Изменения

Перейти к навигации Перейти к поиску

Модуль:Citation/CS1 (посмотреть исходный код)

Версия от 18:09, 24 декабря 2023

93 023 байта добавлено ,  1 год назад
update from enwiki
Строка 1: Строка 1:  +
require ('strict');
   −
local z = {
+
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
−
error_categories = {}; -- for categorizing citations that contain errors
+
 
−
error_ids = {};
+
each of these counts against the Lua upvalue limit
−
message_tail = {};
  −
maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
  −
properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance
  −
}
     −
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
   
]]
 
]]
−
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation
     −
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
+
local validation; -- functions in Module:Citation/CS1/Date_validation
−
local whitelist = {}; -- talbe of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
     −
--[[--------------------------< I S _ S E T >------------------------------------------------------------------
+
local utilities; -- functions in Module:Citation/CS1/Utilities
 +
local z = {}; -- table of tables in Module:Citation/CS1/Utilities
   −
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
+
local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
−
This function is global because it is called from both this module and from Date validation
+
local metadata; -- functions in Module:Citation/CS1/COinS
 +
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
 +
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
 +
 
 +
 
 +
--[[------------------< P A G E  S C O P E  V A R I A B L E S >---------------
 +
 
 +
declare variables here that have page-wide scope that are not brought in from
 +
other modules; that are created here and used here
    
]]
 
]]
−
function is_set( var )
+
 
−
return not (var == nil or var == '');
+
local added_deprecated_cat; -- Boolean flag so that the category is added only once
−
end
+
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category
 +
local added_generic_name_errs; -- Boolean flag so we only emit one generic name error / category and stop testing names once an error is encountered
 +
local added_numeric_name_errs; -- Boolean flag so we only emit one numeric name error / category and stop testing names once an error is encountered
 +
local added_numeric_name_maint; -- Boolean flag so we only emit one numeric name maint category and stop testing names once a category has been emitted
 +
local Frame; -- holds the module's frame table
 +
local is_preview_mode; -- true when article is in preview mode; false when using 'Preview page with this template' (previewing the module)
 +
local is_sandbox; -- true when using sandbox modules to render citation
 +
 
    
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
 
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
   −
First set variable or nil if none
+
Locates and returns the first set value in a table of values where the order established in the table,
 +
left-to-right (or top-to-bottom), is the order in which the values are evaluated.  Returns nil if none are set.
 +
 
 +
This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs.  With the pairs
 +
version the order of evaluation could not be guaranteed.  With the ipairs version, a nil value would terminate
 +
the for-loop before it reached the actual end of the list.
    
]]
 
]]
   −
local function first_set(...)
+
local function first_set (list, count)
−
local list = {...};
+
local i = 1;
−
for _, var in pairs(list) do
+
while i <= count do -- loop through all items in list
−
if is_set( var ) then
+
if utilities.is_set( list[i] ) then
−
return var;
+
return list[i]; -- return the first set list member
 
end
 
end
 +
i = i + 1; -- point to next
 
end
 
end
 
end
 
end
   −
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
     −
Whether needle is in haystack
+
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
 +
 
 +
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
 +
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 +
 
 +
added_vanc_errs is a Boolean declared in page scope variables above
    
]]
 
]]
   −
local function in_array( needle, haystack )
+
local function add_vanc_error (source, position)
−
if needle == nil then
+
if added_vanc_errs then return end
−
return false;
+
−
end
+
added_vanc_errs = true; -- note that we've added this category
−
for n,v in ipairs( haystack ) do
+
utilities.set_message ('err_vancouver', {source, position});
−
if v == needle then
  −
return n;
  −
end
  −
end
  −
return false;
   
end
 
end
   −
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
     −
Populates numbered arguments in a message string using an argument table.
+
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
 +
 
 +
does this thing that purports to be a URI scheme seem to be a valid scheme?  The scheme is checked to see if it
 +
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
 +
Scheme names consist of a sequence of characters beginning with a
 +
  letter and followed by any combination of letters, digits, plus
 +
  ("+"), period ("."), or hyphen ("-").
 +
 
 +
returns true if it does, else false
    
]]
 
]]
   −
local function substitute( msg, args )
+
local function is_scheme (scheme)
−
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
+
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
 
end
 
end
   −
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------
     −
Wraps error messages with css markup according to the state of hidden.
+
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
 +
 
 +
Does this thing that purports to be a domain name seem to be a valid domain name?
 +
 
 +
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
 +
BNF defined here: https://tools.ietf.org/html/rfc4234
 +
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
 +
see also [[Single-letter second-level domain]]
 +
list of TLDs: https://www.iana.org/domains/root/db
 +
 
 +
RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit.  Between
 +
the first and last characters the name may use letters, digits, and the hyphen.
   −
]]
+
Also allowed are IPv4 addresses. IPv6 not supported
−
local function error_comment( content, hidden )
  −
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
  −
end
     −
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
+
domain is expected to be stripped of any path so that the last character in the last character of the TLD.  tld
 +
is two or more alpha characters.  Any preceding '//' (from splitting a URL with a scheme) will be stripped
 +
here.  Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal.
   −
Sets an error condition and returns the appropriate error message. The actual placement of the error message in the output is
+
There are several tests:
−
the responsibility of the calling function.
+
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 set_error( error_id, arguments, raw, prefix, suffix )
+
 
−
local error_state = cfg.error_conditions[ error_id ];
+
]=]
−
+
 
−
prefix = prefix or "";
+
local function is_domain_name (domain)
−
suffix = suffix or "";
+
if not domain then
−
+
return false; -- if not set, abandon
−
if error_state == nil then
  −
error( cfg.messages['undefined_error'] );
  −
elseif is_set( error_state.category ) then
  −
table.insert( z.error_categories, error_state.category );
   
end
 
end
 
 
−
local message = substitute( error_state.message, arguments );
+
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
 
 
−
message = message .. " ([[" .. cfg.messages['help page link'] ..
+
if not domain:match ('^[%w]') then -- first character must be letter or digit
−
"#" .. error_state.anchor .. "|" ..
+
return false;
−
cfg.messages['help page label'] .. "]])";
  −
  −
z.error_ids[ error_id ] = true;
  −
if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
  −
and z.error_ids['citation_missing_title'] then
  −
return '', false;
   
end
 
end
−
  −
message = table.concat({ prefix, message, suffix });
  −
  −
if raw == true then
  −
return message, error_state.hidden;
  −
end
  −
  −
return error_comment( message, error_state.hidden );
  −
end
     −
--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
+
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
 +
return false;
 +
end
   −
Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
+
local patterns = { -- patterns that look like URLs
 +
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
 +
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
 +
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
 +
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
 +
'%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars)
 +
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD
 +
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
 +
}
   −
]]
+
for _, pattern in ipairs (patterns) do -- loop through the patterns list
 +
if domain:match (pattern) then
 +
return true; -- if a match then we think that this thing that purports to be a URL is a URL
 +
end
 +
end
   −
local function add_maint_cat (key, arguments)
+
for _, d in ipairs (cfg.single_letter_2nd_lvl_domains_t) do -- look for single letter second level domain names for these top level domains
−
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
+
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
 
end
   −
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
     −
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
+
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
 +
 
 +
returns true if the scheme and domain parts of a URL appear to be a valid URL; else false.
 +
 
 +
This function is the last step in the validation process.  This function is separate because there are cases that
 +
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
 +
wikilinks.
    
]]
 
]]
   −
local function add_prop_cat (key, arguments)
+
local function is_url (scheme, domain)
−
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
+
if utilities.is_set (scheme) then -- if scheme is set check it and domain
 +
return is_scheme (scheme) and is_domain_name (domain);
 +
else
 +
return is_domain_name (domain); -- scheme not set when URL is protocol-relative
 +
end
 
end
 
end
   −
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
     −
Determines whether a URL string is valid.
+
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
   −
At present the only check is whether the string appears to be prefixed with a URI scheme.  It is not determined whether
+
Split a URL into a scheme, authority indicator, and domain.
−
the URI scheme is valid or whether the URL is otherwise well formed.
     −
]]
+
First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#).
   −
local function check_url( url_str )
+
If protocol-relative URL, return nil scheme and domain else return nil for both scheme and domain.
−
return url_str:sub(1,2) == "//" or url_str:match( "^[^/]*:" ) ~= nil; -- Protocol-relative or URL scheme
  −
end
     −
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
+
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.
   −
Protects a string that will be wrapped in wiki italic markup '' ... ''
+
Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes
 +
like news: that don't use authority indicator?
   −
Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
+
Strip off any port and path;
−
they will be inverted (i.e. unitalicized) in the resulting references.  In addition, <i> and '' tend to interact
  −
poorly under Mediawiki's HTML tidy.
      
]]
 
]]
   −
local function safe_for_italics( str )
+
local function split_url (url_str)
−
if not is_set(str) then
+
local scheme, authority, domain;
−
return str;
+
−
else
+
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
−
if str:sub(1,1) == "'" then str = "<span />" .. str; end
+
 
−
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
+
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL
−
+
domain = url_str:match ('^//(%S*)')
−
-- Remove newlines as they break italics.
+
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
−
return str:gsub( '\n', ' ' );
+
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
 +
if utilities.is_set (authority) then
 +
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
 +
if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
 +
return scheme; -- return scheme only making domain nil which will cause an error message
 +
end
 +
else
 +
if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test?
 +
return scheme; -- return scheme only making domain nil which will cause an error message
 +
end
 +
end
 +
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
 
end
 
end
 +
 +
return scheme, domain;
 
end
 
end
   −
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
     −
Escape sequences for content that will be used for URL descriptions
+
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
   −
]]
+
checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs
   −
local function safe_for_url( str )
+
Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
−
if str:match( "%[%[.-%]%]" ) ~= nil then
+
# < > [ ] | { } _
−
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
+
except the underscore which is used as a space in wiki URLs and # which is used for section links
−
end
  −
  −
return str:gsub( '[%[%]\n]', {
  −
['['] = '&#91;',
  −
[']'] = '&#93;',
  −
['\n'] = ' ' } );
  −
end
     −
--[[--------------------------< W R A P _ S T Y L E >----------------------------------------------------------
+
returns false when the value contains any of these characters.
   −
Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
+
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid URL (the
−
argument; protects italic styled parameters.  Additional text taken from citation_config.presentation - the reason
+
|<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
−
this function is similar to but separate from wrap_msg().
      
]]
 
]]
   −
local function wrap_style (key, str)
+
local function link_param_ok (value)
−
if not is_set( str ) then
+
local scheme, domain;
−
return "";
+
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
−
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
+
return false;
−
str = safe_for_italics( str );
   
end
 
end
   −
return substitute( cfg.presentation[key], {str} );
+
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from URL;
 +
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL
 
end
 
end
   −
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
     −
Format an external link with error checking
+
--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
 +
 
 +
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
 +
 
 +
|<title>= may be wiki-linked but not when |<param>-link= has a value.  This function emits an error message when
 +
that condition exists
 +
 
 +
check <link> for inter-language interwiki-link prefix.  prefix must be a MediaWiki-recognized language
 +
code and must begin with a colon.
    
]]
 
]]
   −
local function external_link( URL, label, source )
+
local function link_title_ok (link, lorig, title, torig)
−
local error_str = "";
+
local orig;
−
if not is_set( label ) then
+
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value
−
label = URL;
+
if not link_param_ok (link) then -- check |<param>-link= markup
−
if is_set( source ) then
+
orig = lorig; -- identify the failing link parameter
−
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
+
elseif title:find ('%[%[') then -- check |title= for wikilink markup
−
else
+
orig = torig; -- identify the failing |title= parameter
−
error( cfg.messages["bare_url_no_origin"] );
+
elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki
−
end
+
local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix
 +
 
 +
if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon
 +
orig = lorig; -- flag as error
 +
end
 +
end
 
end
 
end
−
if not check_url( URL ) then
+
 
−
error_str = set_error( 'bad_url', {}, false, " " ) .. error_str;
+
if utilities.is_set (orig) then
 +
link = ''; -- unset
 +
utilities.set_message ('err_bad_paramlink', orig); -- URL or wikilink in |title= with |title-link=;
 
end
 
end
−
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
+
 +
return link; -- link if ok, empty string else
 
end
 
end
   −
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
     −
Formats a wiki style external link
+
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
 +
 
 +
Determines whether a URL string appears to be valid.
 +
 
 +
First we test for space characters.  If any are found, return false.  Then split the URL into scheme and domain
 +
portions, or for protocol-relative (//example.com) URLs, just the domain.  Use is_url() to validate the two
 +
portions of the URL.  If both are valid, or for protocol-relative if domain is valid, return true, else false.
 +
 
 +
Because it is different from a standard URL, and because this module used external_link() to make external links
 +
that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name
 +
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
    
]]
 
]]
   −
local function external_link_id(options)
+
local function check_url( url_str )
−
local url_string = options.id;
+
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL
−
if options.encode == true or options.encode == nil then
+
return false;
−
url_string = mw.uri.encode( url_string );
   
end
 
end
−
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
+
local scheme, domain;
−
options.link, options.label, options.separator or "&nbsp;",
  −
options.prefix, url_string, options.suffix or "",
  −
mw.text.nowiki(options.id)
  −
);
  −
end
     −
--[[
+
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
−
Categorize and emit an error message when the citation contains one or more deprecated parameters.  Because deprecated parameters (currently |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)
+
if 'news:' == scheme then -- special case for newsgroups
−
details of which parameter caused the error message are not provided.  Only one error message is emitted regardless of the number of deprecated parameters in the citation.
+
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
−
]]
  −
local function deprecated_parameter(name)
  −
if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a  
  −
Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once
  −
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
   
end
 
end
 +
 +
return is_url (scheme, domain); -- return true if value appears to be a valid URL
 
end
 
end
   −
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
     −
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
+
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
−
This function will positive kern either single or double quotes:
+
 
−
"'Unkerned title with leading and trailing single quote marks'"
+
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
−
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
+
non-space characters following the opening bracket appear to be a URL.  The test will also find external wikilinks
−
Double single quotes (italic or bold wikimarkup) are not kerned.
+
that use protocol-relative URLs. Also finds bare URLs.
 +
 
 +
The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs.  The tests that
 +
find bracketed URLs are required because the parameters that call this test (currently |title=, |chapter=, |work=,
 +
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
 +
is possible as might be [[en://Hus]].
   −
Call this function for chapter titles, for website titles, etc; not for book titles.
+
]=]
   −
]]
+
local function is_parameter_ext_wikilink (value)
 +
local scheme, domain;
   −
local function kern_quotes (str)
+
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
−
local cap='';
+
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
−
local cap2='';
+
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz]
−
+
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
−
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
+
elseif value:match ('%a%S*:%S+') then -- if bare URL with scheme; may have leading or trailing plain text
−
if is_set (cap) then
+
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
−
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
+
elseif value:match ('//%S+') then -- if protocol-relative bare URL: //yyyyy.zzz; may have leading or trailing plain text
 +
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
 +
else
 +
return false; -- didn't find anything that is obviously a URL
 
end
 
end
   −
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
+
return is_url (scheme, domain); -- return true if value appears to be a valid URL
−
if is_set (cap) then
  −
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
  −
end
  −
return str;
   
end
 
end
   −
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
  −
  −
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
  −
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
+
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
−
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.
     −
At this writing, only |script-title= is supported.  It is anticipated that additional parameters will be created to use this function.
+
loop through a list of parameters and their values.  Look at the value and if it has an external link, emit an error message.
   −
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
   
]]
 
]]
   −
local function format_script_value (script_value)
+
local function check_for_url (parameter_list, error_list)
−
local lang=''; -- initialize to empty string
+
for k, v in pairs (parameter_list) do -- for each parameter in the list
−
local name;
+
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a URL add an error message
−
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
+
table.insert (error_list, utilities.wrap_style ('parameter', k));
−
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
  −
if not is_set (lang) then
  −
return ''; -- script_value was just the prefix so return empty string
  −
end
  −
-- if we get this far we have prefix and script
  −
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
  −
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
  −
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
  −
-- is prefix one of these language codes?
  −
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'hy', 'ja', 'ka', 'ko', 'ku', 'he', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
  −
add_prop_cat ('script_with_name', {name, lang})
  −
else
  −
add_prop_cat ('script')
  −
end
  −
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
  −
else
  −
lang = ''; -- invalid so set lang to empty string
   
end
 
end
 
end
 
end
−
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
  −
  −
return script_value;
   
end
 
end
   −
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
     −
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
+
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
−
wrapped in <bdi> tags.
+
 
 +
Escape sequences for content that will be used for URL descriptions
 +
 
 
]]
 
]]
   −
local function script_concatenate (title, script)
+
local function safe_for_url( str )
−
if is_set (script) then
+
if str:match( "%[%[.-%]%]" ) ~= nil then  
−
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
+
utilities.set_message ('err_wikilink_in_url', {});
−
if is_set (script) then
  −
title = title .. ' ' .. script; -- concatenate title and script title
  −
end
   
end
 
end
−
return title;
+
 +
return str:gsub( '[%[%]\n]', {
 +
['['] = '&#91;',
 +
[']'] = '&#93;',
 +
['\n'] = ' ' } );
 
end
 
end
      −
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
+
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
   −
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
+
Format an external link with error checking
−
configuration taking one argument.  Supports lower case text for {{citation}} templates.  Additional text taken
  −
from citation_config.messages - the reason this function is similar to but separate from wrap_style().
      
]]
 
]]
   −
local function wrap_msg (key, str, lower)
+
local function external_link (URL, label, source, access)
−
if not is_set( str ) then
+
local err_msg = '';
−
return "";
+
local domain;
 +
local path;
 +
local base_url;
 +
 
 +
if not utilities.is_set (label) then
 +
label = URL;
 +
if utilities.is_set (source) then
 +
utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)});
 +
else
 +
error (cfg.messages["bare_url_no_origin"]); -- programmer error; valid parameter name does not have matching meta-parameter
 +
end
 +
end
 +
if not check_url (URL) then
 +
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)});
 
end
 
end
−
if true == lower then
+
−
local msg;
+
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path
−
msg = cfg.messages[key]:lower(); -- set the message to lower case before
+
if path then -- if there is a path portion
−
str = substitute( msg, {str} ); -- including template text
+
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values
−
return str;
+
URL = table.concat ({domain, path}); -- and reassemble
−
else
+
end
−
return substitute( cfg.messages[key], {str} );
+
 
−
end
+
base_url = table.concat ({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL
 +
 
 +
if utilities.is_set (access) then -- access level (subscription, registration, limited)
 +
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
 +
end
 +
 
 +
return base_url;
 
end
 
end
   −
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
     −
Chooses one matching parameter from a list of parameters to consider
+
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
−
Generates an error if more than one match is present.
+
 
 +
Categorize and emit an error message when the citation contains one or more deprecated parameters.  The function includes the
 +
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
 +
parameters in the citation.
 +
 
 +
added_deprecated_cat is a Boolean declared in page scope variables above
    
]]
 
]]
   −
local function select_one( args, possible, error_condition, index )
+
local function deprecated_parameter(name)
−
local value = nil;
+
if not added_deprecated_cat then
−
local selected = '';
+
added_deprecated_cat = true; -- note that we've added this category
−
local error_list = {};
+
utilities.set_message ('err_deprecated_params', {name}); -- add error message
−
  −
if index ~= nil then index = tostring(index); end
  −
  −
-- Handle special case of "#" replaced by empty string
  −
if index == '1' then
  −
for _, v in ipairs( possible ) do
  −
v = v:gsub( "#", "" );
  −
if is_set(args[v]) then
  −
if value ~= nil and selected ~= v then
  −
table.insert( error_list, v );
  −
else
  −
value = args[v];
  −
selected = v;
  −
end
  −
end
  −
end
   
end
 
end
−
+
end
−
for _, v in ipairs( possible ) do
+
 
−
if index ~= nil then
+
 
−
v = v:gsub( "#", index );
+
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
−
end
+
 
−
if is_set(args[v]) then
+
Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote
−
if value ~= nil and selected ~= v then
+
mark contained in a |title= or |chapter= parameter's value.
−
table.insert( error_list, v );
+
 
−
else
+
This function will positive kern either single or double quotes:
−
value = args[v];
+
"'Unkerned title with leading and trailing single quote marks'"
−
selected = v;
+
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
−
end
+
Double single quotes (italic or bold wiki-markup) are not kerned.
−
end
+
 
−
end
+
Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
−
+
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
−
if #error_list > 0 then
  −
local error_str = "";
  −
for _, k in ipairs( error_list ) do
  −
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
  −
error_str = error_str .. wrap_style ('parameter', k);
  −
end
  −
if #error_list > 1 then
  −
error_str = error_str .. cfg.messages['parameter-final-separator'];
  −
else
  −
error_str = error_str .. cfg.messages['parameter-pair-separator'];
  −
end
  −
error_str = error_str .. wrap_style ('parameter', selected);
  −
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
  −
end
  −
  −
return value, selected;
  −
end
     −
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
+
Call this function for chapter titles, for website titles, etc.; not for book titles.
   −
Format the three chapter parameters: |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
+
]=]
−
parameter (chapter_url_source used for error messages).
     −
]]
+
local function kern_quotes (str)
 +
local cap = '';
 +
local wl_type, label, link;
   −
local function format_chapter_title (chapter, transchapter, chapterurl, chapter_url_source)
+
wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
−
local chapter_error = '';
   
 
−
if not is_set (chapter) then
+
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
−
chapter = ''; -- just to be safe for concatenation
+
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
−
if is_set (transchapter) then
+
str = utilities.substitute (cfg.presentation['kern-left'], str);
−
chapter = wrap_style ('trans-quoted-title', transchapter);
+
str = utilities.substitute (cfg.presentation['kern-right'], str);
−
chapter_error = " " .. set_error ('trans_missing_chapter');
+
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
 +
str = utilities.substitute (cfg.presentation['kern-left'], str);
 +
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
 +
str = utilities.substitute (cfg.presentation['kern-right'], str);
 
end
 
end
−
if is_set (chapterurl) then
+
 
−
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
+
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 = mw.ustring.match (label, "^([\"\'][^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
 +
if utilities.is_set (cap) then
 +
label = utilities.substitute (cfg.presentation['kern-left'], cap);
 
end
 
end
−
return chapter .. chapter_error;
+
−
else -- here when chapter is set
+
cap = mw.ustring.match (label, "^(.+[^\'][\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
−
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
+
if utilities.is_set (cap) then
−
chapter = wrap_style ('quoted-title', chapter);
+
label = utilities.substitute (cfg.presentation['kern-right'], cap);
−
if is_set (transchapter) then
  −
transchapter = wrap_style ('trans-quoted-title', transchapter);
  −
chapter = chapter .. ' ' .. transchapter;
   
end
 
end
−
if is_set (chapterurl) then
+
−
chapter = external_link (chapterurl, chapter); -- adds bare_url_missing_title error if appropriate
+
if 2 == wl_type then
 +
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
 +
else
 +
str = label;
 
end
 
end
 
end
 
end
−
return chapter;
+
return str;
 
end
 
end
   −
--[[
  −
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 )
+
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
−
local origin = {};
+
 
−
+
|script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
−
return setmetatable({
+
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
−
ORIGIN = function( self, k )
+
in italic markup.
−
local dummy = self[k]; --force the variable to be loaded.
+
 
−
return origin[k];
+
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate RTL languages from the English left to right.
 +
 
 +
|script-title= provides a unique feature.  The value in |script-title= may be prefixed with a two-character ISO 639-1 language code and a colon:
 +
|script-title=ja:*** *** (where * represents a Japanese character)
 +
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
 +
|script-title=ja : *** ***
 +
|script-title=ja: *** ***
 +
|script-title=ja :*** ***
 +
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
 +
 
 +
The prefix is checked for validity.  If it is a valid ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
 +
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
 +
is not added.  At this time there is no error message for this condition.
 +
 
 +
Supports |script-title=, |script-chapter=, |script-<periodical>=
 +
 
 +
]]
 +
 
 +
local function format_script_value (script_value, script_param)
 +
local lang=''; -- initialize to empty string
 +
local name;
 +
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
 +
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
 +
if not utilities.is_set (lang) then
 +
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing title part']}); -- prefix without 'title'; add error message
 +
return ''; -- script_value was just the prefix so return empty string
 
end
 
end
−
},
+
-- if we get this far we have prefix and script
−
{
+
name = cfg.lang_tag_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
−
__index = function ( tbl, k )
+
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
−
if origin[k] ~= nil then
+
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
−
return nil;
+
-- is prefix one of these language codes?
 +
if utilities.in_array (lang, cfg.script_lang_codes) then
 +
utilities.add_prop_cat ('script', {name, lang})
 +
else
 +
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['unknown language code']}); -- unknown script-language; add error message
 
end
 
end
−
+
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
−
local args, list, v = args, cfg.aliases[k];
+
else
−
+
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['invalid language code']}); -- invalid language code; add error message
−
if type( list ) == 'table' then
+
lang = ''; -- invalid so set lang to empty string
−
v, origin[k] = select_one( args, list, 'redundant_parameters' );
+
end
−
if origin[k] == nil then
+
else
−
origin[k] = ''; -- Empty string, not nil
+
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing prefix']}); -- no language code prefix; add error message
−
end
+
end
−
elseif list ~= nil then
+
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL
−
v, origin[k] = args[list], list;
+
 
−
else
+
return script_value;
−
-- maybe let through instead of raising an error?
+
end
−
-- v, origin[k] = args[k], k;
+
 
−
error( cfg.messages['unknown_argument_map'] .. ': cfg.aliases = ' .. mw.dumpObject( cfg.aliases ) .. ', k = ' .. mw.dumpObject( k ) );
+
 
−
end
+
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
−
+
 
−
-- Empty strings, not nil;
+
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script
−
if v == nil then
+
value has been wrapped in <bdi> tags.
−
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.
  −
  −
Parameters in the whitelist can have three values:
  −
true - active, supported parameters
  −
false - deprecated, supported parameters
  −
nil - unsupported parameters
   
]]
 
]]
   −
local function validate( name )
+
local function script_concatenate (title, script, script_param)
−
local name = tostring( name );
+
if utilities.is_set (script) then
−
local state = whitelist.basic_arguments[ name ];
+
script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error
−
+
if utilities.is_set (script) then
−
-- Normal arguments
+
title = title .. ' ' .. script; -- concatenate title and script title
−
if true == state then return true; end -- valid actively supported parameter
+
end
−
if false == state then
  −
deprecated_parameter (name); -- parameter is deprecated but still supported
  −
return true;
   
end
 
end
−
+
return title;
−
-- Arguments with numbers in them
  −
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
  −
state = whitelist.numbered_arguments[ name ];
  −
if true == state then return true; end -- valid actively supported parameter
  −
if false == state then
  −
deprecated_parameter (name); -- parameter is deprecated but still supported
  −
return true;
  −
end
  −
  −
return false; -- Not supported because not found or name is set to nil
   
end
 
end
      −
-- Formats a wiki style internal link
+
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
−
local function internal_link_id(options)
  −
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
  −
options.link, options.label, options.separator or "&nbsp;",
  −
options.prefix, options.id, options.suffix or "",
  −
mw.text.nowiki(options.id)
  −
);
  −
end
     −
 
+
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
−
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
+
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().
−
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
  −
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
  −
 
  −
DOES NOT yet support MMMM YYYY or any of the date ranges.
      
]]
 
]]
   −
local function nowrap_date (date)
+
local function wrap_msg (key, str, lower)
−
local cap='';
+
if not utilities.is_set ( str ) then
−
local cap2='';
+
return "";
−
 
  −
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
 
end
−
+
if true == lower then
−
return date;
+
local msg;
 +
msg = cfg.messages[key]:lower(); -- set the message to lower case before
 +
return utilities.substitute ( msg, str ); -- including template text
 +
else
 +
return utilities.substitute ( cfg.messages[key], str );
 +
end
 
end
 
end
   −
--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------
     −
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
+
--[[----------------< W I K I S O U R C E _ U R L _ M A K E >-------------------
−
If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes,
+
 
−
spaces and other non-isxn characters.
+
Makes a Wikisource URL from Wikisource interwiki-link.  Returns the URL and appropriate
 +
label; nil else.
 +
 
 +
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
    
]]
 
]]
   −
local function is_valid_isxn (isxn_str, len)
+
local function wikisource_url_make (str)
−
local temp = 0;
+
local wl_type, D, L;
−
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58
+
local ws_url, ws_label;
−
len = len+1; -- adjust to be a loop counter
+
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
−
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
+
 
−
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
+
wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
−
temp = temp + 10*( len - i ); -- it represents 10 decimal
+
 
−
else
+
if 0 == wl_type then -- not a wikilink; might be from |title-link=
−
temp = temp + tonumber( string.char(v) )*(len-i);
+
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
 +
if utilities.is_set (str) then
 +
ws_url = table.concat ({ -- build a Wikisource URL
 +
wikisource_prefix, -- prefix
 +
str, -- article title
 +
});
 +
ws_label = str; -- label for the URL
 +
end
 +
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
 +
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
 +
if utilities.is_set (str) then
 +
ws_url = table.concat ({ -- build a Wikisource URL
 +
wikisource_prefix, -- prefix
 +
str, -- article title
 +
});
 +
ws_label = str; -- label for the URL
 +
end
 +
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
 +
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
 +
if utilities.is_set (str) then
 +
ws_label = D; -- get ws article name from display portion of interwiki link
 +
ws_url = table.concat ({ -- build a Wikisource URL
 +
wikisource_prefix, -- prefix
 +
str, -- article title without namespace from link portion of wikilink
 +
});
 
end
 
end
 
end
 
end
−
return temp % 11 == 0; -- returns true if calculation result is zero
  −
end
      +
if ws_url then
 +
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL
 +
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker
 +
end
   −
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
+
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 >-----------------------
   −
Determines whether an ISBN string is valid
+
Format the three periodical parameters: |script-<periodical>=, |<periodical>=,
 +
and |trans-<periodical>= into a single Periodical meta-parameter.
    
]]
 
]]
   −
local function check_isbn( isbn_str )
+
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
−
if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
+
 
−
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
+
if not utilities.is_set (periodical) then
−
local len = isbn_str:len();
+
periodical = ''; -- to be safe for concatenation
−
+
else
−
if len ~= 10 and len ~= 13 then
+
periodical = utilities.wrap_style ('italic-title', periodical); -- style
−
return false;
   
end
 
end
   −
if len == 10 then
+
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
−
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
+
 
−
return is_valid_isxn(isbn_str, 10);
+
if utilities.is_set (trans_periodical) then
−
else
+
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
−
local temp = 0;
+
if utilities.is_set (periodical) then
−
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979
+
periodical = periodical .. ' ' .. trans_periodical;
−
isbn_str = { isbn_str:byte(1, len) };
+
else -- here when trans-periodical without periodical or script-periodical
−
for i, v in ipairs( isbn_str ) do
+
periodical = trans_periodical;
−
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) );
+
utilities.set_message ('err_trans_missing_title', {'periodical'});
 
end
 
end
−
return temp % 10 == 0;
   
end
 
end
 +
 +
return periodical;
 
end
 
end
   −
--[[--------------------------< I S S N >----------------------------------------------------------------------
     −
Validate and format an issn.  This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
+
--[[------------------< F O R M A T _ C H A P T E R _ T I T L E >---------------
−
digits with a space.  When that condition occurred, the resulting link looked like this:
     −
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327]  -- can't have spaces in an external link
+
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
−
+
and |chapter-url= into a single chapter meta- parameter (chapter_url_source used
−
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
+
for error messages).
−
with the calculated value.  Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn
  −
error message.  The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
      
]]
 
]]
   −
local function issn(id)
+
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access)
−
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
+
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link
−
local handler = cfg.id_handlers['ISSN'];
+
if ws_url then
−
local text;
+
ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters
−
local valid_issn = true;
+
chapter = ws_label;
 +
end
 +
 
 +
if not utilities.is_set (chapter) then
 +
chapter = ''; -- to be safe for concatenation
 +
else
 +
if false == no_quotes then
 +
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
 +
chapter = utilities.wrap_style ('quoted-title', chapter);
 +
end
 +
end
   −
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
+
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
   −
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
+
if utilities.is_set (chapter_url) then
−
valid_issn=false; -- wrong length or improper character
+
chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
−
else
+
elseif ws_url then
−
valid_issn=is_valid_isxn(id, 8); -- validate issn
+
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
 +
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
 
end
 
end
   −
if true == valid_issn then
+
if utilities.is_set (trans_chapter) then
−
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
+
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter);
−
else
+
if utilities.is_set (chapter) then
−
id = issn_copy; -- if not valid, use the show the invalid issn with error message
+
chapter = chapter .. ' ' .. trans_chapter;
 +
else -- here when trans_chapter without chapter or script-chapter
 +
chapter = trans_chapter;
 +
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>
 +
utilities.set_message ('err_trans_missing_title', {chapter_source});
 +
end
 
end
 
end
−
+
 
−
text = external_link_id({link = handler.link, label = handler.label,
+
return chapter;
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
  −
  −
if false == valid_issn then
  −
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
  −
end
  −
  −
return text
   
end
 
end
   −
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
     −
Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
+
--[[----------------< H A S _ I N V I S I B L E _ C H A R S >-------------------
−
characters.  If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
  −
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
  −
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
     −
]]
+
This function searches a parameter's value for non-printable or invisible characters.
 +
The search stops at the first match.
 +
 
 +
This function will detect the visible replacement character when it is part of the Wikisource.
   −
local function amazon(id, domain)
+
Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers
−
local err_cat = ""
+
(gallery, math, pre, ref) and identifies them with a slightly different error message.
 +
See also coins_cleanup().
   −
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
+
Output of this function is an error message that identifies the character or the
−
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
+
Unicode group, or the stripmarker that was detected along with its position (or,
−
else
+
for multi-byte characters, the position of its first byte) in the parameter value.
−
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
  −
if check_isbn( id ) then -- see if asin value is isbn10
  −
add_maint_cat ('ASIN');
  −
elseif not is_set (err_cat) then
  −
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not isbn10
  −
end
  −
elseif not id:match("^%u[%d%u]+$") then
  −
err_cat =  ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
  −
end
  −
end
  −
if not is_set(domain) then
  −
domain = "com";
  −
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
  −
domain = "co." .. domain;
  −
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
  −
domain = "com." .. domain;
  −
end
  −
local handler = cfg.id_handlers['ASIN'];
  −
return external_link_id({link = handler.link,
  −
label=handler.label , prefix="//www.amazon."..domain.."/dp/",id=id,
  −
encode=handler.encode, separator = handler.separator}) .. err_cat;
  −
end
     −
--[[--------------------------< A R X I V >--------------------------------------------------------------------
+
]]
   −
See: http://arxiv.org/help/arxiv_identifier
+
local function has_invisible_chars (param, v)
 +
local position = ''; -- position of invisible char or starting position of stripmarker
 +
local capture; -- used by stripmarker detection to hold name of the stripmarker
 +
local stripmarker; -- boolean set true when a stripmarker is found
   −
format and error check arXiv identifier. There are three valid forms of the identifier:
+
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
−
the first form, valid only between date codes 9108 and 0703 is:
+
if capture == v then -- if same there are no Unicode characters
−
arXiv:<archive>.<class>/<date code><number><version>
+
return;
−
where:
+
end
−
<archive> is a string of alpha characters - may be hyphenated; no other punctuation
  −
<class> is a string of alpha characters - may be hyphenated; no other punctuation
  −
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
  −
first digit of YY for this form can only 9 and 0
  −
<number> is a three-digit number
  −
<version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented)
  −
  −
the second form, valid from April 2007 through December 2014 is:
  −
arXiv:<date code>.<number><version>
  −
where:
  −
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
  −
<number> is a four-digit number
  −
<version> is a 1 or more digit number preceded with a lowercase v; no spaces
     −
the third form, valid from January 2015 is:
+
for _, invisible_char in ipairs (cfg.invisible_chars) do
−
arXiv:<date code>.<number><version>
+
local char_name = invisible_char[1]; -- the character or group name
−
where:
+
local pattern = invisible_char[2]; -- the pattern used to find it
−
<date code> and <version> are as defined for 0704-1412
+
position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern
−
<number> is a five-digit number
+
−
]]
+
if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
 +
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
 +
position = nil; -- unset position
 +
elseif cfg.emoji_t[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
 +
position = nil; -- unset position
 +
end
 +
end
 +
 +
if position then
 +
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
 +
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
 +
stripmarker = true; -- set a flag
 +
elseif true == stripmarker and cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
 +
position = nil; -- unset
 +
else
 +
local err_msg;
 +
if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
 +
err_msg = capture .. ' ' .. char_name;
 +
else
 +
err_msg = char_name .. ' ' .. 'character';
 +
end
   −
local function arxiv (id, class)
+
utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}); -- add error message
−
local handler = cfg.id_handlers['ARXIV'];
+
return; -- and done with this parameter
−
local year, month, version;
+
end
−
local err_cat = '';
  −
local text;
  −
  −
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
  −
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
  −
year = tonumber(year);
  −
month = tonumber(month);
  −
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
  −
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
  −
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
  −
end
  −
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
  −
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
  −
year = tonumber(year);
  −
month = tonumber(month);
  −
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
  −
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
  −
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
  −
end
  −
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
  −
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
  −
year = tonumber(year);
  −
month = tonumber(month);
  −
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
  −
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
   
end
 
end
−
else
  −
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
   
end
 
end
 +
end
   −
text = external_link_id({link = handler.link, label = handler.label,
  −
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
     −
if is_set (class) then
+
--[[-------------------< A R G U M E N T _ W R A P P E R >----------------------
−
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
  −
else
  −
class = ''; -- empty string for concatenation
  −
end
  −
  −
return text .. class;
  −
end
     −
--[[
+
Argument wrapper. This function provides support for argument mapping defined
−
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
+
in the configuration file so that multiple names can be transparently aliased to
−
1. Remove all blanks.
+
single internal variable.
−
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
  −
3. If there is a hyphen in the string:
  −
a. Remove it.
  −
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
  −
1. All these characters should be digits, and there should be six or less. (not done in this function)
  −
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
     −
Returns a normalized lccn for lccn() to validate.  There is no error checking (step 3.b.1) performed in this function.
   
]]
 
]]
   −
local function normalize_lccn (lccn)
+
local function argument_wrapper ( args )
−
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
+
local origin = {};
−
 
  −
if nil ~= string.find (lccn,'/') then
  −
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
  −
end
  −
 
  −
local prefix
  −
local suffix
  −
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
  −
 
  −
if nil ~= suffix then -- if there was a hyphen
  −
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
  −
lccn=prefix..suffix; -- reassemble the lccn
  −
end
   
 
−
return lccn;
+
return setmetatable({
−
end
+
ORIGIN = function ( self, k )
−
 
+
local dummy = self[k]; -- force the variable to be loaded.
−
--[[
+
return origin[k];
−
Format LCCN link and do simple error checking.  LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the
  −
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
  −
 
  −
length = 8 then all digits
  −
length = 9 then lccn[1] is lower case alpha
  −
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
  −
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
  −
length = 12 then lccn[1] and lccn[2] are both lower case alpha
  −
 
  −
]]
  −
 
  −
local function lccn(lccn)
  −
local handler = cfg.id_handlers['LCCN'];
  −
local err_cat =  ''; -- presume that LCCN is valid
  −
local id = lccn; -- local copy of the lccn
  −
 
  −
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
  −
local len = id:len(); -- get the length of the lccn
  −
 
  −
if 8 == len then
  −
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
  −
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
   
end
 
end
−
elseif 9 == len then -- LCCN should be adddddddd
+
},
−
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
+
{
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
+
__index = function ( tbl, k )
−
end
+
if origin[k] ~= nil then
−
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
+
return nil;
−
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
  −
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
  −
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
   
end
 
end
−
end
+
−
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
+
local args, list, v = args, cfg.aliases[k];
−
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
+
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
+
if type( list ) == 'table' then
−
end
+
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' );
−
elseif 12 == len then -- LCCN should be aadddddddddd
+
if origin[k] == nil then
−
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
+
origin[k] = ''; -- Empty string, not nil
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
+
end
−
end
+
elseif list ~= nil then
−
else
+
v, origin[k] = args[list], list;
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
+
else
−
end
+
-- maybe let through instead of raising an error?
 +
-- v, origin[k] = args[k], k;
 +
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
 +
end
 +
 +
-- Empty strings, not nil;
 +
if v == nil then
 +
v = '';
 +
origin[k] = '';
 +
end
 +
 +
tbl = rawset( tbl, k, v );
 +
return v;
 +
end,
 +
});
 +
end
 +
 
 +
 
 +
--[[--------------------------< N O W R A P _ D A T E >-------------------------
   −
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
+
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
−
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
+
When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
−
end
+
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
   −
return external_link_id({link = handler.link, label = handler.label,
+
DOES NOT yet support MMMM YYYY or any of the date ranges.
−
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
  −
end
     −
--[[
  −
Format PMID and do simple error checking.  PMIDs are sequential numbers beginning at 1 and counting up.  This code checks the PMID to see that it
  −
contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.
   
]]
 
]]
   −
local function pmid(id)
+
local function nowrap_date (date)
−
local test_limit = 30000000; -- update this value as PMIDs approach
+
local cap = '';
−
local handler = cfg.id_handlers['PMID'];
+
local cap2 = '';
−
local err_cat = ''; -- presume that PMID is valid
+
 
−
+
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
−
if id:match("[^%d]") then -- if PMID has anything but digits
+
date = utilities.substitute (cfg.presentation['nowrap1'], date);
−
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
+
−
else -- PMID is only digits
+
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
−
local id_num = tonumber(id); -- convert id to a number for range testing
+
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
−
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
+
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
−
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
  −
end
   
end
 
end
 
 
−
return external_link_id({link = handler.link, label = handler.label,
+
return date;
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
   
end
 
end
   −
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
     −
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is
+
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------
−
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
+
 
−
|embargo= was not set in this cite.
+
This function sets default title types (equivalent to the citation including
 +
|type=<default value>) for those templates that have defaults. Also handles the
 +
special case where it is desirable to omit the title type from the rendered citation
 +
(|type=none).
    
]]
 
]]
   −
local function is_embargoed (embargo)
+
local function set_titletype (cite_class, title_type)
−
if is_set (embargo) then
+
if utilities.is_set (title_type) then
−
local lang = mw.getContentLanguage();
+
if 'none' == cfg.keywords_xlate[title_type] then
−
local good1, embargo_date, good2, todays_date;
+
title_type = ''; -- if |type=none then type parameter not displayed
−
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
  −
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
  −
  −
if good1 and good2 then -- if embargo date and today's date are good dates
  −
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
  −
return embargo; -- still embargoed
  −
else
  −
add_maint_cat ('embargo')
  −
return ''; -- unset because embargo has expired
  −
end
   
end
 
end
 +
return title_type; -- if |type= has been set to any other value use that value
 
end
 
end
−
return ''; -- |embargo= not set return empty string
+
 
 +
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
 
end
 
end
   −
--[[--------------------------< P M C >------------------------------------------------------------------------
     −
Format a PMC, do simple error checking, and check for embargoed articles.
+
--[[--------------------------< S A F E _ J O I N >-----------------------------
   −
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
+
Joins a sequence of strings together while checking for duplicate separation characters.
−
be linked to the article.  If the embargo date is today or in the past, or if it is empty or omitted, then the
  −
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
  −
 
  −
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
  −
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link.  Function is_embargoed ()
  −
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
  −
 
  −
PMCs are sequential numbers beginning at 1 and counting up.  This code checks the PMC to see that it contains only digits and is less
  −
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
      
]]
 
]]
   −
local function pmc(id, embargo)
+
local function safe_join( tbl, duplicate_char )
−
local test_limit = 5000000; -- update this value as PMCs approach
+
local f = {}; -- create a function table appropriate to type of 'duplicate character'
−
local handler = cfg.id_handlers['PMC'];
+
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
−
local err_cat = ''; -- presume that PMC is valid
+
f.gsub = string.gsub
−
+
f.match = string.match
−
local text;
+
f.sub = string.sub
−
 
+
else -- for multi-byte characters use the ustring library functions
−
if id:match("[^%d]") then -- if PMC has anything but digits
+
f.gsub = mw.ustring.gsub
−
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
+
f.match = mw.ustring.match
−
else -- PMC is only digits
+
f.sub = mw.ustring.sub
−
local id_num = tonumber(id); -- convert id to a number for range testing
  −
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
  −
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
   
end
 
end
−
end
  −
  −
if is_set (embargo) then -- is PMC is still embargoed?
  −
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
  −
else
  −
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
  −
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
  −
end
  −
return text;
  −
end
     −
-- Formats a DOI and checks for DOI errors.
+
local str = ''; -- the output string
−
 
+
local comp = ''; -- what does 'comp' mean?
−
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
+
local end_chr = '';
−
--  Prefix: directory indicator '10.' followed by a registrant code
+
local trim;
−
--  Suffix: character string of any length chosen by the registrant
+
for _, value in ipairs( tbl ) do
 +
if value == nil then value = ''; end
 +
 +
if str == '' then -- if output string is empty
 +
str = value; -- assign value to it (first time through the loop)
 +
elseif value ~= '' then
 +
if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup.
 +
comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string)
 +
else
 +
comp = value;
 +
end
 +
-- typically duplicate_char is sepc
 +
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
 +
--  Because individual string segments often (always?) begin with terminal punct for the
 +
--  preceding segment: 'First element' .. 'sepc next element' .. etc.?
 +
trim = false;
 +
end_chr = f.sub(str, -1, -1); -- get the last character of the output string
 +
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff?
 +
if end_chr == duplicate_char then -- if same as separator
 +
str = f.sub(str, 1, -2); -- remove it
 +
elseif end_chr == "'" then -- if it might be wiki-markup
 +
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
 +
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
 +
elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''  
 +
trim = true; -- why? why do this and next differently from previous?
 +
elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
 +
trim = true; -- same question
 +
end
 +
elseif end_chr == "]" then -- if it might be wiki-markup
 +
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
 +
trim = true;
 +
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
 +
trim = true;
 +
elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
 +
trim = true;
 +
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
 +
trim = true;
 +
end
 +
elseif end_chr == " " then -- if last char of output string is a space
 +
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
 +
str = f.sub(str, 1, -3); -- remove them both
 +
end
 +
end
   −
-- This function checks a DOI name for: prefix/suffix.  If the doi name contains spaces or endashes,
+
if trim then
−
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
+
if value ~= comp then -- value does not equal comp when value contains HTML markup
−
 
+
local dup2 = duplicate_char;
−
-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
+
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
−
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
+
−
 
+
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup
−
local function doi(id, inactive)
+
else
−
local cat = ""
+
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
−
local handler = cfg.id_handlers['DOI'];
+
end
−
+
end
−
local text;
+
end
−
if is_set(inactive) then
+
str = str .. value; -- add it to the output string
−
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
  −
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
  −
if is_set(inactive_year) then
  −
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
  −
else
  −
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
   
end
 
end
−
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
  −
else
  −
text = external_link_id({link = handler.link, label = handler.label,
  −
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
  −
inactive = ""
   
end
 
end
−
 
+
return str;
−
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
  −
cat = ' ' .. set_error( 'bad_doi' );
  −
end
  −
return text .. inactive .. cat
   
end
 
end
   −
-- Formats an OpenLibrary link, and checks for associated errors.
  −
local function openlibrary(id)
  −
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
  −
local handler = cfg.id_handlers['OL'];
  −
  −
if ( code == "A" ) then
  −
return external_link_id({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 external_link_id({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 external_link_id({link=handler.link, label=handler.label,
  −
prefix= "http://openlibrary.org/works/OL",id=id, separator=handler.separator,
  −
encode = handler.encode})
  −
else
  −
return external_link_id({link=handler.link, label=handler.label,
  −
prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator,
  −
encode = handler.encode}) ..
  −
' ' .. set_error( 'bad_ol' );
  −
end
  −
end
      +
--[[--------------------------< I S _ S U F F I X >-----------------------------
   −
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
+
returns true if suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
−
 
+
Puncutation not allowed.
−
Validate and format a usenet message id.  Simple error checking, looks for 'id-left@id-right' not enclosed in
  −
'<' and/or '>' angle brackets.
      
]]
 
]]
   −
local function message_id (id)
+
local function is_suffix (suffix)
−
local handler = cfg.id_handlers['USENETID'];
+
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
−
 
+
return true;
−
text = external_link_id({link = handler.link, label = handler.label,
+
end
−
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
+
return false;
−
  −
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
  −
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
  −
end  
  −
  −
return text
   
end
 
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.
+
--[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
−
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
     −
]]
+
For Vancouver style, author/editor names are supposed to be rendered in Latin
 +
(read ASCII) characters.  When a name uses characters that contain diacritical
 +
marks, those characters are to be converted to the corresponding Latin
 +
character. When a name is written using a non-Latin alphabet or logogram, that
 +
name is to be transliterated into Latin characters. The module doesn't do this
 +
so editors may/must.
   −
local function set_titletype (cite_class, title_type)
+
This test allows |first= and |last= names to contain any of the letters defined
−
if is_set(title_type) then
+
in the four Unicode Latin character sets
−
if "none" == title_type then
+
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
−
title_type = ""; -- if |type=none then type parameter not displayed
+
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
−
end
+
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
−
return title_type; -- if |type= has been set to any other value use that value
+
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
−
end
     −
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
+
|lastn= also allowed to contain hyphens, spaces, and apostrophes.
−
end
+
(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
 +
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
   −
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
+
This original test:
 +
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$")
 +
or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
 +
was written outside of the code editor and pasted here because the code editor
 +
gets confused between character insertion point and cursor position. The test has
 +
been rewritten to use decimal character escape sequence for the individual bytes
 +
of the Unicode characters so that it is not necessary to use an external editor
 +
to maintain this code.
   −
Removes irrelevant text and dashes from ISBN number
+
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
−
Similar to that used for Special:BookSources
+
\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 clean_isbn( isbn_str )
+
local function is_good_vanc_name (last, first, suffix, position)
−
return isbn_str:gsub( "[^-0-9X]", "" );
+
if not suffix then
 +
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
 +
first = first:match ('(.-)[,%s]+'); -- get name/initials
 +
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
 +
end
 +
end
 +
if utilities.is_set (suffix) then
 +
if not is_suffix (suffix) then
 +
add_vanc_error (cfg.err_msg_supl.suffix, position);
 +
return false; -- not a name with an appropriate suffix
 +
end
 +
end
 +
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
 +
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
 +
add_vanc_error (cfg.err_msg_supl['non-Latin char'], position);
 +
return false; -- not a string of Latin characters; Vancouver requires Romanization
 +
end;
 +
return true;
 
end
 
end
   −
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
     −
Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
+
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
−
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
+
 
−
]]
+
Attempts to convert names to initials in support of |name-list-style=vanc.   
−
local function escape_lua_magic_chars (argument)
+
 
−
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
+
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period.
−
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
+
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
−
return argument;
  −
end
     −
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
+
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.
   −
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
+
This function uses ustring functions because firstname initials may be any of the
−
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
+
Unicode Latin characters accepted by is_good_vanc_name ().
−
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.
      
]]
 
]]
   −
local function strip_apostrophe_markup (argument)
+
local function reduce_to_initials(first, position)
−
if not is_set (argument) then return argument; end
+
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
   −
while true do
+
if not name then -- if not initials and a suffix
−
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
+
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
−
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
  −
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
  −
argument=argument:gsub("%'%'%'%'", "");
  −
elseif argument:match ("%'%'%'") then -- bold (3)
  −
argument=argument:gsub("%'%'%'", "");
  −
elseif argument:match ("%'%'") then -- italic (2)
  −
argument=argument:gsub("%'%'", "");
  −
else
  −
break;
  −
end
   
end
 
end
−
return argument; -- done
  −
end
     −
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
+
if name then -- if first is initials with or without suffix
−
 
+
if 3 > mw.ustring.len (name) then -- if one or two initials
−
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
+
if suffix then -- if there is a suffix
−
 
+
if is_suffix (suffix) then -- is it legitimate?
−
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
+
return first; -- one or two initials and a valid suffix so nothing to do
−
of %27%27...
+
else
−
]]
+
add_vanc_error (cfg.err_msg_supl.suffix, position); -- one or two initials with invalid suffix so error message
 +
return first; -- and return first unmolested
 +
end
 +
else
 +
return first; -- one or two initials without suffix; nothing to do
 +
end
 +
end
 +
end -- if here then name has 3 or more uppercase letters so treat them as a word
 +
 
 +
local initials, names = {}, {}; -- tables to hold name parts and initials
 +
local i = 1; -- counter for number of initials
 +
 
 +
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
   −
local function make_coins_title (title, script)
+
while names[i] do -- loop through the table
−
if is_set (title) then
+
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
−
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
+
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
−
else
+
if is_suffix (names[i]) then -- if a legitimate suffix
−
title=''; -- if not set, make sure title is an empty string
+
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
 +
break; -- and done because suffix must fall at the end of a name
 +
end -- no error message if not a suffix; possibly because of Romanization
 +
end
 +
if 3 > i then
 +
table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table
 +
end
 +
i = i + 1; -- bump the counter
 
end
 
end
−
if is_set (script) then
+
−
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
+
return table.concat(initials) -- Vancouver format does not include spaces.
−
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
  −
else
  −
script=''; -- if not set, make sure script is an empty string
  −
end
  −
if is_set (title) and is_set (script) then
  −
script = ' ' .. script; -- add a space before we concatenate
  −
end
  −
return title .. script; -- return the concatenation
   
end
 
end
   −
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
     −
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
+
--[[--------------------------< I N T E R W I K I _ P R E F I X E N _ G E T >----------------------------------
 +
 
 +
extract interwiki prefixen from <value>.  Returns two one or two values:
 +
false – no prefixen
 +
nil – prefix exists but not recognized
 +
project prefix, language prefix – when value has either of:
 +
:<project>:<language>:<article>
 +
:<language>:<project>:<article>
 +
project prefix, nil – when <value> has only a known single-letter prefix
 +
nil, language prefix – when <value> has only a known language prefix
 +
 
 +
accepts single-letter project prefixen: 'd' (wikidata), 's' (wikisource), and 'w' (wikipedia) prefixes; at this
 +
writing, the other single-letter prefixen (b (wikibook), c (commons), m (meta), n (wikinews), q (wikiquote), and
 +
v (wikiversity)) are not supported.
    
]]
 
]]
   −
local function get_coins_pages (pages)
+
local function interwiki_prefixen_get (value, is_link)
−
local pattern;
+
if not value:find (':%l+:') then -- if no prefix
−
if not is_set (pages) then return pages; end -- if no page numbers then we're done
+
return false; -- abandon; boolean here to distinguish from nil fail returns later
 +
end
 +
 
 +
local prefix_patterns_linked_t = { -- sequence of valid interwiki and inter project prefixen
 +
'^%[%[:([dsw]):(%l%l+):', -- wikilinked; project and language prefixes
 +
'^%[%[:(%l%l+):([dsw]):', -- wikilinked; language and project prefixes
 +
'^%[%[:([dsw]):', -- wikilinked; project prefix
 +
'^%[%[:(%l%l+):', -- wikilinked; language prefix
 +
}
 +
 +
local prefix_patterns_unlinked_t = { -- sequence of valid interwiki and inter project prefixen
 +
'^:([dsw]):(%l%l+):', -- project and language prefixes
 +
'^:(%l%l+):([dsw]):', -- language and project prefixes
 +
'^:([dsw]):', -- project prefix
 +
'^:(%l%l+):', -- language prefix
 +
}
 +
 +
local cap1, cap2;
 +
for _, pattern in ipairs ((is_link and prefix_patterns_linked_t) or prefix_patterns_unlinked_t) do
 +
cap1, cap2 = value:match (pattern);
 +
if cap1 then
 +
break; -- found a match so stop looking
 +
end
 +
end
 
 
−
while true do
+
if cap1 and cap2 then -- when both then :project:language: or :language:project: (both forms allowed)
−
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
+
if 1 == #cap1 then -- length == 1 then :project:language:
−
if nil == pattern then break; end -- no more urls
+
if cfg.inter_wiki_map[cap2] then -- is language prefix in the interwiki map?
−
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
+
return cap1, cap2; -- return interwiki project and interwiki language
−
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
+
end
 +
else -- here when :language:project:
 +
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map?
 +
return cap2, cap1; -- return interwiki project and interwiki language
 +
end
 +
end
 +
return nil; -- unknown interwiki language
 +
elseif not (cap1 or cap2) then -- both are nil?
 +
return nil; -- we got something that looks like a project prefix but isn't; return fail
 +
elseif 1 == #cap1 then -- here when one capture
 +
return cap1, nil; -- length is 1 so return project, nil language
 +
else -- here when one capture and its length it more than 1
 +
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map?
 +
return nil, cap1; -- return nil project, language
 +
end
 
end
 
end
−
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
  −
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
  −
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like?
  −
return pages;
   
end
 
end
   −
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
  −
local function remove_wiki_link( str )
  −
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
  −
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
  −
end));
  −
end
     −
-- Converts a hyphen to a dash
+
--[[--------------------------< L I S T _ P E O P L E >--------------------------
−
local function hyphen_to_dash( str )
+
 
−
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
+
Formats a list of people (authors, contributors, editors, interviewers, translators)  
−
return str;
  −
end
  −
return str:gsub( '-', '–' );
  −
end
     −
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
+
names in the list will be linked when
 +
|<name>-link= has a value
 +
|<name>-mask- does NOT have a value; masked names are presumed to have been
 +
rendered previously so should have been linked there
   −
Joins a sequence of strings together while checking for duplicate separation characters.
+
when |<name>-mask=0, the associated name is not rendered
    
]]
 
]]
   −
local function safe_join( tbl, duplicate_char )
+
local function list_people (control, people, etal)
−
--[[
+
local sep;
−
Note: we use string functions here, rather than ustring functions.
+
local namesep;
 +
local format = control.format;
 +
local maximum = control.maximum;
 +
local name_list = {};
 +
 
 +
if 'vanc' == format then -- Vancouver-like name styling?
 +
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
 +
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
 +
else
 +
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
 +
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
 +
end
 
 
−
This has considerably faster performance and should work correctly as
+
if sep:sub (-1, -1) ~= " " then sep = sep .. " " end
−
long as the duplicate_char is strict ASCII. The strings
+
if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names
−
in tbl may be ASCII or UTF8.
  −
]]
   
 
−
local str = ''; -- the output string
+
for i, person in ipairs (people) do
−
local comp = ''; -- what does 'comp' mean?
+
if utilities.is_set (person.last) then
−
local end_chr = '';
+
local mask = person.mask;
−
local trim;
+
local one;
−
for _, value in ipairs( tbl ) do
+
local sep_one = sep;
−
if value == nil then value = ''; end
+
 
−
+
if utilities.is_set (maximum) and i > maximum then
−
if str == '' then -- if output string is empty
+
etal = true;
−
str = value; -- assign value to it (first time through the loop)
+
break;
−
elseif value ~= '' then
  −
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
  −
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
  −
else
  −
comp = value;
   
end
 
end
−
-- typically duplicate_char is sepc
+
−
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
+
if mask then
−
--  Because individual string segments often (always?) begin with terminal punct for th
+
local n = tonumber (mask); -- convert to a number if it can be converted; nil else
−
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
+
if n then
−
trim = false;
+
one = 0 ~= n and string.rep("&mdash;", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name
−
end_chr = str:sub(-1,-1); -- get the last character of the output string
+
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
−
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
+
else
−
if end_chr == duplicate_char then -- if same as separator
+
one = mask; -- replace name with mask text (must include name-list separator)
−
str = str:sub(1,-2); -- remove it
+
sep_one = " "; -- modify name-list separator
−
elseif end_chr == "'" then -- if it might be wikimarkup
  −
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
  −
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
  −
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
  −
trim = true; -- why? why do this and next differently from previous?
  −
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
  −
trim = true; -- same question
  −
end
  −
elseif end_chr == "]" then -- if it might be wikimarkup
  −
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
  −
trim = true;
  −
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
  −
trim = true;
  −
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
  −
trim = true;
  −
end
  −
elseif end_chr == " " then -- if last char of output string is a space
  −
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
  −
str = str:sub(1,-3); -- remove them both
  −
end
   
end
 
end
−
 
+
else
−
if trim then
+
one = person.last; -- get surname
−
if value ~= comp then -- value does not equal comp when value contains html markup
+
local first = person.first -- get given name
−
local dup2 = duplicate_char;
+
if utilities.is_set (first) then
−
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
+
if ("vanc" == format) then -- if Vancouver format
−
+
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
−
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
+
if not person.corporate and is_good_vanc_name (one, first, nil, i) then -- and name is all Latin characters; corporate authors not tested
−
else
+
first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials
−
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
+
end
 
end
 
end
 +
one = one .. namesep .. first;
 
end
 
end
 
end
 
end
−
str = str .. value; --add it to the output string
+
if utilities.is_set (person.link) then
−
end
+
one = utilities.make_wikilink (person.link, one); -- link author/editor
−
end
+
end
−
return str;
  −
end
     −
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
+
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
 +
local proj, tag = interwiki_prefixen_get (one, true); -- get the interwiki prefixen if present
   −
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
+
if 'w' == proj and ('Wikipedia' == mw.site.namespaces.Project['name']) then
−
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
+
proj = nil; -- for stuff like :w:de:<article>, :w is unnecessary TODO: maint cat?
−
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
+
end
−
These things are not currently possible in this module so are left to the editor to do.
+
if proj then
−
 
+
proj = ({['d'] = 'Wikidata', ['s'] = 'Wikisource', ['w'] = 'Wikipedia'})[proj]; -- :w (wikipedia) for linking from a non-wikipedia project
−
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
+
if proj then
−
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
+
one = one .. utilities.wrap_style ('interproj', proj); -- add resized leading space, brackets, static text, language name
−
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
+
tag = nil; -- unset; don't do both project and language
−
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
+
end
−
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
+
end
 +
if tag == cfg.this_wiki_code then
 +
tag = nil; -- stuff like :en:<article> at en.wiki is pointless TODO: maint cat?
 +
end
 +
if tag then
 +
local lang = cfg.lang_tag_remap[tag] or cfg.mw_languages_by_tag_t[tag];
 +
if lang then -- error messaging done in extract_names() where we know parameter names
 +
one = one .. utilities.wrap_style ('interwiki', lang); -- add resized leading space, brackets, static text, language name
 +
end
 +
end
   −
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
+
table.insert (name_list, one); -- add it to the list of names
−
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
+
table.insert (name_list, sep_one); -- add the proper name-list separator
 +
end
 +
end
 +
end
   −
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and past it here
+
local count = #name_list / 2; -- (number of names + number of separators) divided by 2
−
because the code editor gets confused between character insertion point and cursor position.
+
if 0 < count then
 +
if 1 < count and not etal then
 +
if 'amp' == format then
 +
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
 +
elseif 'and' == format then
 +
if 2 == count then
 +
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
 +
else
 +
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
 +
end
 +
end
 +
end
 +
name_list[#name_list] = nil; -- erase the last separator
 +
end
   −
]]
+
local result = table.concat (name_list); -- construct list
−
 
+
if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
−
local function is_good_vanc_name (last, first)
+
result = result .. sep .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al.
−
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
+
end
−
if true ~= Page_in_vanc_error_cat then -- if we haven't been here before then set a sticky flag
+
−
Page_in_vanc_error_cat=true; -- so that if there are more than one error the category is added only once
+
return result, count; -- return name-list string and count of number of names (count used for editor names only)
−
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
  −
end
  −
return false; -- not a string of latin characters; Vancouver required Romanization
  −
end;
  −
return true;
   
end
 
end
   −
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
     −
Attempts to convert names to initials in support of |name-list-format=vanc. 
+
--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------
   −
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/.
+
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise
 +
returns an empty string.
   −
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
+
namelist is one of the contributor-, author-, or editor-name lists chosen in that
−
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
+
order.  year is Year or anchor_year.
−
 
  −
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
      
]]
 
]]
   −
local function reduce_to_initials(first)
+
local function make_citeref_id (namelist, year)
−
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
+
local names={}; -- a table for the one to four names and year
−
local initials = {}
+
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
−
local i = 0; -- counter for number of initials
+
names[i] = v.last
−
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
+
if i == 4 then break end -- if four then done
−
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
+
end
−
i = i + 1; -- bump the counter
+
table.insert (names, year); -- add the year at the end
−
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
+
local id = table.concat(names); -- concatenate names and year for CITEREF id
 +
if utilities.is_set (id) then -- if concatenation is not an empty string
 +
return "CITEREF" .. id; -- add the CITEREF portion
 +
else
 +
return ''; -- return an empty string; no reason to include CITEREF id in this citation
 
end
 
end
−
return table.concat(initials) -- Vancouver format does not include spaces.
   
end
 
end
   −
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
     −
Formats a list of people (e.g. authors / editors)
+
--[[--------------------------< C I T E _ C L A S S _A T T R I B U T E _M A K E >------------------------------
 +
 
 +
construct <cite> tag class attribute for this citation.
 +
 
 +
<cite_class> – config.CitationClass from calling template
 +
<mode> – value from |mode= parameter
    
]]
 
]]
   −
local function list_people(control, people, etal)
+
local function cite_class_attribute_make (cite_class, mode)
−
local sep;
+
local class_t = {};
−
local namesep;
+
table.insert (class_t, 'citation'); -- required for blue highlight
−
local format = control.format
+
if 'citation' ~= cite_class then
−
local maximum = control.maximum
+
table.insert (class_t, cite_class); -- identify this template for user css
−
local lastauthoramp = control.lastauthoramp;
+
table.insert (class_t, utilities.is_set (mode) and mode or 'cs1'); -- identify the citation style for user css or javascript
−
local text = {}
  −
 
  −
if 'vanc' == format then -- Vancouver-like author/editor name styling?
  −
sep = ','; -- name-list separator between authors is a comma
  −
namesep = ' '; -- last/first separator is a space
   
else
 
else
−
sep = ';' -- name-list separator between authors is a semicolon
+
table.insert (class_t, utilities.is_set (mode) and mode or 'cs2'); -- identify the citation style for user css or javascript
−
namesep = ', ' -- last/first separator is <comma><space>
   
end
 
end
−
+
for _, prop_key in ipairs (z.prop_keys_t) do
−
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
+
table.insert (class_t, prop_key); -- identify various properties for user css or javascript
−
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 is_good_vanc_name (one, first) then -- and name is all Latin characters
  −
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
  −
end
  −
end
  −
one = one .. namesep .. first
  −
end
  −
if is_set(person.link) and person.link ~= control.page_name then
  −
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
  −
end
  −
 
  −
if is_set(person.link) and ((nil ~= person.link:find("//")) or (nil ~= person.link:find("[%[%]]"))) then
  −
one = one .. " " .. set_error( 'bad_authorlink' ) end -- url or wikilink in author link;
  −
end
  −
table.insert( text, one )
  −
table.insert( text, sep_one )
  −
end
   
end
 
end
   −
local count = #text / 2;
+
return table.concat (class_t, ' '); -- make a big string and done
−
if count > 0 then
  −
if count > 1 and is_set(lastauthoramp) and not etal then
  −
text[#text-2] = " & ";
  −
end
  −
text[#text] = nil;
  −
end
  −
  −
local result = table.concat(text) -- construct list
  −
if etal then
  −
local etal_text = cfg.messages['et al'];
  −
result = result .. " " .. etal_text;
  −
end
  −
  −
return result, count
   
end
 
end
   −
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
     −
Generates a CITEREF anchor ID if we have at least one name or a date.  Otherwise returns an empty string.
+
--[[---------------------< N A M E _ H A S _ E T A L >--------------------------
 +
 
 +
Evaluates the content of name parameters (author, editor, etc.) for variations on
 +
the theme of et al.  If found, the et al. is removed, a flag is set to true and
 +
the function returns the modified name and the flag.
 +
 
 +
This function never sets the flag to false but returns its previous state because
 +
it may have been set by previous passes through this function or by the associated
 +
|display-<names>=etal parameter
    
]]
 
]]
   −
local function anchor_id( options )
+
local function name_has_etal (name, etal, nocat, param)
−
local id = table.concat( options ); -- concatenate names and year for CITEREF id
+
 
−
if is_set (id) then -- if concatenation is not an empty string
+
if utilities.is_set (name) then -- name can be nil in which case just return
−
return "CITEREF" .. id; -- add the CITEREF portion
+
local patterns = cfg.et_al_patterns; -- get patterns from configuration
−
else
+
−
return ''; -- return an empty string; no reason to include CITEREF id in this citation
+
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
 +
if name:match (pattern) then -- if this 'et al' pattern is found in name
 +
name = name:gsub (pattern, ''); -- remove the offending text
 +
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
 +
if not nocat then -- no categorization for |vauthors=
 +
utilities.set_message ('err_etal', {param}); -- and set an error if not added
 +
end
 +
end
 +
end
 
end
 
end
 +
 +
return name, etal;
 
end
 
end
   −
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
  −
Gets name list from the input arguments
     −
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
+
--[[---------------------< N A M E _ I S _ N U M E R I C >----------------------
−
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.
+
Add an error message and category when <name> parameter value does not contain letters.
 +
 
 +
Add a maintenance category when <name> parameter value has numeric characters mixed with characters that are  
 +
not numeric characters; could be letters and/or punctuation characters.
   −
This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
+
This function will only emit one error and one maint message for the current template.  Does not emit both error
−
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
+
and maint messages/categories for the same parameter value.
   −
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
+
returns nothing
−
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 function name_is_numeric (name, name_alias, list_name)
−
local names = {}; -- table of names
+
local patterns = {
−
local last; -- individual name components
+
'^%D+%d', -- <name> must have digits preceded by other characters
−
local first;
+
'^%D*%d+%D+', -- <name> must have digits followed by other characters
−
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 pattern = ",? *'*[Ee][Tt] *[Aa][Ll][%.']*$" -- variations on the 'et al' theme
  −
  −
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
     −
while true do
+
if not added_numeric_name_errs and mw.ustring.match (name, '^[%A]+$') then -- if we have not already set an error message and <name> does not have any alpha characters
−
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
+
utilities.set_message ('err_numeric_names', name_alias); -- add an error message
−
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
+
added_numeric_name_errs = true; -- set the flag so we emit only one error message
−
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
+
return; -- when here no point in further testing; abandon
−
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
+
end
   −
local name = tostring(last);
+
if not added_numeric_name_maint then -- if we have already set a maint message
−
if name:match (pattern) then -- varients on et al.
+
for _, pattern in ipairs (patterns) do -- spin through list of patterns
−
last = name:gsub (pattern, ''); -- if found, remove
+
if mw.ustring.match (name, pattern) then -- digits preceded or followed by anything but digits; %D+ includes punctuation
−
etal = true;
+
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
−
end
+
added_numeric_name_maint = true; -- set the flag so we emit only one maint message
−
name = tostring(first);
+
return; -- when here no point in further testing; abandon
−
if name:match (pattern) then -- varients on et al.
+
end
−
first = name:gsub (pattern, ''); -- if found, remove
  −
etal = true;
   
end
 
end
 +
end
 +
end
 +
 +
 +
--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
 +
 +
Evaluates the content of last/surname (authors etc.) parameters for multiple names.
 +
Multiple names are indicated if there is more than one comma or any "unescaped"
 +
semicolons. Escaped semicolons are ones used as part of selected HTML entities.
 +
If the condition is met, the function adds the multiple name maintenance category.
   −
if first and not last then -- if there is a firstn without a matching lastn
+
Same test for first except that commas should not appear in given names (MOS:JR says
−
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
+
that the generational suffix does not take a separator character).  Titles, degrees,
−
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
+
postnominals, affiliations, all normally comma separated don't belong in a citation.
−
count = count + 1; -- number of times we haven't found last and first
+
 
−
if 2 == count then -- two missing names and we give up
+
<name> – name parameter value
−
break; -- normal exit or there is a two-name hole in the list; can't tell which
+
<list_name> – AuthorList, EditorList, etc
−
end
+
<limit> – number of allowed commas; 1 (default) for surnames; 0 for given names
−
else -- we have last with or without a first
+
 
−
names[n] = {last = last, first = first, link = link, mask = mask}; -- add this name to our names list
+
returns nothing
−
n = n + 1; -- point to next location in the names table
+
 
−
if 1 == count then -- if the previous name was missing
+
]]
−
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
+
 
−
end
+
local function name_has_mult_names (name, list_name, limit)
−
count = 0; -- reset the counter, we're looking for two consecutive missing names
+
local _, commas, semicolons, nbsps;
 +
limit = limit and limit or 1;
 +
if utilities.is_set (name) then
 +
_, commas = name:gsub (',', ''); -- count the number of commas
 +
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
 +
-- nbsps probably should be its own separate count rather than merged in
 +
-- some way with semicolons because Lua patterns do not support the
 +
-- grouping operator that regex does, which means there is no way to add
 +
-- more entities to escape except by adding more counts with the new
 +
-- entities
 +
_, nbsps = name:gsub ('&nbsp;',''); -- count nbsps
 +
 +
-- There is exactly 1 semicolon per &nbsp; entity, so subtract nbsps
 +
-- from semicolons to 'escape' them. If additional entities are added,
 +
-- they also can be subtracted.
 +
if limit < commas or 0 < (semicolons - nbsps) then
 +
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
 
end
 
end
−
i = i + 1; -- point to next args location
  −
end
  −
  −
if true == etal then
  −
add_maint_cat ('etal');
   
end
 
end
−
return names, etal; -- all done, return our list of names
   
end
 
end
   −
-- Populates ID table from arguments using configuration settings
  −
local function extract_ids( args )
  −
local id_list = {};
  −
for k, v in pairs( cfg.id_handlers ) do
  −
v = select_one( args, v.parameters, 'redundant_parameters' );
  −
if is_set(v) then id_list[k] = v; end
  −
end
  −
return id_list;
  −
end
     −
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
+
--[=[-------------------------< I S _ G E N E R I C >----------------------------------------------------------
 +
 
 +
Compares values assigned to various parameters according to the string provided as <item> in the function call.
 +
<item> can have on of two values:
 +
'generic_names' – for name-holding parameters: |last=, |first=, |editor-last=, etc
 +
'generic_titles' – for |title=
 +
 
 +
There are two types of generic tests.  The 'accept' tests look for a pattern that should not be rejected by the
 +
'reject' test.  For example,
 +
|author=[[John Smith (author)|Smith, John]]
 +
would be rejected by the 'author' reject test.  But piped wikilinks with 'author' disambiguation should not be
 +
rejected so the 'accept' test prevents that from happening.  Accept tests are always performed before reject
 +
tests.
 +
 
 +
Each of the 'accept' and 'reject' sequence tables hold tables for en.wiki (['en']) and local.wiki (['local'])
 +
that each can hold a test sequence table  The sequence table holds, at index [1], a test pattern, and, at index
 +
[2], a boolean control value.  The control value tells string.find() or mw.ustring.find() to do plain-text search (true)
 +
or a pattern search (false).  The intent of all this complexity is to make these searches as fast as possible so
 +
that we don't run out of processing time on very large articles.
   −
Takes a table of IDs and turns it into a table of formatted ID outputs.
+
Returns
 +
true when a reject test finds the pattern or string
 +
false when an accept test finds the pattern or string
 +
nil else
   −
]]
+
]=]
   −
local function build_id_list( id_list, options )
+
local function is_generic (item, value, wiki)
−
local new_list, handler = {};
+
local test_val;
 +
local str_lower = { -- use string.lower() for en.wiki (['en']) and use mw.ustring.lower() or local.wiki (['local'])
 +
['en'] = string.lower,
 +
['local'] = mw.ustring.lower,
 +
}
 +
local str_find = { -- use string.find() for en.wiki (['en']) and use mw.ustring.find() or local.wiki (['local'])
 +
['en'] = string.find,
 +
['local'] = mw.ustring.find,
 +
}
   −
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
+
local function test (val, test_t, wiki) -- local function to do the testing; <wiki> selects lower() and find() functions
−
+
val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value
−
for k, v in pairs( id_list ) do
+
return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched
−
-- fallback to read-only cfg
+
end
−
handler = setmetatable( { ['id'] = v }, fallback(k) );
   
 
−
if handler.mode == 'external' then
+
local test_types_t = {'accept', 'reject'}; -- test accept patterns first, then reject patterns
−
table.insert( new_list, {handler.label, external_link_id( handler ) } );
+
local wikis_t = {'en', 'local'}; -- do tests for each of these keys; en.wiki first, local.wiki second
−
elseif handler.mode == 'internal' then
+
 
−
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
+
for _, test_type in ipairs (test_types_t) do -- for each test type
−
elseif handler.mode ~= 'manual' then
+
for _, generic_value in pairs (cfg.special_case_translation[item][test_type]) do -- spin through the list of generic value fragments to accept or reject
−
error( cfg.messages['unknown_ID_mode'] );
+
for _, wiki in ipairs (wikis_t) do
−
elseif k == 'DOI' then
+
if generic_value[wiki] then
−
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
+
if test (value, generic_value[wiki], wiki) then -- go do the test
−
elseif k == 'ARXIV' then
+
return ('reject' == test_type); -- param value rejected, return true; false else
−
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );  
+
end
−
elseif k == 'ASIN' then
+
end
−
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );  
+
end
−
elseif k == 'LCCN' then
  −
table.insert( new_list, {handler.label, lccn( v ) } );
  −
elseif k == 'OL' then
  −
table.insert( new_list, {handler.label, openlibrary( v ) } );
  −
elseif k == 'PMC' then
  −
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
  −
elseif k == 'PMID' then
  −
table.insert( new_list, {handler.label, pmid( v ) } );
  −
elseif k == 'ISSN' then
  −
table.insert( new_list, {handler.label, issn( v ) } );
  −
elseif k == 'ISBN' then
  −
local ISBN = internal_link_id( handler );
  −
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
  −
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
  −
end
  −
table.insert( new_list, {handler.label, ISBN } );
  −
elseif k == 'USENETID' then
  −
table.insert( new_list, {handler.label, message_id( v ) } );
  −
else
  −
error( cfg.messages['unknown_manual_ID'] );
   
end
 
end
 
end
 
end
−
+
end
−
function comp( a, b ) -- used in following table.sort()
+
 
−
return a[1] < b[1];
+
 
−
end
+
--[[--------------------------< N A M E _ I S _ G E N E R I C >------------------------------------------------
−
+
 
−
table.sort( new_list, comp );
+
calls is_generic() to determine if <name> is a 'generic name' listed in cfg.generic_names; <name_alias> is the
−
for k, v in ipairs( new_list ) do
+
parameter name used in error messaging
−
new_list[k] = v[2];
+
 
 +
]]
 +
 
 +
local function name_is_generic (name, name_alias)
 +
if not added_generic_name_errs  and is_generic ('generic_names', name) then
 +
utilities.set_message ('err_generic_name', name_alias); -- set an error message
 +
added_generic_name_errs = true;
 
end
 
end
−
  −
return new_list;
   
end
 
end
−
 
     −
-- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse
+
 
−
-- the citation information.
+
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
−
local function COinS(data, class)
+
 
−
if 'table' ~= type(data) or nil == next(data) then
+
This function calls various name checking functions used to validate the content of the various name-holding parameters.
−
return '';
+
 
 +
]]
 +
 
 +
local function name_checks (last, first, list_name, last_alias, first_alias)
 +
local accept_name;
 +
 
 +
if utilities.is_set (last) then
 +
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
 +
 
 +
if not accept_name then -- <last> not wrapped in accept-as-written markup
 +
name_has_mult_names (last, list_name); -- check for multiple names in the parameter
 +
name_is_numeric (last, last_alias, list_name); -- check for names that have no letters or are a mix of digits and other characters
 +
name_is_generic (last, last_alias); -- check for names found in the generic names list
 +
end
 
end
 
end
−
+
 
−
local ctx_ver = "Z39.88-2004";
+
if utilities.is_set (first) then
−
+
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
−
-- treat table strictly as an array with only set values.
+
 
−
local OCinSoutput = setmetatable( {}, {
+
if not accept_name then -- <first> not wrapped in accept-as-written markup
−
__newindex = function(self, key, value)
+
name_has_mult_names (first, list_name, 0); -- check for multiple names in the parameter; 0 is number of allowed commas in a given name
−
if is_set(value) then
+
name_is_numeric (first, first_alias, list_name); -- check for names that have no letters or are a mix of digits and other characters
−
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
+
name_is_generic (first, first_alias); -- check for names found in the generic names list
−
end
   
end
 
end
−
});
+
local wl_type, D = utilities.is_wikilink (first);
−
+
if 0 ~= wl_type then
−
if is_set(data.Chapter) then
+
first = D;
−
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
+
utilities.set_message ('err_bad_paramlink', first_alias);
−
OCinSoutput["rft.genre"] = "bookitem";
  −
OCinSoutput["rft.atitle"] = data.Chapter;
  −
OCinSoutput["rft.btitle"] = data.Title;
  −
elseif is_set(data.Periodical) then
  −
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
  −
if 'arxiv' == class then
  −
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
  −
else
  −
OCinSoutput["rft.genre"] = "article";
   
end
 
end
−
OCinSoutput["rft.jtitle"] = data.Periodical;
  −
OCinSoutput["rft.atitle"] = data.Title;
  −
else
  −
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
  −
OCinSoutput["rft.genre"] = "book"
  −
OCinSoutput["rft.btitle"] = data.Title;
   
end
 
end
−
+
 
−
OCinSoutput["rft.place"] = data.PublicationPlace;
+
return last, first; -- done
−
OCinSoutput["rft.date"] = data.Date;
  −
OCinSoutput["rft.series"] = data.Series;
  −
OCinSoutput["rft.volume"] = data.Volume;
  −
OCinSoutput["rft.issue"] = data.Issue;
  −
OCinSoutput["rft.pages"] = data.Pages;
  −
OCinSoutput["rft.edition"] = data.Edition;
  −
OCinSoutput["rft.pub"] = data.PublisherName;
  −
  −
for k, v in pairs( data.ID_list ) do
  −
local id, value = cfg.id_handlers[k].COinS;
  −
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
  −
if string.sub( id or "", 1, 4 ) == 'info' then
  −
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
  −
else
  −
OCinSoutput[ id ] = value;
  −
end
  −
end
  −
  −
local last, first;
  −
for k, v in ipairs( data.Authors ) do
  −
last, first = v.last, v.first;
  −
if k == 1 then
  −
if is_set(last) then
  −
OCinSoutput["rft.aulast"] = last;
  −
end
  −
if is_set(first) then
  −
OCinSoutput["rft.aufirst"] = first;
  −
end
  −
end
  −
if is_set(last) and is_set(first) then
  −
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
  −
elseif is_set(last) then
  −
OCinSoutput["rft.au"] = last;
  −
end
  −
end
  −
  −
OCinSoutput.rft_id = data.URL;
  −
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
  −
OCinSoutput = setmetatable( OCinSoutput, nil );
  −
  −
-- sort with version string always first, and combine.
  −
table.sort( OCinSoutput );
  −
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
  −
return table.concat(OCinSoutput, "&");
   
end
 
end
      −
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
+
--[[----------------------< E X T R A C T _ N A M E S >-------------------------
   −
Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
+
Gets name list from the input arguments
−
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
     −
Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia
+
Searches through args in sequential order to find |lastn= and |firstn= parameters
−
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
+
(or their aliases), and their matching link and mask parameters. Stops searching
−
with the code.  When there is no match, we return the original language name string.
+
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.
   −
mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included
+
This function emits an error message when there is a |firstn= without a matching
−
in the list will be found if that name is provided in the |language= parameter.  For example, if |language=Samaritan Aramaic, that name will be
+
|lastn=. When there are 'holes' in the list of last names, |last1= and |last3=
−
found with the associated code 'sam', not an ISO639-1 code. When names are found and the associated code is not two characters, this function
+
are present but |last2= is missing, an error message is emitted. |lastn= is not
−
returns only the Wikimedia language name.
+
required to have a matching |firstn=.
   −
Adapted from code taken from Module:Check ISO 639-1.
+
When an author or editor parameter contains some form of 'et al.', the 'et al.'
 +
is stripped from the parameter and a flag (etal) returned that will cause list_people()
 +
to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps
 +
'et al.' out of the template's metadata.  When this occurs, an error is emitted.
    
]]
 
]]
   −
local function get_iso639_code (lang)
+
local function extract_names(args, list_name)
−
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
+
local names = {}; -- table of names
−
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
+
local last; -- individual name components
−
end
+
local first;
 +
local link;
 +
local mask;
 +
local i = 1; -- loop counter/indexer
 +
local n = 1; -- output table indexer
 +
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
 +
local etal = false; -- return value set to true when we find some form of et al. in an author parameter
 +
 
 +
local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging
 +
while true do
 +
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1
 +
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
 +
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
 +
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
 
 
−
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
+
if last then -- error check |lastn= alias for unknown interwiki link prefix; done here because this is where we have the parameter name
−
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
+
local project, language = interwiki_prefixen_get (last, true); -- true because we expect interwiki links in |lastn= to be wikilinked
−
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
+
if nil == project and nil == language then -- when both are nil
−
+
utilities.set_message ('err_bad_paramlink', last_alias); -- not known, emit an error message -- TODO: err_bad_interwiki?
−
for code, name in pairs(languages) do -- scan the list to see if we can find our language
+
last = utilities.remove_wiki_link (last); -- remove wikilink markup; show display value only
−
if langlc == mw.ustring.lower(name) then
+
end
−
if 2 ~= code:len() then -- ISO639-1 codes only
+
end
−
return name; -- so return the name but not the code
+
 +
if link then -- error check |linkn= alias for unknown interwiki link prefix
 +
local project, language = interwiki_prefixen_get (link, false); -- false because wiki links in |author-linkn= is an error
 +
if nil == project and nil == language then -- when both are nil
 +
utilities.set_message ('err_bad_paramlink', link_alias); -- not known, emit an error message -- TODO: err_bad_interwiki?
 +
link = nil; -- unset so we don't link
 +
link_alias = nil;
 +
end
 +
end
 +
 +
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, last_alias, first_alias); -- multiple names, extraneous annotation, etc. checks
 +
 
 +
if first and not last then -- if there is a firstn without a matching lastn
 +
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias
 +
utilities.set_message ('err_first_missing_last', {
 +
first_alias, -- param name of alias missing its mate
 +
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
 +
}); -- add this error message
 +
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
 +
count = count + 1; -- number of times we haven't found last and first
 +
if 2 <= count then -- two missing names and we give up
 +
break; -- normal exit or there is a two-name hole in the list; can't tell which
 +
end
 +
else -- we have last with or without a first
 +
local result;
 +
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
 +
 
 +
if first then
 +
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup
 +
end
 +
 
 +
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
 +
n = n + 1; -- point to next location in the names table
 +
if 1 == count then -- if the previous name was missing
 +
utilities.set_message ('err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}); -- add this error message
 
end
 
end
−
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
+
count = 0; -- reset the counter, we're looking for two consecutive missing names
 
end
 
end
 +
i = i + 1; -- point to next args location
 
end
 
end
−
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
+
 +
return names, etal; -- all done, return our list of names and the etal flag
 
end
 
end
   −
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
     −
Get language name from ISO639-1 code value provided.  If a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
+
--[[--------------------------< N A M E _ T A G _ G E T >------------------------------------------------------
   −
There is an exception.  There are three ISO639-1 codes for Norewegian language variants.  There are two official variants: Norwegian Bokmål (code 'nb') and
+
attempt to decode |language=<lang_param> and return language name and matching tag; nil else.
−
Norwegian Nynorsk (code 'nn').  The third, code 'no',  is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless.  However, it appears
  −
that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.
     −
Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and
+
This function looks for:
−
return 'Norwegian' when editors use |language=no.  We presume that editors don't know about the variants or can't descriminate between them.
+
<lang_param> as a tag in cfg.lang_tag_remap{}
 +
<lang_param> as a name in cfg.lang_name_remap{}
 +
 +
<lang_param> as a name in cfg.mw_languages_by_name_t
 +
<lang_param> as a tag in cfg.mw_languages_by_tag_t
 +
when those fail, presume that <lang_param> is an IETF-like tag that MediaWiki does not recognize.  Strip all
 +
script, region, variant, whatever subtags from <lang_param> to leave just a two or three character language tag
 +
and look for the new <lang_param> in cfg.mw_languages_by_tag_t{}
   −
See Help talk:Citation Style_1#An ISO 639-1 language name test
+
on success, returns name (in properly capitalized form) and matching tag (in lowercase); on failure returns nil
   −
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
+
]]
−
the page is a mainspace page and the ISO639-1 code is not 'en'.  Similarly, if the  parameter is |language=Norwegian, it will be categorized in the same way.
     −
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 name_tag_get (lang_param)
 +
local lang_param_lc = mw.ustring.lower (lang_param); -- use lowercase as an index into the various tables
 +
local name;
 +
local tag;
   −
]]
+
name = cfg.lang_tag_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name
 +
if name then -- when <name>, <lang_param> is a tag for a remapped language name
 +
if cfg.lang_name_remap[name:lower()][2] ~= lang_param_lc then
 +
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
 +
return name, cfg.lang_name_remap[name:lower()][2]; -- so return name and tag from lang_name_remap[name]; special case to xlate sr-ec and sr-el to sr-cyrl and sr-latn
 +
end
 +
return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc>
 +
end
   −
local function language_parameter (lang, namespace)
+
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags
−
local code; -- the ISO639-1 two character code
+
name = cfg.lang_tag_remap[tag]; -- attempt to get remapped language name with language subtag only
−
local name; -- the language name
+
if name then -- when <name>, <tag> is a tag for a remapped language name
−
local language_list = {}; -- table of language names to be rendered
+
return name, tag; -- so return <name> from remap and <tag>
−
local names_table = {}; -- table made from the value assigned to |language=
+
end
−
local unrec_cat = false -- flag so that we only add unrecognized category once
+
 
 +
if cfg.lang_name_remap[lang_param_lc] then -- not a remapped tag, assume <lang_param_lc> is a name; attempt to get remapped language tag
 +
return cfg.lang_name_remap[lang_param_lc][1], cfg.lang_name_remap[lang_param_lc][2]; -- for this <lang_param_lc>, return a (possibly) new name and appropriate tag
 +
end
 +
 
 +
name = cfg.mw_languages_by_tag_t[lang_param_lc]; -- assume that <lang_param_lc> is a tag; attempt to get its matching language name
 
 
−
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
+
if name then
 +
return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name>
 +
end
 
 
−
for _, lang in ipairs (names_table) do -- reuse lang
+
tag = cfg.mw_languages_by_name_t[lang_param_lc]; -- assume that <lang_param_lc> is a language name; attempt to get its matching tag
−
if 0 == namespace and (('en' == lang:lower()) or ('english' == lang:lower())) then
  −
add_maint_cat ('english');
  −
end
   
 
−
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
+
if tag then
−
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
+
return cfg.mw_languages_by_tag_t[tag], tag; -- <lang_param_lc> is a name so return the name from the table and <tag>
−
end
+
end
−
+
 
−
if is_set (name) then -- if Language specified a valid ISO639-1 code
+
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- is <lang_param_lc> an IETF-like tag that MediaWiki doesn't recognize? <tag> gets the language subtag; nil else
−
code = lang:lower(); -- save it
+
 
−
else
+
if tag then
−
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
+
name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag>
−
end
+
if name then
−
+
return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag
−
if is_set (code) then
  −
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
  −
if 0 == namespace and 'en' ~= code then -- is this page main / article space and English not the language?
  −
add_prop_cat ('foreign_lang_source', {name, code})
  −
end
  −
elseif false == unrec_cat then
  −
unrec_cat = true; -- only add this category once
  −
add_maint_cat (unknown_lang);
   
end
 
end
−
  −
table.insert (language_list, name);
  −
name = ''; -- so we can reuse it
  −
end
  −
  −
code = #language_list -- reuse code as number of languages in the list
  −
if 2 >= code then
  −
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
  −
elseif 2 < code then
  −
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
  −
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
   
end
 
end
−
return (" " .. wrap_msg ('language', name)); -- wrap with '(in ...)'
   
end
 
end
   −
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
     −
Set style settings for CS1 citation templates. Returns separator and postscript settings
+
--[[-------------------< 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.
   −
local function set_cs1_style (ps)
+
When |language= contains a recognized language (either code or name), the page is
−
if not is_set (ps) then -- unless explicitely set to something
+
assigned to the category for that code: Category:Norwegian-language sources (no).
−
ps = '.'; -- terminate the rendered citation with a period
+
For valid three-character code languages, the page is assigned to the single category
−
end
+
for '639-2' codes: Category:CS1 ISO 639-2 language sources.
−
return '.', ps; -- separator is a full stop
  −
end
     −
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
+
Languages that are the same as the local wiki are not categorized.  MediaWiki does
 +
not recognize three-character equivalents of two-character codes: code 'ar' is
 +
recognized but code 'ara' is not.
   −
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
+
This function supports multiple languages in the form |language=nb, French, th
 +
where the language names or codes are separated from each other by commas with
 +
optional space characters.
    
]]
 
]]
   −
local function set_cs2_style (ps, ref)
+
local function language_parameter (lang)
−
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
+
local tag; -- some form of IETF-like language tag; language subtag with optional region, sript, vatiant, etc subtags
−
ps = ''; -- make sure it isn't nil
+
local lang_subtag; -- ve populates |language= with mostly unecessary region subtags the MediaWiki does not recognize; this is the base language subtag
−
end
+
local name; -- the language name
−
if not is_set (ref) then -- if |ref= is not set
+
local language_list = {}; -- table of language names to be rendered
−
ref = "harv"; -- set default |ref=harv
+
local names_t = {}; -- table made from the value assigned to |language=
 +
 
 +
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
 +
 
 +
names_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
 +
 
 +
for _, lang in ipairs (names_t) do -- reuse lang here because we don't yet know if lang is a language name or a language tag
 +
name, tag = name_tag_get (lang); -- attempt to get name/tag pair for <lang>; <name> has proper capitalization; <tag> is lowercase
 +
 
 +
if utilities.is_set (tag) then
 +
lang_subtag = tag:gsub ('^(%a%a%a?)%-.*', '%1'); -- for categorization, strip any IETF-like tags from language tag
 +
 
 +
if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language
 +
if 2 == lang_subtag:len() then -- and is a two-character tag
 +
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
 +
else -- or is a recognized language (but has a three-character tag)
 +
utilities.add_prop_cat ('foreign-lang-source-2', {lang_subtag}, lang_subtag); -- categorize it differently TODO: support multiple three-character tag categories per cs1|2 template?
 +
end
 +
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled
 +
utilities.add_prop_cat ('local-lang-source', {name, lang_subtag}); -- categorize it
 +
end
 +
else
 +
name = lang; -- return whatever <lang> has so that we show something
 +
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
 +
end
 +
 +
table.insert (language_list, name);
 +
name = ''; -- so we can reuse it
 +
end
 +
 +
name = utilities.make_sep_list (#language_list, language_list);
 +
if (1 == #language_list) and (lang_subtag == cfg.this_wiki_code) then -- when only one language, find lang name in this wiki lang name; for |language=en-us, 'English' in 'American English'
 +
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
 
end
 
end
−
return ',', ps, ref; -- separator is a comma
+
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
 +
--[[ TODO: should only return blank or name rather than full list
 +
so we can clean up the bunched parenthetical elements Language, Type, Format
 +
]]
 
end
 
end
   −
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
     −
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
+
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
−
rendered style.
+
 
 +
Gets the default CS style configuration for the given mode.
 +
Returns default separator and either postscript as passed in or the default.
 +
In CS1, the default postscript and separator are '.'.
 +
In CS2, the default postscript is the empty string and the default separator is ','.
    
]]
 
]]
   −
local function get_settings_from_cite_class (ps, ref, cite_class)
+
local function set_cs_style (postscript, mode)
−
local sep;
+
if utilities.is_set(postscript) then
−
if (cite_class == "citation") then -- for citation templates (CS2)
+
-- emit a maintenance message if user postscript is the default cs1 postscript
−
sep, ps, ref = set_cs2_style (ps, ref);
+
-- we catch the opposite case for cs2 in set_style
−
else -- not a citation template so CS1
+
if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then
−
sep, ps = set_cs1_style (ps);
+
utilities.set_message ('maint_postscript');
 +
end
 +
else
 +
postscript = cfg.presentation['ps_' .. mode];
 
end
 
end
 +
return cfg.presentation['sep_' .. mode], postscript;
 +
end
   −
return sep, ps, ref -- return them all
  −
end
     −
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
+
--[[--------------------------< S E T _ S T Y L E >-----------------------------
   −
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
+
Sets the separator and postscript styles. Checks the |mode= first and the
−
config.CitationClass from the template's #invoke: to establish style.
+
#invoke CitationClass second. Removes the postscript if postscript == none.
    
]]
 
]]
   −
local function set_style (mode, ps, ref, cite_class)
+
local function set_style (mode, postscript, cite_class)
 
local sep;
 
local sep;
−
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
+
if 'cs2' == mode then
−
sep, ps, ref = set_cs2_style (ps, ref);
+
sep, postscript = set_cs_style (postscript, 'cs2');
−
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
+
elseif 'cs1' == mode then
−
sep, ps = set_cs1_style (ps);
+
sep, postscript = set_cs_style (postscript, 'cs1');
−
else -- anything but cs1 or cs2
+
elseif 'citation' == cite_class then
−
if is_set (mode) then
+
sep, postscript = set_cs_style (postscript, 'cs2');
−
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'mode', mode}, true ) } ); -- add error message
+
else
 +
sep, postscript = set_cs_style (postscript, 'cs1');
 +
end
 +
 
 +
if cfg.keywords_xlate[postscript:lower()] == 'none' then
 +
-- emit a maintenance message if user postscript is the default cs2 postscript
 +
-- we catch the opposite case for cs1 in set_cs_style
 +
if 'cs2' == mode or 'citation' == cite_class then
 +
utilities.set_message ('maint_postscript');
 
end
 
end
−
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
+
postscript = '';
−
end
  −
if 'none' == ps:lower() then -- if assigned value is 'none' then
  −
ps = ''; -- set to empty string
   
end
 
end
 
 
−
return sep, ps, ref
+
return sep, postscript
 
end
 
end
   −
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
     −
Determines if a url has the file extension is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
+
--[=[-------------------------< I S _ P D F >-----------------------------------
−
applying the pdf icon to external links.
     −
returns true if file extension is one of the recognized extension, else false
+
Determines if a URL has the file extension that is one of the PDF file extensions
 +
used by [[MediaWiki:Common.css]] when applying the PDF icon to external links.
 +
 
 +
returns true if file extension is one of the recognized extensions, else false
    
]=]
 
]=]
    
local function is_pdf (url)
 
local function is_pdf (url)
−
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
+
return url:match ('%.pdf$') or url:match ('%.PDF$') or
 +
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
 +
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
 
end
 
end
   −
--[[--------------------------< S 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
+
--[[--------------------------< S T Y L E _ F O R M A T >-----------------------
−
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
+
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.
 
the appropriate styling.
   Строка 1851: Строка 1884:     
local function style_format (format, url, fmt_param, url_param)
 
local function style_format (format, url, fmt_param, url_param)
−
if is_set (format) then
+
if utilities.is_set (format) then
−
format = wrap_style ('format', format:upper()); -- force upper case, add leading space, parenthases, resize
+
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
−
if not is_set (url) then
+
if not utilities.is_set (url) then
−
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
+
utilities.set_message ('err_format_missing_url', {fmt_param, url_param}); -- add an error message
 
end
 
end
−
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
+
elseif is_pdf (url) then -- format is not set so if URL is a PDF file then
−
format = wrap_style ('format', 'PDF'); -- set format to pdf
+
format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF
 
else
 
else
 
format = ''; -- empty string for concatenation
 
format = ''; -- empty string for concatenation
Строка 1864: Строка 1897:  
end
 
end
   −
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
     −
Returns a number that may or may not limit the length of the author or editor name lists.
+
--[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------
   −
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
+
Returns a number that defines the number of names displayed for author and editor
−
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
+
name lists and a Boolean flag to indicate when et al. should be appended to the name list.
−
some variant of the text 'et al.').
     −
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
+
When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
−
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
+
return the number and the previous state of the 'etal' flag (false by default
−
the names in the name list followed by 'et al.'
+
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.
 
In all other cases, returns nil and the previous state of the 'etal' flag.
 +
 +
inputs:
 +
max: A['DisplayAuthors'] or A['DisplayEditors'], etc; a number or some flavor of etal
 +
count: #a or #e
 +
list_name: 'authors' or 'editors'
 +
etal: author_etal or editor_etal
 +
 +
This function sets an error message when |display-xxxxors= value greater than or equal to number of names but
 +
not when <max> comes from {{cs1 config}} global settings.  When using global settings, <param> is set to the
 +
keyword 'cs1 config' which is used to supress the normal error.  Error is suppressed because it is to be expected
 +
that some citations in an article will have the same or fewer names that the limit specified in {{cs1 config}}.
    
]]
 
]]
   −
local function get_display_authors_editors (max, count, list_name, etal)
+
local function get_display_names (max, count, list_name, etal, param)
−
if is_set (max) then
+
if utilities.is_set (max) then
 
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
 
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.
 
max = count + 1; -- number of authors + 1 so display all author name plus et al.
Строка 1887: Строка 1933:  
elseif max:match ('^%d+$') then -- if is a string of numbers
 
elseif max:match ('^%d+$') then -- if is a string of numbers
 
max = tonumber (max); -- make it a number
 
max = tonumber (max); -- make it a number
−
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
+
if (max >= count) and ('cs1 config' ~= param) then -- error when local |display-xxxxors= value greater than or equal to number of names; not an error when using global setting
−
add_maint_cat ('disp_auth_ed', list_name);
+
utilities.set_message ('err_disp_name', {param, max}); -- add error message
 +
max = nil;
 
end
 
end
 
else -- not a valid keyword or number
 
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
+
utilities.set_message ('err_disp_name', {param, max}); -- add error message
−
max = nil; -- unset
+
max = nil; -- unset; as if |display-xxxxors= had not been set
 
end
 
end
−
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
  −
max = count + 1; -- number of authors + 1
   
end
 
end
 
 
Строка 1901: Строка 1946:  
end
 
end
   −
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
     −
This is the main function doing the majority of the citation
+
--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
−
formatting.
+
 
 +
Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be
 +
some form of p. or pp. abbreviation in the first characters of the parameter content.
 +
 
 +
check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value:
 +
good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px
 +
      where x and X are letters and # is a digit
 +
bad pattern:  '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG
    
]]
 
]]
   −
local function citation0( config, args)
+
local function extra_text_in_page_check (val, name)
−
--[[  
+
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
−
Load Input Parameters
+
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
−
The argument_wrapper facilitates the mapping of multiple
+
if val:match (pattern) then -- when a match, error so
−
aliases to single internal variable.
+
utilities.set_message ('err_extra_text_pages', name); -- add error message
−
]]
+
return; -- and done
−
local A = argument_wrapper( args );
+
end
 +
end
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
 +
 
 +
Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
 +
 
 +
For |volume=:
 +
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
 +
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
 +
are allowed.
   −
local i
+
For |issue=:
−
local PPrefix = A['PPrefix']
+
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
−
local PPPrefix = A['PPPrefix']
+
parameter content (all case insensitive).
−
if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end
+
 +
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
 +
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
 
 
−
-- Pick out the relevant fields from the arguments.  Different citation templates
+
<val> is |volume= or |issue= parameter value
−
-- define different field names for the same underlying things.
+
<name> is |volume= or |issue= parameter name for error message
−
local Authors = A['Authors'];
+
<selector> is 'v' for |volume=, 'i' for |issue=
−
local author_etal;
+
 
−
local a, author_etal = extract_names( args, 'AuthorList' );
+
sets error message on failure; returns nothing
   −
local Coauthors = A['Coauthors'];
+
]]
−
local Others = A['Others'];
  −
local Editors = A['Editors'];
  −
local editor_etal;
  −
local e, editor_etal = extract_names( args, 'EditorList' );
     −
local NameListFormat = A['NameListFormat']; -- replaces |author-format= and |editor-format=
+
local function extra_text_in_vol_iss_check (val, name, selector)
−
if is_set (NameListFormat) and ('vanc' ~= NameListFormat) then -- only accepted value for this parameter is 'vanc'
+
if not utilities.is_set (val) then
−
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'name-list-format', NameListFormat}, true ) } ); -- not vanc so add error message
+
return;
−
NameListFormat = ''; -- set to empty string
   
end
 
end
 +
 +
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;
   −
local Year = A['Year'];
+
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
−
local PublicationDate = A['PublicationDate'];
+
val = val:lower(); -- force parameter value to lower case
−
local OrigYear = A['OrigYear'];
+
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
−
local Date = A['Date'];
+
if val:match (pattern) then -- when a match, error so
−
local LayDate = A['LayDate'];
+
utilities.set_message (handler, name); -- add error message
−
------------------------------------------------- Get title data
+
return; -- and done
−
local Title = A['Title'];
+
end
−
local ScriptTitle = A['ScriptTitle'];
+
end
−
local BookTitle = A['BookTitle'];
+
end
−
local Conference = A['Conference'];
+
 
−
local TransTitle = A['TransTitle'];
+
 
−
local TitleNote = A['TitleNote'];
+
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
−
local TitleLink = A['TitleLink'];
+
 
−
local Chapter = A['Chapter'];
+
split apart a |vauthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
−
local ChapterLink = A['ChapterLink']; -- deprecated
+
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
−
local TransChapter = A['TransChapter'];
+
rendered citation and in the metadata.  Individual author names may be wikilinked
−
local TitleType = A['TitleType'];
+
 
−
local Degree = A['Degree'];
+
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
−
local Docket = A['Docket'];
  −
local ArchiveFormat = A['ArchiveFormat'];
  −
local ArchiveURL = A['ArchiveURL'];
  −
local URL = A['URL']
  −
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
  −
local ChapterURL = A['ChapterURL'];
  −
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
  −
local ConferenceFormat = A['ConferenceFormat'];
  −
local ConferenceURL = A['ConferenceURL'];
  −
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
  −
local Periodical = A['Periodical'];
     −
local Series = A['Series'];
+
]=]
−
local Volume = A['Volume'];
  −
local Issue = A['Issue'];
  −
local Position = '';
  −
local Page = A['Page'];
  −
local Pages = hyphen_to_dash( A['Pages'] );
  −
local At = A['At'];
     −
local Edition = A['Edition'];
+
local function get_v_name_table (vparam, output_table, output_link_table)
−
local PublicationPlace = A['PublicationPlace']
+
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
−
local Place = A['Place'];
+
local wl_type, label, link; -- wl_type not used here; just a placeholder
 
 
−
local PublisherName = A['PublisherName'];
+
local i = 1;
−
local RegistrationRequired = A['RegistrationRequired'];
+
−
local SubscriptionRequired = A['SubscriptionRequired'];
+
while name_table[i] do
−
local Via = A['Via'];
+
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
−
local AccessDate = A['AccessDate'];
+
local name = name_table[i];
−
local ArchiveDate = A['ArchiveDate'];
+
i = i + 1; -- bump indexer to next segment
−
local Agency = A['Agency'];
+
while name_table[i] do
−
local DeadURL = A['DeadURL']
+
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
−
local Language = A['Language'];
+
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses
−
local Format = A['Format'];
+
break; -- and done reassembling so
−
local ChapterFormat = A['ChapterFormat'];
+
end
−
local DoiBroken = A['DoiBroken'];
+
i = i + 1; -- bump indexer
−
local ID = A['ID'];
+
end
−
local ASINTLD = A['ASINTLD'];
+
table.insert (output_table, name); -- and add corporate name to the output table
−
local IgnoreISBN = A['IgnoreISBN'];
+
table.insert (output_link_table, ''); -- no wikilink
−
local Embargo = A['Embargo'];
+
else
−
local Class = A['Class']; -- arxiv class identifier
+
wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
 +
table.insert (output_table, label); -- add this name
 +
if 1 == wl_type then
 +
table.insert (output_link_table, label); -- simple wikilink [[D]]
 +
else
 +
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
 +
end
 +
end
 +
i = i + 1;
 +
end
 +
return output_table;
 +
end
 +
 
 +
 
 +
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
   −
local ID_list = extract_ids( args );
+
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
 +
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
   −
local Quote = A['Quote'];
+
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
 +
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
 +
tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.
   −
local LayFormat = A['LayFormat'];
+
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
−
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'];
+
This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
−
local no_tracking_cats = A['NoTracking'];
     −
--these are used by cite interview
+
]]
−
local Callsign = A['Callsign'];
  −
local City = A['City'];
  −
local Program = A['Program'];
     −
--local variables that are not cs1 parameters
+
local function parse_vauthors_veditors (args, vparam, list_name)
−
local use_lowercase; -- controls capitalization of certain static text
+
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
−
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
+
local v_name_table = {};
−
local anchor_year; -- used in the CITEREF identifier
+
local v_link_table = {}; -- when name is wikilinked, targets go in this table
−
local COinS_date; -- used in the COinS metadata
+
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;
   −
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
+
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)
−
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
+
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
−
local PostScript;
  −
local Ref;
  −
sepc, PostScript, Ref = set_style (A['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
+
for i, v_name in ipairs(v_name_table) do
−
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
+
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
−
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
+
local accept_name;
−
no_tracking_cats = "true"; -- set no_tracking_cats
+
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
−
end
+
 
−
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
+
if accept_name then
−
if this_page.text:match (v) then -- test page name against each pattern
+
last = v_name;
−
no_tracking_cats = "true"; -- set no_tracking_cats
+
corporate = true; -- flag used in list_people()
−
break; -- bail out if one is found
+
elseif string.find(v_name, "%s") then
 +
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;  
 +
add_vanc_error (cfg.err_msg_supl.punctuation, i);
 
end
 
end
−
end
+
local lastfirstTable = {}
−
end
+
lastfirstTable = mw.text.split(v_name, "%s+")
 +
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix
   −
-- check for extra |page=, |pages= or |at= parameters.  
+
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
−
if is_set(Page) then
+
suffix = first; -- not initials so assume that whatever we got is a generational suffix
−
if is_set(Pages) or is_set(At) then
+
first = table.remove(lastfirstTable); -- get what should be the initials from the table
−
Page = Page .. " " .. set_error('extra_pages'); -- add error message
+
end
−
Pages = ''; -- unset the others
+
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
−
At = '';
+
if not utilities.is_set (last) then
 +
first = ''; -- unset
 +
last = v_name; -- last empty because something wrong with first
 +
add_vanc_error (cfg.err_msg_supl.name, i);
 +
end
 +
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
 +
add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
 +
end
 +
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
 +
add_vanc_error (cfg.err_msg_supl.initials, i); -- matches a space between two initials
 +
end
 +
else
 +
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
 
end
 
end
−
elseif is_set(Pages) then
+
−
if is_set(At) then
+
if utilities.is_set (first) then
−
Pages = Pages .. " " .. set_error('extra_pages'); -- add error messages
+
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
−
At = ''; -- unset
+
add_vanc_error (cfg.err_msg_supl.initials, i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
 +
end
 +
is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit
 +
if utilities.is_set (suffix) then
 +
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
 +
suffix = ''; -- unset so we don't add this suffix to all subsequent names
 +
end
 +
else
 +
if not corporate then
 +
is_good_vanc_name (last, '', nil, i);
 +
end
 
end
 
end
−
end
     −
-- both |publication-place= and |place= (|location=) allowed if different
+
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
−
if not is_set(PublicationPlace) and is_set(Place) then
+
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
−
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
+
names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list
 
end
 
end
−
+
return names, etal; -- all done, return our list of names
−
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
+
end
−
+
 
−
--[[
+
 
−
Parameter remapping for cite encyclopedia:
+
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
−
When the citation has these parameters:
+
 
−
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
+
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
−
|encyclopedia and |article then map |encyclopedia to |title
+
select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
−
|encyclopedia then map |encyclopedia to |title
+
 
 +
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest;
 +
|editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn)
 +
 
 +
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
 +
test which mimicks the test used in extract_names() when looking for a hole in the author name list.  There may be a better
 +
way to do this, I just haven't discovered what that way is.
 +
 
 +
Emits an error message when more than one xxxxor name source is provided.
   −
|trans_title maps to |trans_chapter when |title is re-mapped
+
In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.
−
|url maps to |chapterurl when |title is remapped
     −
All other combinations of |encyclopedia, |title, and |article are not modified
  −
TODO: script-title to script-chapter if and when we support script-chapter
   
]]
 
]]
   −
local Encyclopedia = A['Encyclopedia'];
+
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
 +
local lastfirst = false;
 +
if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ...
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
 +
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
 +
lastfirst = true;
 +
end
   −
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
+
if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
−
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
+
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
−
if is_set(Title) then
+
(true == lastfirst and utilities.is_set (xxxxors)) then
−
if not is_set(Chapter) then
+
local err_name;
−
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
+
if 'AuthorList' == list_name then -- figure out which name should be used in error message
−
TransChapter = TransTitle;
+
err_name = 'author';
−
ChapterURL = URL;
+
else
−
Title = Periodical;
+
err_name = 'editor';
−
ChapterFormat = Format;
  −
Periodical = ''; -- redundant so unset
  −
TransTitle = ''; -- redundant so unset
  −
URL = ''; -- redundant so unset
  −
Format = ''; -- redundant so unset
  −
end
  −
else -- |title not set
  −
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
  −
Periodical = ''; -- redundant so unset
   
end
 
end
−
end
+
utilities.set_message ('err_redundant_parameters', err_name .. '-name-list parameters'); -- add error message
 
end
 
end
   −
-- Special case for cite techreport.
+
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
−
if (config.CitationClass == "techreport") then -- special case for cite techreport
+
if utilities.is_set (vxxxxors) then return 2 end;
−
if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue'
+
if utilities.is_set (xxxxors) then return 3 end;
−
if not is_set(ID) then -- can we use ID for the "number"?
+
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
−
ID = Issue; -- yes, use it
+
end
−
Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
+
 
−
else -- can't use ID so emit error message
+
 
−
ID = ID .. " " .. set_error('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
+
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
−
end
+
 
−
end
+
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
−
end
+
of allowable values (yes, y, true, live, dead, etc.). When the parameter value has not been assigned a value (missing
 +
or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one
 +
of the list of allowed values returns the translated value; else, emits an error message and returns the value
 +
specified by ret_val.
   −
-- special case for cite interview
+
TODO: explain <invert>
−
if (config.CitationClass == "interview") then
  −
if is_set(Program) then
  −
ID = ' ' .. Program;
  −
end
  −
if is_set(Callsign) then
  −
if is_set(ID) then
  −
ID = ID .. sepc .. ' ' .. Callsign;
  −
else
  −
ID = ' ' .. Callsign;
  −
end
  −
end
  −
if is_set(City) then
  −
if is_set(ID) then
  −
ID = ID .. sepc .. ' ' .. City;
  −
else
  −
ID = ' ' .. City;
  −
end
  −
end
     −
if is_set(Others) then
+
]]
−
if is_set(TitleType) then
  −
Others = ' ' .. TitleType .. ' with ' .. Others;
  −
TitleType = '';
  −
else
  −
Others = ' ' .. 'Interview with ' .. Others;
  −
end
  −
else
  −
Others = '(Interview)';
  −
end
  −
end
     −
-- special case for cite mailing list
+
local function is_valid_parameter_value (value, name, possible, ret_val, invert)
−
if (config.CitationClass == "mailinglist") then
+
if not utilities.is_set (value) then
−
Periodical = A ['MailingList'];
+
return ret_val; -- an empty parameter is ok
 
end
 
end
   −
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
+
if (not invert and utilities.in_array (value, possible)) then -- normal; <value> is in <possible> table
−
if 'conference' == config.CitationClass then
+
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
−
if is_set(BookTitle) then
+
elseif invert and not utilities.in_array (value, possible) then -- invert; <value> is not in <possible> table
−
Chapter = Title;
+
return value; -- return <value> as it is
−
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
+
else
−
ChapterURL = URL;
+
utilities.set_message ('err_invalid_param_val', {name, value}); -- not an allowed value so add error message
−
ChapterURLorigin = URLorigin;
+
return ret_val;
−
URLorigin = '';
  −
ChapterFormat = Format;
  −
TransChapter = TransTitle;
  −
Title = BookTitle;
  −
Format = '';
  −
-- TitleLink = '';
  −
TransTitle = '';
  −
URL = '';
  −
end
  −
elseif 'speech' ~= config.CitationClass then
  −
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
   
end
 
end
 +
end
 +
 +
 +
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
 +
 +
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
 +
when the last character is not a sepc character or when the last three characters are not sepc followed by two
 +
closing square brackets (close of a wikilink).  When either of these is true, the name_list is terminated with a
 +
single space character.
 +
 +
]]
   −
-- cite map oddities
+
local function terminate_name_list (name_list, sepc)
−
local Cartography = "";
+
if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
−
local Scale = "";
+
return name_list; -- just return the name list
−
local Sheet = A['Sheet'] or '';
+
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
−
local Sheets = A['Sheets'] or '';
+
return name_list .. " "; -- don't add another
−
if config.CitationClass == "map" then
+
else
−
Chapter = A['Map'];
+
return name_list .. sepc .. ' '; -- otherwise terminate the name list
−
ChapterURL = A['MapURL'];
+
end
−
TransChapter = A['TransMap'];
+
end
−
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 Began = A['Began']; -- these two are deprecated because the module understands date ranges
  −
local Ended = A['Ended'];
  −
local SeriesLink = A['SeriesLink'];
  −
local Network = A['Network'];
  −
local Station = A['Station'];
  −
local s, n = {}, {};
     −
-- do common parameters first
+
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >-----------------------------------------
−
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) then -- promote airdate or Began/Ended to date
  −
if is_set (AirDate) then
  −
Date = AirDate;
  −
elseif is_set (Began) then -- deprecated
  −
if Began:match('%s') or Ended:match('%s') then -- so we don't create errors: if either has spaces then
  −
Date = Began .. ' – ' .. Ended; -- use spaced ndash as separator
  −
else
  −
Date = Began .. '–' .. Ended; -- elsewise no spaces
  −
end
  −
end
  −
end
     −
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
+
returns the concatenation of the formatted volume and issue (or journal article number) parameters as a single
−
local Season = A['Season'];
+
string; or formatted volume or formatted issue, or an empty string if neither are set.
−
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=
+
local function format_volume_issue (volume, issue, article, cite_class, origin, sepc, lower)
−
end
+
if not utilities.is_set (volume) and not utilities.is_set (issue) and not utilities.is_set (article) then
−
-- assemble a table of parts concatenated later into Series
+
return '';
−
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
  −
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
  −
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
  −
Issue = ''; -- unset because this is not a unique parameter
  −
  −
Chapter = Title; -- promote title parameters to chapter
  −
ChapterLink = TitleLink; -- alias episodelink
  −
TransChapter = TransTitle;
  −
ChapterURL = URL;
  −
ChapterURLorigin = A:ORIGIN('URL');
  −
  −
Title = Series; -- promote series to title
  −
TitleLink = SeriesLink;
  −
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
  −
 
  −
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
  −
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
  −
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
  −
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
  −
end
  −
URL = ''; -- unset
  −
TransTitle = ''; -- unset
  −
  −
else -- now oddities that are cite serial
  −
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
  −
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
  −
if is_set (Series) and is_set (SeriesLink) then
  −
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
  −
end
  −
Series = wrap_style ('italic-title', Series); -- series is italicized
  −
end
   
end
 
end
−
-- end of {{cite episode}} stuff
     −
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
+
-- same condition as in format_pages_sheets()
−
if 'arxiv' == config.CitationClass then
+
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
−
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
  −
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
  −
end
  −
if first_set (AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
  −
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
  −
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
  −
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']) then
  −
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
     −
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
+
local is_numeric_vol = volume and (volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')); -- is only uppercase roman numerals or only digits?
−
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
+
local is_long_vol = volume and (4 < mw.ustring.len(volume)); -- is |volume= value longer than 4 characters?
−
Chapter = '';
+
−
URL = '';
+
if volume and (not is_numeric_vol and is_long_vol) then -- when not all digits or Roman numerals, is |volume= longer than 4 characters?
−
Format = '';
+
utilities.add_prop_cat ('long-vol'); -- yes, add properties cat
−
Page = ''; Pages = ''; At = '';
  −
end
  −
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
   
end
 
end
   −
-- handle type parameter for those CS1 citations that have default values
+
if is_journal then -- journal-style formatting
 +
local vol = '';
   −
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
+
if utilities.is_set (volume) then
−
TitleType = set_titletype (config.CitationClass, TitleType);
+
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals?
−
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
+
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
−
TitleType = Degree .. " thesis";
+
elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters?
 +
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, utilities.hyphen_to_dash (volume)}); -- not bold
 +
else -- four or fewer characters
 +
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, utilities.hyphen_to_dash (volume)}); -- bold
 +
end
 
end
 
end
 +
vol = vol .. (utilities.is_set (issue) and utilities.substitute (cfg.messages['j-issue'], issue) or '')
 +
vol = vol .. (utilities.is_set (article) and utilities.substitute (cfg.messages['j-article-num'], article) or '')
 +
return vol;
 
end
 
end
−
 
+
−
if is_set(TitleType) then -- if type parameter is specified
+
if 'podcast' == cite_class and utilities.is_set (issue) then
−
TitleType = " (" .. TitleType .. ")"; -- display it in parentheses
+
return wrap_msg ('issue', {sepc, issue}, lower);
 +
end
 +
 +
if 'conference' == cite_class and utilities.is_set (article) then -- |article-number= supported only in journal and conference cites
 +
if utilities.is_set (volume) and utilities.is_set (article) then -- both volume and article number
 +
return wrap_msg ('vol-art', {sepc, utilities.hyphen_to_dash (volume), article}, lower);
 +
elseif utilities.is_set (article) then -- article number alone; when volume alone, handled below
 +
return wrap_msg ('art', {sepc, article}, lower);
 +
end
 
end
 
end
   −
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
+
-- all other types of citation
−
if not is_set (Date) then
+
if utilities.is_set (volume) and utilities.is_set (issue) then
−
Date = Year; -- promote Year to Date
+
return wrap_msg ('vol-no', {sepc, utilities.hyphen_to_dash (volume), issue}, lower);
−
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
+
elseif utilities.is_set (volume) then
−
if is_set(Date) then
+
return wrap_msg ('vol', {sepc, utilities.hyphen_to_dash (volume)}, lower);
−
local Month = A['Month'];
+
else
−
if is_set(Month) then
+
return wrap_msg ('issue', {sepc, issue}, lower);
−
Date = Month .. " " .. Date;
  −
end
  −
elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
  −
Date = PublicationDate; -- promote PublicationDate to Date
  −
PublicationDate = ''; -- unset, no longer needed
  −
end
   
end
 
end
 +
end
 +
 +
 +
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
   −
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
+
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
 +
The return order is:
 +
page, pages, sheet, sheets
   −
--[[
+
Singular has priority over plural when both are provided.
−
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
  −
we get the date used in the metadata.
     −
Date validation supporting code is in Module:Citation/CS1/Date_validation
   
]]
 
]]
−
do -- create defined block to contain local variables error_message and mismatch
  −
local error_message = '';
  −
-- AirDate has been promoted to Date so not necessary to check it
  −
anchor_year, COinS_date, error_message = dates({['accessdate']=AccessDate, ['archivedate']=ArchiveDate, ['date']=Date, ['doi_brokendate']=DoiBroken,
  −
['embargo']=Embargo, ['laydate']=LayDate, ['publicationdate']=PublicationDate, ['year']=Year});
     −
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
+
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
−
local mismatch = year_date_check (Year, Date)
+
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
−
if 0 == mismatch then -- |year= does not match a year-value in |date=
+
if utilities.is_set (sheet) then
−
if is_set (error_message) then -- if there is already an error message
+
if 'journal' == origin then
−
error_message = error_message .. ', '; -- tack on this additional message
+
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
−
end
+
else
−
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
+
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
−
elseif 1 == mismatch then -- |year= matches year-value in |date=
+
end
−
add_maint_cat ('date_year');
+
elseif utilities.is_set (sheets) then
 +
if 'journal' == origin then
 +
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
 +
else
 +
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
 
end
 
end
 
end
 
end
 +
end
   −
if is_set(error_message) then
+
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
−
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
+
 +
if utilities.is_set (page) then
 +
if is_journal then
 +
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
 +
elseif not nopp then
 +
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
 +
else
 +
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
 
end
 
end
−
end -- end of do
+
elseif utilities.is_set (pages) then
−
 
+
if is_journal then
−
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
+
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
−
-- 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
+
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
−
Embargo = is_embargoed (Embargo); --  
+
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
−
 
+
elseif not nopp then
−
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
+
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
−
if not is_set (Embargo) then -- if not embargoed or embargo has expired
+
else
−
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
+
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
−
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
   
end
 
end
 
end
 
end
 +
 +
return '', '', '', ''; -- return empty strings
 +
end
   −
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
  −
-- Test if citation has no title
  −
if not is_set(Title) and
  −
not is_set(TransTitle) and
  −
not is_set(ScriptTitle) then
  −
table.insert( z.message_tail, { set_error( 'citation_missing_title', {}, true ) } );
  −
end
  −
  −
if 'none' == Title and is_set(Periodical) and not (( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia))) then -- special case
  −
Title = ''; -- set title to empty string
  −
add_maint_cat ('untitled');
  −
end
     −
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
+
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
−
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
  −
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
  −
-- is the article title, and Chapter is a section within the article.  So, we remap
  −
  −
local coins_chapter = Chapter; -- default assuming that remapping not required
  −
local coins_title = Title; -- et tu
  −
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
  −
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
  −
coins_chapter = Title; -- remap
  −
coins_title = Periodical;
  −
end
  −
end
  −
  −
-- this is the function call to COinS()
  −
local OCinSoutput = COinS({
  −
['Periodical'] = Periodical,
  −
['Chapter'] = strip_apostrophe_markup (coins_chapter), -- Chapter stripped of bold / italic wikimarkup
  −
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
  −
['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'] = get_coins_pages (first_set(Sheet, Sheets, Page, Pages, At)), -- pages stripped of external links
  −
['Edition'] = Edition,
  −
['PublisherName'] = PublisherName,
  −
['URL'] = first_set( URL, ChapterURL ),
  −
['Authors'] = a,
  −
['ID_list'] = ID_list,
  −
['RawPage'] = this_page.prefixedText,
  −
}, config.CitationClass);
     −
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
+
returns one of the in-source locators: page, pages, or at.
−
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
  −
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
  −
end
     −
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
+
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
−
if 'newsgroup' == config.CitationClass then
+
for use in COinS.  This COinS thing is done because here we convert an interwiki-link to an external link and
−
if is_set (PublisherName) then
+
add an icon span around that; get_coins_pages() doesn't know about the span.  TODO: should it? 
−
PublisherName = '[[Newsgroup]]:&nbsp;' ..  external_link( 'news:' .. PublisherName, PublisherName );
  −
end
  −
end
      +
TODO: add support for sheet and sheets?; streamline;
    +
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
 +
to a new name)?
   −
-- Now perform various field substitutions.
+
]]
−
-- We also add leading spaces and surrounding markup and punctuation to the
  −
-- various parts of the citation, but only when they are non-nil.
  −
do -- do-block to limit scope of LastFirstAuthors
  −
local LastFirstAuthors;
  −
local Maximum = A['DisplayAuthors'];
     −
Maximum , author_etal = get_display_authors_editors (Maximum, #a, 'authors', author_etal);
+
local function insource_loc_get (page, page_orig, pages, pages_orig, at)
 +
local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
   −
local control = {
+
if utilities.is_set (page) then
−
format = NameListFormat, -- empty string or 'vanc'
+
if utilities.is_set (pages) or utilities.is_set (at) then
−
maximum = Maximum,
+
pages = ''; -- unset the others
−
lastauthoramp = LastAuthorAmp,
+
at = '';
−
page_name = this_page.text -- get current page name so that we don't wikilink to it via authorlinkn
+
end
−
};
+
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
−
+
 
−
-- If the coauthor field is also used, prevent ampersand and et al. formatting.
+
ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label
−
if is_set(Coauthors) then
+
if ws_url then
−
control.lastauthoramp = nil;
+
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?
−
control.maximum = #a + 1;
+
page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
 +
coins_pages = ws_label;
 +
end
 +
elseif utilities.is_set (pages) then
 +
if utilities.is_set (at) then
 +
at = ''; -- unset
 
end
 
end
−
+
extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
−
LastFirstAuthors = list_people(control, a, author_etal);
     −
if is_set (Authors) then
+
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label
−
if is_set (LastFirstAuthors) then -- if both author name styles
+
if ws_url then
−
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'authors') .. ' and ' .. wrap_style ('parameter', 'last')}, true ) } ); -- add error message
+
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?
−
Authors = LastFirstAuthors; -- TODO: is this correct or should we use |authors= instead?
+
pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
−
end
+
coins_pages = ws_label;
−
else
+
end
−
Authors = LastFirstAuthors; -- either an author name list or an empty string
+
elseif utilities.is_set (at) then
 +
ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label
 +
if ws_url then
 +
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
 +
coins_pages = ws_label;
 
end
 
end
−
end -- end of do
  −
  −
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
  −
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
   
end
 
end
 +
 +
return page, pages, at, coins_pages;
 +
end
   −
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
+
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
−
if not is_set(Editors) then
  −
local Maximum = A['DisplayEditors'];
     −
Maximum , editor_etal = get_display_authors_editors (Maximum, #e, 'editors', editor_etal);
+
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value
−
-- Preserve old-style implicit et al.
  −
if not is_set(Maximum) and #e == 4 then
  −
Maximum = 3;
  −
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
  −
end
     −
local control = {
+
]]
−
format = NameListFormat, -- empty string or 'vanc'
  −
maximum = Maximum,
  −
lastauthoramp = LastAuthorAmp,
  −
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
  −
};
     −
Editors, EditorCount = list_people(control, e, editor_etal);
+
local function is_unique_archive_url (archive, url, c_url, source, date)
−
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
+
if utilities.is_set (archive) then
−
EditorCount = 2; -- spoof to display (eds.) annotation
+
if archive == url or archive == c_url then
 +
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); -- add error message
 +
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
 
end
 
end
−
else
  −
EditorCount = 1;
   
end
 
end
   −
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
+
return archive, date;
−
-- an error message if the associated url is not set, or an empty string for concatenation
+
end
−
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
+
 
−
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
+
 
−
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
+
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
−
Format = style_format (Format, URL, 'format', 'url');
+
 
−
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
+
Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the
−
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
+
save snapshot URL or to calendar pages.  When the archive URL is 'https://web.archive.org/save/' (or http://...)
 +
archive.org saves a snapshot of the target page in the URL.  That is something that Wikipedia should not allow
 +
unwitting readers to do.
   −
if not is_set(URL) then --and
+
When the archive.org URL does not have a complete timestamp, archive.org chooses a snapshot according to its own
−
-- not is_set(ArchiveURL) then --and -- prevents format_missing_url error from registering
+
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
−
-- not is_set(ConferenceURL) and -- TODO: keep this here? conference as part of cite web or cite podcast?
+
 
−
-- not is_set(TranscriptURL) then -- TODO: remove? |transcript-url= and |transcript= has separate test
+
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
−
+
|archive-date= and an error message when:
−
-- Test if cite web or cite podcast |url= is missing or empty
+
|archive-url= holds an archive.org save command URL
−
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then
+
|archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
−
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
+
correct place
−
end
+
otherwise returns |archive-url= and |archive-date=
−
+
 
−
-- Test if accessdate is given without giving a URL
+
There are two mostly compatible archive.org URLs:
−
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test?
+
//web.archive.org/<timestamp>... -- the old form
−
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
+
//web.archive.org/web/<timestamp>... -- the new form
−
AccessDate = '';
+
 
−
end
+
The old form does not support or map to the new form when it contains a display flag. There are four identified flags
 +
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
 +
we don't check for these specific flags but we do check the form.
 +
 
 +
This function supports a preview mode.  When the article is rendered in preview mode, this function may return a modified
 +
archive URL:
 +
for save command errors, return undated wildcard (/*/)
 +
for timestamp errors when the timestamp has a wildcard, return the URL unmodified
 +
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
 +
 
 +
A secondary function is to return an archive-url timestamp from those urls that have them (archive.org and
 +
archive.today).  The timestamp is used by validation.archive_date_check() to see if the value in |archive-date=
 +
matches the timestamp in the archive url.
 +
 
 +
]=]
 +
 
 +
local function archive_url_check (url, date)
 +
local err_msg = ''; -- start with the error message empty
 +
local path, timestamp, flag; -- portions of the archive.org URL
 +
 +
timestamp = url:match ('//archive.today/(%d%d%d%d%d%d%d%d%d%d%d%d%d%d)/'); -- get timestamp from archive.today urls
 +
if timestamp then -- if this was an archive.today url ...
 +
return url, date, timestamp; -- return ArchiveURL, ArchiveDate, and timestamp from |archive-url=, and done
 
end
 
end
−
 
+
-- here for archive.org urls
−
local OriginalURL, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
+
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
−
DeadURL = DeadURL:lower(); -- used later when assembling archived text
+
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
−
if is_set( ArchiveURL ) then
  −
if is_set (URL) then
  −
OriginalURL = URL; -- save copy of original source URL
  −
OriginalFormat = Format; -- and original |format=
  −
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
  −
URL = ArchiveURL -- swap-in the archive's url
  −
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
  −
Format = ArchiveFormat or ''; -- swap in archive's format
  −
end
  −
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
  −
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
  −
OriginalFormat = ChapterFormat; -- and original |format=
  −
if 'no' ~= DeadURL then
  −
ChapterURL = ArchiveURL -- swap-in the archive's url
  −
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
  −
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
  −
end
  −
end
   
end
 
end
   −
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", 'arxiv'}) or
+
if url:match('//web%.archive%.org/save/') then -- if a save command URL, we don't want to allow saving of the target page
−
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
+
err_msg = cfg.err_msg_supl.save;
−
if is_set (Chapter) or is_set (TransChapter) or is_set (ChapterURL)then -- chapter parameters not supported for these citation types
+
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
−
table.insert( z.message_tail, { set_error( 'chapter_ignored', {}, true ) } ); -- add error message
+
elseif url:match('//liveweb%.archive%.org/') then
−
Chapter = ''; -- set to empty string to be safe with concatenation
+
err_msg = cfg.err_msg_supl.liveweb;
−
TransChapter = '';
+
else
−
ChapterURL = '';
+
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation
 +
if not path then -- malformed in some way; pattern did not match
 +
err_msg = cfg.err_msg_supl.timestamp;
 +
elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
 +
err_msg = cfg.err_msg_supl.timestamp;
 +
if '*' ~= flag then
 +
local replacement = timestamp:match ('^%d%d%d%d%d%d') or timestamp:match ('^%d%d%d%d'); -- get the first 6 (YYYYMM) or first 4 digits (YYYY)
 +
if replacement then -- nil if there aren't at least 4 digits (year)
 +
replacement = replacement .. string.rep ('0', 14 - replacement:len()); -- year or yearmo (4 or 6 digits) zero-fill to make 14-digit timestamp
 +
url=url:gsub ('(//web%.archive%.org/[^%d]*)%d[^/]*', '%1' .. replacement .. '*', 1) -- for preview, modify ts to 14 digits plus splat for calendar display
 +
end
 
end
 
end
−
else -- otherwise, format chapter / article title
+
elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element
−
Chapter = format_chapter_title (Chapter, TransChapter, ChapterURL, ChapterURLorigin);
+
err_msg = cfg.err_msg_supl.path;
−
if is_set (Chapter) then
+
elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element)
−
if 'map' == config.CitationClass and is_set (TitleType) then
+
err_msg = cfg.err_msg_supl.flag;
−
Chapter = Chapter .. ' ' .. TitleType;
+
elseif utilities.is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
−
end
+
err_msg = cfg.err_msg_supl.flag;
−
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
+
else
 +
return url, date, timestamp; -- return ArchiveURL, ArchiveDate, and timestamp from |archive-url=
 
end
 
end
 
end
 
end
 +
-- if here, something not right so
 +
utilities.set_message ('err_archive_url', {err_msg}); -- add error message and
   −
-- Format main title.
+
if is_preview_mode then
−
if is_set(TitleLink) and is_set(Title) then
+
return url, date, timestamp; -- preview mode so return ArchiveURL, ArchiveDate, and timestamp from |archive-url=
−
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
+
else
 +
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
 
end
 
end
 +
end
 +
 +
 +
--[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------
   −
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", "mailinglist", 'arxiv'}) or
+
check |place=, |publication-place=, |location= to see if these params include digits. This function added because
−
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
+
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
−
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
+
 
−
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
+
returns the original parameter value without modification; added maint cat when parameter value contains digits
−
Title = wrap_style ('quoted-title', Title);
+
 
−
+
]]
−
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
  −
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
  −
elseif 'report' == config.CitationClass then -- no styling for cite report
  −
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
  −
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
  −
else
  −
Title = wrap_style ('italic-title', Title);
  −
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
  −
TransTitle = wrap_style ('trans-italic-title', TransTitle);
  −
end
     −
TransError = "";
+
local function place_check (param_val)
−
if is_set(TransTitle) then
+
if not utilities.is_set (param_val) then -- parameter empty or omitted
−
if is_set(Title) then
+
return param_val; -- return that empty state
−
TransTitle = " " .. TransTitle;
  −
else
  −
TransError = " " .. set_error( 'trans_missing_title' );
  −
end
   
end
 
end
 
 
−
Title = Title .. TransTitle;
+
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
 +
utilities.set_message ('maint_location'); -- yep, add maint cat
 +
end
 
 
−
if is_set(Title) then
+
return param_val; -- and done
−
if not is_set(TitleLink) and is_set(URL) then
+
end
−
Title = external_link( URL, Title ) .. TransError .. Format;
+
 
−
URL = "";
+
 
−
Format = "";
+
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
−
else
+
 
−
Title = Title .. TransError;
+
compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else
−
end
  −
end
     −
if is_set(Place) then
+
]]
−
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
  −
end
     −
if is_set (Conference) then
+
local function is_archived_copy (title)
−
if is_set (ConferenceURL) then
+
title = mw.ustring.lower(title); -- switch title to lower case
−
Conference = external_link( ConferenceURL, Conference );
+
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
 +
return true;
 +
elseif cfg.special_case_translation.archived_copy['local'] then
 +
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
 +
return true;
 
end
 
end
−
Conference = sepc .. " " .. Conference .. ConferenceFormat;
  −
elseif is_set(ConferenceURL) then
  −
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
   
end
 
end
 +
end
   −
if not is_set(Position) then
+
 
−
local Minutes = A['Minutes'];
+
--[[--------------------------< D I S P L A Y _ N A M E S _ S E L E C T >--------------------------------------
−
if is_set(Minutes) then
+
 
−
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
+
for any of the |display-authors=, |display-editors=, etc parameters, select either the local or global setting.
−
else
+
When both are present, look at <local_display_names> value.  When the value is some sort of 'et al.'string,
−
local Time = A['Time'];
+
special handling is required.
−
if is_set(Time) then
+
 
−
local TimeCaption = A['TimeCaption']
+
When {{cs1 config}} has |display-<namelist>= AND this template has |display-<namelist>=etal AND:
−
if not is_set(TimeCaption) then
+
the number of names specified by <number_of_names> is:
−
TimeCaption = cfg.messages['event'];
+
greater than the number specified in the global |display-<namelist>= parameter (<global_display_names>)
−
if sepc ~= '.' then
+
use global |display-<namelist>= parameter value
−
TimeCaption = TimeCaption:lower();
+
set overridden maint category
−
end
+
less than or equal to the number specified in the global |display-<namelist>=  parameter
−
end
+
use local |display-<namelist>= parameter value
−
Position = " " .. TimeCaption .. " " .. Time;
+
 
 +
The purpose of this function is to prevent categorizing a template that has fewer names than the global setting
 +
to keep the etal annotation specified by <local_display_names>.
 +
 
 +
]]
 +
 
 +
local function display_names_select (global_display_names, local_display_names, param_name, number_of_names, test)
 +
if global_display_names and utilities.is_set (local_display_names) then -- when both
 +
if 'etal' == local_display_names:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
 +
number_of_names = tonumber (number_of_names); -- convert these to numbers for comparison
 +
local global_display_names_num = tonumber (global_display_names); -- <global_display_names> not set when parameter value is not digits
 +
 
 +
if number_of_names > global_display_names_num then -- template has more names than global config allows to be displayed?
 +
utilities.set_message ('maint_overridden_setting'); -- set a maint message because global is overriding local |display-<namelist>=etal
 +
return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names())
 +
else
 +
return local_display_names, param_name; -- return local because fewer names so let <local_display_names> control
 
end
 
end
 
end
 
end
−
else
+
-- here when <global_display_names> and <local_display_names> both numbers; <global_display_names> controls
−
Position = " " .. Position;
+
utilities.set_message ('maint_overridden_setting'); -- set a maint message
−
At = '';
+
return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names())
 
end
 
end
−
+
-- here when only one of <global_display_names> or <local_display_names> set
−
if not is_set(Page) then
+
if global_display_names then
−
if is_set(Pages) then
+
return global_display_names, 'cs1 config'; -- return global with spoof parameter name (for get_display_names())
−
if is_set(Periodical) and
  −
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
  −
Pages = ": " .. Pages;
  −
elseif tonumber(Pages) ~= nil then
  −
Pages = sepc .." " .. PPrefix .. Pages;
  −
else
  −
Pages = sepc .." " .. PPPrefix .. Pages;
  −
end
  −
end
   
else
 
else
−
if is_set(Periodical) and
+
return local_display_names, param_name; -- return local
−
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
  −
Page = ": " .. Page;
  −
else
  −
Page = sepc .." " .. PPrefix .. Page;
  −
end
   
end
 
end
 +
end
   −
if 'map' == config.CitationClass then -- cite map oddity done after COinS call (and with other in-source locators)
  −
if is_set (Sheet) or is_set (Sheets) then
  −
local err_msg1 = 'sheet=, &#124;sheets'; -- default error message in case any of page pages or at are set
  −
local err_msg2;
  −
if is_set (Page) or is_set (Pages) or is_set (At) then -- are any set?
  −
err_msg2 = 'page=, &#124;pages=, &#124;at'; -- a generic error message
  −
Page = ''; Pages = ''; At = '';
  −
elseif is_set (Sheet) and is_set (Sheets) then -- if both are set make error message
  −
err_msg1 = 'sheet';
  −
err_msg2 = 'sheets';
  −
end
  −
if is_set (err_msg2) then
  −
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', err_msg1) .. ' and ' .. wrap_style ('parameter', err_msg2)}, true ) } ); -- add error message
  −
end
  −
if not is_set (Sheet) then -- do sheet static text and formatting; Sheet has priority over Sheets if both provided
  −
if is_set (Sheets) then
  −
if is_set (Periodical) then
  −
Sheet = ": Sheets " .. Sheets; -- because Sheet has priority, no need to support both later on
  −
else
  −
Sheet = sepc .. " Sheets " .. Sheets;
  −
end
  −
end
  −
else
  −
if is_set (Periodical) then
  −
Sheet = ": Sheet " .. Sheet;
  −
else
  −
Sheet = sepc .. " Sheet " .. Sheet;
  −
end
  −
end
  −
end
  −
end
     −
At = is_set(At) and (sepc .. " " .. At) or "";
+
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
−
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
+
This is the main function doing the majority of the citation formatting.
−
Language = language_parameter (Language, this_page.namespace); -- format, categories (article namespace only), name from ISO639-1, etc
  −
else
  −
Language=""; -- language not specified so make sure this is an empty string;
  −
end
     −
Others = is_set(Others) and (sepc .. " " .. Others) or "";
+
]]
   −
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
+
local function citation0( config, args )
−
Edition = is_set(Edition) and (" " .. wrap_msg ('edition', Edition)) or "";
+
--[[
−
Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
+
Load Input Parameters
−
Series = is_set(Series) and (sepc .. " " .. Series) or "";
+
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
−
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
+
]]
−
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
+
local A = argument_wrapper ( args );
 +
local i
   −
if is_set(Volume) then
+
-- Pick out the relevant fields from the arguments.  Different citation templates
−
if ( mw.ustring.len(Volume) > 4 )
+
-- define different field names for the same underlying things.
−
  then Volume = sepc .." " .. Volume;
+
 
−
  else Volume = " <b>" .. hyphen_to_dash(Volume) .. "</b>";
+
local author_etal;
 +
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
 +
local Authors;
 +
local NameListStyle;
 +
if cfg.global_cs1_config_t['NameListStyle'] then -- global setting in {{cs1 config}} overrides local |name-list-style= parameter value; nil when empty or assigned value invalid
 +
NameListStyle = is_valid_parameter_value (cfg.global_cs1_config_t['NameListStyle'], 'cs1 config: name-list-style', cfg.keywords_lists['name-list-style'], ''); -- error messaging 'param' here is a hoax
 +
else
 +
NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
 
end
 
end
−
end
     −
------------------------------------ totally unrelated data
+
if cfg.global_cs1_config_t['NameListStyle'] and utilities.is_set (A['NameListStyle']) then -- when template has |name-list-style=<something> which global setting has overridden
−
if is_set(Via) then
+
utilities.set_message ('maint_overridden_setting'); -- set a maint message
−
Via = " " .. wrap_msg ('via', Via);
+
end
−
end
     −
--[[
+
local Collaboration = A['Collaboration'];
−
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.
     −
]]
+
do -- to limit scope of selected
−
if in_array(SubscriptionRequired:lower(), {'yes', 'true', 'y'}) then
+
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
−
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
+
if 1 == selected then
−
elseif in_array(RegistrationRequired:lower(), {'yes', 'true', 'y'}) then
+
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
−
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
+
elseif 2 == selected then
−
else
+
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
−
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
+
a, author_etal = parse_vauthors_veditors (args, A['Vauthors'], 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
 +
elseif 3 == selected then
 +
Authors = A['Authors']; -- use content of |people= or |credits=; |authors= is deprecated; TODO: constrain |people= and |credits= to cite av media, episode, serial?
 +
end
 +
if utilities.is_set (Collaboration) then
 +
author_etal = true; -- so that |display-authors=etal not required
 +
end
 
end
 
end
   −
if is_set(AccessDate) then
+
local editor_etal;
−
local retrv_text = " " .. cfg.messages['retrieved']
+
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
   −
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
+
do -- to limit scope of selected
−
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
+
local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn
−
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
+
if 1 == selected then
−
-- neither of these work; don't know why; it seems that substitute() isn't being called
+
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
−
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
+
elseif 2 == selected then
 +
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
 +
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
 +
end
 
end
 
end
 +
 +
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
 +
local Chapter_origin = A:ORIGIN ('Chapter');
 +
local Contribution; -- because contribution is required for contributor(s)
 +
if 'contribution' == Chapter_origin then
 +
Contribution = Chapter; -- get the name of the contribution
 +
end
 +
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
 
 
−
if is_set(ID) then ID = sepc .." ".. ID; end
+
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
−
  if "thesis" == config.CitationClass and is_set(Docket) then
+
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
−
ID = sepc .." Docket ".. Docket .. ID;
+
−
end
+
if 0 < #c then
−
  if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
+
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
−
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
+
utilities.set_message ('err_contributor_missing_required_param', 'contribution'); -- add missing contribution error message
 +
c = {}; -- blank the contributors' table; it is used as a flag later
 +
end
 +
if 0 == #a then -- |contributor= requires |author=
 +
utilities.set_message ('err_contributor_missing_required_param', 'author'); -- add missing author error message
 +
c = {}; -- blank the contributors' table; it is used as a flag later
 +
end
 +
end
 +
else -- if not a book cite
 +
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters?
 +
utilities.set_message ('err_contributor_ignored'); -- add contributor ignored error message
 +
end
 +
Contribution = nil; -- unset
 
end
 
end
   −
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
+
local Title = A['Title'];
 +
local TitleLink = A['TitleLink'];
   −
if is_set(URL) then
+
local auto_select = ''; -- default is auto
−
URL = " " .. external_link( URL, nil, URLorigin );
+
local accept_link;
 +
TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup
 +
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
 +
auto_select = TitleLink; -- remember selection for later
 +
TitleLink = ''; -- treat as if |title-link= would have been empty
 
end
 
end
   −
if is_set(Quote) then
+
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
−
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then
+
 
−
Quote = Quote:sub(2,-2);
+
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
−
end
+
if 'map' == config.CitationClass and 'section' == Chapter_origin then
−
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
+
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
−
PostScript = ""; -- CS1 does not supply terminal punctuation when |quote= is set
+
Chapter = ''; -- unset for now; will be reset later from |map= if present
 
end
 
end
 +
 +
local Periodical = A['Periodical'];
 +
local Periodical_origin = A:ORIGIN('Periodical');
 +
local ScriptPeriodical = A['ScriptPeriodical'];
 +
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
 +
local TransPeriodical =  A['TransPeriodical'];
 +
local TransPeriodical_origin =  A:ORIGIN ('TransPeriodical');
 
 
−
local Archived
+
if (utilities.in_array (config.CitationClass, {'book', 'encyclopaedia'}) and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical))) then
−
if is_set(ArchiveURL) then
+
local param;
−
if not is_set(ArchiveDate) then
+
if utilities.is_set (Periodical) then -- get a parameter name from one of these periodical related meta-parameters
−
ArchiveDate = set_error('archive_missing_date');
+
Periodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters
 +
param = Periodical_origin -- get parameter name for error messaging
 +
elseif utilities.is_set (TransPeriodical) then
 +
TransPeriodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters
 +
param = TransPeriodical_origin; -- get parameter name for error messaging
 +
elseif utilities.is_set (ScriptPeriodical) then
 +
ScriptPeriodical = ''; -- unset because not valid {{cite book}} or {{cite encyclopedia}} parameters
 +
param = ScriptPeriodical_origin; -- get parameter name for error messaging
 
end
 
end
−
if "no" == DeadURL then
+
 
−
local arch_text = cfg.messages['archived'];
+
if utilities.is_set (param) then -- if we found one
−
if sepc ~= "." then arch_text = arch_text:lower() end
+
utilities.set_message ('err_periodical_ignored', {param}); -- emit an error message
−
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
  −
{ external_link( ArchiveURL, arch_text ) .. ArchiveFormat, ArchiveDate } );
  −
if not is_set(OriginalURL) then
  −
Archived = Archived .. " " .. set_error('archive_missing_url');  
  −
end
  −
elseif is_set(OriginalURL) then
  −
local arch_text = cfg.messages['archived-dead'];
  −
if sepc ~= "." then arch_text = arch_text:lower() end
  −
Archived = sepc .. " " .. substitute( arch_text,
  −
{ external_link( OriginalURL, cfg.messages['original'] ) .. OriginalFormat, ArchiveDate } ); -- format already styled
  −
else
  −
local arch_text = cfg.messages['archived-missing'];
  −
if sepc ~= "." then arch_text = arch_text:lower() end
  −
Archived = sepc .. " " .. substitute( arch_text,
  −
{ set_error('archive_missing_url'), ArchiveDate } );
   
end
 
end
−
elseif is_set (ArchiveFormat) then
  −
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
  −
else
  −
Archived = ""
   
end
 
end
−
+
 
−
local Lay = '';
+
if utilities.is_set (Periodical) then
−
if is_set(LayURL) then
+
local i;
−
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
+
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated
−
if is_set(LaySource) then  
+
if i then -- non-zero when markup was stripped so emit an error message
−
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
+
utilities.set_message ('err_apostrophe_markup', {Periodical_origin});
−
else
  −
LaySource = "";
   
end
 
end
−
if sepc == '.' then
  −
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'] ) .. LayFormat .. LaySource .. LayDate
  −
else
  −
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower() ) .. LayFormat .. LaySource .. LayDate
  −
end
  −
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
  −
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
   
end
 
end
   −
if is_set(Transcript) then
+
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
−
if is_set(TranscriptURL) then
+
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error TODO: make a function for this and similar?
−
Transcript = external_link( TranscriptURL, Transcript );
+
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'mailinglist')});
 
end
 
end
−
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
+
 
−
elseif is_set(TranscriptURL) then
+
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
−
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
+
Periodical_origin = A:ORIGIN('MailingList');
 
end
 
end
   −
local Publisher;
+
-- web and news not tested for now because of
−
if is_set(Periodical) and
+
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
−
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
+
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
−
if is_set(PublisherName) then
+
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
−
if is_set(PublicationPlace) then
+
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
−
Publisher = PublicationPlace .. ": " .. PublisherName;
+
if p[config.CitationClass]  then
−
else
+
utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]});
−
Publisher = PublisherName;
+
end
 +
end
 +
 +
local Volume;
 +
if 'citation' == config.CitationClass then
 +
if utilities.is_set (Periodical) then
 +
if not utilities.in_array (Periodical_origin, cfg.citation_no_volume_t) then -- {{citation}} does not render |volume= when these parameters are used
 +
Volume = A['Volume']; -- but does for all other 'periodicals'
 
end
 
end
−
elseif is_set(PublicationPlace) then
+
elseif utilities.is_set (ScriptPeriodical) then
−
Publisher= PublicationPlace;
+
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
−
else
+
Volume = A['Volume']; -- but does for all other 'periodicals'
−
Publisher = "";
  −
end
  −
if is_set(PublicationDate) then
  −
if is_set(Publisher) then
  −
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
  −
else
  −
Publisher = PublicationDate;
   
end
 
end
 +
else
 +
Volume = A['Volume']; -- and does for non-'periodical' cites
 
end
 
end
−
if is_set(Publisher) then
+
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
−
Publisher = " (" .. Publisher .. ")";
+
Volume = A['Volume'];
 +
end
 +
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v');
 +
 
 +
local Issue;
 +
if 'citation' == config.CitationClass then
 +
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, cfg.citation_issue_t) then -- {{citation}} may render |issue= when these parameters are used
 +
Issue = utilities.hyphen_to_dash (A['Issue']);
 
end
 
end
−
else
+
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
−
if is_set(PublicationDate) then
+
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
−
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
+
Issue = utilities.hyphen_to_dash (A['Issue']);
−
end
  −
if is_set(PublisherName) then
  −
if is_set(PublicationPlace) then
  −
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
  −
else
  −
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
  −
end
  −
elseif is_set(PublicationPlace) then
  −
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
  −
else
  −
Publisher = PublicationDate;
   
end
 
end
 
end
 
end
 
 
−
-- Several of the above rely upon detecting this as nil, so do it last.
+
local ArticleNumber;
−
if is_set(Periodical) then
+
 
−
if is_set(Title) or is_set(TitleNote) then  
+
if utilities.in_array (config.CitationClass, {'journal', 'conference'}) or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then
−
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
+
ArticleNumber = A['ArticleNumber'];
−
else
+
end
−
Periodical = wrap_style ('italic-title', Periodical)
+
 
−
end
+
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
 +
 
 +
local Page;
 +
local Pages;
 +
local At;
 +
local QuotePage;
 +
local QuotePages;
 +
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then -- TODO: rewrite to emit ignored parameter error message?
 +
Page = A['Page'];
 +
Pages = utilities.hyphen_to_dash (A['Pages']);
 +
At = A['At'];
 +
QuotePage = A['QuotePage'];
 +
QuotePages = utilities.hyphen_to_dash (A['QuotePages']);
 
end
 
end
   −
--[[
+
local Edition = A['Edition'];
−
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
+
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
−
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
+
local Place = place_check (A['Place'], A:ORIGIN('Place'));
−
]]
+
−
if "speech" == config.CitationClass then -- cite speech only
+
local PublisherName = A['PublisherName'];
−
TitleNote = " (Speech)"; -- annotate the citation
+
local PublisherName_origin = A:ORIGIN('PublisherName');
−
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
+
if utilities.is_set (PublisherName) and (cfg.keywords_xlate['none'] ~= PublisherName) then
−
if is_set (Conference) then -- and if |event= is set
+
local i = 0;
−
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
+
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
−
end
+
if i and (0 < i) then -- non-zero when markup was stripped so emit an error message
 +
utilities.set_message ('err_apostrophe_markup', {PublisherName_origin});
 
end
 
end
 
end
 
end
 +
 +
if ('document' == config.CitationClass) and not utilities.is_set (PublisherName) then
 +
utilities.set_message ('err_missing_publisher', {config.CitationClass, 'publisher'});
 +
end
 +
 +
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
 +
local Newsgroup_origin = A:ORIGIN('Newsgroup');
   −
-- Piece all bits together at last. Here, all should be non-nil.
+
if 'newsgroup' == config.CitationClass then
−
-- We build things this way because it is more efficient in LUA
+
if utilities.is_set (PublisherName) and (cfg.keywords_xlate['none'] ~= PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
−
-- not to keep reassigning to the same string variable over and over.
+
utilities.set_message ('err_parameter_ignored', {PublisherName_origin});
 +
end
   −
local tcommon
+
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
−
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
+
end
−
if is_set(Others) then Others = Others .. sepc .. " " end
+
 
−
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
+
local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL?
−
Language, Edition, Publisher, Agency, Volume, Issue}, sepc );
+
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
−
+
−
elseif 'map' == config.CitationClass then -- special cases for cite map
+
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
−
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
+
UrlAccess = nil;
−
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
+
utilities.set_message ('err_param_access_requires_param', 'url');
−
elseif is_set (Periodical) then -- map in a periodical
  −
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume, Issue}, sepc );
  −
else -- a sheet or stand-alone map
  −
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
  −
end
  −
  −
elseif 'episode' == config.CitationClass then -- special case for cite episode
  −
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
  −
else -- all other CS1 templates
  −
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
  −
Volume, Issue, Others, Edition, Publisher, Agency}, sepc );
   
end
 
end
 
 
−
if #ID_list > 0 then
+
local ChapterURL = A['ChapterURL'];
−
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
+
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
−
else
+
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
−
ID_list = ID;
+
ChapterUrlAccess = nil;
 +
utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')});
 +
end
 +
 
 +
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
 +
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
 +
MapUrlAccess = nil;
 +
utilities.set_message ('err_param_access_requires_param', {'map-url'});
 
end
 
end
−
+
 
−
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
+
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
−
local text;
+
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
−
local pgtext = Position .. Sheet .. Page .. Pages .. At;
+
 
−
+
-- 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 is_set(Authors) then
+
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
−
if is_set(Coauthors) then
+
if cfg.uncategorized_namespaces[this_page.namespace] then -- is this page's namespace id one of the uncategorized namespace ids?
−
local sep = '; ';
+
no_tracking_cats = "true"; -- set no_tracking_cats
−
if 'vanc' == NameListFormat then
+
end
−
sep = ', ';
+
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
−
Authors = Authors .. sep .. 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) or (string.sub(Editors,-3,-1) == sepc .. ']]') then -- if last editor name ends with sepc char
  −
Editors = Editors .. " "; -- don't add another
  −
else
  −
Editors = Editors .. sepc .. " " -- otherwise terninate the editor list
  −
end
  −
end
  −
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
  −
text = safe_join( {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 = safe_join( {Editors, Date, Chapter, Place, tcommon}, sepc );
  −
text = safe_join( {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 = safe_join( {Chapter, Place, tcommon}, sepc );
  −
text = safe_join( {text, pgtext, Date, idcommon}, sepc );
  −
else
  −
text = safe_join( {Chapter, Place, tcommon, Date}, sepc );
  −
text = safe_join( {text, pgtext, idcommon}, sepc );
   
end
 
end
 
end
 
end
 +
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
 +
utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category
 +
 +
local coins_pages;
 
 
−
if is_set(PostScript) and PostScript ~= sepc then
+
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
−
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 <span/> element
+
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
−
local options = {};
+
 
−
+
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
−
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
+
utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
−
options.class = "citation " .. config.CitationClass;
+
if PublicationPlace == Place then
−
else
+
Place = ''; -- unset; don't need both if they are the same
−
options.class = "citation";
  −
end
  −
  −
if is_set(Ref) and Ref:lower() ~= "none" then
  −
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 and for YMD dates that require disambiguation
  −
id = anchor_id(names)
   
end
 
end
−
options.id = id;
+
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
 +
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
 
end
 
end
 +
 +
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
 +
 +
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
 +
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
 +
local ScriptChapter = A['ScriptChapter'];
 +
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
 +
local Format = A['Format'];
 +
local ChapterFormat = A['ChapterFormat'];
 +
local TransChapter = A['TransChapter'];
 +
local TransChapter_origin = A:ORIGIN ('TransChapter');
 +
local TransTitle = A['TransTitle'];
 +
local ScriptTitle = A['ScriptTitle'];
 
 
−
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
+
--[[
−
z.error_categories = {};
+
Parameter remapping for cite encyclopedia:
−
text = set_error('empty_citation');
+
When the citation has these parameters:
−
z.message_tail = {};
+
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title= for rendering
−
end
+
|encyclopedia= and |article= then map |encyclopedia= to |title= for rendering
−
  −
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
     −
local empty_span = '<span style="display:none;">&nbsp;</span>';
+
|trans-title= maps to |trans-chapter= when |title= is re-mapped
 +
|url= maps to |chapter-url= when |title= is remapped
 
 
−
-- Note: Using display: none on then COinS span breaks some clients.
+
All other combinations of |encyclopedia=, |title=, and |article= are not modified
−
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
  −
text = text .. OCinS;
   
 
−
if #z.message_tail ~= 0 then
+
]]
−
text = text .. " ";
+
 
−
for i,v in ipairs( z.message_tail ) do
+
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
−
if is_set(v[1]) then
+
 
−
if i == #z.message_tail then
+
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
−
text = text .. error_comment( v[1], v[2] );
+
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
−
else
+
utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')});
−
text = text .. error_comment( v[1] .. "; ", v[2] );
+
Encyclopedia = nil; -- unset because not supported by this template
−
end
  −
end
   
end
 
end
 
end
 
end
   −
if #z.maintenance_cats ~= 0 then
+
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
−
text = text .. ' <span class="citation-comment" style="display:none; color:#33aa33">';
+
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both parameters set emit an error message; {{citation}} only; Periodical not allowed in {{cite encyclopedia}}
−
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
+
utilities.set_message ('err_periodical_ignored', {Periodical_origin});
−
text = text .. v .. ' ([[:Category:' .. v ..'|link]])';
   
end
 
end
−
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
+
 
−
end
+
if utilities.is_set (Encyclopedia) then
−
+
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia for rendering; {{citation}} could (not legitimately) have both; use Encyclopedia
−
no_tracking_cats = no_tracking_cats:lower();
+
Periodical_origin = A:ORIGIN ('Encyclopedia');
−
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
+
 
−
for _, v in ipairs( z.error_categories ) do
+
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
−
text = text .. '[[Category:' .. v ..']]';
+
if not utilities.is_set (Chapter) then
−
end
+
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title= for rendering
−
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
+
ScriptChapter = ScriptTitle;
−
text = text .. '[[Category:' .. v ..']]';
+
ScriptChapter_origin = A:ORIGIN('ScriptTitle')
−
end
+
TransChapter = TransTitle;
−
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
+
ChapterURL = URL;
−
text = text .. '[[Category:' .. v ..']]';
+
ChapterURL_origin = URL_origin;
 +
 
 +
ChapterUrlAccess = UrlAccess;
 +
 
 +
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
 +
Chapter = utilities.make_wikilink (TitleLink, Chapter);
 +
end
 +
Title = Periodical;
 +
ChapterFormat = Format;
 +
Periodical = ''; -- redundant so unset
 +
TransTitle = '';
 +
URL = '';
 +
Format = '';
 +
TitleLink = '';
 +
ScriptTitle = '';
 +
end
 +
elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set
 +
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= for rendering
 +
Periodical = ''; -- redundant so unset
 +
end
 
end
 
end
 
end
 
end
−
  −
return text
  −
end
     −
-- This is used by templates such as {{cite book}} to create the actual citation text.
+
-- special case for cite techreport.
−
function z.citation(frame)
+
local ID = A['ID'];
−
local pframe = frame:getParent()
+
if (config.CitationClass == "techreport") then -- special case for cite techreport
−
local validation;
+
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
−
+
if not utilities.is_set (ID) then -- can we use ID for the "number"?
−
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
+
ID = A['Number']; -- yes, use it
−
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ...
+
else -- ID has a value so emit error message
−
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
+
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'number')});
−
validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code
+
end
−
 
+
end
−
else -- otherwise
  −
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...
  −
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
  −
validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code
   
end
 
end
   −
dates = validation.dates; -- imported functions
+
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
−
year_date_check = validation.year_date_check;
+
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
−
 
+
local Conference = A['Conference'];
−
local args = {};
+
local BookTitle = A['BookTitle'];
−
local suggestions = {};
+
local TransTitle_origin = A:ORIGIN ('TransTitle');
−
local error_text, error_state;
+
if 'conference' == config.CitationClass then
−
 
+
if utilities.is_set (BookTitle) then
−
local config = {};
+
Chapter = Title;
−
for k, v in pairs( frame.args ) do
+
Chapter_origin = 'title';
−
config[k] = v;
+
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
−
args[k] = v;  
+
ChapterURL = URL;
−
end
+
ChapterUrlAccess = UrlAccess;
 +
ChapterURL_origin = URL_origin;
 +
URL_origin = '';
 +
ChapterFormat = Format;
 +
TransChapter = TransTitle;
 +
TransChapter_origin = TransTitle_origin;
 +
Title = BookTitle;
 +
Format = '';
 +
-- TitleLink = '';
 +
TransTitle = '';
 +
URL = '';
 +
end
 +
elseif 'speech' ~= config.CitationClass then
 +
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
 +
end
 +
 +
-- CS1/2 mode
 +
local Mode;
 +
if cfg.global_cs1_config_t['Mode'] then -- global setting in {{cs1 config}} overrides local |mode= parameter value; nil when empty or assigned value invalid
 +
Mode = is_valid_parameter_value (cfg.global_cs1_config_t['Mode'], 'cs1 config: mode', cfg.keywords_lists['mode'], ''); -- error messaging 'param' here is a hoax
 +
else
 +
Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
 +
end
 +
 
 +
if cfg.global_cs1_config_t['Mode'] and utilities.is_set (A['Mode']) then -- when template has |mode=<something> which global setting has overridden
 +
utilities.set_message ('maint_overridden_setting'); -- set a maint message
 +
end
   −
for k, v in pairs( pframe.args ) do
+
-- separator character and postscript
−
if v ~= '' then
+
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
−
if not validate( k ) then
+
-- controls capitalization of certain static text
−
error_text = "";
+
local use_lowercase = ( sepc == ',' );
−
if type( k ) ~= 'string' then
  −
-- Exclude empty numbered parameters
  −
if v:match("%S+") ~= nil then
  −
error_text, error_state = set_error( 'text_ignored', {v}, true );
  −
end
  −
elseif validate( k:lower() ) then
  −
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
  −
else
  −
if #suggestions == 0 then
  −
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
  −
end
  −
if suggestions[ k:lower() ] ~= nil then
  −
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
  −
else
  −
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
  −
end
  −
end  
  −
if error_text ~= '' then
  −
table.insert( z.message_tail, {error_text, error_state} );
  −
end
  −
end
  −
args[k] = v;
  −
elseif args[k] ~= nil or (k == 'postscript') then
  −
args[k] = v;
  −
end
  −
end
   
 
−
return citation0( config, args)
+
-- cite map oddities
 +
local Cartography = "";
 +
local Scale = "";
 +
local Sheet = A['Sheet'] or '';
 +
local Sheets = A['Sheets'] or '';
 +
if config.CitationClass == "map" then
 +
if utilities.is_set (Chapter) then --TODO: make a function for this and similar?
 +
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Chapter_origin)}); -- add error message
 +
end
 +
Chapter = A['Map'];
 +
Chapter_origin = A:ORIGIN('Map');
 +
ChapterURL = A['MapURL'];
 +
ChapterURL_origin = A:ORIGIN('MapURL');
 +
TransChapter = A['TransMap'];
 +
ScriptChapter = A['ScriptMap']
 +
ScriptChapter_origin = A:ORIGIN('ScriptMap')
 +
 
 +
ChapterUrlAccess = MapUrlAccess;
 +
ChapterFormat = A['MapFormat'];
 +
 
 +
Cartography = A['Cartography'];
 +
if utilities.is_set ( Cartography ) then
 +
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
 +
end
 +
Scale = A['Scale'];
 +
if utilities.is_set ( Scale ) then
 +
Scale = sepc .. " " .. Scale;
 +
end
 +
end
 +
 
 +
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
 +
local Series = A['Series'];
 +
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
 +
local SeriesLink = A['SeriesLink'];
 +
 
 +
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set
 +
 
 +
local Network = A['Network'];
 +
local Station = A['Station'];
 +
local s, n = {}, {};
 +
-- do common parameters first
 +
if utilities.is_set (Network) then table.insert(n, Network); end
 +
if utilities.is_set (Station) then table.insert(n, Station); end
 +
ID = table.concat(n, sepc .. ' ');
 +
 +
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
 +
local Season = A['Season'];
 +
local SeriesNumber = A['SeriesNumber'];
 +
 
 +
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set TODO: make a function for this and similar?
 +
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'seriesno')}); -- add error message
 +
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
 +
end
 +
-- assemble a table of parts concatenated later into Series
 +
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
 +
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
 +
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
 +
Issue = ''; -- unset because this is not a unique parameter
 +
 +
Chapter = Title; -- promote title parameters to chapter
 +
ScriptChapter = ScriptTitle;
 +
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
 +
ChapterLink = TitleLink; -- alias |episode-link=
 +
TransChapter = TransTitle;
 +
ChapterURL = URL;
 +
ChapterUrlAccess = UrlAccess;
 +
ChapterURL_origin = URL_origin;
 +
ChapterFormat = Format;
 +
 
 +
Title = Series; -- promote series to title
 +
TitleLink = SeriesLink;
 +
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 +
 
 +
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
 +
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
 +
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
 +
Series = utilities.make_wikilink (ChapterLink, Series);
 +
end
 +
URL = ''; -- unset
 +
TransTitle = '';
 +
ScriptTitle = '';
 +
Format = '';
 +
 +
else -- now oddities that are cite serial
 +
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
 +
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
 +
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
 +
Series = utilities.make_wikilink (SeriesLink, Series);
 +
end
 +
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
 +
end
 +
end
 +
-- end of {{cite episode}} stuff
 +
 
 +
-- handle type parameter for those CS1 citations that have default values
 +
local TitleType = A['TitleType'];
 +
local Degree = A['Degree'];
 +
if utilities.in_array (config.CitationClass, {'AV-media-notes', 'document', 'interview', 'mailinglist', 'map', 'podcast', 'pressrelease', 'report', 'speech', 'techreport', 'thesis'}) then
 +
TitleType = set_titletype (config.CitationClass, TitleType);
 +
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis
 +
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
 +
end
 +
end
 +
 
 +
if utilities.is_set (TitleType) then -- if type parameter is specified
 +
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
 +
-- TODO: Hack on TitleType to fix bunched parentheses problem
 +
end
 +
 
 +
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
 +
local Date = A['Date'];
 +
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
 +
local PublicationDate = A['PublicationDate'];
 +
local Year = A['Year'];
 +
 
 +
if not utilities.is_set (Date) then
 +
Date = Year; -- promote Year to Date
 +
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
 +
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
 +
Date = PublicationDate; -- promote PublicationDate to Date
 +
PublicationDate = ''; -- unset, no longer needed
 +
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
 +
else
 +
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
 +
end
 +
else
 +
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
 +
end
 +
 
 +
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
 +
 
 +
--[[
 +
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
 +
we get the date used in the metadata.
 +
 +
Date validation supporting code is in Module:Citation/CS1/Date_validation
 +
]]
 +
 
 +
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
 +
if not utilities.is_set (DF) then
 +
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
 +
end
 +
 
 +
local ArchiveURL;
 +
local ArchiveDate;
 +
local ArchiveFormat = A['ArchiveFormat'];
 +
local archive_url_timestamp; -- timestamp from wayback machine url
 +
 +
ArchiveURL, ArchiveDate, archive_url_timestamp = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
 +
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
 +
 +
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL
 +
 
 +
local AccessDate = A['AccessDate'];
 +
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
 +
local DoiBroken = A['DoiBroken'];
 +
local Embargo = A['Embargo'];
 +
local anchor_year; -- used in the CITEREF identifier
 +
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
 +
local error_message = '';
 +
-- AirDate has been promoted to Date so not necessary to check it
 +
local date_parameters_list = {
 +
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
 +
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
 +
['date'] = {val = Date, name = Date_origin},
 +
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
 +
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')},
 +
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')},
 +
['year'] = {val = Year, name = A:ORIGIN ('Year')},
 +
};
 +
 
 +
local error_list = {};
 +
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
 +
 
 +
-- start temporary Julian / Gregorian calendar uncertainty categorization
 +
if COinS_date.inter_cal_cat then
 +
utilities.add_prop_cat ('jul-greg-uncertainty');
 +
end
 +
-- end temporary Julian / Gregorian calendar uncertainty categorization
 +
 
 +
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
 +
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
 +
end
 +
 +
if 0 == #error_list then -- error free dates only; 0 when error_list is empty
 +
local modified = false; -- flag
 +
 +
if utilities.is_set (DF) then -- if we need to reformat dates
 +
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate
 +
end
 +
 
 +
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
 +
modified = true;
 +
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
 +
end
 +
 +
-- for those wikis that can and want to have English date names translated to the local language; not supported at en.wiki
 +
if cfg.date_name_auto_xlate_enable and validation.date_name_xlate (date_parameters_list, cfg.date_digit_auto_xlate_enable ) then
 +
utilities.set_message ('maint_date_auto_xlated'); -- add maint cat
 +
modified = true;
 +
end
 +
 
 +
if modified then -- if the date_parameters_list values were modified
 +
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
 +
ArchiveDate = date_parameters_list['archive-date'].val;
 +
Date = date_parameters_list['date'].val;
 +
DoiBroken = date_parameters_list['doi-broken-date'].val;
 +
PublicationDate = date_parameters_list['publication-date'].val;
 +
end
 +
 
 +
if archive_url_timestamp and utilities.is_set (ArchiveDate) then
 +
validation.archive_date_check (ArchiveDate, archive_url_timestamp, DF); -- does YYYYMMDD in archive_url_timestamp match date in ArchiveDate
 +
end
 +
else
 +
utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}); -- add this error message
 +
end
 +
end -- end of do
 +
 
 +
if utilities.in_array (config.CitationClass, {'book', 'encyclopaedia'}) or -- {{cite book}}, {{cite encyclopedia}}; TODO: {{cite conference}} and others?
 +
('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) or -- {{citation}} as an encylopedia citation
 +
('citation' == config.CitationClass and not utilities.is_set (Periodical)) then -- {{citation}} as a book citation
 +
if utilities.is_set (PublicationPlace) then
 +
if not utilities.is_set (PublisherName) then
 +
local date = COinS_date.rftdate and tonumber (COinS_date.rftdate:match ('%d%d%d%d')); -- get year portion of COinS date (because in Arabic numerals); convert string to number
 +
if date and (1850 <= date) then -- location has no publisher; if date is 1850 or later
 +
utilities.set_message ('maint_location_no_publisher'); -- add maint cat
 +
end
 +
else -- PublisherName has a value
 +
if cfg.keywords_xlate['none'] == PublisherName then -- if that value is 'none' (only for book and encyclopedia citations)
 +
PublisherName = ''; -- unset
 +
end
 +
end
 +
end
 +
end
 +
 
 +
local ID_list = {}; -- sequence table of rendered identifiers
 +
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
 +
local Class = A['Class']; -- arxiv class identifier
 +
 +
local ID_support = {
 +
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
 +
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
 +
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')},
 +
}
 +
 
 +
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
 +
 
 +
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite medrxiv}}, {{cite ssrn}}, before generation of COinS data.
 +
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list_t) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv=, |citeseerx=, |medrxiv=, |ssrn= required for their templates
 +
if not (args[cfg.id_handlers[config.CitationClass:upper()].parameters[1]] or -- can't use ID_list_coins k/v table here because invalid parameters omitted
 +
args[cfg.id_handlers[config.CitationClass:upper()].parameters[2]]) then -- which causes unexpected parameter missing error message
 +
utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message
 +
end
 +
 
 +
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['medrxiv'] = 'medRxiv', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
 +
end
 +
 
 +
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
 +
 
 +
if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead
 +
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
 +
if identifiers.auto_link_urls[auto_select] then -- manual selection
 +
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
 +
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
 +
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
 +
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
 +
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
 +
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
 +
URL = identifiers.auto_link_urls['doi'];
 +
URL_origin = cfg.id_handlers['DOI'].parameters[1];
 +
end
 +
end
 +
 
 +
if utilities.is_set (URL) then -- set when using an identifier-created URL
 +
if utilities.is_set (AccessDate) then -- |access-date= requires |url=; identifier-created URL is not |url=
 +
utilities.set_message ('err_accessdate_missing_url'); -- add an error message
 +
AccessDate = ''; -- unset
 +
end
 +
 
 +
if utilities.is_set (ArchiveURL) then -- |archive-url= requires |url=; identifier-created URL is not |url=
 +
utilities.set_message ('err_archive_missing_url'); -- add an error message
 +
ArchiveURL = ''; -- unset
 +
end
 +
end
 +
end
 +
 
 +
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
 +
-- Test if citation has no title
 +
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
 +
utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'});
 +
end
 +
 
 +
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
 +
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
 +
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
 +
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
 +
Title = ''; -- set title to empty string
 +
utilities.set_message ('maint_untitled'); -- add maint cat
 +
end
 +
 
 +
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
 +
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
 +
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
 +
-- is the article title, and Chapter is a section within the article.  So, we remap
 +
 +
local coins_chapter = Chapter; -- default assuming that remapping not required
 +
local coins_title = Title; -- et tu
 +
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
 +
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then
 +
coins_chapter = Title; -- remap
 +
coins_title = Periodical;
 +
end
 +
end
 +
local coins_author = a; -- default for coins rft.au
 +
if 0 < #c then -- but if contributor list
 +
coins_author = c; -- use that instead
 +
end
 +
 +
-- this is the function call to COinS()
 +
local OCinSoutput = metadata.COinS({
 +
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
 +
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
 +
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic / accept-as-written markup
 +
['Degree'] = Degree; -- cite thesis only
 +
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic / accept-as-written markup
 +
['PublicationPlace'] = PublicationPlace,
 +
['Date'] = COinS_date.rftdate, -- COinS_date.* has correctly formatted date values if Date is valid;
 +
['Season'] = COinS_date.rftssn,
 +
['Quarter'] = COinS_date.rftquarter,
 +
['Chron'] =  COinS_date.rftchron,
 +
['Series'] = Series,
 +
['Volume'] = Volume,
 +
['Issue'] = Issue,
 +
['ArticleNumber'] = ArticleNumber,
 +
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links
 +
['Edition'] = Edition,
 +
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
 +
['URL'] = first_set ({ChapterURL, URL}, 2),
 +
['Authors'] = coins_author,
 +
['ID_list'] = ID_list_coins,
 +
['RawPage'] = this_page.prefixedText,
 +
}, config.CitationClass);
 +
 
 +
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite medrxiv}}, and {{cite ssrn}} AFTER generation of COinS data.
 +
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list_t) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, medRxiv, or ssrn now unset so it isn't displayed
 +
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
 +
end
 +
 
 +
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
 +
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
 +
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
 +
end
 +
 
 +
local Editors;
 +
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
 +
local Contributors; -- assembled contributors name list
 +
local contributor_etal;
 +
local Translators; -- assembled translators name list
 +
local translator_etal;
 +
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
 +
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 +
local Interviewers;
 +
local interviewers_list = {};
 +
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
 +
local interviewer_etal;
 +
 +
-- Now perform various field substitutions.
 +
-- We also add leading spaces and surrounding markup and punctuation to the
 +
-- various parts of the citation, but only when they are non-nil.
 +
do
 +
local last_first_list;
 +
local control = {
 +
format = NameListStyle, -- empty string, '&', 'amp', 'and', or 'vanc'
 +
maximum = nil, -- as if display-authors or display-editors not set
 +
mode = Mode
 +
};
 +
 
 +
do -- do editor name list first because the now unsupported coauthors used to modify control table
 +
local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayEditors'], A['DisplayEditors'], A:ORIGIN ('DisplayEditors'), #e);
 +
control.maximum, editor_etal = get_display_names (display_names, #e, 'editors', editor_etal, param);
 +
 
 +
Editors, EditorCount = list_people (control, e, editor_etal);
 +
 
 +
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
 +
EditorCount = 2; -- spoof to display (eds.) annotation
 +
end
 +
end
 +
do -- now do interviewers
 +
local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayInterviewers'], A['DisplayInterviewers'], A:ORIGIN ('DisplayInterviewers'), #interviewers_list);
 +
control.maximum, interviewer_etal = get_display_names (display_names, #interviewers_list, 'interviewers', interviewer_etal, param);
 +
 
 +
Interviewers = list_people (control, interviewers_list, interviewer_etal);
 +
end
 +
do -- now do translators
 +
local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayTranslators'], A['DisplayTranslators'], A:ORIGIN ('DisplayTranslators'), #t);
 +
control.maximum, translator_etal = get_display_names (display_names, #t, 'translators', translator_etal, param);
 +
 
 +
Translators = list_people (control, t, translator_etal);
 +
end
 +
do -- now do contributors
 +
local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayContributors'], A['DisplayContributors'], A:ORIGIN ('DisplayContributors'), #c);
 +
control.maximum, contributor_etal = get_display_names (display_names, #c, 'contributors', contributor_etal, param);
 +
 
 +
Contributors = list_people (control, c, contributor_etal);
 +
end
 +
do -- now do authors
 +
local display_names, param = display_names_select (cfg.global_cs1_config_t['DisplayAuthors'], A['DisplayAuthors'], A:ORIGIN ('DisplayAuthors'), #a, author_etal);
 +
control.maximum, author_etal = get_display_names (display_names, #a, 'authors', author_etal, param);
 +
 
 +
last_first_list = list_people (control, a, author_etal);
 +
 
 +
if utilities.is_set (Authors) then
 +
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
 +
if author_etal then
 +
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
 +
end
 +
else
 +
Authors = last_first_list; -- either an author name list or an empty string
 +
end
 +
end -- end of do
 +
 +
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
 +
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
 +
end
 +
 
 +
end
 +
 
 +
local ConferenceFormat = A['ConferenceFormat'];
 +
local ConferenceURL = A['ConferenceURL'];
 +
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
 +
Format = style_format (Format, URL, 'format', 'url');
 +
 
 +
-- special case for chapter format so no error message or cat when chapter not supported
 +
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or
 +
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
 +
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
 +
end
 +
 
 +
if not utilities.is_set (URL) then
 +
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
 +
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
 +
utilities.set_message ('err_cite_web_url');
 +
end
 +
 +
-- do we have |accessdate= without either |url= or |chapter-url=?
 +
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
 +
utilities.set_message ('err_accessdate_missing_url');
 +
AccessDate = '';
 +
end
 +
end
 +
 
 +
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
 +
local OriginalURL
 +
local OriginalURL_origin
 +
local OriginalFormat
 +
local OriginalAccess;
 +
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
 +
if utilities.is_set ( ArchiveURL ) then
 +
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it
 +
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
 +
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
 +
OriginalFormat = ChapterFormat; -- and original |chapter-format=
 +
 
 +
if 'live' ~= UrlStatus then
 +
ChapterURL = ArchiveURL -- swap-in the archive's URL
 +
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages
 +
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
 +
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs
 +
end
 +
elseif utilities.is_set (URL) then
 +
OriginalURL = URL; -- save copy of original source URL
 +
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
 +
OriginalFormat = Format; -- and original |format=
 +
OriginalAccess = UrlAccess;
 +
 
 +
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
 +
URL = ArchiveURL -- swap-in the archive's URL
 +
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages
 +
Format = ArchiveFormat or ''; -- swap in archive's format
 +
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs
 +
end
 +
end
 +
elseif utilities.is_set (UrlStatus) then -- if |url-status= is set when |archive-url= is not set
 +
utilities.set_message ('maint_url_status'); -- add maint cat
 +
end
 +
 
 +
if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
 +
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
 +
local chap_param;
 +
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
 +
chap_param = A:ORIGIN ('Chapter')
 +
elseif utilities.is_set (TransChapter) then
 +
chap_param = A:ORIGIN ('TransChapter')
 +
elseif utilities.is_set (ChapterURL) then
 +
chap_param = A:ORIGIN ('ChapterURL')
 +
elseif utilities.is_set (ScriptChapter) then
 +
chap_param = ScriptChapter_origin;
 +
else utilities.is_set (ChapterFormat)
 +
chap_param = A:ORIGIN ('ChapterFormat')
 +
end
 +
 
 +
if utilities.is_set (chap_param) then -- if we found one
 +
utilities.set_message ('err_chapter_ignored', {chap_param}); -- add error message
 +
Chapter = ''; -- and set them to empty string to be safe with concatenation
 +
TransChapter = '';
 +
ChapterURL = '';
 +
ScriptChapter = '';
 +
ChapterFormat = '';
 +
end
 +
else -- otherwise, format chapter / article title
 +
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
 +
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
 +
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
 +
no_quotes = true; -- then render it unquoted
 +
end
 +
end
 +
 
 +
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
 +
if utilities.is_set (Chapter) then
 +
Chapter = Chapter .. ChapterFormat ;
 +
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
 +
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
 +
end
 +
Chapter = Chapter .. sepc .. ' ';
 +
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
 +
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
 +
end
 +
end
 +
 
 +
-- Format main title
 +
local plain_title = false;
 +
local accept_title;
 +
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
 +
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
 +
Title = cfg.messages['notitle']; -- replace by predefined "No title" message
 +
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
 +
ScriptTitle = ''; -- just mute for now
 +
TransTitle = ''; -- just mute for now
 +
plain_title = true; -- suppress text decoration for descriptive title
 +
utilities.set_message ('maint_untitled'); -- add maint cat
 +
end
 +
 
 +
if not accept_title then -- <Title> not wrapped in accept-as-written markup
 +
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title=
 +
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
 +
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
 +
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
 +
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
 +
end
 +
 
 +
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
 +
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
 +
end
 +
 
 +
if is_generic ('generic_titles', Title) then
 +
utilities.set_message ('err_generic_title'); -- set an error message
 +
end
 +
end
 +
 
 +
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'document', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'medrxiv', 'ssrn'}) or
 +
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
 +
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article
 +
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks
 +
Title = utilities.wrap_style ('quoted-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
 +
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
 +
else
 +
Title = utilities.wrap_style ('italic-title', Title);
 +
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
 +
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
 +
end
 +
 
 +
if utilities.is_set (TransTitle) then
 +
if utilities.is_set (Title) then
 +
TransTitle = " " .. TransTitle;
 +
else
 +
utilities.set_message ('err_trans_missing_title', {'title'});
 +
end
 +
end
 +
 
 +
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
 +
if utilities.is_set (TitleLink) and utilities.is_set (URL) then
 +
utilities.set_message ('err_wikilink_in_url'); -- set an error message because we can't have both
 +
TitleLink = ''; -- unset
 +
end
 +
 +
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
 +
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. Format;
 +
URL = ''; -- unset these because no longer needed
 +
Format = "";
 +
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then
 +
local ws_url;
 +
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
 +
if ws_url then
 +
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
 +
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
 +
Title = Title .. TransTitle;
 +
else
 +
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle;
 +
end
 +
else
 +
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
 +
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label
 +
if ws_url then
 +
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
 +
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
 +
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
 +
Title = Title .. TransTitle;
 +
else
 +
Title = Title .. TransTitle;
 +
end
 +
end
 +
else
 +
Title = TransTitle;
 +
end
 +
 
 +
if utilities.is_set (Place) then
 +
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
 +
end
 +
 
 +
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
 +
if utilities.is_set (Conference) then
 +
if utilities.is_set (ConferenceURL) then
 +
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
 +
end
 +
Conference = sepc .. " " .. Conference .. ConferenceFormat;
 +
elseif utilities.is_set (ConferenceURL) then
 +
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
 +
end
 +
 
 +
local Position = '';
 +
if not utilities.is_set (Position) then
 +
local Minutes = A['Minutes'];
 +
local Time = A['Time'];
 +
 
 +
if utilities.is_set (Minutes) then
 +
if utilities.is_set (Time) then --TODO: make a function for this and similar?
 +
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'time')});
 +
end
 +
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
 +
else
 +
if utilities.is_set (Time) then
 +
local TimeCaption = A['TimeCaption']
 +
if not utilities.is_set (TimeCaption) then
 +
TimeCaption = cfg.messages['event'];
 +
if sepc ~= '.' then
 +
TimeCaption = TimeCaption:lower();
 +
end
 +
end
 +
Position = " " .. TimeCaption .. " " .. Time;
 +
end
 +
end
 +
else
 +
Position = " " .. Position;
 +
At = '';
 +
end
 +
 
 +
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
 +
 
 +
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
 +
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
 +
if config.CitationClass == 'map' then
 +
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
 +
local Inset = A['Inset'];
 +
 +
if utilities.is_set ( Inset ) then
 +
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
 +
end
 +
 
 +
if utilities.is_set ( Sections ) then
 +
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
 +
elseif utilities.is_set ( Section ) then
 +
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
 +
end
 +
At = At .. Inset .. Section;
 +
end
 +
 
 +
local Others = A['Others'];
 +
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
 +
if config.CitationClass == "AV-media-notes"
 +
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now
 +
utilities.set_message ('maint_others_avm')
 +
else
 +
utilities.set_message ('maint_others');
 +
end
 +
end
 +
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
 +
 +
if utilities.is_set (Translators) then
 +
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
 +
end
 +
if utilities.is_set (Interviewers) then
 +
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
 +
end
 +
 +
local TitleNote = A['TitleNote'];
 +
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
 +
if utilities.is_set (Edition) then
 +
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
 +
utilities.set_message ('err_extra_text_edition'); -- add error message
 +
end
 +
Edition = " " .. wrap_msg ('edition', Edition);
 +
else
 +
Edition = '';
 +
end
 +
 
 +
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
 +
local Agency = A['Agency'];
 +
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
 +
Volume = format_volume_issue (Volume, Issue, ArticleNumber, config.CitationClass, Periodical_origin, sepc, use_lowercase);
 +
 
 +
if utilities.is_set (AccessDate) then
 +
local retrv_text = " " .. cfg.messages['retrieved']
 +
 
 +
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
 +
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
 +
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text
 +
 
 +
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
 +
end
 +
 +
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
 +
 +
local Docket = A['Docket'];
 +
  if "thesis" == config.CitationClass and utilities.is_set (Docket) then
 +
ID = sepc .. " Docket " .. Docket .. ID;
 +
end
 +
  if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
 +
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
 +
end
 +
 
 +
if utilities.is_set (URL) then
 +
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
 +
end
 +
 
 +
local Quote = A['Quote'];
 +
local TransQuote = A['TransQuote'];
 +
local ScriptQuote = A['ScriptQuote'];
 +
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
 +
 
 +
if utilities.is_set (Quote) then
 +
if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks
 +
Quote = Quote:sub(2, -2); -- strip them off
 +
end
 +
end
 +
 +
Quote = kern_quotes (Quote); -- kern if needed
 +
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
 +
 +
if utilities.is_set (ScriptQuote) then
 +
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
 +
end
 +
 
 +
if utilities.is_set (TransQuote) then
 +
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
 +
TransQuote = TransQuote:sub(2, -2); -- strip them off
 +
end
 +
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
 +
end
 +
 
 +
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
 +
local quote_prefix = '';
 +
if utilities.is_set (QuotePage) then
 +
extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc.
 +
if not NoPP then
 +
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
 +
else
 +
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
 +
end
 +
elseif utilities.is_set (QuotePages) then
 +
extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc.
 +
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page
 +
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', '';
 +
elseif not NoPP then
 +
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', '';
 +
else
 +
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', '';
 +
end
 +
end
 +
                       
 +
Quote = quote_prefix .. ": " .. Quote;
 +
else
 +
Quote = sepc .. " " .. Quote;
 +
end
 +
 
 +
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
 +
end
 +
 +
-- We check length of PostScript here because it will have been nuked by
 +
-- the quote parameters. We'd otherwise emit a message even if there wasn't
 +
-- a displayed postscript.
 +
-- TODO: Should the max size (1) be configurable?
 +
-- TODO: Should we check a specific pattern?
 +
if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then
 +
utilities.set_message ('maint_postscript')
 +
end
 +
 +
local Archived;
 +
if utilities.is_set (ArchiveURL) then
 +
if not utilities.is_set (ArchiveDate) then -- ArchiveURL set but ArchiveDate not set
 +
utilities.set_message ('err_archive_missing_date'); -- emit an error message
 +
ArchiveURL = ''; -- empty string for concatenation
 +
ArchiveDate = ''; -- empty string for concatenation
 +
end
 +
else
 +
if utilities.is_set (ArchiveDate) then -- ArchiveURL not set but ArchiveDate is set
 +
utilities.set_message ('err_archive_date_missing_url'); -- emit an error message
 +
ArchiveURL = ''; -- empty string for concatenation
 +
ArchiveDate = ''; -- empty string for concatenation
 +
end
 +
end
 +
 
 +
if utilities.is_set (ArchiveURL) then
 +
local arch_text;
 +
if "live" == UrlStatus then
 +
arch_text = cfg.messages['archived'];
 +
if sepc ~= "." then arch_text = arch_text:lower() end
 +
if utilities.is_set (ArchiveDate) then
 +
Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'],
 +
{external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } );
 +
else
 +
Archived = '';
 +
end
 +
if not utilities.is_set (OriginalURL) then
 +
utilities.set_message ('err_archive_missing_url');
 +
Archived = ''; -- empty string for concatenation
 +
end
 +
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
 +
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
 +
arch_text = cfg.messages['archived-unfit'];
 +
if sepc ~= "." then arch_text = arch_text:lower() end
 +
Archived = sepc .. ' ' .. arch_text .. ArchiveDate; -- format already styled
 +
if 'bot: unknown' == UrlStatus then
 +
utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added
 +
else
 +
utilities.set_message ('maint_unfit'); -- and add a category if not already added
 +
end
 +
else -- UrlStatus is empty, 'dead'
 +
arch_text = cfg.messages['archived-dead'];
 +
if sepc ~= "." then arch_text = arch_text:lower() end
 +
if utilities.is_set (ArchiveDate) then
 +
Archived = sepc .. " " .. utilities.substitute ( arch_text,
 +
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
 +
else
 +
Archived = ''; -- unset for concatenation
 +
end
 +
end
 +
else -- OriginalUrl not set
 +
utilities.set_message ('err_archive_missing_url');
 +
Archived = ''; -- empty string for concatenation
 +
end
 +
elseif utilities.is_set (ArchiveFormat) then
 +
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
 +
else
 +
Archived = '';
 +
end
 +
 +
local TranscriptURL = A['TranscriptURL']
 +
local TranscriptFormat = A['TranscriptFormat'];
 +
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
 +
local Transcript = A['Transcript'];
 +
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
 +
if utilities.is_set (Transcript) then
 +
if utilities.is_set (TranscriptURL) then
 +
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
 +
end
 +
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
 +
elseif utilities.is_set (TranscriptURL) then
 +
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
 +
end
 +
 
 +
local Publisher;
 +
if utilities.is_set (PublicationDate) then
 +
PublicationDate = wrap_msg ('published', PublicationDate);
 +
end
 +
if utilities.is_set (PublisherName) then
 +
if utilities.is_set (PublicationPlace) then
 +
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
 +
else
 +
Publisher = sepc .. " " .. PublisherName .. PublicationDate; 
 +
end
 +
elseif utilities.is_set (PublicationPlace) then
 +
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
 +
else
 +
Publisher = PublicationDate;
 +
end
 +
 +
-- Several of the above rely upon detecting this as nil, so do it last.
 +
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
 +
if utilities.is_set (Title) or utilities.is_set (TitleNote) then
 +
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
 +
else
 +
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
 +
end
 +
end
 +
 +
local Language = A['Language'];
 +
if utilities.is_set (Language) then
 +
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
 +
else
 +
Language=''; -- language not specified so make sure this is an empty string;
 +
--[[ TODO: need to extract the wrap_msg from language_parameter
 +
so that we can solve parentheses bunching problem with Format/Language/TitleType
 +
]]
 +
end
 +
 
 +
--[[
 +
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
 +
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
 +
]]
 +
if "speech" == config.CitationClass then -- cite speech only
 +
TitleNote = TitleType; -- move TitleType to TitleNote so that it renders ahead of |event=
 +
TitleType = ''; -- and unset
 +
 
 +
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
 +
if utilities.is_set (Conference) then -- and if |event= is set
 +
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
 +
end
 +
end
 +
end
 +
 
 +
-- Piece all bits together at last.  Here, all should be non-nil.
 +
-- We build things this way because it is more efficient in LUA
 +
-- not to keep reassigning to the same string variable over and over.
 +
 
 +
local tcommon;
 +
local tcommon2; -- used for book cite when |contributor= is set
 +
 +
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
 +
if not (utilities.is_set (Authors) or utilities.is_set (Editors)) then
 +
Others = Others:gsub ('^' .. sepc .. ' ', ''); -- when no authors and no editors, strip leading sepc and space
 +
end
 +
if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
 +
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
 +
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
 +
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
 +
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
 +
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 +
else
 +
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 +
end
 +
 
 +
elseif 'map' == config.CitationClass then -- special cases for cite map
 +
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
 +
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 +
elseif utilities.is_set (Periodical) then -- map in a periodical
 +
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
 +
else -- a sheet or stand-alone map
 +
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
 +
end
 +
 +
elseif 'episode' == config.CitationClass then -- special case for cite episode
 +
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
 +
 
 +
else -- all other CS1 templates
 +
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
 +
Volume, Others, Edition, Publisher, Agency}, sepc );
 +
end
 +
 +
if #ID_list > 0 then
 +
ID_list = safe_join( { sepc .. " ",  table.concat( ID_list, sepc .. " " ), ID }, sepc );
 +
else
 +
ID_list = ID;
 +
end
 +
 +
local Via = A['Via'];
 +
Via = utilities.is_set (Via) and  wrap_msg ('via', Via) or '';
 +
local idcommon;
 +
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
 +
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Quote }, sepc );
 +
else
 +
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Quote }, sepc );
 +
end
 +
 +
local text;
 +
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 +
 
 +
local OrigDate = A['OrigDate'];
 +
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
 +
if utilities.is_set (Date) then
 +
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
 +
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
 +
else -- neither of authors and editors set
 +
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
 +
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
 +
else
 +
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
 +
end
 +
end
 +
end
 +
if utilities.is_set (Authors) then
 +
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
 +
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
 +
end
 +
if utilities.is_set (Editors) then
 +
local in_text = '';
 +
local post_text = '';
 +
if utilities.is_set (Chapter) and 0 == #c then
 +
in_text = cfg.messages['in'] .. ' ';
 +
if (sepc ~= '.') then
 +
in_text = in_text:lower(); -- lowercase for cs2
 +
end
 +
end
 +
if EditorCount <= 1 then
 +
post_text = ' (' .. cfg.messages['editor'] .. ')'; -- be consistent with no-author, no-date case
 +
else
 +
post_text = ' (' .. cfg.messages['editors'] .. ')';
 +
end
 +
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
 +
end
 +
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
 +
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
 +
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
 +
Authors = by_text .. Authors; -- author follows title so tweak it here
 +
if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated
 +
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
 +
end
 +
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
 +
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
 +
end
 +
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
 +
else
 +
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
 +
end
 +
elseif utilities.is_set (Editors) then
 +
if utilities.is_set (Date) then
 +
if EditorCount <= 1 then
 +
Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editor'];
 +
else
 +
Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editors'];
 +
end
 +
else
 +
if EditorCount <= 1 then
 +
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
 +
else
 +
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
 +
end
 +
end
 +
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
 +
else
 +
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
 +
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
 +
else
 +
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
 +
end
 +
end
 +
 +
if utilities.is_set (PostScript) and PostScript ~= sepc then
 +
text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc.
 +
text = text:sub(1, -sepc:len() - 1);
 +
end
 +
 +
text = safe_join( {text, PostScript}, sepc );
 +
 
 +
-- Now enclose the whole thing in a <cite> element
 +
local options_t = {};
 +
options_t.class = cite_class_attribute_make (config.CitationClass, Mode);
 +
 
 +
local Ref = is_valid_parameter_value (A['Ref'], A:ORIGIN('Ref'), cfg.keywords_lists['ref'], nil, true); -- nil when |ref=harv; A['Ref'] else
 +
 
 +
if 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then
 +
local namelist_t = {}; -- 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_t = c; -- select it
 +
elseif #a > 0 then -- or an author list
 +
namelist_t = a;
 +
elseif #e > 0 then -- or an editor list
 +
namelist_t = e;
 +
end
 +
local citeref_id;
 +
if #namelist_t > 0 then -- if there are names in namelist_t
 +
citeref_id = make_citeref_id (namelist_t, year); -- go make the CITEREF anchor
 +
if mw.uri.anchorEncode (citeref_id) == ((Ref and mw.uri.anchorEncode (Ref)) or '') then -- Ref may already be encoded (by {{sfnref}}) so citeref_id must be encoded before comparison
 +
utilities.set_message ('maint_ref_duplicates_default');
 +
end
 +
else
 +
citeref_id = ''; -- unset
 +
end
 +
options_t.id = Ref or citeref_id;
 +
end
 +
 
 +
if string.len (text:gsub('%b<>', '')) <= 2 then -- remove html and html-like tags; then get length of what remains;
 +
z.error_cats_t = {}; -- blank the categories list
 +
z.error_msgs_t = {}; -- blank the error messages list
 +
OCinSoutput = nil; -- blank the metadata string
 +
text = ''; -- blank the the citation
 +
utilities.set_message ('err_empty_citation'); -- set empty citation message and category
 +
end
 +
 +
local render_t = {}; -- here we collect the final bits for concatenation into the rendered citation
 +
 
 +
if utilities.is_set (options_t.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
 +
table.insert (render_t, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options_t.id), mw.text.nowiki(options_t.class), text})); -- when |ref= is set or when there is a namelist
 +
else
 +
table.insert (render_t, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options_t.class), text})); -- when |ref=none or when namelist_t empty and |ref= is missing or is empty
 +
end
 +
 
 +
if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span
 +
table.insert (render_t, utilities.substitute (cfg.presentation['ocins'], OCinSoutput)); -- format and append metadata to the citation
 +
end
 +
 
 +
local template_name = ('citation' == config.CitationClass) and 'citation' or 'cite ' .. (cfg.citation_class_map_t[config.CitationClass] or config.CitationClass);
 +
local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]';
 +
local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: ';
 +
 
 +
if 0 ~= #z.error_msgs_t then
 +
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, template_link));
 +
 
 +
table.insert (render_t, ' '); -- insert a space between citation and its error messages
 +
table.sort (z.error_msgs_t); -- sort the error messages list; sorting includes wrapping <span> and <code> tags; hidden-error sorts ahead of visible-error
 +
 
 +
local hidden = true; -- presume that the only error messages emited by this template are hidden
 +
for _, v in ipairs (z.error_msgs_t) do -- spin through the list of error messages
 +
if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name
 +
hidden = false; -- found one; so don't hide the error message prefix
 +
break; -- and done because no need to look further
 +
end
 +
end
 +
 
 +
z.error_msgs_t[1] = table.concat ({utilities.error_comment (msg_prefix, hidden), z.error_msgs_t[1]}); -- add error message prefix to first error message to prevent extraneous punctuation
 +
table.insert (render_t, table.concat (z.error_msgs_t, '; ')); -- make a big string of error messages and add it to the rendering
 +
end
 +
 
 +
if 0 ~= #z.maint_cats_t then
 +
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, template_link));
 +
 
 +
table.sort (z.maint_cats_t); -- sort the maintenance messages list
 +
 
 +
local maint_msgs_t = {}; -- here we collect all of the maint messages
 +
 
 +
if 0 == #z.error_msgs_t then -- if no error messages
 +
table.insert (maint_msgs_t, msg_prefix); -- insert message prefix in maint message livery
 +
end
 +
 +
for _, v in ipairs( z.maint_cats_t ) do -- append maintenance categories
 +
table.insert (maint_msgs_t, -- assemble new maint message and add it to the maint_msgs_t table
 +
table.concat ({v, ' (', utilities.substitute (cfg.messages[':cat wikilink'], v), ')'})
 +
);
 +
end
 +
table.insert (render_t, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs_t, ' '))); -- wrap the group of maint messages with proper presentation and save
 +
end
 +
 
 +
if not no_tracking_cats then
 +
local sort_key;
 +
local cat_wikilink = 'cat wikilink';
 +
if cfg.enable_sort_keys then -- when namespace sort keys enabled
 +
local namespace_number = mw.title.getCurrentTitle().namespace; -- get namespace number for this wikitext
 +
sort_key = (0 ~= namespace_number and (cfg.name_space_sort_keys[namespace_number] or cfg.name_space_sort_keys.other)) or nil; -- get sort key character; nil for mainspace
 +
cat_wikilink = (not sort_key and 'cat wikilink') or 'cat wikilink sk'; -- make <cfg.messages> key
 +
end
 +
 
 +
for _, v in ipairs (z.error_cats_t) do -- append error categories
 +
table.insert (render_t, utilities.substitute (cfg.messages[cat_wikilink], {v, sort_key}));
 +
end
 +
for _, v in ipairs (z.maint_cats_t) do -- append maintenance categories
 +
table.insert (render_t, utilities.substitute (cfg.messages[cat_wikilink], {v, sort_key}));
 +
end
 +
 
 +
for _, v in ipairs (z.prop_cats_t) do -- append properties categories
 +
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); -- no sort keys
 +
end
 +
end
 +
 
 +
return table.concat (render_t); -- make a big string and done
 
end
 
end
   −
return z
+
 
 +
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
 +
 
 +
Looks for a parameter's name in one of several whitelists.
 +
 
 +
Parameters in the whitelist can have three values:
 +
true - active, supported parameters
 +
false - deprecated, supported parameters
 +
nil - unsupported parameters
 +
 +
]]
 +
 
 +
local function validate (name, cite_class, empty)
 +
local name = tostring (name);
 +
local enum_name; -- parameter name with enumerator (if any) replaced with '#'
 +
local state;
 +
local function state_test (state, name) -- local function to do testing of state values
 +
if true == state then return true; end -- valid actively supported parameter
 +
if false == state then
 +
if empty then return nil; end -- empty deprecated parameters are treated as unknowns
 +
deprecated_parameter (name); -- parameter is deprecated but still supported
 +
return true;
 +
end
 +
if 'tracked' == state then
 +
local base_name = name:gsub ('%d', ''); -- strip enumerators from parameter names that have them to get the base name
 +
utilities.add_prop_cat ('tracked-param', {base_name}, base_name); -- add a properties category; <base_name> modifies <key>
 +
return true;
 +
end
 +
return nil;
 +
end
 +
 
 +
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
 +
return nil;
 +
end
 +
-- replace wnumerator digit(s) with # (|last25= becomes |last#=) (mw.ustring because non-Western 'local' digits)
 +
enum_name = mw.ustring.gsub (name, '%d+$', '#'); -- where enumerator is last charaters in parameter name (these to protect |s2cid=)
 +
enum_name = mw.ustring.gsub (enum_name, '%d+([%-l])', '#%1'); -- where enumerator is in the middle of the parameter name; |author#link= is the oddity
 +
 
 +
if 'document' == cite_class then -- special case for {{cite document}}
 +
state = whitelist.document_parameters_t[enum_name]; -- this list holds enumerated and nonenumerated parameters
 +
if true == state_test (state, name) then return true; end
 +
 +
return false;
 +
end
 +
 
 +
if utilities.in_array (cite_class, whitelist.preprint_template_list_t) then -- limited parameter sets allowed for these templates
 +
state = whitelist.limited_parameters_t[enum_name]; -- this list holds enumerated and nonenumerated parameters
 +
if true == state_test (state, name) then return true; end
 +
 
 +
state = whitelist.preprint_arguments_t[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
 +
if true == state_test (state, name) then return true; end
 +
 
 +
return false; -- not supported because not found or name is set to nil
 +
end -- end limited parameter-set templates
 +
 
 +
if utilities.in_array (cite_class, whitelist.unique_param_template_list_t) then -- template-specific parameters for templates that accept parameters from the basic argument list
 +
state = whitelist.unique_arguments_t[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
 +
if true == state_test (state, name) then return true; end
 +
end -- if here, fall into general validation
 +
 
 +
state = whitelist.common_parameters_t[enum_name]; -- all other templates; all normal parameters allowed; this list holds enumerated and nonenumerated parameters
 +
if true == state_test (state, name) then return true; end
 +
 
 +
return false; -- not supported because not found or name is set to nil
 +
end
 +
 
 +
 
 +
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
 +
 
 +
check <value> for inter-language interwiki-link markup.  <prefix> must be a MediaWiki-recognized language
 +
code.  when these values have the form (without leading colon):
 +
[[<prefix>:link|label]] return label as plain-text
 +
[[<prefix>:link]] return <prefix>:link as plain-text
 +
 
 +
return value as is else
 +
 
 +
]=]
 +
 
 +
local function inter_wiki_check (parameter, value)
 +
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
 +
local _;
 +
 +
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
 +
utilities.set_message ('err_bad_paramlink', parameter); -- emit an error message
 +
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
 +
end
 +
return value;
 +
end
 +
 
 +
 
 +
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
 +
 
 +
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
 +
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
 +
parameter that is missing its pipe.  There are two tests made:
 +
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
 +
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
 +
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc.  To prevent false positives XML/HTML
 +
tags are removed before the search.
 +
 
 +
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 +
 
 +
]]
 +
 
 +
local function missing_pipe_check (parameter, value)
 +
local capture;
 +
value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc.
 +
 
 +
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
 +
if capture and validate (capture) then -- if the capture is a valid parameter name
 +
utilities.set_message ('err_missing_pipe', parameter);
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
 +
 
 +
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
 +
 
 +
]]
 +
 
 +
local function has_extraneous_punc (param, value)
 +
if 'number' == type (param) then
 +
return;
 +
end
 +
 +
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
 +
if cfg.punct_skip[param] then
 +
return; -- parameter name found in the skip table so done
 +
end
 +
 +
if value:match ('[,;:]$') then
 +
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
 +
end
 +
if value:match ('^=') then -- sometimes an extraneous '=' character appears ...
 +
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------
 +
 
 +
look for extraneous url parameter values; parameters listed in skip table are not checked
 +
 
 +
]]
 +
 
 +
local function has_extraneous_url (url_param_t)
 +
local url_error_t = {};
 +
 +
check_for_url (url_param_t, url_error_t); -- extraneous url check
 +
if 0 ~= #url_error_t then -- non-zero when there are errors
 +
table.sort (url_error_t);
 +
utilities.set_message ('err_param_has_ext_link', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
 +
 
 +
This is used by templates such as {{cite book}} to create the actual citation text.
 +
 
 +
]]
 +
 
 +
local function citation(frame)
 +
Frame = frame; -- save a copy in case we need to display an error message in preview mode
 +
 
 +
local config = {}; -- table to store parameters from the module {{#invoke:}}
 +
for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame
 +
config[k] = v;
 +
-- args[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep?
 +
end
 +
-- i18n: set the name that your wiki uses to identify sandbox subpages from sandbox template invoke (or can be set here)
 +
local sandbox = ((config.SandboxPath and '' ~= config.SandboxPath) and config.SandboxPath) or '/sandbox'; -- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}}
 +
is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true); -- is this invoke the sandbox module?
 +
sandbox = is_sandbox and sandbox or ''; -- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else
 +
 
 +
local pframe = frame:getParent()
 +
local styles;
 +
 +
cfg = mw.loadData ('Module:Citation/CS1/Configuration' .. sandbox); -- load sandbox versions of support modules when {{#invoke:Citation/CS1/sandbox|...}}; live modules else
 +
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';
 +
 
 +
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables
 +
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
 +
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
 +
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 +
 
 +
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 +
 
 +
is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}'));
 +
 
 +
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; -- used as a flag
 +
 
 +
local capture; -- the single supported capture when matching unknown parameters using patterns
 +
local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing
 +
for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame
 +
v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
 +
if v ~= '' then
 +
if ('string' == type (k)) then
 +
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
 +
end
 +
if not validate( k, config.CitationClass ) then
 +
if type (k) ~= 'string' then -- exclude empty numbered parameters
 +
if v:match("%S+") ~= nil then
 +
error_text = utilities.set_message ('err_text_ignored', {v});
 +
end
 +
elseif validate (k:lower(), config.CitationClass) then
 +
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, k:lower()}); -- suggest the lowercase version of the parameter
 +
else
 +
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
 +
suggestions = mw.loadData ('Module:Citation/CS1/Suggestions' .. sandbox); --load sandbox version of suggestion module when {{#invoke:Citation/CS1/sandbox|...}}; live module else
 +
end
 +
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
 +
capture = k:match (pattern); -- the whole match if no capture in pattern else the capture if a match
 +
if capture then -- if the pattern matches
 +
param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator)
 +
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
 +
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message
 +
else
 +
error_text = utilities.set_message ('err_parameter_ignored', {k}); -- suggested param not supported by this template
 +
v = ''; -- unset
 +
end
 +
end
 +
end
 +
if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an explicit suggestion?
 +
if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
 +
utilities.set_message ('err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]});
 +
else
 +
utilities.set_message ('err_parameter_ignored', {k});
 +
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
 +
end
 +
end
 +
end  
 +
end
 +
 
 +
args[k] = v; -- save this parameter and its value
 +
 
 +
elseif not utilities.is_set (v) then -- for empty parameters
 +
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
 +
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
 +
table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list
 +
end
 +
-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
 +
-- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
 +
-- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
 +
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
 +
end
 +
 
 +
if 0 ~= #empty_unknowns then -- create empty unknown error message
 +
utilities.set_message ('err_param_unknown_empty', {
 +
1 == #empty_unknowns and '' or 's',
 +
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
 +
});
 +
end
 +
 
 +
local url_param_t = {};
 +
 
 +
for k, v in pairs( args ) do
 +
if 'string' == type (k) then -- don't evaluate positional parameters
 +
has_invisible_chars (k, v); -- look for invisible characters
 +
end
 +
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
 +
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
 +
args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label
 +
 
 +
if 'string' == type (k) and not cfg.url_skip[k] then -- when parameter k is not positional and not in url skip table
 +
url_param_t[k] = v; -- make a parameter/value list for extraneous url check
 +
end
 +
end
 +
 
 +
has_extraneous_url (url_param_t); -- look for url in parameter values where a url does not belong
 +
 
 +
return table.concat ({
 +
frame:extensionTag ('templatestyles', '', {src=styles}),
 +
citation0( config, args)
 +
});
 +
end
 +
 
 +
 
 +
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
 +
]]
 +
 
 +
return {citation = citation};
Источник — https://in.wiki/Служебная:Сравнение_версий/343298

Реклама:

Навигация