end

--[[--------------------------< 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)
	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', {source}, true ) } );
	end
end


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

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

returns true if it does, else false

]]

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


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

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

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

rfc952 (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 incase 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 TLD
	q, x, and z SL domains in the .com TLD
	i and q SL domains in the .net TLD
	single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
	two-character SL domains in gTLDs (where the gTLD is two or more letters)
	three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
	IPv4 dot-decimal address format; TLD not allowed

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
																				-- Do most common case first
	if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then				-- three or more character hostname.hostname or hostname.tld
		return true;
	elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then	-- internationalized domain name with ACE prefix
		return true;
	elseif domain:match ('%f[%a%d][%a%d]%.org$') then							-- one character .org hostname
		return true;
	elseif domain:match ('%f[%a][qxz]%.com$') then								-- assigned one character .com hostname (x.com times out 2015-12-10)
		return true;
	elseif domain:match ('%f[%a][iq]%.net$') then								-- assigned one character .net hostname (q.net registered but not active 2015-12-10)
		return true;
	elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then							-- one character hostname and cctld (2 chars)
		return true;
	elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then					-- two character hostname and tld
		return true;
	elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then		-- IPv4 address
		return true;
	else
		return false;
	end
end


--[[--------------------------< 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 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.

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
		authority = authority:gsub ('//', '', 1);								-- replace place 1 pair of '/' with nothing;
		if is_set(authority) then												-- if anything left (1 or 3+ '/' where authority should be) then
			return scheme;														-- return scheme only making domain nil which will cause an error message
		end
		domain = domain:gsub ('(%a):%d+', '%1');								-- strip port number if present
	end
	
	return scheme, domain;
end


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

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 wikilinked but not when |<param>-link= has a value.  This function emits an error message when
that condition exists

]]

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

	if 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
		end
	end

	if is_set (orig) then
		table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)});	-- url or wikilink in |title= with |title-link=;
	end
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 is_set(error_message) then										-- once we've added the first portion of the error message ...
				error_message=error_message .. ", ";							-- ... add a comma space separator
			end
			error_message=error_message .. "&#124;" .. k .. "=";				-- add the failed parameter
		end
	end
	if is_set (error_message) then												-- done looping, if there is an error message, display it
		table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
	end
end


--[[--------------------------< 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, { set_error( '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 is_set( label ) then
		label = URL;
		if is_set( source ) then
			error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
		else
			error( cfg.messages["bare_url_no_origin"] );
		end			
	end
	if not check_url( URL ) then
		error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
	end
	
	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=domain..path;														-- and reassemble
	end
	
	base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" });
	
	if is_set(access) then -- access level (free, paywalled, ...)
		base_url = substitute(cfg.presentation[access], base_url);
	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, { set_error( 'deprecated_params', {name}, true ) } );		-- add error 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 wikimarkup) are not kerned.

Replaces unicode quotemarks with typewriter quote marks regardless of the need for kerning.

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

]]

local function kern_quotes (str)
	local cap='';
	local cap2='';
																				-- TODO: move this elswhere so that all title-holding elements get these quote marks replaced?
	str= mw.ustring.gsub (str, '[“”]', '\"');									-- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
	str= mw.ustring.gsub (str, '[‘’]', '\'');									-- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
	
	cap, cap2 = str:match ("^([\"\'])([^\'].+)");								-- match leading double or single quote but not double single quotes
	if is_set (cap) then
		str = substitute (cfg.presentation['kern-left'], {cap, cap2});
	end

	cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
	if is_set (cap) then
		str = substitute (cfg.presentation['kern-right'], {cap, cap2});
	end
	return str;
end

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

|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
not be italicized and may be written right-to-left.  The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.

Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.

|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon:
	|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
	|script-title=ja : *** ***
	|script-title=ja: *** ***
	|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***

The prefix is checked for validity.  If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.

Supports |script-title= and |script-chapter=

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

local function format_script_value (script_value)
	local lang='';																-- initialize to empty string
	local name;
	if script_value:match('^%l%l%s*:') then										-- if first 3 non-space characters are script language prefix
		lang = script_value:match('^(%l%l)%s*:%s*%S.*');						-- get the language prefix or nil if there is no script
		if not is_set (lang) then
			return '';															-- script_value was just the prefix so return empty string
		end
																				-- if we get this far we have prefix and script
		name = mw.language.fetchLanguageName( lang, "en" );						-- get language name so that we can use it to categorize
		if is_set (name) then													-- is prefix a proper ISO 639-1 language code?
			script_value = script_value:gsub ('^%l%l%s*:%s*', '');				-- strip prefix from script
																				-- is prefix one of these language codes?
			if in_array (lang, cfg.script_lang_codes) then
				add_prop_cat ('script_with_name', {name, lang})
			else
				add_prop_cat ('script')
			end
			lang = ' lang="' .. lang .. '" ';									-- convert prefix into a lang attribute
		else
			lang = '';															-- invalid so set lang to empty string
		end
	end
	script_value = 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)
	if is_set (script) then
		script = format_script_value (script);									-- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
		if is_set (script) then
			title = title .. ' ' .. script;										-- concatenate title and script title
		end
	end
	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 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 substitute( msg, str );										-- including template text
	else
		return substitute( cfg.messages[key], str );
	end		
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 (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

	if is_set (transchapter) then
		transchapter = wrap_style ('trans-quoted-title', transchapter);
		if is_set (chapter) then
			chapter = chapter ..  ' ' .. transchapter;
		else																	-- here when transchapter without chapter or script-chapter
			chapter = transchapter;												-- 
			chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
		end
	end

	if is_set (chapterurl) then
		chapter = external_link (chapterurl, chapter, chapter_url_source, nil);		-- 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 >----------------------------------------

This function searches a parameter's value for nonprintable 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().

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

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

]]

local function has_invisible_chars (param, v)
	local position = '';														-- position of invisible char or starting position of stripmarker
	local dummy;																-- end of matching string; not used but required to hold end position when a capture is returned
	local capture;																-- used by stripmarker detection to hold name of the stripmarker
	local i=1;
	local stripmarker, apostrophe;
	
	capture = string.match (v, '[%w%p ]*');										-- Test for values that are simple ASCII text and bypass other tests if true
	if capture == v then														-- if same there are no unicode characters
		return;
	end

	while cfg.invisible_chars[i] do
		local char=cfg.invisible_chars[i][1]									-- the character or group name
		local pattern=cfg.invisible_chars[i][2]									-- the pattern used to find it
		position, dummy, capture = mw.ustring.find (v, pattern)					-- see if the parameter value contains characters that match the pattern
		
		if position then
			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
			else
				local err_msg;
				if capture then
					err_msg = capture .. ' ' .. char;
				else
					err_msg = char .. ' ' .. 'character';
				end

				table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } );	-- add error message
				return;															-- and done with this parameter
			end
		end
		i=i+1;																	-- bump our index
	end
end


--[[--------------------------< 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] = select_one( args, list, 'redundant_parameters' );
				if origin[k] == nil then
					origin[k] = ''; -- Empty string, not nil
				end
			elseif list ~= nil then
				v, origin[k] = args[list], list;
			else
				-- maybe let through instead of raising an error?
				-- v, origin[k] = args[k], k;
				error( cfg.messages['unknown_argument_map'] );
			end
			
			-- Empty strings, not nil;
			if v == nil then
				v = cfg.defaults[k] or '';
				origin[k] = '';
			end
			
			tbl = rawset( tbl, k, v );
			return v;
		end,
	});
end

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

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
	
	-- 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


--[[--------------------------< 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 = 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 = 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 is_set(title_type) then
		if "none" == 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

]]

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


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

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

]]

local function safe_join( tbl, duplicate_char )
	--[[
	Note: we use string functions here, rather than ustring functions.
	
	This has considerably faster performance and should work correctly as 
	long as the duplicate_char is strict ASCII.  The strings
	in tbl may be ASCII or UTF8.
	]]
	
	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 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
					if value ~= comp then 										-- value does not equal comp when value contains html markup
						local dup2 = duplicate_char;
						if dup2:match( "%A" ) then dup2 = "%" .. dup2; end		-- if duplicate_char not a letter then escape it
						
						value = value:gsub( "(%b<>)" .. dup2, "%1", 1 )			-- remove duplicate_char if it follows html markup
					else
						value = value:sub( 2, -1 );								-- remove duplicate_char when it is first character
					end
				end
			end
			str = str .. value;													--add it to the output string
		end
	end
	return str;
end  


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

returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9.  Puncutation not allowed.

]]

local function is_suffix (suffix)
	if in_array (suffix, {'Jr', 'Sr', '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 converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.

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

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

This original test:
	if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
was written ouside 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)
	local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first;		-- if first has something that looks like a generational suffix, get it

	if is_set (suffix) then
		if not is_suffix (suffix) then
			add_vanc_error ('suffix');
			return false;														-- not a name with an appropriate suffix
		end
	end
	if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
		nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
			add_vanc_error ('non-Latin character');
			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-format=vanc.  

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

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)
	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 intials?
	end

	if name then																-- if first is initials with or without suffix
		if 3 > name:len() 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 ('suffix');									-- 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 intial 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 (e.g. authors / editors) 

]]

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

	if 'vanc' == format then													-- Vancouver-like author/editor name styling?
		sep = ',';																-- name-list separator between authors is a comma
		namesep = ' ';															-- last/first separator is a space
	elseif 'mla' == control.mode then
		sep = ',';																-- name-list separator between authors is a comma
		namesep = ', '															-- last/first separator is <comma><space>
	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 'mla' == control.mode then 
						if i == 1 then											-- for mla
							one = one .. namesep .. first;						-- first name last, first
						else													-- all other names
							one = first .. ' ' .. one;							-- first last
						end
					else
						if ( "vanc" == format ) then								-- if vancouver format
							one = one:gsub ('%.', '');								-- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
							if not person.corporate and is_good_vanc_name (one, first) then					-- and name is all Latin characters; corporate authors not tested
								first = reduce_to_initials(first)					-- attempt to convert first name(s) to initials
							end
						end
						one = one .. namesep .. first;
					end
				end
				if is_set(person.link) and person.link ~= control.page_name then
					one = "[[" .. person.link .. "|" .. one .. "]]"				-- link author/editor if this page is not the author's/editor's page
				end
			end
			table.insert( text, one )
			table.insert( text, sep_one )
		end
	end

	local count = #text / 2;													-- (number of names + number of separators) divided by 2
	if count > 0 then 
		if count > 1 and is_set(lastauthoramp) and not etal then
			if 'mla' == control.mode then
				text[#text-2] = ", and ";										-- replace last separator with ', and ' text
			else
				text[#text-2] = " & ";											-- replace last separator with ampersand text
			end
		end
		text[#text] = nil;														-- erase the last separator
	end
	
	local result = table.concat(text)											-- construct list
	if etal and is_set (result) then											-- etal may be set by |display-authors=etal but we might not have a last-first list
		result = result .. sep .. ' ' .. cfg.messages['et al'];					-- we've go a last-first list and etal so add et al.
	end
	
	return result, count
end

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

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

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

]]
local function anchor_id (namelist, year)
	local 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


--[[--------------------------< 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,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.

This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal

]]

local function name_has_etal (name, etal, nocat)

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

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

Evaluates the content of author and editor (surnames only) parameters for multiple names.  Multiple names are
indicated if there is more than one comma and or semicolon.  If found, the function adds the multiple name
(author or editor) maintenance category.

]]

local function name_has_mult_names (name, list_name)
local count, _;
	if is_set (name) then
		if name:match ('^%(%(.*%)%)$') then										-- if wrapped in doubled parentheses, ignore 
			name = name:match ('^%(%((.*)%)%)$');								-- strip parens
		else
			_, count = name:gsub ('[;,]', '');									-- count the number of separator-like characters
			
			if 1 < count then													-- param could be |author= or |editor= so one separactor character is acceptable
				add_maint_cat ('mult_names', cfg.special_case_translation [list_name]);	-- more than one separator indicates multiple names so add a maint cat for this template
			end
		end
	end
	return name;																-- and 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, the page is added to a maintenance category.

]]

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 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.
		first, etal = name_has_etal (first, etal, false);						-- find and remove variations on et al.
--		last = name_has_mult_names (last, err_msg_list_name);					-- check for multiple names in last and its aliases
		last = name_has_mult_names (last, list_name);					-- check for multiple names in last and its aliases
		
		if first and not last then												-- if there is a firstn without a matching lastn
			table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } );	-- add this error message
		elseif not first and not last then										-- if both firstn and lastn aren't found, are we done?
			count = count + 1;													-- number of times we haven't found last and first
			if 2 <= count then													-- two missing names and we give up
				break;															-- normal exit or there is a two-name hole in the list; can't tell which
			end
		else																	-- we have last with or without a first
			link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i);	-- check for improper wikimarkup

			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

--[[--------------------------< 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') return 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'.

Names but 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.

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

]]

local function get_iso639_code (lang, this_wiki_code)
	local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all')		-- get a list of language names known to Wikimedia
																				-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
	local langlc = mw.ustring.lower(lang);										-- lower case version for comparisons
	
	for code, name in pairs(languages) do										-- scan the list to see if we can find our language
		if langlc == mw.ustring.lower(name) then
			if 2 ~= code:len() and 3 ~= code:len() then							-- two- or three-character codes only; extensions not supported
				return name;													-- so return the name but not the code
			end
			return name, code;													-- found it, return name to ensure proper capitalization and the the code
		end
	end
	return lang;																-- not valid language; return language in original case and nil for the code
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 bit 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.

]]

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 = mw.getContentLanguage();									-- get a language object for this wiki
	local this_wiki_code = this_wiki:getCode()									-- get this wiki's language code
	local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, 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

		if lang:match ('^%a%a%-') then											-- strip ietf language tags from code; TODO: is there a need to support 3-char with tag?
			lang = lang:match ('(%a%a)%-')										-- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
		end
		if 2 == lang:len() or 3 == lang:len() then								-- if two-or three-character code
			name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code);	-- get language name if |language= is a proper code
		end
	
		if is_set (name) then													-- if |language= specified a valid code
			code = lang:lower();												-- save it
		else
			name, code = get_iso639_code (lang, this_wiki_code);				-- attempt to get code from name (assign name here so that we are sure of proper capitalization)
		end
	
		if is_set (code) then													-- only 2- or 3-character codes
			if 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
					add_prop_cat ('foreign_lang_source', {name, code})			-- categorize it
				else															-- or is a recognized language (but has a three-character code)
					add_prop_cat ('foreign_lang_source_2', {code})				-- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
				end
			end
		else
			add_maint_cat ('unknown_lang');										-- add maint category if not already added
		end
		
		table.insert (language_list, name);
		name = '';																-- so we can reuse it
	end
	
	code = #language_list														-- reuse code as number of languages in the list
	if 2 >= code then
		name = table.concat (language_list, ' and ')							-- insert '<space>and<space>' between two language names
	elseif 2 < code then
		language_list[code] = 'and ' .. language_list[code];					-- prepend last name with 'and<space>'
		name = table.concat (language_list, ', ')								-- and concatenate with '<comma><space>' separators
	end
	if this_wiki_name == name then
		return '';																-- if one language and that language is this wiki's return an empty string (no annotation)
	end
	return (" " .. wrap_msg ('language', name));								-- otherwise wrap with '(in ...)'
	--[[ TODO: should only return blank or name rather than full list
	so we can clean up the bunched parenthetical elements Language, Type, Format
	]]
end

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

Set style settings for CS1 citation templates. Returns separator and postscript settings

]]

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 >----------------------------------------------------

Set style settings for CS2 citation templates. Returns separator, postscript, ref settings

]]

local function set_cs2_style (ps, ref)
	if not is_set (ps) then														-- if |postscript= has not been set, set cs2 default
		ps = '';																-- make sure it isn't nil
	end
	if not is_set (ref) then													-- if |ref= is not set
		ref = "harv";															-- set default |ref=harv
	end
	return ',', ps, ref;														-- separator is a comma
end

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

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

]]

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 citation.  Uses |mode= if set and valid or uses
config.CitationClass from the template's #invoke: to establish style.

]]

local function set_style (mode, ps, ref, cite_class)
	local sep;
	if 'cs2' == mode then														-- if this template is to be rendered in CS2 (citation) style
		sep, ps, ref = set_cs2_style (ps, ref);
	elseif 'cs1' == mode then													-- if this template is to be rendered in CS1 (cite xxx) style
		sep, ps = set_cs1_style (ps);
	elseif 'mla' == mode then													-- if this template is to be rendered in mla style use cs1 for bot cs1 & cs2 templates
		sep, ps = set_cs1_style (ps);
	else																		-- anything but cs1 or cs2
		sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class);		-- get settings based on the template's CitationClass
	end
	if 'none' == ps:lower() then												-- if assigned value is 'none' then
		ps = '';																-- set to empty string
	end
	
	return sep, ps, ref
end

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

Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
applying the pdf icon to external links.

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

]=]

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)
	if is_set (format) then
		format = wrap_style ('format', format);									-- add leading space, parenthases, resize
		if not is_set (url) then
			format = format .. set_error( 'format_missing_url', {fmt_param, url_param} );	-- add an error message
		end
	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
	return format;
end

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

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_authors_editors (max, count, list_name, etal)
	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
			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
				add_maint_cat ('disp_auth_ed', cfg.special_case_translation [list_name]);
			end
		else																	-- not a valid keyword or number
			table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } );		-- add error message
			max = nil;															-- unset; 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 page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp. 
abbreviation in the first characters of the parameter content.

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

]]

local function extra_text_in_page_check (page)
--	local 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
		add_maint_cat ('extra_text');
	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

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

split apart a |vautthors= 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 parnetheses were included in the
rendered citation and in the metadata.

	|vauthors=Jones AB, White EB, ((Black, Brown, and Co.))

This code is experimental and may not be retained.

]]
local function get_v_name_table (vparam, output_table)
	local name_table = mw.text.split(vparam, "%s*,%s*");						-- names are separated by commas
	
	local i = 1;
	
	while name_table[i] do
		if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then						-- first segment of corporate with one or more commas; this segment has the opening doubled parens
			local name = name_table[i];
			i=i+1;																-- bump indexer to next segment
			while name_table[i] do
				name = name .. ', ' .. name_table[i];							-- concatenate with previous segments
				if name_table[i]:match ('^.*%)%)$') then						-- if this table member has the closing doubled parens
					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
		else
			table.insert (output_table, name_table[i]);							-- add this name 
		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 paranethese ((corporate name)) to suppress the format tests.

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

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

]]

local function parse_vauthors_veditors (args, vparam, list_name)
	local names = {};															-- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
	local v_name_table = {};
	local etal = false;															-- return value set to true when we find some form of et al. vauthors parameter
	local last, first, link, mask, 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)
	if vparam:find ('%[%[') or vparam:find ('%]%]')	then						-- no wikilinking vauthors names
		add_vanc_error ('wikilink');
	end
	v_name_table = get_v_name_table (vparam, v_name_table);						-- names are separated by commas

	for i, v_name in ipairs(v_name_table) do
		if v_name:match ('^%(%(.+%)%)$') then									-- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
			first = '';															-- set to empty string for concatenation and because it may have been set for previous author/editor
			last = v_name:match ('^%(%((.+)%)%)$')								-- remove doubled parntheses
			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 ('punctuation');
			end
			local lastfirstTable = {}
			lastfirstTable = mw.text.split(v_name, "%s")
			first = table.remove(lastfirstTable);								-- removes and returns value of last element in table which should be author intials
			if is_suffix (first) then											-- if a valid suffix
				suffix = first													-- save it as a suffix and
				first = table.remove(lastfirstTable);							-- get what should be the initials from the table
			end																	-- no suffix error message here because letter combination may be result of Romanization; check for digits?
			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+') then
				add_vanc_error ('missing comma');								-- matches last II last; the case when a comma is missing
			end
			if mw.ustring.match (v_name, ' %u %u$') then						-- this test is in the wrong place TODO: move or replace with a more appropriate test
				add_vanc_error ('name');										-- matches a space between two intiials
			end
		else
			first = '';															-- set to empty string for concatenation and because it may have been set for previous author/editor
			last = v_name;														-- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
		end
																
		if is_set (first) then
			if not mw.ustring.match (first, "^%u?%u$") then						-- first shall contain one or two upper-case letters, nothing else
				add_vanc_error ('initials');									-- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
			end
			is_good_vanc_name (last, first);									-- check first and last before restoring the suffix which may have a non-Latin digit
			if is_set (suffix) then
				first = first .. ' ' .. suffix;									-- if there was a suffix concatenate with the initials
				suffix = '';													-- unset so we don't add this suffix to all subsequent names
			end
		else
			if not corporate then
				is_good_vanc_name (last, '');
			end
		end
																				-- this from extract_names ()
		link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
		mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
		names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate};		-- add this assembled name to our names list
	end
	return names, etal;															-- all done, return our list of names
end


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

Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.

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

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

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

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

]]

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

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

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


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

This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.

]]

local function is_valid_parameter_value (value, name, possible, cite_class)
-- begin hack to limit |mode=mla to a specific set of templates
	if ('mode' == name) and ('mla' == value) and not in_array (cite_class, {'book', 'journal', 'news'}) then
		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 hack

	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


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


--[[-------------------------< 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, mode)
	if not is_set (volume) and not is_set (issue) then
		return '';
	end
	
	if ('mla' == mode) and ('journal' == cite_class) then						-- same as cs1 for magazines
		lower = true;															-- mla 8th edition; force these to lower case
		if is_set (volume) and is_set (issue) then
			return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
		elseif is_set (volume) then
			return wrap_msg ('vol', {sepc, volume}, lower);
		else
			return '';
		end
	end

	if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
		if is_set (volume) and is_set (issue) then
			return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
		elseif is_set (volume) then
			return wrap_msg ('vol', {sepc, volume}, lower);
		else
			return wrap_msg ('issue', {sepc, issue}, lower);
		end
	end

	local vol = '';
		
	if is_set (volume) then
		if (4 < mw.ustring.len(volume)) then
			vol = substitute (cfg.messages['j-vol'], {sepc, volume});
		else
			vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)});
		end
	end
	if is_set (issue) then
		return vol .. substitute (cfg.messages['j-issue'], issue);
	end
	return vol;
end


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

not currently used

normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
returns list unchanged if there are no commas else strips whitespace and then reformats the list

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


--[[-------------------------< 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, mode)
	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

	local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
	
	if is_journal and 'mla' == mode then
		is_journal = false;														-- mla always uses p & pp
	end

	if is_set (page) then
		if is_journal then
			return substitute (cfg.messages['j-page(s)'], page), '', '', '';
		elseif not nopp then
			return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
		else
			return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
		end
	elseif is_set(pages) then
		if is_journal then
			return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
		elseif tonumber(pages) ~= nil and not nopp then										-- if pages is only digits, assume a single page number
			return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
		elseif not nopp then
			return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
		else
			return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
		end
	end
	
	return '', '', '', '';														-- return empty strings
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 funct 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.or url
	
	if not url:match('//web%.archive%.org/') then
		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 = 'save command';
		url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1);				-- for preview mode: modify ArchiveURL
	else
		path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/');		-- split out some of the url parts for evaluation
		
		if not is_set(timestamp) or 14 ~= timestamp:len() then					-- path and flag optional, must have 14-digit timestamp here
			err_msg = '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 is_set(path) and 'web/' ~= path then								-- older archive urls do not have the extra 'web/' path element
			err_msg = 'path';
		elseif is_set (flag) and not is_set (path) then							-- flag not allowed with the old form url (without the 'web/' path element)
			err_msg = 'flag';
		elseif 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 = 'flag';
		else
			return url, date;													-- return archiveURL and ArchiveDate
		end
	end
																				-- if here, something not right so
	table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } );	-- add error message and
	if 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


--[[--------------------------< 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:
	{{cite ... |title=Title access-date=2016-03-17}}

cs1|2 shares some parameter names with xml/html atributes: 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 (value)
	local capture;
	value = value:gsub ('%b<>', '');											-- remove xml/html tags because attributes: class=, title=, etc 

	capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*=');	-- find and categorize parameters with possible missing pipes
	if capture and validate (capture) then								-- if the capture is a valid parameter name
		add_maint_cat ('missing_pipe');
	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.	

-- 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'], config.CitationClass) then
		Mode = '';
	end

	local author_etal;
	local a	= {};																-- authors list from |lastn= / |firstn= pairs or |vauthors=
	local Authors;
	local NameListFormat = A['NameListFormat'];
	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
			NameListFormat = 'vanc';											-- override whatever |name-list-format= might be
			a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList');	-- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
		elseif 3 == selected then
			Authors = A['Authors'];												-- use content of |authors=
			if 'authors' == A:ORIGIN('Authors') then							-- but add a maint cat if the parameter is |authors=
				add_maint_cat ('authors');										-- because use of this parameter is discouraged; what to do about the aliases is a TODO:
			end
		end
		if is_set (Collaboration) then
			author_etal = true;													-- so that |display-authors=etal not required
		end
	end

	local Coauthors = A['Coauthors'];
	local Others = A['Others'];

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

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

	local t = {};																-- translators list from |translator-lastn= / translator-firstn= pairs
	local Translators;															-- assembled translators name list
	t = extract_names (args, 'TranslatorList');									-- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
	
	local Interviewers = A['Interviewers']
	
	local c = {};																-- contributors list from |contributor-lastn= / contributor-firstn= pairs
	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
		c = extract_names (args, 'ContributorList');							-- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
		
		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

	if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then			-- only accepted value for this parameter is 'vanc'
		NameListFormat = '';													-- anything else, set to empty string
	end

	local Year = A['Year'];
	local PublicationDate = A['PublicationDate'];
	local OrigYear = A['OrigYear'];
	local Date = A['Date'];
	local LayDate = A['LayDate'];
	------------------------------------------------- Get title data
	local Title = A['Title'];
	local ScriptTitle = A['ScriptTitle'];
	local BookTitle = A['BookTitle'];
	local Conference = A['Conference'];
	local TransTitle = A['TransTitle'];
	local TitleNote = A['TitleNote'];
	local TitleLink = A['TitleLink'];
			link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title');	-- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set

	local Chapter = A['Chapter'];
	local ScriptChapter = A['ScriptChapter'];
	local ChapterLink	-- = A['ChapterLink'];									-- deprecated as a parameter but still used internally by cite episode
	local TransChapter = A['TransChapter'];
	local TitleType = A['TitleType'];
	local Degree = A['Degree'];
	local Docket = A['Docket'];
	local ArchiveFormat = A['ArchiveFormat'];

	local ArchiveDate;
	local ArchiveURL;

	ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
	
	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 URL = A['URL']
	local URLorigin = A:ORIGIN('URL');											-- get name of parameter that holds URL
	local ChapterURL = A['ChapterURL'];
	local ChapterURLorigin = A:ORIGIN('ChapterURL');							-- get name of parameter that holds ChapterURL
	local ConferenceFormat = A['ConferenceFormat'];
	local ConferenceURL = A['ConferenceURL'];
	local ConferenceURLorigin = A:ORIGIN('ConferenceURL');						-- get name of parameter that holds ConferenceURL
	local Periodical = A['Periodical'];
	local Periodical_origin = A:ORIGIN('Periodical');							-- get the name of the periodical parameter

	local Series = A['Series'];
	
	local Volume;
	local Issue;
	local Page;
	local Pages;
	local At;
																				-- previously conference books did not support volume
--	if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
	if in_array (config.CitationClass, cfg.templates_using_volume) then
		Volume = A['Volume'];
	end
																				-- conference & map books do not support issue
	if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
		Issue = A['Issue'];
	end
	local Position = '';
	if not in_array (config.CitationClass, cfg.templates_not_using_page) then
		Page = A['Page'];
		Pages = hyphen_to_dash( A['Pages'] );	
		At = A['At'];
	end

	local Edition = A['Edition'];
	local PublicationPlace = A['PublicationPlace']
	local Place = A['Place'];
	
	local PublisherName = A['PublisherName'];
	local RegistrationRequired = A['RegistrationRequired'];
		if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
			RegistrationRequired=nil;
		end
	local SubscriptionRequired = A['SubscriptionRequired'];
		if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
			SubscriptionRequired=nil;
		end
	local UrlAccess = A['UrlAccess'];
		if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
			UrlAccess = nil;
		end
		if not is_set(URL) and is_set(UrlAccess) then
			UrlAccess = nil;
			table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } );
		end

		if is_set (UrlAccess) and is_set (SubscriptionRequired) then			-- while not aliases, these are much the same so if both are set
			table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } );		-- add error message
			SubscriptionRequired = nil;											-- unset; prefer |access= over |subscription=
		end
		if is_set (UrlAccess) and is_set (RegistrationRequired) then			-- these are not the same but contradictory so if both are set
			table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } );		-- add error message
			RegistrationRequired = nil;											-- unset; prefer |access= over |registration=
		end


	local Via = A['Via'];
	local AccessDate = A['AccessDate'];
	local Agency = A['Agency'];

	local Language = A['Language'];
	local Format = A['Format'];
	local ChapterFormat = A['ChapterFormat'];
	local DoiBroken = A['DoiBroken'];
	local ID = A['ID'];
	local ASINTLD = A['ASINTLD'];
	local IgnoreISBN = A['IgnoreISBN'];
		if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
			IgnoreISBN = nil;													-- anything else, set to empty string
		end
	local Embargo = A['Embargo'];
	local Class = A['Class'];													-- arxiv class identifier

	local ID_list = extract_ids( args );
	local ID_access_levels = extract_id_access_levels( args, ID_list );

	local Quote = A['Quote'];

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

	local LastAuthorAmp = A['LastAuthorAmp'];
		if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
			LastAuthorAmp = nil;												-- set to empty string
		end
		if 'mla' == Mode then												
			LastAuthorAmp = 'yes';												-- replaces last author/editor separator with ' and ' text
		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

--these deprecated parameters are used by cite interview
	local Callsign = A['Callsign'];
	local City = A['City'];
	local Program = A['Program'];

--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

	local DF = A['DF'];															-- date format set in cs1|2 template
	if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then	-- validate reformatting keyword
		DF = '';																-- not valid, set to empty string
	end

	local sepc;											-- separator between citation elements for CS1 a period, for CS2, a comma
	local PostScript;
	local Ref;
	sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
	use_lowercase = ( sepc == ',' );					-- used to control capitalization for certain static text

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

-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
	select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' );		-- this is a dummy call simply to get the error message and category

	local NoPP = A['NoPP'] 
	if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
		NoPP = true;
	else
		NoPP = nil;																-- unset, used as a flag later
	end

	if is_set(Page) then
		if is_set(Pages) or is_set(At) then
			Pages = '';															-- unset the others
			At = '';
		end
		extra_text_in_page_check (Page);										-- add this page to maint cat if |page= value begins with what looks like p. or pp.
	elseif is_set(Pages) then
		if is_set(At) then
			At = '';															-- unset
		end
		extra_text_in_page_check (Pages);										-- add this page to maint cat if |pages= value begins with what looks like p. or pp.
	end	

-- both |publication-place= and |place= (|location=) allowed if different
	if not is_set(PublicationPlace) and is_set(Place) then
		PublicationPlace = Place;							-- promote |place= (|location=) to |publication-place
	end
	
	if PublicationPlace == Place then Place = ''; end		-- don't need both if they are the same
	
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
	|encyclopedia and |title then map |title to |article and |encyclopedia to |title
	|encyclopedia and |article then map |encyclopedia to |title
	|encyclopedia then map |encyclopedia to |title

	|trans_title maps to |trans_chapter when |title is re-mapped
	|url maps to |chapterurl when |title is remapped

All other combinations of |encyclopedia, |title, and |article are not modified

]]

local Encyclopedia = A['Encyclopedia'];

	if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then	-- test code for citation
		if is_set(Periodical) then												-- Periodical is set when |encyclopedia is set
			if is_set(Title) or is_set (ScriptTitle) then
				if not is_set(Chapter) then
					Chapter = Title;											-- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
					ScriptChapter = ScriptTitle;
					TransChapter = TransTitle;
					ChapterURL = URL;
					if not is_set (ChapterURL) and is_set (TitleLink) then
						Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
					end
					Title = Periodical;
					ChapterFormat = Format;
					Periodical = '';											-- redundant so unset
					TransTitle = '';
					URL = '';
					Format = '';
					TitleLink = '';
					ScriptTitle = '';
				end
			else																-- |title not set
				Title = Periodical;												-- |encyclopedia set and |article set or not set so map |encyclopedia to |title
				Periodical = '';												-- redundant so unset
			end
		end
	end

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

-- special case for cite interview
-- TODO: make cite interview not need any special cases
--[[
Program, Callsign, City deprecated, so avoid using /Configuration
for reassignment, which would allow these parameters' use outside interview
]]
	if (config.CitationClass == "interview") then
		if is_set(Program) then
			if not is_set(Periodical) then
				Periodical = Program;
			end
		end
		if is_set(Callsign) then
			if not is_set(PublisherName) then
				PublisherName = Callsign;
			end
		end
		if is_set(City) then
			if not is_set(PublicationPlace) then
				PublicationPlace = City;
			end
		end
	end

-- special case for cite mailing list
	if (config.CitationClass == "mailinglist") then
		Periodical = A ['MailingList'];
	elseif 'mailinglist' == A:ORIGIN('Periodical') then
		Periodical = '';														-- unset because mailing list is only used for cite mailing list
	end

-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
	if 'conference' == config.CitationClass then
		if is_set(BookTitle) then
			Chapter = Title;
--			ChapterLink = TitleLink;											-- |chapterlink= is deprecated
			ChapterURL = URL;
			ChapterURLorigin = URLorigin;
			URLorigin = '';
			ChapterFormat = Format;
			TransChapter = TransTitle;
			Title = BookTitle;
			Format = '';
--			TitleLink = '';
			TransTitle = '';
			URL = '';
		end
	elseif 'speech' ~= config.CitationClass then
		Conference = '';														-- not cite conference or cite speech so make sure this is empty string
	end

-- cite map oddities
	local Cartography = "";
	local Scale = "";
	local Sheet = A['Sheet'] or '';
	local Sheets = A['Sheets'] or '';
	if config.CitationClass == "map" then
		Chapter = A['Map'];
		ChapterURL = A['MapURL'];
		TransChapter = A['TransMap'];
		ChapterURLorigin = A:ORIGIN('MapURL');
		ChapterFormat = A['MapFormat'];
		
		Cartography = A['Cartography'];
		if is_set( Cartography ) then
			Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
		end		
		Scale = A['Scale'];
		if is_set( Scale ) then
			Scale = sepc .. " " .. Scale;
		end
	end

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

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

		local Network = A['Network'];
		local Station = A['Station'];
		local s, n = {}, {};
																				-- do common parameters first
		if is_set(Network) then table.insert(n, Network); end
		if is_set(Station) then table.insert(n, Station); end
		ID = table.concat(n, sepc .. ' ');
		
		if not is_set (Date) and is_set (AirDate) then							-- promote airdate to date
			Date = AirDate;
		end

		if 'episode' == config.CitationClass then								-- handle the oddities that are strictly {{cite episode}}
			local Season = A['Season'];
			local SeriesNumber = A['SeriesNumber'];

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

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

-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
	if 'arxiv' == config.CitationClass then
		if not is_set (ID_list['ARXIV']) then									-- |arxiv= or |eprint= required for cite arxiv
			table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } );		-- add error message
		elseif is_set (Series) then												-- series is an alias of version
			ID_list['ARXIV'] = ID_list['ARXIV'] .. Series;						-- concatenate version onto the end of the arxiv identifier
			Series = '';														-- unset
			deprecated_parameter ('version');									-- deprecated parameter but only for cite arxiv
		end
		
		if first_set ({AccessDate, At, Authors, 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'],		-- TODO: find a better way to do this
			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
				Authors = '';
				PublisherName = '';												-- (if the article has been published, use cite journal, or other)
				Chapter = '';
				URL = '';
				Format = '';
				Page = ''; Pages = ''; At = '';
		end
		Periodical = 'arXiv';													-- set to arXiv for COinS; after that, must be set to empty string
	end

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

	if is_set(TitleType) then													-- if type parameter is specified
		TitleType = 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.
	if not is_set (Date) then
		Date = Year;															-- promote Year to Date
		Year = nil;																-- make nil so Year as empty string isn't used for CITEREF
		if not is_set (Date) and is_set(PublicationDate) then					-- use PublicationDate when |date= and |year= are not set
			Date = PublicationDate;												-- promote PublicationDate to Date
			PublicationDate = '';												-- unset, no longer needed
		end
	end

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

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

Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
	do	-- create defined block to contain local variables error_message, 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']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
				['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};

		anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);

		if is_set (Year) and is_set (Date) then									-- both |date= and |year= not normally needed; 
			local mismatch = year_date_check (Year, Date)
			if 0 == mismatch then												-- |year= does not match a year-value in |date=
				if is_set (error_message) then									-- if there is already an error message
					error_message = error_message .. ', ';						-- tack on this additional message
				end
				error_message = error_message .. '&#124;year= / &#124;date= mismatch';
			elseif 1 == mismatch then											-- |year= matches year-value in |date=
				add_maint_cat ('date_year');
			end
		end
		
		if not is_set(error_message) then										-- error free dates only
			local modified = false;												-- flag
			if is_set (DF) then													-- if we need to reformat dates
				modified = reformat_dates (date_parameters_list, DF, false);	-- reformat to DF format, use long month names if appropriate
			end

			if true == date_hyphen_to_dash (date_parameters_list) then					-- convert hyphens to dashes where appropriate
				modified = true;
				add_maint_cat ('date_format');									-- hyphens were converted so add maint category
			end
			
			if modified then													-- if the date_parameters_list values were modified
				AccessDate = date_parameters_list['access-date'];				-- overwrite date holding parameters with modified values
				ArchiveDate = date_parameters_list['archive-date'];
				Date = date_parameters_list['date'];
				DoiBroken = date_parameters_list['doi-broken-date'];
				LayDate = date_parameters_list['lay-date'];
				PublicationDate = date_parameters_list['publication-date'];
			end
		else
			table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } );	-- add this error message
		end
	end	-- end of do

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

	if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
		if not is_set (Embargo) then											-- if not embargoed or embargo has expired
			URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC'];				-- set url to be the same as the PMC external link if not embargoed
			URLorigin = cfg.id_handlers['PMC'].parameters[1];					-- set URLorigin to parameter name for use in error message if citation is missing a |title=
			if is_set(AccessDate) then											-- access date requires |url=; pmc created url is not |url=
				table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
				AccessDate = '';												-- unset
			end

		end
	end

-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
	-- Test if citation has no title
	if	not is_set(Title) and
		not is_set(TransTitle) and
		not is_set(ScriptTitle) then
			if 'episode' == config.CitationClass then							-- special case for cite episode; TODO: is there a better way to do this?
				table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
			else
				table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
			end
	end
	
	if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then	-- special case for journal cites
		Title = '';																-- set title to empty string
		add_maint_cat ('untitled');
	end

	check_for_url ({															-- add error message when any of these parameters contains a URL
		['title']=Title,
		[A:ORIGIN('Chapter')]=Chapter,
		[A:ORIGIN('Periodical')]=Periodical,
		[A:ORIGIN('PublisherName')] = PublisherName
		});

	-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
	-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
	-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
	-- is the article title, and Chapter is a section within the article.  So, we remap 
	
	local coins_chapter = Chapter;												-- default assuming that remapping not required
	local coins_title = Title;													-- et tu
	if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
		if is_set (Chapter) and is_set (Title) and is_set (Periodical) then		-- if all are used then
			coins_chapter = Title;												-- remap
			coins_title = Periodical;
		end
	end
	local coins_author = a;														-- default for coins rft.au 
	if 0 < #c then																-- but if contributor list
		coins_author = c;														-- use that instead
	end

	-- this is the function call to COinS()
	local OCinSoutput = COinS({
		['Periodical'] = Periodical,
		['Encyclopedia'] = Encyclopedia,
		['Chapter'] = make_coins_title (coins_chapter, ScriptChapter),			-- Chapter and ScriptChapter stripped of bold / italic wikimarkup
		['Degree'] = Degree;													-- cite thesis only
		['Title'] = make_coins_title (coins_title, ScriptTitle),				-- Title and ScriptTitle stripped of bold / italic wikimarkup
		['PublicationPlace'] = PublicationPlace,
		['Date'] = COinS_date.rftdate,											-- COinS_date has correctly formatted date if Date is valid;
		['Season'] = COinS_date.rftssn,
		['Chron'] =  COinS_date.rftchron or (not COinS_date.rftdate and Date) or '',	-- chron but if not set and invalid date format use Date; keep this last bit?
		['Series'] = Series,
		['Volume'] = Volume,
		['Issue'] = Issue,
		['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)),				-- pages stripped of external links
		['Edition'] = Edition,
		['PublisherName'] = PublisherName,
		['URL'] = first_set ({ChapterURL, URL}, 2),
		['Authors'] = coins_author,
		['ID_list'] = ID_list,
		['RawPage'] = this_page.prefixedText,
	}, config.CitationClass);

-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
	if 'arxiv' == config.CitationClass then										-- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
		Periodical = '';														-- periodical not allowed in cite arxiv; if article has been published, use cite journal
	end

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



	-- Now perform various field substitutions.
	-- We also add leading spaces and surrounding markup and punctuation to the
	-- various parts of the citation, but only when they are non-nil.
	local EditorCount;															-- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
	do
		local last_first_list;
		local control = { 
			format = NameListFormat,											-- empty string or 'vanc'
			maximum = nil,														-- as if display-authors or display-editors not set
			lastauthoramp = LastAuthorAmp,
			page_name = this_page.text,											-- get current page name so that we don't wikilink to it via editorlinkn
			mode = Mode
		};

		do																		-- do editor name list first because coauthors can modify control table
			control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
			last_first_list, EditorCount = list_people(control, e, editor_etal);

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

			if 1 == EditorCount and (true == editor_etal or 1 < #e) then		-- only one editor displayed but includes etal then 
				EditorCount = 2;												-- spoof to display (eds.) annotation
			end
		end
		do																		-- now do translators
			control.maximum = #t;												-- number of translators
			Translators = list_people(control, t, false);						-- et al not currently supported
		end
		do																		-- now do contributors
			control.maximum = #c;												-- number of contributors
			Contributors = list_people(control, c, false);						-- et al not currently supported
		end
		do																		-- now do authors
			control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);

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

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

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

-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
	ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
	ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
	Format = style_format (Format, URL, 'format', 'url');
	LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
	TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');

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

	if not is_set(URL) then
		if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then	-- |url= required for cite web, cite podcast, and cite mailinglist
			table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
		end
		
		-- do we have |accessdate= without either |url= or |chapter-url=?
		if is_set(AccessDate) and not is_set(ChapterURL)then					-- ChapterURL may be set when URL is not set;
			table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
			AccessDate = '';
		end
	end

	local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess;
	DeadURL = DeadURL:lower();													-- used later when assembling archived text
	if is_set( ArchiveURL ) then
		if 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
		elseif is_set (URL) then
			OriginalURL = URL;													-- save copy of original source URL
			OriginalURLorigin = URLorigin;										-- name of url parameter for error messages
			OriginalFormat = Format; 											-- and original |format=
			OriginalAccess = UrlAccess;
			if 'no' ~= DeadURL then												-- if URL set then archive-url applies to it
				URL = ArchiveURL												-- swap-in the archive's url
				URLorigin = A:ORIGIN('ArchiveURL')								-- name of archive url parameter for error messages
				Format = ArchiveFormat or '';									-- swap in archive's format
				UrlAccess = nil;												-- restricted access levels do not make sense for archived urls
			end
 		end
	end

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

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

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

	-- Format main title.
	if is_set(TitleLink) and is_set(Title) then
		Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
	end

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

	local TransError = "";
	if is_set(TransTitle) then
		if is_set(Title) then
			TransTitle = " " .. TransTitle;
		else
			TransError = " " .. set_error( 'trans_missing_title', {'title'} );
		end
	end
	
	Title = Title .. TransTitle;
	
	if is_set(Title) then
		if not is_set(TitleLink) and is_set(URL) then
			
			Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransError .. Format;
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
--			local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format;	-- do this so we get error message even if url is usurped no archive
--			if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then	-- when url links to inappropriate location and there is no archive of original source available
--				local err_msg
--				if temp_title:match ('%[%S+%s+(.+)%](<.+)') then				-- if there is an error message
--					Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)');	-- strip off external link; TODO: find a better to do this
--					Title = Title .. (err_msg or '');
--				end
--			else
--				Title = temp_title;
--			end

			URL = '';															-- unset these because no longer needed
			Format = "";
		else
			Title = Title .. TransError;
		end
	end

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

	if is_set (Conference) then
		if is_set (ConferenceURL) then
			Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil );
		end
		Conference = sepc .. " " .. Conference .. ConferenceFormat;
	elseif is_set(ConferenceURL) then
		Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
	end

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

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

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

	At = is_set(At) and (sepc .. " " .. At) or "";
	Position = is_set(Position) and (sepc .. " " .. Position) or "";
	if config.CitationClass == 'map' then
		local Section = A['Section'];
		local Sections = A['Sections'];
		local Inset = A['Inset'];
		
		if is_set( Inset ) then
			Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
		end			

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

	if is_set (Language) then
		Language = language_parameter (Language);								-- format, categories, name from ISO639-1, etc
	else
		Language="";															-- language not specified so make sure this is an empty string;
	--[[ TODO: need to extract the wrap_msg from language_parameter
	so that we can solve parentheses bunching problem with Format/Language/TitleType
	]]
	end

	Others = is_set(Others) and (sepc .. " " .. Others) or "";
	
	if is_set (Translators) then
		if 'mla' == Mode then
			Others = sepc .. ' Trans. ' .. Translators .. Others;
		else
			Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;
		end
	end
	if is_set (Interviewers) then
		Others = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others;
	end
	
	TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
	if is_set (Edition) then
		if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
			add_maint_cat ('extra_text', 'edition');
		end
		if 'mla' == Mode then
			Edition = '. ' .. Edition .. ' ed.';
		else
			Edition = " " .. wrap_msg ('edition', Edition);
		end
	else
		Edition = '';
	end

	Series = is_set(Series) and (sepc .. " " .. Series) or "";
	if 'mla' == Mode then														-- not in brackets for mla
		OrigYear = is_set(OrigYear) and (". " .. OrigYear) or "";
	else
		OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
	end
	Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";

	Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase, Mode);

	------------------------------------ totally unrelated data
	if is_set(Via) then
		Via = " " .. wrap_msg ('via', Via);
	end

--[[
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.

]]
	if is_set (SubscriptionRequired) then
		SubscriptionRequired = sepc .. " " .. cfg.messages['subscription'];		-- subscription required message
	elseif is_set (RegistrationRequired) then
		SubscriptionRequired = sepc .. " " .. cfg.messages['registration'];		-- registration required message
	else
		SubscriptionRequired = '';												-- either or both might be set to something other than yes true y
	end

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

		AccessDate = nowrap_date (AccessDate);									-- wrap in nowrap span if date in appropriate format
		if 'mla' == Mode then													-- retrieved text not used in mla
			AccessDate = ' ' .. AccessDate;
		else
			if (sepc ~= ".") then retrv_text = retrv_text:lower() end			-- if mode is cs2, lower case
			AccessDate = substitute (retrv_text, AccessDate);					-- add retrieved text
		end
		AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate});	-- allow editors to hide accessdates
	end
	
	if is_set(ID) then ID = sepc .." ".. ID; end
   	if "thesis" == config.CitationClass and is_set(Docket) then
		ID = sepc .." Docket ".. Docket .. ID;
	end
   	if "report" == config.CitationClass and is_set(Docket) then					-- for cite report when |docket= is set
		ID = sepc .. ' ' .. Docket;												-- overwrite ID even if |id= is set
	end

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

	if is_set(URL) then
		URL = " " .. external_link( URL, nil, URLorigin, Access );
	end

	if is_set(Quote) then
		if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then				-- if first and last characters of quote are quote marks
			Quote = Quote:sub(2,-2);											-- strip them off
		end
		Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); 				-- wrap in <q>...</q> tags
		PostScript = "";														-- cs1|2 does not supply terminal punctuation when |quote= is set
	end
	
	local Archived
	if is_set(ArchiveURL) then
		if not is_set(ArchiveDate) then
			ArchiveDate = set_error('archive_missing_date');
		end
		if "no" == DeadURL then
			local arch_text = cfg.messages['archived'];
			if sepc ~= "." then arch_text = arch_text:lower() end
			Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
				{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
			if not is_set(OriginalURL) then
				Archived = Archived .. " " .. set_error('archive_missing_url');							   
			end
		elseif is_set(OriginalURL) then											-- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
			local arch_text = cfg.messages['archived-dead'];
			if sepc ~= "." then arch_text = arch_text:lower() end
			if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then
				Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate;	-- format already styled
				if 'bot: unknown' == DeadURL then
					add_maint_cat ('bot:_unknown');								-- and add a category if not already added
				else
					add_maint_cat ('unfit');									-- and add a category if not already added
				end
			else																-- DeadURL is empty, 'yes', 'true', or 'y'
				Archived = sepc .. " " .. substitute( arch_text,
					{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } );	-- format already styled
			end	
		else
			local arch_text = cfg.messages['archived-missing'];
			if sepc ~= "." then arch_text = arch_text:lower() end
			Archived = sepc .. " " .. substitute( arch_text, 
				{ set_error('archive_missing_url'), ArchiveDate } );
		end
	elseif is_set (ArchiveFormat) then
		Archived = ArchiveFormat;												-- if set and ArchiveURL not set ArchiveFormat has error message
	else
		Archived = ""
	end
	
	local Lay = '';
	if is_set(LayURL) then
		if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
		if is_set(LaySource) then 
			LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
		else
			LaySource = "";
		end
		if sepc == '.' then
			Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
		else
			Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
		end			
	elseif is_set (LayFormat) then												-- Test if |lay-format= is given without giving a |lay-url=
		Lay = sepc .. LayFormat;												-- if set and LayURL not set, then LayFormat has error message
	end

	if is_set(Transcript) then
		if is_set(TranscriptURL) then
			Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil );
		end
		Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
	elseif is_set(TranscriptURL) then
		Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
	end

	local Publisher;
	if is_set(PublicationDate) then
		PublicationDate = wrap_msg ('published', PublicationDate);
	end
	if is_set(PublisherName) then
		if is_set(PublicationPlace) then
			Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
		else
			Publisher = sepc .. " " .. PublisherName .. PublicationDate;  
		end			
	elseif is_set(PublicationPlace) then 
		Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
	else 
		Publisher = PublicationDate;
	end
	
	-- Several of the above rely upon detecting this as nil, so do it last.
	if is_set(Periodical) then
		if is_set(Title) or is_set(TitleNote) then 
			Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical) 
		else 
			Periodical = wrap_style ('italic-title', Periodical)
		end
	end

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

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

	local tcommon;
	local tcommon2;																-- used for book cite when |contributor= is set
	
	if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
		if is_set(Others) then Others = Others .. sepc .. " " end
		if 'mla' == Mode then
			tcommon = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
		else
			tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, 
				Language, Edition, Publisher, Agency, Volume}, sepc );
		end		
	elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then		-- special cases for book cites
		if is_set (Contributors) then											-- when we are citing foreword, preface, introduction, etc
			tcommon = safe_join( {Title, TitleNote}, sepc );					-- author and other stuff will come after this and before tcommon2
			if 'mla' == Mode then
				tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Edition, Publisher, Agency}, sepc );
			else
				tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
			end
		elseif 'mla' == Mode then
			tcommon = safe_join( {TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Publisher, Agency}, sepc );
		else
			tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
		end

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

	elseif ('news' == config.CitationClass) and ('mla' == Mode) then			-- special case for cite news in MLA mode
		tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, Edition, Agency}, sepc );

	elseif ('web' == config.CitationClass) and ('mla' == Mode) then				-- special case for cite web in MLA mode
		tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, 
			Edition, Publisher, Agency}, sepc );

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

	if is_set(Date) then
		if ('mla' == Mode) then
			if in_array (config.CitationClass, {'book', 'news', 'web'}) then
				Date = ', ' .. Date;											-- origyear follows title in mla
			elseif 'journal' == config.CitationClass then
				Date = ', (' .. Date .. ')';
			end
		elseif is_set (Authors) or is_set (Editors) then						-- date follows authors or editors when authors not set
			Date = " (" .. Date ..")" .. OrigYear .. sepc .. " ";				-- in paranetheses
		else																	-- neither of authors and editors set
			if (string.sub(tcommon,-1,-1) == sepc) then							-- if the last character of tcommon is sepc
				Date = " " .. Date .. OrigYear;									-- Date does not begin with sepc
			else
				Date = sepc .. " " .. Date .. OrigYear;							-- Date begins with sepc
			end
		end
	end	
	if is_set(Authors) then
		if is_set(Coauthors) then
			if 'vanc' == NameListFormat then									-- separate authors and coauthors with proper name-list-separator
				Authors = Authors .. ', ' .. Coauthors;
			else
				Authors = Authors .. '; ' .. Coauthors;
			end
		end
		if (not is_set (Date)) or ('mla' == Mode) then							-- when date is set it's in parentheses; no Authors termination
			Authors = terminate_name_list (Authors, sepc);						-- when no date, terminate with 0 or 1 sepc and a space
		end
		if is_set(Editors) then
			local in_text = " ";
			local post_text = "";
			if is_set(Chapter) and 0 == #c and 'mla' ~= Mode then
				in_text = in_text .. cfg.messages['in'] .. " "
				if (sepc ~= '.') then in_text = in_text:lower() end				-- lowercase for cs2
			elseif is_set(Chapter) and 'mla' == Mode then
				if EditorCount <= 1 then
					in_text = '. Ed. ';
				else
					in_text = '. Eds. ';
				end
			else
				if EditorCount <= 1 then
					post_text = ", " .. cfg.messages['editor'];
				else
					post_text = ", " .. cfg.messages['editors'];
				end
			end 
			Editors = terminate_name_list (in_text .. Editors .. post_text, sepc);	-- terminate with 0 or 1 sepc and a space
		end
		if is_set (Contributors) then											-- book cite and we're citing the intro, preface, etc
			local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
			if (sepc ~= '.') then by_text = by_text:lower() end					-- lowercase for cs2
			Authors = by_text .. Authors;										-- author follows title so tweak it here
			if is_set (Editors) and ('mla' ~= Mode)then											-- when Editors make sure that Authors gets terminated
				Authors = terminate_name_list (Authors, sepc);					-- terminate with 0 or 1 sepc and a space
			end
			if (not is_set (Date)) or ('mla' == Mode) 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
			if 'mla' == Mode then
				text = safe_join( {Contributors, Chapter, tcommon, OrigYear, Authors, Place, Others, Editors, tcommon2, Date, pgtext, idcommon }, sepc );
			else
				text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
			end
		elseif 'mla' == Mode then
			tcommon = tcommon .. Date;											-- hack to avoid duplicate separators
			text = safe_join( {Authors, Chapter, Title, OrigYear, Others, Editors, Edition, Place, tcommon, pgtext, idcommon }, sepc );
		else
			text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
		end
	elseif is_set(Editors) then
		if is_set(Date) then
			if EditorCount <= 1 then
				Editors = Editors .. ", " .. cfg.messages['editor'];
			else
				Editors = Editors .. ", " .. cfg.messages['editors'];
			end
		else
			if EditorCount <= 1 then
				Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
			else
				Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
			end
		end
		if 'mla' == Mode then
			if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
				text = safe_join( {Editors, Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
			else
				text = safe_join( {Editors, Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
			end
		else
			text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
		end
	elseif 'mla' == Mode then
		if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
			text = safe_join( {Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
		else
			text = safe_join( {Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
		end
	else
		if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
			text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
		else
			text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
		end
	end
	
	if is_set(PostScript) and PostScript ~= sepc then
		text = safe_join( {text, sepc}, sepc );  --Deals with italics, spaces, etc.
		text = text:sub(1,-sepc:len()-1);
	end	
	
	text = safe_join( {text, PostScript}, sepc );

	-- Now enclose the whole thing in a <cite/> element
	local options = {};
	
	if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
		options.class = config.CitationClass;
		options.class = "citation " .. config.CitationClass;					-- class=citation required for blue highlight when used with |ref=
	else
		options.class = "citation";
	end
	
	if is_set(Ref) and Ref:lower() ~= "none" then								-- set reference anchor if appropriate
		local id = Ref
		if ('harv' == Ref ) then
			local namelist = {};												-- holds selected contributor, author, editor name list
			local year = first_set ({Year, anchor_year}, 2);					-- Year first for legacy citations and for YMD dates that require disambiguation

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

	text = text .. substitute (cfg.presentation['ocins'], {OCinSoutput});		-- append metadata to the citation
	
	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
		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

--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------

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

]]

function cs1.citation(frame)
	Frame = frame;																-- save a copy incase we need to display an error message in preview mode
	local pframe = frame:getParent()
	local validation, utilities, identifiers, metadata;
	
	if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then			-- did the {{#invoke:}} use sandbox version?
		cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox');		-- load sandbox versions of support modules
		whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
		utilities = require ('Module:Citation/CS1/Utilities/sandbox');
		validation = require ('Module:Citation/CS1/Date_validation/sandbox');
		identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
		metadata = require ('Module:Citation/CS1/COinS/sandbox');
		
	else																		-- otherwise
		cfg = mw.loadData ('Module:Citation/CS1/Configuration');				-- load live versions of support modules
		whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
		utilities = require ('Module:Citation/CS1/Utilities');
		validation = require ('Module:Citation/CS1/Date_validation');
		identifiers = require ('Module:Citation/CS1/Identifiers');
		metadata = require ('Module:Citation/CS1/COinS');
	end

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

	dates = validation.dates;													-- imported functions from Module:Citation/CS1/Date validation
	year_date_check = validation.year_date_check;
	reformat_dates = validation.reformat_dates;
	date_hyphen_to_dash = validation.date_hyphen_to_dash;
	
	is_set = utilities.is_set;													-- imported functions from Module:Citation/CS1/Utilities
	in_array = utilities.in_array;
	substitute = utilities.substitute;
	error_comment = utilities.error_comment;
	set_error = utilities.set_error;
	select_one = utilities.select_one;
	add_maint_cat = utilities.add_maint_cat;
	wrap_style = utilities.wrap_style;
	safe_for_italics = utilities.safe_for_italics;
	remove_wiki_link = utilities.remove_wiki_link;

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

	extract_ids = identifiers.extract_ids;										-- imported functions from Module:Citation/CS1/Utilities
	build_id_list = identifiers.build_id_list;
	is_embargoed = identifiers.is_embargoed;
	extract_id_access_levels = identifiers.extract_id_access_levels;
	
	make_coins_title = metadata.make_coins_title;								-- imported functions from Module:Citation/CS1/COinS
	get_coins_pages = metadata.get_coins_pages;
	COinS = metadata.COinS;

	local args = {};
	local suggestions = {};
	local error_text, error_state;

	local config = {};
	for k, v in pairs( frame.args ) do
		config[k] = v;
		args[k] = v;	   
	end	

	local capture;																-- the single supported capture when matching unknown parameters using patterns
	for k, v in pairs( pframe.args ) do
		if v ~= '' then
			if not validate( k ) then			
				error_text = "";
				if type( k ) ~= 'string' then
					-- Exclude empty numbered parameters
					if v:match("%S+") ~= nil then
						error_text, error_state = set_error( 'text_ignored', {v}, true );
					end
				elseif validate( k:lower() ) then 
					error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
				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 caputre in pattern else the capture if a match
						if capture then											-- if the pattern matches 
							param = substitute( param, capture );				-- add the capture to the suggested parameter (typically the enumerator)
							error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true );	-- set the error message
						end
					end
					if not is_set (error_text) then								-- couldn't match with a pattern, is there an expicit suggestion?
						if suggestions.suggestions[ k:lower() ] ~= nil then
							error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
						else
							error_text, error_state = set_error( 'parameter_ignored', {k}, true );
						end
					end
				end				  
				if error_text ~= '' then
					table.insert( z.message_tail, {error_text, error_state} );
				end				
			end
			missing_pipe_check (v);												-- do we think that there is a parameter that is missing a pipe?
			
			args[k] = v;
		elseif args[k] ~= nil or (k == 'postscript') then
			args[k] = v;
		end		
	end	

	for k, v in pairs( args ) do
		if 'string' == type (k) then											-- don't evaluate positional parameters
			has_invisible_chars (k, v);
		end
	end
	return citation0( config, args)
end

return cs1;
Retrieved from "http://timelines.issarice.com/index.php?title=Module:Citation/CS1&oldid=4111"