వికీపీడియా

మాడ్యూల్:Citation/CS1/sandbox: కూర్పుల మధ్య తేడాలు

చరిత్రలో దిద్దుబాట్లను ఎంపిక చేసుకుంటూ తేడాలు చూడండి
← మునుపటి తేడాతరువాతి తేడా →
Content deleted Content added
trial fix
చి reset changes list;
పంక్తి 1:
--[[
local z = {
History of changes since last sync: 2019-09-03
error_categories = {};
error_ids = {};
message_tail = {};
}
 
-- Include translation message hooks, ID and error handling configuration settings.
local cfg = mw.loadData( 'Module:Citation/CS1/Configuration' );
 
]]
-- Contains a list of all recognized parameters
local whitelist = mw.loadData( 'Module:Citation/CS1/Whitelist' );
 
-- Whether variable is set or not
function is_set( var )
return not (var == nil or var == '');
end
 
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
-- First set variable or nil if none
]]
function first_set(...)
local list = {...};
for _, var in pairs(list) do
if is_set( var ) then
return var;
end
end
end
 
local dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation
-- Whether needle is in haystack
date_name_xlate
function inArray( needle, haystack )
 
if needle == nil then
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
return false;
add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink,
end
strip_apostrophe_markup;
for n,v in ipairs( haystack ) do
 
if v == needle then
local z ={}; -- tables in Module:Citation/CS1/Utilities
return n;
 
end
local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
end
 
return false;
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 >--------------------------------------------------------
Categorize and emit an error message when the citation contains one or more deprecated parameters. Because deprecated parameters (currently |day=, |month=,
 
|coauthor=, and |coauthors=) aren't related to each other and because these parameters may be concatenated into the variables used by |date= and |author#= (and aliases)
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
details of which parameter caused the error message are not provided. Only one error message is emitted regarless of the number of deprecated parameters in the citation.
 
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages
may be categorized but multiples of the same language are not categorized.
 
added_prop_cats is a table declared in page scope variables above
 
]]
 
function deprecated_parameter()
local function add_prop_cat (key, arguments)
if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a
if not added_prop_cats [key] then
Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once
added_prop_cats [key] = true; -- note that we've added this category
table.insert( z.message_tail, { seterror( 'deprecated_params', {error_message}, true ) } ); -- add error message
key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
 
 
-- Populates numbered arguments in a message string using an argument table.
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
function substitute( msg, args )
 
-- return args and tostring( mw.message.newRawMessage( msg, args ) ) or msg;
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
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 >------------------------------------------------------------
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:
does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it
"'Unkerned title with leading and trailing single quote marks'"
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
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
 
]]
 
function kern_quotes (str)
local function is_scheme (scheme)
local left='<span style="padding-left:0.2em;">%1</span>'; -- spacing to use when title contains leading single or double quote mark
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
local right='<span style="padding-right:0.2em;">%1</span>'; -- spacing to use when title contains trailing single or double quote mark
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, .cash, and .today TLDs
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
two-character SL domains in gTLDs (where the gTLD is two or more letters)
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
IPv4 dot-decimal address format; TLD not allowed
 
returns true if domain appears to be a proper name and tld or IPv4 address, else false
 
]=]
 
local function is_domain_name (domain)
if not domain then
return false; -- if not set, abandon
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if str:match ("^[\"\'][^\']") then
str = string.gsub( str, "^[\"\']", left, 1 ); -- replace (captured) leading single or double quote with left-side <span>
if not domain:match ('^[%w]') then -- first character must be letter or digit
return false;
end
 
if str:match ("[^\'][\"\']$") then
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at wikisource
str = string.gsub( str, "[\"\']$", right, 1 ); -- replace (captured) trailing single or double quote with right-side <span>
return false;
end
return str;
end
 
local patterns = { -- patterns that look like urls
-- Wraps a string using a message_list configuration taking one argument
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
function wrap( key, str, lower )
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
if not is_set( str ) then
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
return "";
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
elseif inArray( key, { 'italic-title', 'trans-italic-title' } ) then
'%f[%w][%w]%.%a%a$', -- one character hostname and cctld (2 chars)
str = safeforitalics( str );
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and tld
end
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
if lower == true then
}
return substitute( cfg.messages[key]:lower(), {str} );
 
else
for _, pattern in ipairs (patterns) do -- loop through the patterns list
return substitute( cfg.messages[key], {str} );
if domain:match (pattern) then
end
return true; -- if a match then we think that this thing that purports to be a url is a url
end
end
 
for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
if domain:match ('%f[%w][%w]%.' .. d) then
return true
end
end
return false; -- no matches, we don't know what this thing is
end
 
 
--[[
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
Argument wrapper. This function provides support for argument
 
mapping defined in the configuration file so that multiple names
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
can be transparently aliased to single internal variable.
 
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.
 
]]
 
function argument_wrapper( args )
local function is_url (scheme, domain)
local origin = {};
if is_set (scheme) then -- if scheme is set check it and domain
return is_scheme (scheme) and is_domain_name (domain);
return setmetatable({
else
ORIGIN = function( self, k )
return is_domain_name (domain); -- scheme not set when url is protocol relative
local dummy = self[k]; --force the variable to be loaded.
end
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] = selectone( 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
 
--[[
Looks for a parameter's name in the whitelist.
 
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
Parameters in the whitelist can have three values:
 
true - active, supported parameters
Split a url into a scheme, authority indicator, and domain.
false - deprecated, supported parameters
 
nil - unsupported parameters
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;
 
]]
 
function validate( name )
local namefunction =split_url tostring( name url_str);
local scheme, authority, domain;
local state = whitelist.basic_arguments[ name ];
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
-- Normal arguments
 
if true == state then return true; end -- valid actively supported parameter
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
if false == state then
domain = url_str:match ('^//(%S*)')
deprecated_parameter (); -- parameter is deprecated but still supported
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
return true;
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;
-- 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 (); -- parameter is deprecated but still supported
return true;
end
return false; -- Not supported because not found or name is set to nil
end
 
 
-- Formats a comment for error trapping
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
function errorcomment( content, hidden )
 
return wrap( hidden and 'hidden-error' or 'visible-error', content );
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 >---------------------------------------------------
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.
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
 
]]
 
function seterror( error_id, arguments, raw, prefix, suffix )
local function link_title_ok (link, lorig, title, torig)
local error_state = cfg.error_conditions[ error_id ];
local orig;
 
prefix = prefix or "";
if is_set (link) then -- don't bother if <param>-link doesn't have a value
suffix = suffix or "";
if not link_param_ok (link) then -- check |<param>-link= markup
orig = lorig; -- identify the failing link parameter
if error_state == nil then
elseif title:find ('%[%[') then -- check |title= for wikilink markup
error( cfg.messages['undefined_error'] );
orig = torig; -- identify the failing |title= parameter
elseif is_set( error_state.category ) then
end
table.insert( z.error_categories, error_state.category );
end
 
if is_set (orig) then
local message = substitute( error_state.message, arguments );
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=;
end
message = message .. " ([[" .. cfg.messages['help page link'] ..
"#" .. error_state.anchor .. "|" ..
cfg.messages['help page label'] .. "]])";
z.error_ids[ error_id ] = true;
if inArray( 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 errorcomment( message, error_state.hidden );
end
 
 
-- Formats a wiki style external link
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
function externallinkid(options)
 
local url_string = options.id;
Determines whether a URL string appears to be valid.
if options.encode == true or options.encode == nil then
 
url_string = mw.uri.encode( url_string );
First we test for space characters. If any are found, return false. Then split the url into scheme and domain
end
portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false.
options.link, options.label, options.separator or "&nbsp;",
 
options.prefix, url_string, options.suffix or "",
Because it is different from a standard url, and because this module used external_link() to make external links
mw.text.nowiki(options.id)
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
 
 
-- Formats a wiki style internal link
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
function internallinkid(options)
 
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
options.link, options.label, options.separator or "&nbsp;",
non-space characters following the opening bracket appear to be a url. The test will also find external wikilinks
options.prefix, options.id, options.suffix or "",
that use protocol relative urls. Also finds bare urls.
mw.text.nowiki(options.id)
 
);
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
 
 
-- Format an external link with error checking
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
function externallink( URL, label, source )
 
local error_str = "";
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
if not is_set( label ) then
 
label = URL;
]]
if is_set( source ) then
 
error_str = seterror( 'bare_url_missing_title', { wrap( 'parameter', source ) }, false, " " );
local function check_for_url (parameter_list)
else
local error_message = '';
error( cfg.messages["bare_url_no_origin"] );
for k, v in pairs (parameter_list) do -- for each parameter in the list
end
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
end
if is_set(error_message) then -- once we've added the first portion of the error message ...
if not checkurl( URL ) then
error_message=error_message .. ", "; -- ... add a comma space separator
error_str = seterror( 'bad_url', {}, false, " " ) .. error_str;
end
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
return table.concat({ "[", URL, " ", safeforurl( label ), "]", error_str });
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
 
 
-- Formats a link to Amazon
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
function amazon(id, domain)
 
if not is_set(domain) then
Escape sequences for content that will be used for URL descriptions
domain = "com"
 
elseif ( "jp" == domain or "uk" == domain ) then
]]
domain = "co." .. domain
 
end
local function safe_for_url( str )
local handler = cfg.id_handlers['ASIN'];
if str:match( "%[%[.-%]%]" ) ~= nil then
return externallinkid({link = handler.link,
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
label=handler.label , prefix="//www.amazon."..domain.."/dp/",id=id,
end
encode=handler.encode, separator = handler.separator})
return str:gsub( '[%[%]\n]', {
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
 
 
--[[
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
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.
Format an external link with error checking
 
]]
 
function pmid(id)
local function external_link( URL, label, source, access)
local test_limit = 30000000; -- update this value as PMIDs approach
local handlererror_str = cfg.id_handlers['PMID']"";
local domain;
local err_cat = ''; -- presume that PMID is valid
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
ifdomain, idpath = URL:match ("['^([/%.%-%+:%a%d]"+) then ([/%?#].*)$'); -- ifsplit the url into PMIDscheme hasplus anythingdomain butand digitspath
if path then -- if there is a path portion
err_cat = ' ' .. seterror( 'bad_pmid' ); -- set an error message
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
else -- PMID is only digits
URL = table.concat ({domain, path}); -- and reassemble
local id_num = tonumber(id); -- convert id to a number for range testing
end
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
 
err_cat = ' ' .. seterror( 'bad_pmid' ); -- set an error message
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url
end
 
if is_set (access) then -- access level (subscription, registration, limited)
base_url = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
end
return table.concat ({base_url, error_str});
return externallinkid({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
 
 
--[[
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is
 
in the future, returns true; otherwse, returns false because the embargo has expired or |embargo= not set in this cite.
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
 
]]
 
function is_embargoed(embargo)
local function deprecated_parameter(name)
if is_set(embargo) then
if not added_deprecated_cat then
local lang = mw.getContentLanguage();
added_deprecated_cat = true; -- note that we've added this category
local good1, embargo_date, good2, todays_date;
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
end
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
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 in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
 
Call this function for chapter titles, for website titles, etc; not for book titles.
 
]=]
 
local function kern_quotes (str)
local cap='';
local cap2='';
local wl_type, label, link;
 
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
if good1 and good2 and tonumber( embargo_date ) >= tonumber( todays_date ) then --is embargo date is in the future?
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
return true; -- still embargoed
str = substitute (cfg.presentation['kern-wl-both'], str);
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = substitute (cfg.presentation['kern-wl-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = substitute (cfg.presentation['kern-wl-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
 
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
label = substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
label = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
return str;
return false; -- embargo expired or |embargo= not set
end
 
 
--[[
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
Formats a PMC and checks for embargoed articles. The embargo parameter takes a date for a value. If the embargo date is in the future
 
the PMC identifier will not be linked to the article. If the embargo specifies a date in the past, or if it is empty or omitted, then
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
the PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
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=, |script-chapter=, |script-<periodical>=
 
]]
function pmc(id, embargo)
local handler = cfg.id_handlers['PMC'];
local text;
 
local function format_script_value (script_value, script_param)
if is_embargoed(embargo) then
local lang=''; -- initialize to empty string
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id; --still embargoed so no external link
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
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
return ''; -- script_value was just the prefix so return empty string
end
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, "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
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
end
else
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
text = externallinkid({link = handler.link, label = handler.label, --no embargo date, ok to link to article
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
return text;
 
return script_value;
end
 
 
-- Formats a DOI and checks for DOI errors.
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
function doi(id, inactive)
 
local cat = ""
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
local handler = cfg.id_handlers['DOI'];
wrapped in <bdi> tags.
]]
local text;
 
if is_set(inactive) then
local function script_concatenate (title, script, script_param)
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
if is_set (script) then
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
script = format_script_value (script, script_param); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set(inactive_year) then
if is_set (script) then
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
title = title .. ' ' .. script; -- concatenate title and script title
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 = externallinkid({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
inactive = ""
end
return title;
end
 
 
if nil == id:match("^10%.[^%s–]-[^%.,]$") then -- doi must begin with '10.', must not contain spaces or endashes, and must not end with period or comma
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
cat = ' ' .. seterror( 'bad_doi' );
 
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
return text .. inactive .. cat
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
 
-- Formats an OpenLibrary link, and checks for associated errors.
function openlibrary(id)
local code = id:sub(-1,-1)
local handler = cfg.id_handlers['OL'];
if ( code == "A" ) then
return externallinkid({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/authors/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "M" ) then
return externallinkid({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/books/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "W" ) then
return externallinkid({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/works/OL",id=id, separator=handler.separator,
encode = handler.encode})
else
return externallinkid({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator,
encode = handler.encode}) ..
' ' .. seterror( 'bad_ol' );
end
end
 
--[[--------------------------< W I K I S O U R C E _ U R L _ M A K E >----------------------------------------
--[[
Validate and format an issn. This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
digits with a space. When that condition occurred, the resulting link looked like this:
 
makes a wikisource url from wikisource interwiki link. returns the url and appropriate label; nil else.
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
 
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
 
]]
 
local function wikisource_url_make (str)
local wl_type, D, L;
local ws_url, ws_label;
 
wl_type, D, L = is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
 
if 0 == wl_type then -- not a wikilink; might be from |title-link=
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_label = D; -- get ws article name from display portion of interwiki link
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
if ws_url then
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
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable url
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
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of anchor
error message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
end
 
return ws_url, ws_label, L or D; -- return proper url or nil and a label or nil
end
 
 
--[[--------------------------< F O R M A T _ P E R I O D I C A L >--------------------------------------------
 
Format the four periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta-
parameter.
 
]]
function issn(id)
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local handler = cfg.id_handlers['ISSN'];
local text;
local valid_issn = true;
 
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and ndashes from the issn
local periodical_error = '';
 
if not is_set (periodical) then
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 didgits long, containing only 0-9 or X in the last position
valid_issnperiodical =false ''; -- wrongto lengthbe orsafe improperfor characterconcatenation
else
valid_issnperiodical =is_valid_isxn wrap_style (id'italic-title', 8periodical); -- validatestyle issn
end
 
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
if true == valid_issn then
 
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
if is_set (trans_periodical) then
trans_periodical = wrap_style ('trans-italic-title', trans_periodical);
if is_set (periodical) then
periodical = periodical .. ' ' .. trans_periodical;
else -- here when transchapter without chapter or script-chapter
periodical = trans_periodical;
periodical_error = ' ' .. set_error ('trans_missing_title', {'periodical'});
end
end
 
return periodical .. periodical_error;
end
 
 
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
 
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
parameter (chapter_url_source used for error messages).
 
]]
 
local function format_chapter_title (scriptchapter, script_chapter_source, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access)
local chapter_error = '';
 
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource url and label from a wikisource interwiki link
if ws_url then
ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters
chapter = ws_label;
end
 
if not is_set (chapter) then
chapter = ''; -- to be safe for concatenation
else
if false == no_quotes then
id = issn_copy; -- if not valid, use the show the invalid issn with error message
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, script_chapter_source); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
elseif ws_url then
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
chapter = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
 
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, access); -- 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().
 
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
text = externallinkid({link = handler.link, label = handler.label,
if capture == v then -- if same there are no unicode characters
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
return;
end
if false == valid_issn then
 
text = text .. ' ' .. seterror( 'bad_issn' ) -- add an error message if the issn is invalid
while cfg.invisible_chars[i] do
end
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 and (char == 'zero width joiner') then -- if we found a zero width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts
position = nil; -- unset position
end
end
if position then
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
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 textsetmetatable({
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'] .. ': ' .. k);
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
 
 
--[[
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
This function sets default title types (equivalent to the citation including |type=<default value>) for those citations that have defaults.
 
Also handles the special case where it is desireable to omit the title type from the rendered citation (|type=none).
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.
 
]]
 
function set_titletype(cite_class, title_type)
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
 
ifreturn "podcast" ==cfg.title_types [cite_class] thenor ''; -- ifset template's default title type; thiselse citationempty isstring citefor podcastconcatenation
end
return "Podcast"; -- display podcast annotation
 
elseif "pressrelease" == cite_class then -- if this citation is cite press release
return "Press release"; -- display press release annotation
 
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
elseif "techreport" == cite_class then -- if this citation is cite techreport
 
return "Technical report"; -- display techreport annotation
Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items are
returned unmodified. These forms are modified:
letter - letter (A - B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5)
digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d)
 
any other forms are returned unmodified.
 
str may be a comma- or semicolon-separated list
 
]]
 
local function hyphen_to_dash( str )
if not is_set (str) then
return str;
end
str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str
elseif "thesis" == cite_class then -- if this citation is cite thesis (degree option handled after this function returns)
if 0 ~= count then -- non-zero when markup removed; zero else
return "Thesis"; -- display simple thesis annotation (without |degree= modification)
return str; -- nothing to do, we're done
end
end
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split
local out = {};
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any
 
for _, item in ipairs (list) do -- for each item in the list
-- returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct. If not a valid month, returns 0
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
function get_month_number (month)
if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
local long_months = {['January']=1, ['February']=2, ['March']=3, ['April']=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12};
item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or -- digitletter hyphen digitletter (optional separator between digit and letter)
local short_months = {['Jan']=1, ['Feb']=2, ['Mar']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12};
item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or -- digit separator digit hyphen digit separator digit
local temp;
item:match ('%d+%s*%-%s*%d+') or -- digit hyphen digit
temp=long_months[month];
item:match ('%a+%s*%-%s*%a+') then -- letter hyphen letter
if temp then return temp; end -- if month is the long-form name
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
temp=short_months[month];
else
if temp then return temp; end -- if month is the short-form name
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space
return 0; -- misspelled, improper case, or not a month name
end
end
item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup
table.insert (out, item); -- add the (possibly modified) item to the output table
end
 
return table.concat (out, ', '); -- concatenate the output table into a comma separated string
-- returns a number according to the sequence of seasons in a year: 1 for Winter, etc. Capitalization and spelling must be correct. If not a valid season, returns 0
function get_season_number (season)
local season_list = {['Winter']=1, ['Spring']=2, ['Summer']=3, ['Fall']=4, ['Autumn']=4}
local temp;
temp=season_list[season];
if temp then return temp; end -- if season is a valid name return its number
return 0; -- misspelled, improper case, or not a season name
end
 
--[[
Returns true if day is less than or equal to the number of days in month; else returns false.
 
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
Assumes Julian calendar prior to year 1582 and Gregorian calendar thereafter. Accounts for Julian calendar leap years before 1582 and Gregorian leap years after 1582.
 
Where the two calendars overlap (1582 to approximately 1923) dates are assumed to be Gregorian.
Joins a sequence of strings together while checking for duplicate separation characters.
 
]]
 
function is_valid_date (year, month, day)
local function safe_join( tbl, duplicate_char )
local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
local f = {}; -- create a function table appropriate to type of 'dupicate character'
local month_length;
if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions
if (2==month) then -- if February
f.gsub=string.gsub
month_length = 28; -- then 28 days unless
f.match=string.match
if 1582 > tonumber(year) then -- Julian calendar
f.sub=string.sub
if 0==(year%4) then
else -- for multi-byte characters use the ustring library functions
month_length = 29;
f.gsub=mw.ustring.gsub
f.match=mw.ustring.match
f.sub=mw.ustring.sub
end
 
local str = ''; -- the output string
local comp = ''; -- what does 'comp' mean?
local end_chr = '';
local trim;
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then -- if output string is empty
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
else
comp = value;
end
else -- Gregoriantypically duplicate_char is calendarsepc
if f.sub(comp, 1,1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
if (0==(year%4) and (0~=(year%100) or 0==(year%400))) then -- is a leap year?
-- Because individual string segments often (always?) begin with terminal punct for the
month_length = 29; -- if leap year then 29 days in February
-- preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
end_chr = f.sub(str, -1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = f.sub(str, 1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
trim = true;
elseif f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = f.sub(str, 1,-3); -- remove them both
end
end
 
if trim then
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; --add it to the output string
end
else
month_length=days_in_month[month];
end
return str;
end
 
 
if tonumber (day) > month_length then
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
return false;
 
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
 
--[[
Check a pair of months or seasons to see if both are valid members of a month or season pair.
 
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Month pairs are expected to be left to right, earliest to latest in time. Similarly, seasons are also left to right, earliest to latest in time. There is
 
an oddity with seasons. Winter is assigned a value of 1, spring 2, ..., fall and autumn 4. Because winter can follow fall/autumn at the end of a calender year, a special test
Attempts to convert names to initials in support of |name-list-format=vanc.
is made to see if |date=Fall-Winter yyyy (4-1) is the date.
 
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)
function is_valid_month_season_range(range_start, range_end)
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
local range_start_number = get_month_number (range_start);
if 0 == range_start_number then -- is this a month range?
local range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number
local range_end_number = get_season_number (range_end); -- get end season number
 
if 0not ~= range_start_numbername then -- isif startnot ofinitials rangeand a season?suffix
name = mw.ustring.match(first, "^(%u+)$"); -- is it just intials?
if range_start_number < range_end_number then -- range_start is a season
end
return true; -- return true when range_end is also a season and follows start season; else false
 
if name then -- if first is initials with or without suffix
if 3 > mw.ustring.len (name) then -- if one or two initials
if suffix then -- if there is a suffix
if is_suffix (suffix) then -- is it legitimate?
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error ('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
if 4 == range_start_number and 1 == range_end_number then -- special case when range is Fall-Winter or Autumn-Winter
end -- if here then name has 3 or more uppercase letters so treat them as a word
return true;
 
 
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 = cfg.presentation['sep_nl_vanc']; -- name-list separator between authors is a comma
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
else
sep = cfg.presentation['sep_nl']; -- name-list separator between authors is a semicolon
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first;
end
if is_set(person.link) and person.link ~= control.page_name then
one = make_wikilink (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
return false; -- range_start is not a month or a season; or range_start is a season and range_end is not; or improper season sequence
end
 
local range_end_numbercount = get_month_number#text (range_end)/ 2; -- get(number endof monthnames + number of separators) divided by 2
if count > 0 then
if range_start_number < range_end_number then -- range_start is a month; does range_start precede range_end?
if count > 1 and is_set(lastauthoramp) and not etal then
return true; -- if yes, return true
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month
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
 
--[[
Check date format to see that it is one of the formats approved by MOS:DATE: MMMM D, YYYY; D MMMM YYYY; MMMM YYYY; YYYY-MM-DD; YYYY.
Additionally, check the date to see that it is a real date: no 31 in 30-day months; no 29 February when not a leap year. Months, both long-form and three
character abbreviations, and seasons must be spelled correctly.
 
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
If the date fails the fomat tests, this function returns false but does not return values for anchor_year and COinS_date. When this happens, the date parameter is
used in the COinS metadata and the CITEREF identifier gets its year from the year parameter if present.
 
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
Inputs:
 
date_string - date string from date-holding parameters (date, year, accessdate, embargo, archivedate, etc)
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
 
Returns:
false if date string is not a real date; else
true, anchor_year, COinS_date
anchor_year can be used in CITEREF anchors
COinS_date is date_string without anchor_year disambiguator if any
]]
local function check_dateanchor_id (date_stringnamelist, year)
local names={}; -- a table for the one to four names and year
local year;
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
local month=0; -- assume that month and day are not used; if either is zero then final year/month/day validation is not necessary
names[i] = v.last
local day=0;
if i == 4 then break end -- if four then done
local day2=0; -- second day in a day range
end
local anchor_year;
table.insert (names, year); -- add the year at the end
local coins_date;
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
 
if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- Year-initial numerical year month day format
year, month, day=string.match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)");
month=tonumber(month);
if 12 < month or 1 > month or 1583 > tonumber(year) then return false; end -- month number not valid or not Gregorian calendar
anchor_year = year;
 
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial: month day, year
month, day, anchor_year, year=string.match(date_string, "(%a+)%s*(%d%d?),%s*((%d%d%d%d)%a?)");
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
elseif date_string:match("^%a+ +[1-9]%d?–[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash
month, day, day2, anchor_year, year=string.match(date_string, "(%a+) +(%d%d?)–(%d%d?), +((%d%d%d%d)%a?)");
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
 
Evaluates the content of name parameters (author, editor, etc) for variations on the theme of et al. If found,
elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-initial: day month year
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
day, month, anchor_year, year=string.match(date_string, "(%d%d*)%s*(%a+)%s*((%d%d%d%d)%a?)");
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
 
This function never sets the flag to false but returns it's previous state because it may have been set by
elseif date_string:match("^[1-9]%d?–[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash
previous passes through this function or by the associated |display-<names>=etal parameter
day, day2, month, anchor_year, year=string.match(date_string, "(%d%d?)–(%d%d?) +(%a+) +((%d%d%d%d)%a?)");
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
 
]]
elseif mw.ustring.match (date_string, "^%a+–%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash
 
local month2
local function name_has_etal (name, etal, nocat, param)
month, month2, anchor_year, year=mw.ustring.match (date_string, "(%a+)[%-/–](%a+)%s*((%d%d%d%d)%a?)");
 
if false == is_valid_month_season_range(month, month2) then
if is_set (name) then -- name can be nil in which case just return
return false;
local patterns = cfg.et_al_patterns; --get patterns from configuration
end
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
elseif date_string:match("^%a+ +%d%d%d%d%a?$") then -- month/season year
if name:match (pattern) then -- if this 'et al' pattern is found in name
month, anchor_year, year=string.match(date_string, "(%a+)%s*((%d%d%d%d)%a?)");
name = name:gsub (pattern, ''); -- remove the offending text
if 0 == get_month_number (month) then -- if month text isn't one of the twelve months, might be a season
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
if 0 == get_season_number (month) then -- not a month, is it a season?
if not nocat then -- no categorization for |vauthors=
return false; -- return false not a month or one of the five seasons
table.insert( z.message_tail, {set_error ('etal', {param})}); -- and set an error if not added
end
end
end
end
 
return name, etal; --
elseif date_string:match("^[1-9]%d%d%d?%a?$") then -- year; here accept either YYY or YYYY
end
anchor_year, year=string.match(date_string, "((%d%d%d%d?)%a?)");
 
 
else
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
return false; -- date format not one of the MOS:DATE approved formats
 
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
 
]]
 
local function name_has_ed_markup (name, list_name)
local _, pattern;
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
 
if is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
end
end
return name; -- and done
end
 
 
if 0~=month and 0~=day then -- check year month day dates for validity
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
if 0~=day2 then -- If there is a second day (d–d Mmm YYYY or Mmm d–d, YYYY) test the second date
 
if false==is_valid_date(year,month,day2) then
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are
return false; -- second date in date range string is not a real date return false; unset anchor_year and coins_date
indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name
end -- if second date range string is valid, fall through to test the first date range
(author or editor) maintenance category.
 
]]
 
local function name_has_mult_names (name, list_name)
local count, _;
if is_set (name) then
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
if 1 < count then -- param could be |author= or |editor= so one separator 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
if false==is_valid_date(year,month,day) then
return falsename; -- date string is not a real date return false; unset anchor_year and coins_datedone
end
 
 
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
This function calls various name checking functions used to validate the content of the various name-holding
parameters.
 
]]
 
local function name_checks (last, first, list_name)
if is_set (last) then
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
last = last:match ('^%(%((.*)%)%)$'); -- strip parens
else
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
end
end
if is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
else
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
end
end
return last, first; -- done
end
 
 
coins_date= mw.ustring.gsub( date_string, "–", "-" ); -- if here, then date_string is valid; set coins_date and replace any ndash with a hyphen
--[[--------------------------< 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 last_alias, first_alias; -- selected parameter aliases used in error messaging
while true do
last, last_alias = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first, first_alias = 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, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {first_alias, first_alias:gsub('first', 'last')}, 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', {list_name:match ("(%w+)List"):lower(), i-1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
return truenames, anchor_year, coins_dateetal; -- formatall is good and datedone, stringreturn representsour alist realof datenames
end
 
--[[
Cycle the date-holding parameters in passed table date_parameters_list through check_date() to check compliance with MOS:DATE. For all valid dates, check_date() returns
true and values for anchor_year (used in CITEREF identifiers) and COinS_date (used in the COinS metadata). The |date= parameter test is unique. This function only
accepts anchor_year and COinS_date results from the |date= parameter test and |date= is the only date-holding parameter that is allowed to contain the no-date keywords
"n.d." or "nd" (without quotes).
 
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Unlike most error messages created in this module, only one error message is created by this function. Because all of the date holding parameters are processed serially,
 
a single error message is created as the dates are tested.
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
 
Returns the language name and associated two- or three-character code. Because case of the source may be incorrect
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we
return the original language name string.
 
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they
are used as sub-domain names: cbk-zam.wikipedia.org. A list of language names and codes supported by fetchLanguageNames()
can be found at Template:Citation Style documentation/language/doc
 
Names that are included in the list will be found if that name is provided in the |language= parameter. For example,
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found
and the associated code is not two or three characters, this function returns only the WikiMedia language name.
 
Some language names have multiple entries under different codes:
Aromanian has code rup and code roa-rup
When this occurs, this function returns the language name and the 2- or 3-character code
 
Adapted from code taken from Module:Check ISO 639-1.
 
]]
 
local function datesget_iso639_code (date_parameters_listlang, this_wiki_code)
if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
local anchor_year; -- will return as nil if the date being tested is not |date=
return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
local COinS_date; -- will return as nil if the date being tested is not |date=
end
local error_message ="";
 
local good_date=false;
local ietf_code; -- because some languages have both ietf-like codes and iso 639-like codes
local ietf_name;
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
if is_set(v) then -- if the parameter has a value
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
 
if 'date'==k then
for code, name in pairs(languages) do -- scan the list to see if we can find our language
good_date, anchor_year, COinS_date = true, v:match("((c%. [1-9]d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
elseifif langlc 'year'==k mw.ustring.lower(name) then
if 2 == code:len() or 3 == code:len() then -- two- or three-character codes only; extensions not supported
good_date = true;
return name, code; -- so return the name and the code
end
elseif 'year'==k then -- if the parameter is |year= (but not c. year)
if v:match("^[1-9]%d%d%d?%a?$") then -- year with or without CITEREF disambiguator
good_date = true;
end
elseif 'date'==k then -- if the parameter is |date=
if v:match("n%.d%.%a?") then -- if |date=n.d. with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
elseif v:match("nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
else
good_date, anchor_year, COinS_date = check_date (v); -- go test the date
end
else -- any other date-holding parameter
good_date = check_date (v); -- go test the date
end
ietf_code = code; -- remember that we found an ietf-like code and save its name
if false==good_date then -- assemble one error message so we don't add the tracking category multiple times
ietf_name = name; -- but keep looking for a 2- or 3-char code
if is_set(error_message) then -- once we've added the first portion of the error message ...
end
error_message=error_message .. ", "; -- ... add a comma space separator
end
-- didn't find name with 2- or 3-char code; if ietf-like code found return
return ietf_code and ietf_name or lang; -- associated name; return original language text else
end
 
 
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
 
Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki,
use the returned name; if not, then use the value that was provided with the language parameter.
 
When |language= contains a recognized language (either code or name), the page is assigned to the category for
that code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assigned
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources.
 
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character
equivalents of two-character codes: code 'ar' is recognized 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
name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap
 
if name then -- there was a remapped code so
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietf tags from code
else
if lang:match ('^%a%a%-') then -- strip ietf 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 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
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
 
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' .. code, {name, code}) -- categorize it
else -- or is a recognized language (but has a three-character code)
add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
end
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
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
if is_set(error_message) then
code = #language_list -- reuse code as number of languages in the list
table.insert( z.message_tail, { seterror( 'bad_date', {error_message}, true ) } ); -- add this error message
if 2 >= code then
name = table.concat (language_list, cfg.messages['parameter-pair-separator']) -- insert '<space>and<space>' between two language names
elseif 2 < code then
name = table.concat (language_list, ', '); -- and concatenate with '<comma><space>' separators
name = name:gsub (', ([^,]+)$', cfg.messages['parameter-final-separator'] .. '%1'); -- replace last '<comma><space>' separator with '<comma><space>and<space>' separator
end
if this_wiki_name == name then
 
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
return anchor_year, COinS_date; -- and done
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
 
--[[
Determines whether a URL string is valid
 
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
At present the only check is whether the string appears to
 
be prefixed with a URI scheme. It is not determined whether
Set style settings for CS1 citation templates. Returns separator and postscript settings
the URI scheme is valid or whether the URL is otherwise well
At en.wiki, for cs1:
formed.
ps gets: '.'
sep gets: '.'
 
]]
 
function checkurl( url_str )
local function set_cs1_style (ps)
-- Protocol-relative or URL scheme
if not is_set (ps) then -- unless explicitely set to something
return url_str:sub(1,2) == "//" or url_str:match( "^[^/]*:" ) ~= nil;
ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation
end
return cfg.presentation['sep_cs1'], ps; -- element separator
end
 
 
-- Removes irrelevant text and dashes from ISBN number
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
-- Similar to that used for Special:BookSources
 
function cleanisbn( isbn_str )
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
return isbn_str:gsub( "[^-0-9X]", "" );
At en.wiki, for cs2:
ps gets: '' (empty string - no terminal punctuation)
sep gets: ','
 
]]
 
local function set_cs2_style (ps, ref)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation
end
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
return cfg.presentation['sep_cs2'], ps, ref; -- element separator
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 >----------------------
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in checkisbn().
 
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,
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
spaces and other non-isxn characters.
rendered style.
 
]]
 
function is_valid_isxn (isxn_str, len)
local function get_settings_from_cite_class (ps, ref, cite_class)
local temp = 0;
local sep;
isxn_str = { isxn_str:byte(1, len) }; -- make a table of bytes
if (cite_class == "citation") then -- for citation templates (CS2)
len = len+1; -- adjust to be a loop counter
sep, ps, ref = set_cs2_style (ps, ref);
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
else -- not a citation template so CS1
if v == string.byte( "X" ) then -- if checkdigit is X
sep, ps = set_cs1_style (ps);
temp = temp + 10*( len - i ); -- it represents 10 decimal
else
temp = temp + tonumber( string.char(v) )*(len-i);
end
end
 
return temp % 11 == 0; -- returns true if calculation result is zero
return sep, ps, ref -- return them all
end
 
 
-- Determines whether an ISBN string is valid
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
function checkisbn( 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
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
config.CitationClass from the template's #invoke: to establish style.
local len = isbn_str:len();
 
]]
if len ~= 10 and len ~= 13 then
 
return false;
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);
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
 
 
if len == 10 then
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
 
return is_valid_isxn(isbn_str, 10);
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
else
applying the pdf icon to external links.
local temp = 0;
 
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979
returns true if file extension is one of the recognized extensions, else false
isbn_str = { isbn_str:byte(1, len) };
 
for i, v in ipairs( isbn_str ) do
]=]
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) );
 
local function is_pdf (url)
return url:match ('%.pdf$') or url:match ('%.PDF$') or
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end
 
 
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
 
Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does
not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.
 
]]
 
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parentheses, 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
return temp % 10 == 0;
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
return format;
end
 
 
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
--[[--------------------------< G E T _ D I S P L A Y _ N A M E S >--------------------------------------------
function removewikilink( str )
 
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
to indicate when et al. should be appended to the name list.
end));
 
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
some variant of the text 'et al.').
 
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
the names in the name list followed by 'et al.'
 
In all other cases, returns nil and the previous state of the 'etal' flag.
 
inputs:
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
count: #a or #e
list_name: 'authors' or 'editors'
etal: author_etal or editor_etal
 
]]
 
local function get_display_names (max, count, list_name, etal)
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_name', 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
 
 
-- Escape sequences for content that will be used for URL descriptions
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
function safeforurl( str )
 
if str:match( "%[%[.-%]%]" ) ~= nil then
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
table.insert( z.message_tail, { seterror( 'wikilink_in_url', {}, true ) } );
abbreviation in the first characters of the parameter content.
end
 
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
return str:gsub( '[%[%]\n]', {
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
['['] = '&#91;',
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
[']'] = '&#93;',
 
['\n'] = ' ' } );
]]
 
local function extra_text_in_page_check (page)
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]%.?[ %d]';
 
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
add_maint_cat ('extra_text');
end
end
 
 
-- Converts a hyphen to a dash
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
function hyphentodash( str )
 
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
return str;
parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the
end
rendered citation and in the metadata. Individual author names may be wikilinked
return str:gsub( '-', '–' );
 
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
 
]=]
 
local function get_v_name_table (vparam, output_table, output_link_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local wl_type, label, link; -- wl_type not used here; just a place holder
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
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
end
i = i+1;
end
return output_table;
end
 
 
-- Protects a string that will be wrapped in wiki italic markup '' ... ''
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
function safeforitalics( str )
 
--[[ Note: We can not use <i> for italics, as the expected behavior for
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
italics specified by ''...'' in the title is that they will be inverted
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
(i.e. unitalicized) in the resulting references. In addition, <i> and ''
 
tend to interact poorly under Mediawiki's HTML tidy. ]]
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
if not is_set(str) then
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
return str;
 
else
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
if str:sub(1,1) == "'" then str = "<span />" .. str; end
 
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
 
-- Remove newlines as they break italics.
]]
return str:gsub( '\n', ' ' );
 
end
local function parse_vauthors_veditors (args, vparam, list_name)
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local v_link_table = {}; -- when name is wikilinked, targets go in this table
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
local corporate = false;
 
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
 
for i, v_name in ipairs(v_name_table) do
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
 
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[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 >------------------------
Joins a sequence of strings together while checking for duplicate separation
 
characters.
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.
 
]]
function safejoin( 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 = '';
local comp = '';
local end_chr = '';
local trim;
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then
str = value;
elseif value ~= '' then
if value:sub(1,1) == '<' then
-- Special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" );
else
comp = value;
end
if comp:sub(1,1) == duplicate_char then
trim = false;
end_chr = str:sub(-1,-1);
-- str = str .. "<HERE(enchr=" .. end_chr.. ")"
if end_chr == duplicate_char then
str = str:sub(1,-2);
elseif end_chr == "'" then
if str:sub(-3,-1) == duplicate_char .. "''" then
str = str:sub(1, -4) .. "''";
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "]''" then
trim = true;
end
elseif end_chr == "]" then
if str:sub(-3,-1) == duplicate_char .. "]]" then
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then
trim = true;
end
elseif end_chr == " " then
if str:sub(-2,-1) == duplicate_char .. " " then
str = str:sub(1,-3);
end
end
 
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
if trim then
local lastfirst = false;
if value ~= comp then
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 dup2 = duplicate_char;
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 )
lastfirst=true;
else
end
value = value:sub( 2, -1 );
 
end
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
end
(is_set (vxxxxors) and is_set (xxxxors)) or
end
(true == lastfirst and is_set (xxxxors)) then
str = str .. value;
local err_name;
end
if 'AuthorList' == list_name then -- figure out which name should be used in error message
end
err_name = 'author';
return str;
else
end
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
-- Attempts to convert names to initials.
if is_set (vxxxxors) then return 2 end;
function reducetoinitials(first)
if is_set (xxxxors) then return 3 end;
local initials = {}
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
for word in string.gmatch(first, "%S+") do
table.insert(initials, string.sub(word,1,1)) -- Vancouver format does not include full stops.
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
 
-- Formats a list of people (e.g. authors / editors)
function listpeople(control, people)
local sep = control.sep;
local namesep = control.namesep
local format = control.format
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
local text = {}
local etal = false;
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if maximum ~= nil and maximum < 1 then return "", 0; end
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if maximum ~= nil and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then first = reducetoinitials(first) end
one = one .. namesep .. first
end
if is_set(person.link) then one = "[[" .. person.link .. "|" .. one .. "]]" end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
 
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
local count = #text / 2;
 
if count > 0 then
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
if count > 1 and is_set(lastauthoramp) and not etal then
of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
text[#text-2] = " & ";
in the source template) the function returns true. If the parameter value is one of the list of allowed values returns
end
true; else, emits an error message and returns false.
text[#text] = nil;
 
end
]]
 
local result = table.concat(text) -- construct list
local function is_valid_parameter_value (value, name, possible)
if etal then
if not is_set (value) then
local etal_text = cfg.messages['et al'];
return true; -- an empty parameter is ok
result = result .. " " .. etal_text;
elseif in_array (value, possible) then
end
return true;
else
-- if necessary wrap result in <span> tag to format in Small Caps
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
if ( "scap" == format ) then result =
return false
'<span class="smallcaps" style="font-variant:small-caps">' .. result .. '</span>';
end
return result, count
end
 
 
-- Generates a CITEREF anchor ID.
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
function anchorid( options )
 
return "CITEREF" .. table.concat( options );
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
when the last character is not a sepc character or when the last three characters are not sepc followed by two
closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
single space character.
 
]]
 
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list,-3,-1) == sepc .. '. ') then -- if already properly terminated
return name_list; -- just return the name list
elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
return name_list .. sepc .. ' '; -- otherwise terninate the name list
end
end
 
-- Gets name list from the input arguments
function extractnames(args, list_name)
local names = {};
local i = 1;
local last;
while true do
last = selectone( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i );
if not is_set(last) then
-- just in case someone passed in an empty parameter
break;
end
names[i] = {
last = last,
first = selectone( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ),
link = selectone( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ),
mask = selectone( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i )
};
i = i + 1;
end
return names;
end
 
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
-- Populates ID table from arguments using configuration settings
 
function extractids( args )
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
local id_list = {};
or formatted issue, or an empty string if neither are set.
for k, v in pairs( cfg.id_handlers ) do
 
v = selectone( args, v.parameters, 'redundant_parameters' );
]]
if is_set(v) then id_list[k] = v; end
end
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
return id_list;
if not is_set (volume) and not is_set (issue) then
return '';
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
 
local vol = ''; -- here for all cites except magazine
if is_set (volume) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face
elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters
vol = substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold
add_prop_cat ('long_vol');
else -- four or less characters
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end
 
 
-- Takes a table of IDs and turns it into a table of formatted ID outputs.
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
function buildidlist( id_list, options )
 
local new_list, handler = {};
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:
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
page, pages, sheet, sheets
 
for k, v in pairs( id_list ) do
Singular has priority over plural when both are provided.
-- fallback to read-only cfg
 
handler = setmetatable( { ['id'] = v }, fallback(k) );
]]
 
if handler.mode == 'external' then
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
table.insert( new_list, {handler.label, externallinkid( handler ) } );
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
elseif handler.mode == 'internal' then
if is_set (sheet) then
table.insert( new_list, {handler.label, internallinkid( handler ) } );
if 'journal' == origin then
elseif handler.mode ~= 'manual' then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
error( cfg.messages['unknown_ID_mode'] );
else
elseif k == 'DOI' then
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
end
elseif k == 'ASIN' then
elseif is_set (sheets) then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
if elseif k'journal' == 'OL'origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
table.insert( new_list, {handler.label, openlibrary( v ) } );
else
elseif k == 'PMC' then
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
end
elseif k == 'PMID' then
end
table.insert( new_list, {handler.label, pmid( v ) } );
end
elseif k == 'ISSN' then
 
table.insert( new_list, {handler.label, issn( v ) } );
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
elseif k == 'ISBN' then
local ISBN = internallinkid( handler );
if is_set (page) then
if not checkisbn( v ) and not is_set(options.IgnoreISBN) then
if is_journal then
ISBN = ISBN .. seterror( 'bad_isbn', {}, false, " ", "" );
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
end
elseif not nopp then
table.insert( new_list, {handler.label, ISBN } );
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
else
error( cfg.messages['unknown_manual_ID'] );
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
end
elseif is_set(pages) then
if is_journal then
function comp( a, b ) -- used in following table.sort()
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
return a[1] < b[1];
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
end
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
table.sort( new_list, comp );
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
for k, v in ipairs( new_list ) do
else
new_list[k] = v[2];
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
end
return new_list;
return '', '', '', ''; -- return empty strings
end
 
 
-- Chooses one matching parameter from a list of parameters to consider
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
-- Generates an error if more than one match is present.
 
function selectone( args, possible, error_condition, index )
returns one of the in-source locators: page, pages, or at.
local value = nil;
 
local selected = '';
If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain text
local error_list = {};
for use in COinS. This COinS thing is done because here we convert an interwiki link to and external link and
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?
if index ~= nil then index = tostring(index); end
 
TODO: add support for sheet and sheets?; streamline;
-- Handle special case of "#" replaced by empty string
 
if index == '1' then
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
for _, v in ipairs( possible ) do
to a new name)?
v = v:gsub( "#", "" );
 
if is_set(args[v]) then
]]
if value ~= nil and selected ~= v then
 
table.insert( error_list, v );
local function insource_loc_get (page, pages, at)
else
local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
value = args[v];
 
selected = v;
if is_set (page) then
end
if is_set (pages) or is_set(at) then
end
pages = ''; -- unset the others
end
at = '';
end
end
extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
for _, v in ipairs( possible ) do
 
if index ~= nil then
ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label
v = v:gsub( "#", index );
if ws_url then
end
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
if is_set(args[v]) then
page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
if value ~= nil and selected ~= v then
coins_pages = ws_label;
table.insert( error_list, v );
end
else
elseif is_set (pages) then
value = args[v];
if is_set (at) then
selected = v;
at = ''; -- unset
end
end
extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
 
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label
if #error_list > 0 then
if ws_url then
local error_str = "";
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
for _, k in ipairs( error_list ) do
pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
coins_pages = ws_label;
error_str = error_str .. wrap( 'parameter', k );
end
elseif is_set (at) then
if #error_list > 1 then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label
error_str = error_str .. cfg.messages['parameter-final-separator'];
if ws_url then
else
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
error_str = error_str .. cfg.messages['parameter-pair-separator'];
at = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
end
coins_pages = ws_label;
error_str = error_str .. wrap( 'parameter', selected );
end
table.insert( z.message_tail, { seterror( error_condition, {error_str}, true ) } );
end
return page, pages, at, coins_pages;
return value, selected;
end
 
 
-- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse
 
-- the citation information.
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
function COinS(data)
 
if 'table' ~= type(data) or nil == next(data) then
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the
return '';
save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...)
end
archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allow
unwitting readers to do.
local ctx_ver = "Z39.88-2004";
 
When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own
-- treat table strictly as an array with only set values.
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
local OCinSoutput = setmetatable( {}, {
 
__newindex = function(self, key, value)
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
if is_set(value) then
|archive-date= and an error message when:
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( removewikilink( value ) ) } );
|archive-url= holds an archive.org save command url
end
|archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
end
correct place
});
otherwise returns |archive-url= and |archive-date=
 
if is_set(data.Chapter) then
There are two mostly compatible archive.org urls:
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
//web.archive.org/<timestamp>... -- the old form
OCinSoutput["rft.genre"] = "bookitem";
//web.archive.org/web/<timestamp>... -- the new form
OCinSoutput["rft.btitle"] = data.Chapter;
 
OCinSoutput["rft.atitle"] = data.Title;
The old form does not support or map to the new form when it contains a display flag. There are four identified flags
elseif is_set(data.Periodical) then
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
we don't check for these specific flags but we do check the form.
OCinSoutput["rft.genre"] = "article";
 
OCinSoutput["rft.jtitle"] = data.Periodical;
This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modified
OCinSoutput["rft.atitle"] = data.Title;
archive url:
else
for save command errors, return undated wildcard (/*/)
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
for timestamp errors when the timestamp has a wildcard, return the url unmodified
OCinSoutput["rft.genre"] = "book"
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
OCinSoutput["rft.btitle"] = data.Title;
 
end
]=]
 
OCinSoutput["rft.place"] = data.PublicationPlace;
local function archive_url_check (url, date)
OCinSoutput["rft.date"] = data.Date;
local err_msg = ''; -- start with the error message empty
OCinSoutput["rft.series"] = data.Series;
local path, timestamp, flag; -- portions of the archive.or url
OCinSoutput["rft.volume"] = data.Volume;
OCinSoutput["rft.issue"] = data.Issue;
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url
OCinSoutput["rft.pages"] = data.Pages;
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
OCinSoutput["rft.edition"] = data.Edition;
end
OCinSoutput["rft.pub"] = data.PublisherName;
 
if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page
for k, v in pairs( data.ID_list ) do
err_msg = 'save command';
local id, value = cfg.id_handlers[k].COinS;
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
if k == 'ISBN' then value = cleanisbn( v ); else value = v; end
elseif url:match('//liveweb%.archive%.org/') then
if string.sub( id or "", 1, 4 ) == 'info' then
err_msg = 'liveweb';
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
OCinSoutput[ id ] = value;
end
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
end
err_msg = 'timestamp';
if '*' ~= flag then
local last, first;
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)
for k, v in ipairs( data.Authors ) do
end
last, first = v.last, v.first;
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
if k == 1 then
err_msg = 'path';
if is_set(last) then
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
OCinSoutput["rft.aulast"] = last;
err_msg = 'flag';
end
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)
if is_set(first) then
err_msg = 'flag';
OCinSoutput["rft.aufirst"] = first;
else
end
return url, date; -- return archiveURL and ArchiveDate
end
end
if is_set(last) and is_set(first) then
end
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
-- if here, something not right so
elseif is_set(last) then
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
OCinSoutput["rft.au"] = last;
if is_set (Frame:preprocess('{{REVISIONID}}')) then
end
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
else
return url, date; -- preview mode so return archiveURL and ArchiveDate
OCinSoutput.rft_id = data.URL;
end
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end
 
 
--[[
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
This is the main function doing the majority of the citation
 
formatting.
This is the main function doing the majority of the citation formatting.
 
]]
function citation0( config, args)
--[[
Load Input Parameters
The argment_wrapper facillitates the mapping of multiple
aliases to single internal variable.
]]
local A = argument_wrapper( args );
 
local function citation0( config, args)
local i
--[[
local PPrefix = A['PPrefix']
Load Input Parameters
local PPPrefix = A['PPPrefix']
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end
]]
local A = argument_wrapper( args );
-- Pick out the relevant fields from the arguments. Different citation templates
local i
-- define different field names for the same underlying things.
local Authors = A['Authors'];
local a = extractnames( args, 'AuthorList' );
 
-- Pick out the relevant fields from the arguments. Different citation templates
local Coauthors = A['Coauthors'];
-- define different field names for the same underlying things.
local Others = A['Others'];
local Editors = A['Editors'];
local e = extractnames( args, 'EditorList' );
 
-- set default parameter values defined by |mode= parameter.
local Year = A['Year'];
local PublicationDateMode = A['PublicationDateMode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
local OrigYear = A['OrigYear'];
local Date Mode = A['Date'];
end
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
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 ChapterLink = A['ChapterLink'];
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
local Degree = A['Degree'];
local Docket = A['Docket'];
local ArchiveURL = A['ArchiveURL'];
local URL = A['URL']
local URLorigin = A:ORIGIN('URL');
local ChapterURL = A['ChapterURL'];
local ChapterURLorigin = A:ORIGIN('ChapterURL');
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL');
local Periodical = A['Periodical'];
 
local author_etal;
--[[
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
Parameter remapping for cite encyclopedia:
local Authors;
When the citation has these parameters:
local NameListFormat = A['NameListFormat'];
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
local Collaboration = A['Collaboration'];
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title
 
do -- to limit scope of selected
|trans_title maps to |trans_chapter when |title is re-mapped
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 Others = A['Others'];
All other combinations of |encyclopedia, |title, and |article are not modified
 
]]
local editor_etal;
if ( config.CitationClass == "encyclopaedia" ) then
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
local Editors;
if is_set(Title) then
 
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 translator_etal;
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 interviewer_etal;
local interviewers_list = {};
local Interviewers; -- used later
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
 
local contributor_etal;
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
 
if is_set (Others) then
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
add_maint_cat ('others');
end
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 ScriptChapterOrigin = A:ORIGIN ('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 UrlStatus = A['UrlStatus'];
if 'url-status' == A:ORIGIN ('UrlStatus') then -- interim: TODO: this line goes away
if not is_valid_parameter_value (UrlStatus, 'url-status', cfg.keywords ['url-status']) then -- set in config.defaults to 'dead'
UrlStatus = ''; -- anything else, set to empty string
end -- interim: TODO: this line goes away
elseif is_set (A:ORIGIN ('UrlStatus')) then -- interim: while both |dead-url= and |url-status= allowed use separate keyword lists; TODO: remove this section
if not is_valid_parameter_value (UrlStatus, A:ORIGIN ('UrlStatus'), cfg.keywords ['deadurl']) then -- interim: assume |dead-url=; use those keywords; TODO: this line goes away
UrlStatus = ''; -- anything else, set to empty string; interim: TODO: this line goes away
end -- interim: TODO: this line goes away
end -- interim: TODO: this line goes away
if in_array (UrlStatus, {'yes', 'true', 'y'}) then -- TODO: remove this whole thing when |dead-url=[yes|no] parameters removed from articles
UrlStatus = 'dead';
elseif 'no' == UrlStatus then
UrlStatus = 'live';
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 = '';
if is_set (Periodical) then
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local i;
Periodical, i = strip_apostrophe_markup (Periodical); -- strip appostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_error ('apostrophe_markup', {Periodical_origin}, true)});
end
end
 
local ScriptPeriodical = A['ScriptPeriodical'];
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
-- web and news not tested for now because of
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
if not (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
if p[config.CitationClass] then
table.insert( z.message_tail, {set_error ('missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
end
end
 
local TransPeriodical = A['TransPeriodical'];
 
local Series = A['Series'];
local Volume;
local Issue;
local Page;
local Pages;
local At;
 
if 'citation' == config.CitationClass then
if is_set (Periodical) then
if not in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
end
else
Volume = A['Volume']; -- and does for non-'periodical' cites
end
elseif in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
Volume = A['Volume'];
end
 
if 'citation' == config.CitationClass then
if is_set (Periodical) and in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
is_set (ScriptPeriodical) and in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
Issue = hyphen_to_dash (A['Issue']);
end
elseif in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
if not (in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (is_set (Periodical) or is_set (ScriptPeriodical))) then
Issue = hyphen_to_dash (A['Issue']);
end
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 PublisherName_origin = A:ORIGIN('PublisherName');
if is_set (PublisherName) then
local i=0;
PublisherName, i = strip_apostrophe_markup (PublisherName); -- strip appostrophe markup so that metadata isn't contaminated; publisher is never italicized
 
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_error ('apostrophe_markup', {PublisherName_origin}, true)});
end
end
 
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 ChapterUrlAccess = A['ChapterUrlAccess'];
if not is_valid_parameter_value (ChapterUrlAccess, A:ORIGIN('ChapterUrlAccess'), cfg.keywords ['url-access']) then -- same as url-access
ChapterUrlAccess = nil;
end
if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then
ChapterUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
end
 
local MapUrlAccess = A['MapUrlAccess'];
if not is_valid_parameter_value (MapUrlAccess, 'map-url-access', cfg.keywords ['url-access']) then
MapUrlAccess = nil;
end
if not is_set(A['MapURL']) and is_set(MapUrlAccess) then
MapUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'map-url'}, true ) } );
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 );
if is_set (DoiBroken) and not ID_list['DOI'] then
table.insert( z.message_tail, { set_error( 'doibroken_missing_doi', A:ORIGIN('DoiBroken'))});
end
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
 
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
 
--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 not is_set (DF) then
DF = cfg.global_df;
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 coins_pages;
Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);
 
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 not is_set(PublicationPlace) and is_set(Place) then -- both |publication-place= and |place= (|location=) allowed if different
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
 
|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;
ScriptChapterOrigin = 'title';
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
 
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter = make_wikilink (TitleLink, Chapter);
end
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset
TransTitlePeriodical = ''; -- redundant so unset
TransTitle = '';
URL = '';
Format = '';
TitleLink = '';
ScriptTitle = '';
end
elseelseif is_set (Chapter) then -- |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.
local Series = A['Series'];
if (config.CitationClass == "techreport") then -- special case for cite techreport
local Volume = A['Volume'];
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
local Issue = A['Issue'];
if not is_set(ID) then -- can we use ID for the "number"?
local Position = '';
ID = A['Number']; -- yes, use it
local Page, Pages, At, page_type;
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 )});
Page = A['Page'];
end
Pages = hyphentodash( A['Pages'] );
end
At = A['At'];
end
 
if is_set(Page) then
-- special case for cite mailing list
if is_set(Pages) or is_set(At) then
if (config.CitationClass == "mailinglist") then
Page = Page .. " " .. seterror('extra_pages');
Periodical = A ['MailingList'];
Pages = '';
elseif 'mailinglist' == Periodical_origin then
At = '';
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
end
elseif is_set(Pages) then
 
if is_set(At) then
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
Pages = Pages .. " " .. seterror('extra_pages');
if 'conference' == config.CitationClass then
At = '';
if is_set(BookTitle) then
end
Chapter = Title;
end
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
ChapterURL = URL;
local Edition = A['Edition'];
ChapterUrlAccess = UrlAccess;
local PublicationPlace = A['PublicationPlace']
ChapterURLorigin = URLorigin;
local Place = A['Place'];
URLorigin = '';
ChapterFormat = Format;
if not is_set(PublicationPlace) and is_set(Place) then
TransChapter = TransTitle;
PublicationPlace = Place;
Title = BookTitle;
end
Format = '';
-- TitleLink = '';
if PublicationPlace == Place then Place = ''; end
TransTitle = '';
URL = '';
local PublisherName = A['PublisherName'];
end
local RegistrationRequired = A['RegistrationRequired'];
elseif 'speech' ~= config.CitationClass then
local SubscriptionRequired = A['SubscriptionRequired'];
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
local Via = A['Via'];
end
local AccessDate = A['AccessDate'];
 
local ArchiveDate = A['ArchiveDate'];
-- cite map oddities
local Agency = A['Agency'];
local DeadURLCartography = A['DeadURL']"";
local LanguageScale = A['Language']"";
local FormatSheet = A['FormatSheet'] or '';
local RefSheets = A['RefSheets'] or '';
if config.CitationClass == "map" then
local DoiBroken Chapter = A['DoiBrokenMap'];
ChapterURL = A['MapURL'];
ChapterUrlAccess = MapUrlAccess;
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 ('seriesnum', 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
-- Special case for cite techreport.
ScriptChapter = ScriptTitle;
local ID = A['ID'];
ScriptChapterOrigin = 'title';
if (config.CitationClass == "techreport") then -- special case for cite techreport
ChapterLink = TitleLink; -- alias episodelink
if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue'
TransChapter = TransTitle;
if not is_set(ID) then -- can we use ID for the "number"?
ChapterURL = URL;
ID = Issue; -- yes, use it
ChapterUrlAccess = UrlAccess;
Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
ChapterURLorigin = A:ORIGIN('URL');
else -- can't use ID so emit error message
ID = ID .. " " .. seterror('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
Title = Series; -- promote series to title
TitleLink = SeriesLink;
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
Chapter = make_wikilink (ChapterLink, Chapter);
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
Series = make_wikilink (ChapterLink, Series);
end
URL = ''; -- unset
TransTitle = '';
ScriptTitle = '';
else -- now oddities that are cite serial
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
Series = make_wikilink (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}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
do
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then
if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message
end
 
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = bioRxiv, ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
end
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.
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
 
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
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
else
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
end
else
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
end
 
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
 
--[[
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
we get the date used in the metadata.
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {
['access-date'] = {val=AccessDate, name=A:ORIGIN ('AccessDate')},
['archive-date'] = {val=ArchiveDate, name=A:ORIGIN ('ArchiveDate')},
['date'] = {val=Date, name=Date_origin},
['doi-broken-date'] = {val=DoiBroken, name=A:ORIGIN ('DoiBroken')},
['embargo'] = {val=Embargo, name=A:ORIGIN ('Embargo')},
['lay-date'] = {val=LayDate, name=A:ORIGIN ('LayDate')},
['publication-date'] ={val=PublicationDate, name=A:ORIGIN ('PublicationDate')},
['year'] = {val=Year, name=A:ORIGIN ('Year')},
};
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
 
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
 
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
local ASINTLD = A['ASINTLD'];
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
local IgnoreISBN = A['IgnoreISBN'];
end
local Embargo = A['Embargo'];
 
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
local ID_list = extractids( args );
modified = true;
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
local Quote = A['Quote'];
end
local PostScript = A['PostScript'];
local LayURL = A['LayURL'];
-- for those wikis that can and want to have English date names translated to the local language,
local LaySource = A['LaySource'];
-- uncomment these three lines. Not supported by en.wiki (for obvious reasons)
local Transcript = A['Transcript'];
-- set date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
local TranscriptURL = A['TranscriptURL']
-- if date_name_xlate (date_parameters_list, false) then
local TranscriptURLorigin = A:ORIGIN('TranscriptURL');
-- modified = true;
local sepc = A['Separator'];
-- end
local LastAuthorAmp = A['LastAuthorAmp'];
local no_tracking_cats = A['NoTracking'];
 
if modified then -- if the date_parameters_list values were modified
local use_lowercase = ( sepc ~= '.' );
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
local this_page = mw.title.getCurrentTitle(); --Also used for COinS and for language
ArchiveDate = date_parameters_list['archive-date'].val;
Date = date_parameters_list['date'].val;
if not is_set(no_tracking_cats) then
DoiBroken = date_parameters_list['doi-broken-date'].val;
for k, v in pairs( cfg.uncategorized_namespaces ) do
LayDate = date_parameters_list['lay-date'].val;
if this_page.nsText == v then
PublicationDate = date_parameters_list['publication-date'].val;
no_tracking_cats = "true";
end
break;
else
end
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
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.
local anchor_year; -- used in the CITEREF identifier
-- 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
local COinS_date; -- used in the COinS metadata
Embargo = is_embargoed (Embargo);
 
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
-- legacy: promote concatenation of |day=, |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
if not is_set (DateEmbargo) 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
Date = Year; -- promote Year to Date
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
if is_set(Date) then
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
local Month = A['Month'];
AccessDate = ''; -- unset
if is_set(Month) then
Date = Month .. " " .. Date;
local Day = A['Day']
if is_set(Day) then Date = Day .. " " .. Date end
end
 
elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promonte PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
end
end
 
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
-- 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
-- Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates.
in_array (config.CitationClass, {'journal', 'citation'}) and
-- TODO: 2013-10-27: AirDate is nil when dates() is called because it hasn't been set yet. Move the call to dates() or set AirDate earlier.
(is_set (Periodical) or is_set (ScriptPeriodical)) and
anchor_year, COinS_date = dates({['accessdate']=AccessDate, ['airdate']=AirDate, ['archivedate']=ArchiveDate, ['date']=Date, ['doi_brokendate']=DoiBroken,
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
['embargo']=Embargo, ['laydate']=LayDate, ['publicationdate']=PublicationDate, ['year']=Year});
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
 
check_for_url ({ -- add error message when any of these parameters hold a URL
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[Periodical_origin] = Periodical,
[PublisherName_origin] = PublisherName
});
 
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
--Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
if not is_embargoed(Embargo) then
-- is the article title, and Chapter is a section within the article. So, we remap
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=
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()
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
local OCinSoutput = COinS({
if is_set(BookTitle) then
['Periodical'] = strip_apostrophe_markup (Periodical), -- no markup in the metadata
Chapter = Title;
['Encyclopedia'] = strip_apostrophe_markup (Encyclopedia),
ChapterLink = TitleLink;
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
TransChapter = TransTitle;
['Degree'] = Degree; -- cite thesis only
Title = BookTitle;
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
TitleLink = '';
['PublicationPlace'] = PublicationPlace,
TransTitle = '';
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
end
['Season'] = COinS_date.rftssn,
-- Account for the oddity that is {{cite episode}}, before generation of COinS data.
['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
if config.CitationClass == "episode" then
['Series'] = Series,
local AirDate = A['AirDate'];
['Volume'] = Volume,
local SeriesLink = A['SeriesLink'];
['Issue'] = Issue,
local Season = A['Season'];
['Pages'] = coins_pages or get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
local SeriesNumber = A['SeriesNumber'];
['Edition'] = Edition,
local Network = A['Network'];
['PublisherName'] = PublisherName, -- any apostrophe markup already removed
local Station = A['Station'];
['URL'] = first_set ({ChapterURL, URL}, 2),
local s, n = {}, {};
['Authors'] = coins_author,
local Sep = (first_set(A["SeriesSeparator"], A["Separator"]) or "") .. " ";
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
if is_set(Issue) then table.insert(s, cfg.messages["episode"] .. " " .. Issue); Issue = ''; end
}, config.CitationClass);
if is_set(Season) then table.insert(s, cfg.messages["season"] .. " " .. Season); end
if is_set(SeriesNumber) then table.insert(s, cfg.messages["series"] .. " " .. SeriesNumber); end
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
Date = Date or AirDate;
Chapter = Title;
ChapterLink = TitleLink;
TransChapter = TransTitle;
Title = Series;
TitleLink = SeriesLink;
TransTitle = '';
Series = table.concat(s, Sep);
ID = table.concat(n, Sep);
end
-- COinS metadata (see <http://ocoins.info/>) for
-- automated parsing of citation information.
local OCinSoutput = COinS{
['Periodical'] = Periodical,
['Chapter'] = Chapter,
['Title'] = Title,
['PublicationPlace'] = PublicationPlace,
['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?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = first_set(Page, Pages, At),
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['URL'] = first_set( URL, ChapterURL ),
['Authors'] = a,
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
};
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
if is_set(Periodical) and not is_set(Chapter) and is_set(Title) then
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
Chapter = Title;
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
ChapterLink = TitleLink;
end
TransChapter = TransTitle;
Title = '';
TitleLink = '';
TransTitle = '';
end
 
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
-- Now perform various field substitutions.
if 'newsgroup' == config.CitationClass then
-- We also add leading spaces and surrounding markup and punctuation to the
if is_set (PublisherName) then
-- various parts of the citation, but only when they are non-nil.
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, PublisherName_origin, nil ));
if not is_set(Authors) then
end
local Maximum = tonumber( A['DisplayAuthors'] );
end
 
-- Preserve old-style implicit et al.
-- Now perform various field substitutions.
if not is_set(Maximum) and #a == 9 then
-- We also add leading spaces and surrounding markup and punctuation to the
Maximum = 8;
-- various parts of the citation, but only when they are non-nil.
table.insert( z.message_tail, { seterror('implict_etal_author', {}, true ) } );
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
elseif not is_set(Maximum) then
do
Maximum = #a + 1;
local last_first_list;
end
local control = {
format = NameListFormat, -- empty string or 'vanc'
local control = {
maximum = nil, -- as if display-authors or display-editors not set
sep = A["AuthorSeparator"] .. " ",
lastauthoramp = LastAuthorAmp,
namesep = (first_set(A["AuthorNameSeparator"], A["NameSeparator"]) or "") .. " ",
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn
format = A["AuthorFormat"],
mode = Mode
maximum = Maximum,
};
lastauthoramp = LastAuthorAmp
 
};
do -- do editor name list first because the now unsupported coauthors used to modify control table
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal);
-- If the coauthor field is also used, prevent ampersand and et al. formatting.
last_first_list, EditorCount = list_people(control, e, editor_etal);
if is_set(Coauthors) then
 
control.lastauthoramp = nil;
if is_set (Editors) then
control.maximum = #a + 1;
Editors, editor_etal = name_has_etal (Editors, editor_etal, false, 'editors'); -- find and remove variations on et al.
end
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
Authors = listpeople(control, a)
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
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 interviewers
control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal);
Interviewers = list_people (control, interviewers_list, interviewer_etal);
end
do -- now do translators
control.maximum , translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal);
Translators = list_people (control, t, translator_etal);
end
do -- now do contributors
control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal);
Contributors = list_people (control, c, contributor_etal);
end
do -- now do authors
control.maximum , author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal);
 
last_first_list = list_people(control, a, author_etal);
 
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
end
else
Authors = last_first_list; -- either an author name list or an empty string
end
end -- end of do
if 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, { seterror('coauthors_missing_author', {}, true) } ); -- emit error message
end
 
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
local EditorCount
-- an error message if the associated url is not set, or an empty string for concatenation
if not is_set(Editors) then
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
local Maximum = tonumber( A['DisplayEditors'] );
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
-- Preserve old-style implicit et al.
Format = style_format (Format, URL, 'format', 'url');
if not is_set(Maximum) and #e == 4 then
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
Maximum = 3;
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
table.insert( z.message_tail, { seterror('implict_etal_editor', {}, true) } );
elseif not is_set(Maximum) then
Maximum = #e + 1;
end
 
-- special case for chapter format so no error message or cat when chapter not supported
local control = {
if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
sep = A["EditorSeparator"] .. " ",
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia))) then
namesep = (first_set(A["EditorNameSeparator"], A["NameSeparator"]) or "") .. " ",
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
format = A['EditorFormat'],
end
maximum = Maximum,
lastauthoramp = LastAuthorAmp
};
 
if not is_set(URL) then
Editors, EditorCount = listpeople(control, e);
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
else
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
EditorCount = 1;
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
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;
local Cartography = "";
-- DeadURL = DeadURL:lower(); -- used later when assembling archived text
local Scale = "";
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
if config.CitationClass == "map" then
if not is_set( Authors ) and is_set( PublisherNameArchiveURL ) then
if is_set (ChapterURL) then -- if chapter-url is set apply archive url to it
Authors = PublisherName;
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
PublisherName = "";
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
end
OriginalFormat = ChapterFormat; -- and original |chapter-format=
Cartography = A['Cartography'];
-- if is_set('no' Cartography~= )DeadURL then
if 'live' ~= UrlStatus then
Cartography = sepc .. " " .. wrap( 'cartography', Cartography, use_lowercase );
ChapterURL = ArchiveURL -- swap-in the archive's url
end
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
Scale = A['Scale'];
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
if is_set( Scale ) then
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls
Scale = sepc .. " " .. Scale;
end
end
elseif is_set (URL) then
end
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
if not is_set(URL) and
OriginalFormat = Format; -- and original |format=
not is_set(ChapterURL) and
OriginalAccess = UrlAccess;
not is_set(ArchiveURL) and
-- if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
not is_set(ConferenceURL) and
if 'live' ~= UrlStatus then -- if URL set then archive-url applies to it
not is_set(TranscriptURL) then
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
-- Test if cite web or cite podcast |url= is missing or empty
Format = ArchiveFormat or ''; -- swap in archive's format
if inArray(config.CitationClass, {"web","podcast"}) then
UrlAccess = nil; -- restricted access levels do not make sense for archived urls
table.insert( z.message_tail, { seterror( 'cite_web_url', {}, true ) } );
end
end
end
 
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) 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 = ScriptChapterOrigin;
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
-- Test if accessdate is given without giving a URL
if is_set(AccessDate) then
table.insert( z.message_tail, { seterror( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
-- Test if format is given without giving a URL
if is_set(Format) then
Format = Format .. seterror( 'format_missing_url' );
end
end
-- Test if citation has no title
if not is_set(Chapter) and
not is_set(Title) and
not is_set(Periodical) and
not is_set(Conference) and
not is_set(TransTitle) and
not is_set(TransChapter) then
table.insert( z.message_tail, { seterror( 'citation_missing_title', {}, true ) } );
end
Format = is_set(Format) and " (" .. Format .. ")" or "";
local OriginalURL = URL
DeadURL = DeadURL:lower();
if is_set( ArchiveURL ) then
if ( DeadURL ~= "no" ) then
URL = ArchiveURL
URLorigin = A:ORIGIN('ArchiveURL')
end
end
-- Cite Kavyam fixes
if config.CitationClass == 'kavyam' then
if is_set(Chapter) and is_set (chaptertitle) then
Chapter = Chapter.. "వ " .. chaptertitle;
end
end
-- Format chapter / article title
if is_set(Chapter) and is_set(ChapterLink) then
Chapter = "[[" .. ChapterLink .. "|" .. Chapter .. "]]";
end
if is_set(Periodical) and is_set(Title) then
Chapter = wrap( 'italic-title', Chapter );
TransChapter = wrap( 'trans-italic-title', TransChapter );
else
Chapter = kern_quotes (Chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
Chapter = wrap( 'quoted-title', Chapter );
TransChapter = wrap( 'trans-quoted-title', TransChapter );
end
local TransError = ""
if is_set(TransChapter) then
if not is_set(Chapter) then
TransError = " " .. seterror( 'trans_missing_chapter' );
else
TransChapter = " " .. TransChapter;
end
end
Chapter = Chapter .. TransChapter;
if is_set(Chapter) then
if not is_set(ChapterLink) then
if is_set(ChapterURL) then
Chapter = externallink( ChapterURL, Chapter ) .. TransError;
if not is_set(URL) then
Chapter = Chapter .. Format;
Format = "";
end
elseif is_set(URL) then
Chapter = externallink( URL, Chapter ) .. TransError .. Format;
URL = "";
Format = "";
else
Chapter = Chapter .. TransError;
end
elseif is_set(ChapterURL) then
Chapter = Chapter .. " " .. externallink( ChapterURL, nil, ChapterURLorigin ) ..
TransError;
else
Chapter = Chapter .. TransError;
end
Chapter = Chapter .. sepc .. " " -- with end-space
elseif is_set(ChapterURL) then
Chapter = " " .. externallink( ChapterURL, nil, ChapterURLorigin ) .. sepc .. " ";
end
-- Format main title.
if is_set(TitleLink) and is_set(Title) then
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
end
if is_set(Periodical) then
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap( 'quoted-title', Title );
TransTitle = wrap( 'trans-quoted-title', TransTitle );
elseif inArray(config.CitationClass, {"web","news","pressrelease","conference","podcast"}) and
not is_set(Chapter) then
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap( 'quoted-title', Title );
TransTitle = wrap( 'trans-quoted-title', TransTitle );
else
Title = wrap( 'italic-title', Title );
TransTitle = wrap( 'trans-italic-title', TransTitle );
end
TransError = "";
if is_set(TransTitle) then
if not is_set(Title) then
TransError = " " .. seterror( 'trans_missing_title' );
else
TransTitle = " " .. TransTitle;
end
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = externallink( URL, Title ) .. TransError .. Format
URL = "";
Format = "";
else
Title = Title .. TransError;
end
end
if is_set(Place) then
Place = " " .. wrap( 'written', Place, use_lowercase ) .. sepc .. " ";
end
if is_set(Conference) then
if is_set(ConferenceURL) then
Conference = externallink( ConferenceURL, Conference );
end
Conference = sepc .. " " .. Conference
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. externallink( ConferenceURL, nil, ConferenceURLorigin );
end
if not is_set(Position) then
local Minutes = A['Minutes'];
if is_set(Minutes) then
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
local Time = A['Time'];
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
if not is_set(Page) then
if is_set(Pages) then
if is_set(Periodical) and
not inArray(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
else
if is_set(Periodical) and
not inArray(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
Page = ": " .. Page;
else
Page = sepc .." " .. PPrefix .. Page;
end
end
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 Inset = A['Inset'];
if first_set( Pages, Page, At ) ~= nil or sepc ~= '.' then
if is_set( Section ) then
Section = ", " .. wrap( 'section', Section, true );
end
if is_set( Inset ) then
Inset = ", " .. wrap( 'inset', Inset, true );
end
else
if is_set( Section ) then
Section = sepc .. " " .. wrap( 'section', Section, use_lowercase );
if is_set( Inset ) then
Inset = ", " .. wrap( 'inset', Inset, true );
end
elseif is_set( Inset ) then
Inset = sepc .. " " .. wrap( 'inset', Inset, use_lowercase );
end
end
At = At .. Section .. Inset;
end
 
Chapter = format_chapter_title (ScriptChapter, ScriptChapterOrigin, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
--[[Look in the list of iso639-1 language codes to see if the value provided in the language parameter matches one of them. If a match is found,
if is_set (Chapter) then
use that value; if not, then use the value that was provided with the language parameter.
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 (ArchiveURL) and mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation['archived_copy']) then -- if title is 'Archived copy' (place holder added by bots that can't find proper title)
add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title
end
 
if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup:
Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup
else
if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title=
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
end
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
Categories are assigned in a manner similar to the {{xx icon}} templates - categorizes only mainspace citations and only when the language code is not 'en' (English).
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) or
]]
('map' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical))) then -- special case for cite map when the map is in a periodical treat as an article
if is_set (Language) then
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
-- local name = mw.language.fetchLanguageName( Language:lower(), "en" ); -- experiment: this seems to return correct ISO 639-1 language names
Title = wrap_style ('quoted-title', Title);
local name = cfg.iso639_1[Language:lower()]; -- get the language name if Language parameter has a valid iso 639-1 code
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
if nil == name then
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
Language=" " .. wrap( 'language', Language ); -- no match, use parameter's value
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <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, 'script-title'); -- <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'} );
if 0 == this_page.namespace and 'en' ~= Language:lower() then --found a match; is this page main / article space and English not the language?
end
Language=" " .. wrap( 'language', name .. '[[Category:Articles with ' .. name .. '-language external links]]' ); -- in main space and not English: categorize
end
 
if is_set(Title) then
if not is_set (TitleLink) and is_set (URL) then
Title = external_link (URL, Title, URLorigin, UrlAccess) .. TransTitle .. TransError .. Format;
URL = ''; -- unset these because no longer needed
Format = "";
elseif is_set (TitleLink) and not is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
Language=" " .. wrap( 'language', name ); --not in mainspace or language is English so don't categorize
end
else
local ws_url, ws_label;
ws_url, ws_label, L = wikisource_url_make (Title); -- make ws url from |title= interwiki link; link portion L becomes tool tip label
if ws_url then
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Title = Title .. TransTitle .. TransError;
end
end
else
Title = TransTitle .. TransError;
Language=""; -- language not specified so make sure this is an empty string;
end
 
if is_set(Place) then
Others = is_set(Others) and (sepc .. " " .. Others) or "";
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
 
if is_set (Conference) then
-- handle type parameter for those CS1 citations that have default values
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
if inArray(config.CitationClass, {"podcast","pressrelease","techreport","thesis"}) then
local Minutes = A['Minutes'];
TitleType = set_titletype (config.CitationClass, TitleType);
local Time = A['Time'];
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
 
TitleType = Degree .. " thesis";
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);
if is_set(TitleType) then -- if type parameter is specified
 
TitleType = " (" .. TitleType .. ")"; -- display it in parentheses
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
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
end
if is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
Edition = if is_set(Edition) and (" " .. wrap( 'edition', Edition )) or "";then
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
add_maint_cat ('extra_text', 'edition');
Series = is_set(Series) and (sepc .. " " .. Series) or "";
end
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Edition = " " .. wrap_msg ('edition', Edition);
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
else
Edition = '';
if is_set(Volume) then
end
if ( mw.ustring.len(Volume) > 4 )
then Volume = sepc .." " .. Volume;
else Volume = " <b>" .. hyphentodash(Volume) .. "</b>";
end
end
------------------------------------ totally unrelated data
--[[ Loosely mimic {{subscription required}} template; Via parameter identifies a delivery source that is not the publisher; these sources often, but not always, exist
behind a registration or paywall. So here, we've chosen to decouple via from subscription (via has never been part of the registration required template).
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(Via) then
Via = " " .. wrap( 'via', Via );
end
 
Series = is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
if is_set(SubscriptionRequired) then
OrigYear = is_set (OrigYear) and wrap_msg ('origyear', OrigYear) or '';
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; --here when 'via' parameter not used but 'subscription' is
Agency = is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
elseif is_set(RegistrationRequired) then
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; --here when 'via' and 'subscription' parameters not used but 'registration' is
end
 
------------------------------------ totally unrelated data
if is_set(AccessDate) then
Via = is_set (Via) and wrap_msg ('via', Via) or '';
local retrv_text = " " .. cfg.messages['retrieved']
 
if (sepc ~= ".") then retrv_text = retrv_text:lower() end
--[[
AccessDate = '<span class="reference-accessdate">' .. sepc
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
.. substitute( retrv_text, {AccessDate} ) .. '</span>'
note is displayed. There are no error messages for this condition.
end
]]
if is_set(ID) then ID = sepc .." ".. ID; end
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif is_set (RegistrationRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
end
 
if is_set(AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
 
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
 
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} );
ID_list = buildidlist( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo} );
 
if is_set(URL) then
URL = " " .. externallinkexternal_link( URL, nil, URLorigin, UrlAccess );
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(wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
PostScript = "";
end
elseif PostScript:lower() == "none" then
PostScript = "";
local Archived
end
if is_set(ArchiveURL) then
if not is_set(ArchiveDate) then
local Archived
ArchiveDate = set_error('archive_missing_date');
if is_set(ArchiveURL) then
end
if not is_set(ArchiveDate) then
if "live" == UrlStatus then
ArchiveDate = seterror('archive_missing_date');
local arch_text = cfg.messages['archived'];
end
if sepc ~= "." then arch_text = arch_text:lower() end
if "no" == DeadURL then
Archived = sepc .. " " .. local arch_text =substitute( cfg.messages['archived-live'];,
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if sepc ~= "." then arch_text = arch_text:lower() end
if not is_set(OriginalURL) then
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
Archived = Archived .. " " .. set_error('archive_missing_url');
{ externallink( ArchiveURL, arch_text ), ArchiveDate } );
end
if not is_set(OriginalURL) then
elseif is_set(OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
Archived = Archived .. " " .. seterror('archive_missing_url');
local arch_text = cfg.messages['archived-dead'];
end
if sepc ~= "." then arch_text = arch_text:lower() end
elseif is_set(OriginalURL) then
if in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
local arch_text = cfg.messages['archived-dead'];
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
if sepc ~= "." then arch_text = arch_text:lower() end
if 'bot: unknown' == UrlStatus then
Archived = sepc .. " " .. substitute( arch_text,
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
{ externallink( OriginalURL, cfg.messages['original'] ), ArchiveDate } );
else
add_maint_cat ('unfit'); -- and add a category if not already added
local arch_text = cfg.messages['archived-missing'];
end
if sepc ~= "." then arch_text = arch_text:lower() end
else -- UrlStatus is empty, 'dead'
Archived = sepc .. " " .. substitute( arch_text,
Archived = sepc .. " " .. substitute( arch_text,
{ seterror('archive_missing_url'), ArchiveDate } );
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
end
else
else
Archived = ""
local arch_text = cfg.messages['archived-missing'];
end
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( arch_text,
local Lay
{ set_error('archive_missing_url'), ArchiveDate } );
if is_set(LayURL) then
end
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
elseif is_set (ArchiveFormat) then
if is_set(LaySource) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
LaySource = " &ndash; ''" .. safeforitalics(LaySource) .. "''";
else
Archived = ""
LaySource = "";
end
if sepc == '.' then
local Lay = '';
Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary'] ) .. LaySource .. LayDate
if is_set(LayURL) then
else
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary']:lower() ) .. LaySource .. LayDate
if is_set(LaySource) then
end
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
else
else
Lay = "";
LaySource = "";
end
end
if sepc == '.' then
if is_set(Transcript) then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
if is_set(TranscriptURL) then Transcript = externallink( TranscriptURL, Transcript ); end
else
elseif is_set(TranscriptURL) then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
Transcript = externallink( TranscriptURL, nil, TranscriptURLorigin );
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
local Publisher;
end
if is_set(Periodical) and
not inArray(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = PublicationPlace .. ": " .. PublisherName;
else
Publisher = PublisherName;
end
elseif is_set(PublicationPlace) then
Publisher= PublicationPlace;
else
Publisher = "";
end
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap( 'published', PublicationDate );
else
Publisher = PublicationDate;
end
end
if is_set(Publisher) then
Publisher = " (" .. Publisher .. ")";
end
else
if is_set(PublicationDate) then
PublicationDate = " (" .. wrap( 'published', PublicationDate ) .. ")";
end
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
elseif is_set(PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
end
-- Several of the above rely upon detecting this as nil, so do it last.
if is_set(Periodical) then
if is_set(Title) or is_set(TitleNote) then
Periodical = sepc .. " " .. wrap( 'italic-title', Periodical )
else
Periodical = wrap( 'italic-title', Periodical )
end
end
 
if is_set(Transcript) then
--[[
if is_set(TranscriptURL) then
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
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil );
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
end
]]
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
if "speech" == config.CitationClass then -- cite speech only
elseif is_set(TranscriptURL) then
TitleNote = " (Speech)"; -- annotate the citation
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
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
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) or is_set (ScriptPeriodical) or is_set (TransPeriodical)) then
if is_set(Title) or is_set(TitleNote) then
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical);
else
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical);
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 inArray(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
tcommon = safejoin( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series,
if is_set(Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
Language, Cartography, Edition, Publisher, Agency, Volume, Issue}, sepc );
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
else
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
tcommon = safejoin( {Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series, Language,
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
Volume, Issue, Others, Cartography, Edition, Publisher, Agency}, sepc );
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
end
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
else
if #ID_list > 0 then
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
ID_list = safejoin( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
end
else
ID_list = ID;
end
local idcommon = safejoin( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Page .. Pages .. At;
if is_set(Authors) then
if is_set(Coauthors) then
Authors = Authors .. A['AuthorSeparator'] .. " " .. Coauthors
end
if is_set(Date) then
Date = " ("..Date..")" .. OrigYear .. sepc .. " "
elseif string.sub(Authors,-1,-1) == sepc then
Authors = Authors .. " "
else
Authors = Authors .. sepc .. " "
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) then
in_text = in_text .. cfg.messages['in'] .. " "
else
if EditorCount <= 1 then
post_text = ", " .. cfg.messages['editor'];
else
post_text = ", " .. cfg.messages['editors'];
end
end
if (sepc ~= '.') then in_text = in_text:lower() end
Editors = in_text .. Editors .. post_text;
if (string.sub(Editors,-1,-1) == sepc)
then Editors = Editors .. " "
else Editors = Editors .. sepc .. " "
end
end
text = safejoin( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
text = safejoin( {text, pgtext, idcommon}, sepc );
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
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safejoin( {Editors, Date, Chapter, Place, tcommon}, sepc );
text = safejoin( {text, pgtext, idcommon}, sepc );
else
if is_set(Date) then
if ( string.sub(tcommon,-1,-1) ~= sepc )
then Date = sepc .." " .. Date .. OrigYear
else Date = " " .. Date .. OrigYear
end
end
if config.CitationClass=="journal" and is_set(Periodical) then
text = safejoin( {Chapter, Place, tcommon}, sepc );
text = safejoin( {text, pgtext, Date, idcommon}, sepc );
else
text = safejoin( {Chapter, Place, tcommon, Date}, sepc );
text = safejoin( {text, pgtext, idcommon}, sepc );
end
end
if is_set(PostScript) and PostScript ~= sepc then
text = safejoin( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1,-2); --Remove final seperator
end
text = safejoin( {text, PostScript}, sepc );
 
elseif 'map' == config.CitationClass then -- special cases for cite map
-- Now enclose the whole thing in a <span/> element
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
local options = {};
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
options.class = "citation " .. config.CitationClass;
else -- a sheet or stand-alone map
else
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
options.class = "citation";
end
elseif 'episode' == config.CitationClass then -- special case for cite episode
if is_set(Ref) and Ref:lower() ~= "none" then
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
local id = Ref
if ( "harv" == Ref ) then
local names = {} --table of last names & year
if #a > 0 then
for i,v in ipairs(a) do
names[i] = v.last
if i == 4 then break end
end
elseif #e > 0 then
for i,v in ipairs(e) do
names[i] = v.last
if i == 4 then break end
end
end
names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations
id = anchorid(names)
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
z.error_categories = {};
text = seterror('empty_citation');
z.message_tail = {};
end
if is_set(options.id) then
text = '<span id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
else
text = '<span class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
end
 
else -- all other CS1 templates
local empty_span = '<span style="display:none;">&nbsp;</span>';
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume, Others, Edition, Publisher, Agency}, sepc );
-- Note: Using display: none on then COinS span breaks some clients.
end
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
text = text .. OCinS;
if #ID_list > 0 then
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
if #z.message_tail ~= 0 then
else
text = text .. " ";
ID_list = ID;
for i,v in ipairs( z.message_tail ) do
end
if is_set(v[1]) then
if i == #z.message_tail then
local idcommon;
text = text .. errorcomment( v[1], v[2] );
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
else
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
text = text .. errorcomment( v[1] .. "; ", v[2] );
else
end
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
end
end
end
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
no_tracking_cats = no_tracking_cats:lower();
 
if inArray(no_tracking_cats, {"", "no", "false", "n"}) then
if is_set(Date) then
for _, v in ipairs( z.error_categories ) do
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
text = text .. '[[Category:' .. v ..']]';
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
end
else -- neither of authors and editors set
end
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
return text
else
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
end
end
end
if is_set(Authors) then
if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then
in_text = in_text:lower() -- lowercase for cs2
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
post_text = " (" .. cfg.messages['editors'] .. ")";
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if 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 is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if (not is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif is_set(Editors) then
if is_set(Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
else
Editors = Editors .. ", " .. cfg.messages['editors'];
end
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if 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
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
 
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render, substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
table.insert (render, substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
 
table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
 
if 0 ~= #z.message_tail then
table.insert (render, ' ');
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if i == #z.message_tail then
table.insert (render, error_comment( v[1], v[2] ));
else
table.insert (render, error_comment( v[1] .. "; ", v[2] ));
end
end
end
end
 
if 0 ~= #z.maintenance_cats then
local maint_msgs = {}; -- here we collect all of the maint messages
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
local maint = {}; -- here we assemble a maintenence message
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint, make_wikilink (':Category:' .. v, 'link')); -- add the link
table.insert (maint, ')'); -- and close it
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
end
table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
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
table.insert (render, make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
table.insert (render, make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.properties_cats ) do -- append properties categories
table.insert (render, make_wikilink ('Category:' .. v));
end
end
 
return table.concat (render);
end
 
-- This is used by templates such as {{cite book}} to create the actual citation text.
function z.citation(frame)
local pframe = frame:getParent()
local args = {};
local suggestions = {};
local error_text, error_state;
 
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
local config = {};
for k, v in pairs( frame.args ) do
config[k] = v;
args[k] = v;
end
 
Looks for a parameter's name in one of several whitelists.
for k, v in pairs( pframe.args ) do
 
if v ~= '' then
Parameters in the whitelist can have three values:
if not validate( k ) then
true - active, supported parameters
error_text = "";
false - deprecated, supported parameters
if type( k ) ~= 'string' then
nil -- Exclude empty numberedunsupported parameters
if v:match("%S+") ~= nil then
]]
error_text, error_state = seterror( 'text_ignored', {v}, true );
 
end
local elseiffunction validate( k:lower()name, cite_class) then
local name = tostring (name);
error_text, error_state = seterror( 'parameter_ignored_suggest', {k, k:lower()}, true );
local state;
else
if #suggestions == 0 then
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- limited parameter sets allowed for these templates
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
state = whitelist.limited_basic_arguments[name];
end
if true == state then return true; end -- valid actively supported parameter
if suggestions[ k:lower() ] ~= nil then
if false == state then
error_text, error_state = seterror( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
deprecated_parameter (name); -- parameter is deprecated but still supported
else
return true;
error_text, error_state = seterror( 'parameter_ignored', {k}, true );
end
end
 
end
state = whitelist[cite_class .. '_basic_arguments'][name]; -- look in the parameter-list for the template identified by cite_class
if error_text ~= '' then
 
table.insert( z.message_tail, {error_text, error_state} );
if true == state then return true; end -- valid actively supported parameter
end
if false == state then
end
deprecated_parameter (name); -- parameter is deprecated but still supported
args[k] = v;
return true;
elseif args[k] ~= nil or (k == 'postscript') then
end
args[k] = v;
-- limited enumerated parameters list
end
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
end
state = whitelist.limited_numbered_arguments[name];
if true == state then return true; end -- valid actively supported parameter
return citation0( config, args)
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
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
-- all enumerated parameters allowed
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
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
 
 
return z
--[[--------------------------< 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 (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
 
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {set_error ('missing_pipe',parameter)});
end
end
 
 
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
 
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
 
]]
 
local function has_extraneous_punc (param, value)
if cfg.punct_skip[param] then
return; -- parameter name found in the skip table so done
end
if value:match ('[,;:]$') then
add_maint_cat ('extra_punct'); -- has extraneous punctuation; add maint cat
end
end
 
 
--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
 
This is used by templates such as {{cite book}} to create the actual citation text.
 
]]
 
local function citation(frame)
Frame = frame; -- save a copy incase we need to display an error message in preview mode
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata, styles;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox');
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
styles = 'Module:Citation/CS1/sandbox/styles.css';
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
utilities = require ('Module:Citation/CS1/Utilities');
validation = require ('Module:Citation/CS1/Date_validation');
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
 
end
 
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 
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;
date_name_xlate = validation.date_name_xlate;
 
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;
is_wikilink = utilities.is_wikilink;
make_wikilink = utilities.make_wikilink;
strip_apostrophe_markup = utilities.strip_apostrophe_markup;
 
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/Identifiers
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 = {}; -- table where we store all of the template's arguments
local suggestions = {}; -- table where we store suggestions if we need to loadData them
local error_text, error_state;
 
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
config[k] = v;
-- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}}
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 ('string' == type (k)) then
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
end
if not validate( k, config.CitationClass ) then
error_text = "";
if type( k ) ~= 'string' then
-- Exclude empty numbered parameters
if v:match("%S+") ~= nil then
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
else
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
end
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
capture = k:match (pattern); -- the whole match if no 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)
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
error_text, error_state = set_error ('parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = set_error( 'parameter_ignored', {param}, true ); -- suggested param not supported by this template
end
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 );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end
if error_text ~= '' then
table.insert( z.message_tail, {error_text, error_state} );
end
end
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
-- TODO: is this the best place for this translation?
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then -- here when v is empty string
args[k] = v; -- why do we do this? we don't support 'empty' parameters
end
end
 
for k, v in pairs( args ) do
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v);
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
end
end
return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles, wrapper=".cs1-sandbox"})});
end
 
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
 
return {citation = citation};
"https://te.wikipedia.org/wiki/మాడ్యూల్:Citation/CS1/sandbox" నుండి వెలికితీశారు