Module:Citation/CS1: Difference between revisions

Synch from sandbox;
m>Trappist the monk
(bug fix in page number rendering (NoPP);)
m>Trappist the monk
(Synch from sandbox;)
Line 27: Line 27:
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------


First set variable or nil if none
Locates and returns the first set value in a table of values where the order established in the table,
left-to-right (or top-to-bottom), is the order in which the values are evaluated.  Returns nil if none are set.
 
This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs.  With the pairs
version the order of evaluation could not be guaranteed.  With the ipairs version, a nil value would terminate
the for-loop before it reached the actual end of the list.


]]
]]


local function first_set(...)
local function first_set (list, count)
local list = {...};
local i = 1;
for _, var in pairs(list) do
while i <= count do -- loop through all items in list
if is_set( var ) then
if is_set( list[i] ) then
return var;
return list[i]; -- return the first set list member
end
end
i = i + 1; -- point to next
end
end
end
end
Line 160: Line 166:
end
end


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


Determines whether a URL string is valid.
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------


At present the only check is whether the string appears to be prefixed with a URI scheme. It is not determined whether
does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it
the URI scheme is valid or whether the URL is otherwise well formed.
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
 
The scheme is checked http://tools.ietf.org/html/std66#section-3.1 which says:
Scheme names consist of a sequence of characters beginning with a
Scheme names consist of a sequence of characters beginning with a
   letter and followed by any combination of letters, digits, plus
   letter and followed by any combination of letters, digits, plus
   ("+"), period ("."), or hyphen ("-").
   ("+"), period ("."), or hyphen ("-").


First we test for space characters.  If any are found, return false.  Then test for the case where the url is
returns true if it does, else false
protocol relative (//example.com).  If the first two characters of the |url= value are //, return true.  Last
 
look for what appears to be a scheme according to the definition above.  If the characters preceding the colon
are in the allowed set, return true, else false
]]
]]


local function check_url( url_str )
local function is_scheme (scheme)
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
return false;
end
return url_str:sub(1,2) == "//" or nil ~= url_str:match ("^%a[%a%d%+%.%-]*:") -- protocol relative or scheme part composed of legitimate characters
end
end


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


Protects a string that will be wrapped in wiki italic markup '' ... ''
--[[--------------------------< 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?
 
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between
the first and last characters the name may use letters, digits, and the hyphen. Single character names are not allowed.
 
Also allowed are IPv4 addresses. IPv6 not supported
 
There are three tests: the first is looking for a hostname that is 2 to n letters or digits followed by a dot and a
letter (tld); the second looks for a hostname that is 3 to n characters where the first and last are letters or
digits and the middle characters are letters, digits, or the hyphen; the whole followed by a dot and a letter or digit.
The third test is for IPv4 dot-decimal address format; tld not allowed.


Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
returns true if domain appears to be a proper name and tld or IPv4 address, else false
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 is_domain_name (domain)
if not is_set(str) then
if not domain then
return str;
return false; -- if not set, abandon
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if domain:match ('^[%a%d][%a%d]+%.%a') then -- two character hostname and tld
return true;
elseif domain:match ('^[%a%d][%a%d%-]+[%a%d]%.[%a%d]') then -- three or more character hostname.hostname or hostname.tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
else
if str:sub(1,1) == "'" then str = "<span />" .. str; end
return false;
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
-- Remove newlines as they break italics.
return str:gsub( '\n', ' ' );
end
end
end
end


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


Escape sequences for content that will be used for URL descriptions
--[[--------------------------< 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 safe_for_url( str )
local function is_url (scheme, domain)
if str:match( "%[%[.-%]%]" ) ~= nil then  
if is_set (scheme) then -- if scheme is set check it and domain
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when url is protocol relative
end
end
 
 
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
 
Split a url into a scheme and domain pair and return both parts.  If protocol relative url, return nil for scheme
and domain else return nil for both scheme and domain.
 
]]
 
local function split_url (url_str)
local scheme, domain;
if url_str:match ('%S-:%S+') then -- if there is what appears to be a scheme domain pair
scheme, domain = url_str:match ('(%S-:)(%S+)'); -- extract the scheme and domain portions
elseif url_str:match ('//%S*') then -- if there is what appears to be a protocol relative url
domain = url_str:match ('//(%S*)')
end
end
return str:gsub( '[%[%]\n]', {
return scheme, domain;
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
end


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


Applies styling to various parameters.  Supplied string is wrapped using a message_list configuration taking one
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason
 
this function is similar to but separate from wrap_msg().
checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
 
Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
# < > [ ] | { } _
returns false when the value contains any of these characters.
 
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).


]]
]]


local function wrap_style (key, str)
local function link_param_ok (value)
if not is_set( str ) then
local scheme, domain;
return "";
if value:find ('[#<>%[%]|{}_]') then -- if any prohibited characters
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
return false;
str = safe_for_italics( str );
end
end


return substitute( cfg.presentation[key], {str} );
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
end


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


Format an external link with error checking
--[[--------------------------< 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_scheme() and is_domain() to
validate the two portions of the url.  If both are valid, or for protocol relative if domain is valid, return true, else false.


]]
]]


local function external_link( URL, label, source )
local function check_url( url_str )
local error_str = "";
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
if not is_set( label ) then
return false;
label = URL;
end
if is_set( source ) then
local scheme, domain;
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
 
else
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
error( cfg.messages["bare_url_no_origin"] );
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {}, false, " " ) .. error_str;
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end
end


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


Formats a wiki style external link
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
 
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
characters following the opening bracket obey the rules of a uri scheme (see check_url()).  The test will also find
external wikilinks that use protocol relative urls. Also finds bare urls.
 
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls.  The tests that
find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, and
|work=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]] is
possible as might be [[en://Hus]].
 
]=]


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


local function external_link_id(options)
if value:match ('%f[%[]%[%a%S*:%S.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
local url_string = options.id;
scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S.*)%]')
if options.encode == true or options.encode == nil then
elseif value:match ('%f[%[]%[//%S*%.%S*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
url_string = mw.uri.encode( url_string );
domain = value:match ('%f[%[]%[//(%S*%.%S*)%]');
else
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;  
end
end
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
 
options.link, options.label, options.separator or "&nbsp;",
return is_url (scheme, domain); -- return true if value appears to be a valid url
options.prefix, url_string, options.suffix or "",
mw.text.nowiki(options.id)
);
end
end


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


Categorize and emit an error message when the citation contains one or more deprecated parametersThe function includes the
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
 
parameters in the citation.
loop through a list of parameters and their valuesLook at the value and if it has an external link, emit an error message.


]]
]]


local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local function check_for_url (parameter_list)
local function deprecated_parameter(name)
local error_message = '';
if not page_in_deprecated_cat then
for k, v in pairs (parameter_list) do -- for each parameter in the list
page_in_deprecated_cat = true; -- note that we've added this category
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
if is_set(error_message) then -- once we've added the first portion of the error message ...
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
if is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
end
end
end
end


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


Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
This function will positive kern either single or double quotes:
 
"'Unkerned title with leading and trailing single quote marks'"
Protects a string that will be wrapped in wiki italic markup '' ... ''
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.


Call this function for chapter titles, for website titles, etc; not for book titles.
Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that
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 kern_quotes (str)
local function safe_for_italics( str )
local cap='';
if not is_set(str) then
local cap2='';
return str;
else
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if str:sub(1,1) == "'" then str = "<span />" .. str; end
if is_set (cap) then
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
-- Remove newlines as they break italics.
return str:gsub( '\n', ' ' );
end
end
end


cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
if is_set (cap) then
 
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
Escape sequences for content that will be used for URL descriptions
 
]]
 
local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then  
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
end
end
return str;
return str:gsub( '[%[%]\n]', {
['['] = '&#91;',
[']'] = '&#93;',
['\n'] = ' ' } );
end
end


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


|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
Applies styling to various parameters. Supplied string is wrapped using a message_list configuration taking one
not be italicized and may be written right-to-leftThe value supplied by |script-title= is concatenated onto Title after Title has been wrapped
argument; protects italic styled parametersAdditional text taken from citation_config.presentation - the reason
in italic markup.
this function is similar to but separate from wrap_msg().


Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.
]]
 
local function wrap_style (key, str)
if not is_set( str ) then
return "";
elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then
str = safe_for_italics( str );
end


|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:
return substitute( cfg.presentation[key], {str} );
|script-title=ja:*** *** (where * represents a Japanese character)
end
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
|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
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.


Supports |script-title= and |script-chapter=
Format an external link with error checking


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 external_link( URL, label, source )
local lang=''; -- initialize to empty string
local error_str = "";
local name;
if not is_set( label ) then
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
label = URL;
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if is_set( source ) then
if not is_set (lang) then
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
return ''; -- script_value was just the prefix so return empty string
else
end
error( cfg.messages["bare_url_no_origin"] );
-- if we get this far we have prefix and script
end
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
end
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
if not check_url( URL ) then
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
-- is prefix one of these language codes?
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
add_prop_cat ('script')
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end


return script_value;
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
end


--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Formats a wiki style external link


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


local function script_concatenate (title, script)
local function external_link_id(options)
if is_set (script) then
local url_string = options.id;
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if options.encode == true or options.encode == nil then
if is_set (script) then
url_string = mw.uri.encode( url_string );
title = title .. ' ' .. script; -- concatenate title and script title
end
end
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
end
options.link, options.label, options.separator or "&nbsp;",
return title;
options.prefix, url_string, options.suffix or "",
mw.text.nowiki(options.id)
);
end
end


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


--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
Categorize and emit an error message when the citation contains one or more deprecated parametersThe function includes the
 
offending parameter name to the error messageOnly one error message is emitted regardless of the number of deprecated
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
parameters in the citation.
configuration taking one argumentSupports lower case text for {{citation}} templatesAdditional 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 page_in_deprecated_cat; -- sticky flag so that the category is added only once
if not is_set( str ) then
local function deprecated_parameter(name)
return "";
if not page_in_deprecated_cat then
page_in_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
end
if true == lower then
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
str = substitute( msg, {str} ); -- including template text
return str;
else
return substitute( cfg.messages[key], {str} );
end
end
end


--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
 
Chooses one matching parameter from a list of parameters to consider
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.
Generates an error if more than one match is present.
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.
 
Call this function for chapter titles, for website titles, etc; not for book titles.


]]
]]


local function select_one( args, possible, error_condition, index )
local function kern_quotes (str)
local value = nil;
local cap='';
local selected = '';
local cap2='';
local error_list = {};
if index ~= nil then index = tostring(index); end
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if is_set (cap) then
-- Handle special case of "#" replaced by empty string
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
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
 
for _, v in ipairs( possible ) do
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
if index ~= nil then
if is_set (cap) then
v = v:gsub( "#", index );
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if is_set(args[v]) then
if value ~= nil and selected ~=  v then
table.insert( error_list, v );
else
value = args[v];
selected = v;
end
end
end
end
return str;
if #error_list > 0 then
end
local error_str = "";
 
for _, k in ipairs( error_list ) do
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
 
error_str = error_str .. wrap_style ('parameter', k);
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
end
not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
if #error_list > 1 then
in italic markup.
error_str = error_str .. cfg.messages['parameter-final-separator'];
 
else
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.
error_str = error_str .. cfg.messages['parameter-pair-separator'];
 
end
|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:
error_str = error_str .. wrap_style ('parameter', selected);
|script-title=ja:*** *** (where * represents a Japanese character)
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
end
|script-title=ja : *** ***
|script-title=ja: *** ***
return value, selected;
|script-title=ja :*** ***
end
Spaces preceding the prefix are allowed: |script-title = ja:*** ***


--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
The prefix is checked for validity.  If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains.  This may help the browser render the script more correctly.  If the prefix is invalid, the lang attribute
is not added.  At this time there is no error message for this condition.


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


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


local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source)
local function format_script_value (script_value)
local chapter_error = '';
local lang=''; -- initialize to empty string
local name;
if not is_set (chapter) then
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
chapter = ''; -- to be safe for concatenation
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
else
if not is_set (lang) then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
return ''; -- script_value was just the prefix so return empty string
chapter = wrap_style ('quoted-title', chapter);
end
-- if we get this far we have prefix and script
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
add_prop_cat ('script')
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl


chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
return script_value;
end


if is_set (transchapter) then
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
transchapter = wrap_style ('trans-quoted-title', transchapter);
if is_set (chapter) then
chapter = chapter ..  ' ' .. transchapter;
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --  
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end


if is_set (chapterurl) then
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
wrapped in <bdi> tags.
]]
 
local function script_concatenate (title, script)
if is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
end
return title;
end


return chapter .. chapter_error;
end


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


--[[
Argument wrapper.  This function provides support for argument
mapping defined in the configuration file so that multiple names
can be transparently aliased to single internal variable.
]]
]]


local function argument_wrapper( args )
local function wrap_msg (key, str, lower)
local origin = {};
if not is_set( str ) then
return "";
return setmetatable({
end
ORIGIN = function( self, k )
if true == lower then
local dummy = self[k]; --force the variable to be loaded.
local msg;
return origin[k];
msg = cfg.messages[key]:lower(); -- set the message to lower case before
end
return substitute( msg, str ); -- including template text
},
else
{
return substitute( cfg.messages[key], str );
__index = function ( tbl, k )
end
if origin[k] ~= nil then
return nil;
end
local args, list, v = args, cfg.aliases[k];
if type( list ) == 'table' then
v, origin[k] = select_one( args, list, 'redundant_parameters' );
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
end
elseif list ~= nil then
v, origin[k] = args[list], list;
else
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
end
-- Empty strings, not nil;
if v == nil then
v = cfg.defaults[k] or '';
origin[k] = '';
end
tbl = rawset( tbl, k, v );
return v;
end,
});
end
end


--[[
Looks for a parameter's name in the whitelist.


Parameters in the whitelist can have three values:
--[[-------------------------< I S _ A L I A S _ U S E D >-----------------------------------------------------
true - active, supported parameters
 
false - deprecated, supported parameters
This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
nil - unsupported parameters
provided by the template.
 
Input:
args – pointer to the arguments table from calling template
alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration
index – for enumerated parameters, identifies which one
enumerated – true/false flag used choose how enumerated aliases are examined
value – value associated with an alias that has previously been selected; nil if not yet selected
selected – the alias that has previously been selected; nil if not yet selected
error_list – list of aliases that are duplicates of the alias already selected
 
Returns:
value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected
selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected
 
]]
]]


local function validate( name )
local function is_alias_used (args, alias, index, enumerated, value, selected, error_list)
local name = tostring( name );
if enumerated then -- is this a test for an enumerated parameters?
local state = whitelist.basic_arguments[ name ];
alias = alias:gsub ('#', index); -- replace '#' with the value in index
else
-- Normal arguments
alias = alias:gsub ('#', ''); -- remove '#' if it exists
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
 
-- Arguments with numbers in them
if is_set(args[alias]) then -- alias is in the template's argument list
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases
state = whitelist.numbered_arguments[ name ];
local skip;
if true == state then return true; end -- valid actively supported parameter
for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias
if false == state then
if v == alias then
deprecated_parameter (name); -- parameter is deprecated but still supported
skip = true;
return true;
break; -- has been added so stop looking
end
end
if not skip then -- has not been added so
table.insert( error_list, alias ); -- add error alias to the error list
end
else
value = args[alias]; -- not yet selected an alias, so select this one
selected = alias;
end
end
end
return value, selected; -- return newly selected alias, or previously selected alias
return false; -- Not supported because not found or name is set to nil
end
end




-- Formats a wiki style internal link
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
local function internal_link_id(options)
 
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just
options.link, options.label, options.separator or "&nbsp;",
names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified
options.prefix, options.id, options.suffix or "",
by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
mw.text.nowiki(options.id)
 
);
Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
end




--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
Generates an error if more than one match is present.


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 select_one( args, aliases_list, error_condition, index )
local value = nil; -- the value assigned to the selected parameter
local selected = ''; -- the name of the parameter we have chosen
local error_list = {};


]]
if index ~= nil then index = tostring(index); end


local function nowrap_date (date)
for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list
local cap='';
if alias:match ('#') then -- if this alias can be enumerated
local cap2='';
if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias
end
value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias
else
value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias
end
end


if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names()
date = substitute (cfg.presentation['nowrap1'], date);
local error_str = "";
for _, k in ipairs( error_list ) do
elseif date:match("^%a+%s*%d%d?,%s*%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s*%d%d%d%d$") then
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
error_str = error_str .. wrap_style ('parameter', k);
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
if #error_list > 1 then
error_str = error_str .. cfg.messages['parameter-final-separator'];
else
error_str = error_str .. cfg.messages['parameter-pair-separator'];
end
error_str = error_str .. wrap_style ('parameter', selected);
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
end
end
return date;
return value, selected;
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().
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L 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.
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
parameter (chapter_url_source used for error messages).


]]
]]


local function is_valid_isxn (isxn_str, len)
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local temp = 0;
local chapter_error = '';
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
len = len+1; -- adjust to be a loop counter
if not is_set (chapter) then
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
chapter = ''; -- to be safe for concatenation
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
else
temp = temp + 10*( len - i ); -- it represents 10 decimal
if false == no_quotes then
else
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
temp = temp + tonumber( string.char(v) )*(len-i);
chapter = wrap_style ('quoted-title', chapter);
end
end
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
end


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


--[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >----------------------------------------------
if is_set (transchapter) then
transchapter = wrap_style ('trans-quoted-title', transchapter);
if is_set (chapter) then
chapter = chapter .. ' ' .. transchapter;
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --  
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end


ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
if is_set (chapterurl) then
If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
and stripped of dashes, spaces and other non-isxn-13 characters.
end


]]
return chapter .. chapter_error;
 
local function is_valid_isxn_13 (isxn_str)
local temp=0;
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
for i, v in ipairs( isxn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
end
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
end
end


--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
Determines whether an ISBN string is valid


--[[
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 check_isbn( isbn_str )
local function argument_wrapper( args )
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
local origin = {};
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
local len = isbn_str:len();
return setmetatable({
ORIGIN = function( self, k )
if len ~= 10 and len ~= 13 then
local dummy = self[k]; --force the variable to be loaded.
return false;
return origin[k];
end
end
},
{
__index = function ( tbl, k )
if origin[k] ~= nil then
return nil;
end
local args, list, v = args, cfg.aliases[k];
if type( list ) == 'table' then
v, origin[k] = select_one( args, list, 'redundant_parameters' );
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
end
elseif list ~= nil then
v, origin[k] = args[list], list;
else
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
end
-- Empty strings, not nil;
if v == nil then
v = cfg.defaults[k] or '';
origin[k] = '';
end
tbl = rawset( tbl, k, v );
return v;
end,
});
end


if len == 10 then
--[[
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
Looks for a parameter's name in the whitelist.
return is_valid_isxn(isbn_str, 10);
 
else
Parameters in the whitelist can have three values:
local temp = 0;
true - active, supported parameters
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
false - deprecated, supported parameters
return is_valid_isxn_13 (isbn_str);
nil - unsupported parameters
]]
 
local function validate( name )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
-- Normal arguments
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
end
return false; -- Not supported because not found or name is set to nil
end
end


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


Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
-- Formats a wiki style internal link
same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
local function internal_link_id(options)
section 2, pages 9–12.
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
options.link, options.label, options.separator or "&nbsp;",
options.prefix, options.id, options.suffix or "",
mw.text.nowiki(options.id)
);
end


]]


local function ismn (id)
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
local handler = cfg.id_handlers['ISMN'];
 
local text;
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
local valid_ismn = true;
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY


id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn
DOES NOT yet support MMMM YYYY or any of the date ranges.


if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
]]
valid_ismn = false;
else
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
end


-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
local function nowrap_date (date)
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
local cap='';
local cap2='';
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet


if false == valid_ismn then
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
date = substitute (cfg.presentation['nowrap1'], date);
end
return text;
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
end
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
 
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
--[[--------------------------< I S S N >----------------------------------------------------------------------
end
return date;
end


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
--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------
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
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
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,
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
spaces and other non-isxn characters.
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 is_valid_isxn (isxn_str, len)
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local temp = 0;
local handler = cfg.id_handlers['ISSN'];
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39, 'X' → 0x58
local text;
len = len+1; -- adjust to be a loop counter
local valid_issn = true;
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
temp = temp + 10*( len - i ); -- it represents 10 decimal
else
temp = temp + tonumber( string.char(v) )*(len-i);
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
end


id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn


if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
--[[--------------------------< IS _ V A L I D _ I S X N  _ 1 3 >----------------------------------------------
valid_issn=false; -- wrong length or improper character
 
else
ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
valid_issn=is_valid_isxn(id, 8); -- validate issn
If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length
end
and stripped of dashes, spaces and other non-isxn-13 characters.
 
]]


if true == valid_issn then
local function is_valid_isxn_13 (isxn_str)
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
local temp=0;
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9'  → 0x39
for i, v in ipairs( isxn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit
end
end
return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if false == valid_issn then
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
end
return text
end
end


--[[--------------------------< A M A Z O N >------------------------------------------------------------------
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------


Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
Determines whether an ISBN string is valid
characters.  If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.


]]
]]


local function amazon(id, domain)
local function check_isbn( isbn_str )
local err_cat = ""
if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
local len = isbn_str:len();
if len ~= 10 and len ~= 13 then
return false;
end


if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
if len == 10 then
err_cat =  ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
return is_valid_isxn(isbn_str, 10);
else
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
local temp = 0;
if check_isbn( id ) then -- see if asin value is isbn10
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979
add_maint_cat ('ASIN');
return is_valid_isxn_13 (isbn_str);
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
end
if not is_set(domain) then
domain = "com";
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
domain = "co." .. domain;
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
end
local handler = cfg.id_handlers['ASIN'];
return external_link_id({link=handler.link,
label=handler.label, prefix=handler.prefix .. domain .. "/dp/",
id=id, encode=handler.encode, separator = handler.separator}) .. err_cat;
end
end


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


See: http://arxiv.org/help/arxiv_identifier
Determines whether an ISMN string is validSimilar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
 
same check digit calculations.  See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
format and error check arXiv identifierThere are three valid forms of the identifier:
section 2, pages 9–12.
the first form, valid only between date codes 9108 and 0703 is:
arXiv:<archive>.<class>/<date code><number><version>
where:
<archive> is a string of alpha characters - may be hyphenated; no other punctuation
<class> is a string of alpha characters - may be hyphenated; no other punctuation
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
first digit of YY for this form can only 9 and 0
<number> is a three-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented)
the second form, valid from April 2007 through December 2014 is:
arXiv:<date code>.<number><version>
where:
<date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01
<number> is a four-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces


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


local function arxiv (id, class)
local function ismn (id)
local handler = cfg.id_handlers['ARXIV'];
local handler = cfg.id_handlers['ISMN'];
local year, month, version;
local err_cat = '';
local text;
local text;
local valid_ismn = true;
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]*$");
id=id:gsub( "[%s-]", "" ); -- strip spaces, hyphens, and endashes from the ismn
year = tonumber(year);
 
month = tonumber(month);
if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
valid_ismn = false;
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
else
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
valid_ismn=is_valid_isxn_13 (id); -- validate ismn
end
end


text = external_link_id({link = handler.link, label = handler.label,
-- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
-- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet


if is_set (class) then
if false == valid_ismn then
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid
else
end  
class = ''; -- empty string for concatenation
end
return text .. class;
return text;
end
end


--[[
--[[--------------------------< I S S N >----------------------------------------------------------------------
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
 
1. Remove all blanks.
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
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
digits with a space. When that condition occurred, the resulting link looked like this:
3. If there is a hyphen in the string:
 
a. Remove it.
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327]  -- can't have spaces in an external link
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)
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
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
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.


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 issn(id)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local handler = cfg.id_handlers['ISSN'];
local text;
local valid_issn = true;


if nil ~= string.find (lccn,'/') then
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end


local prefix
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
local suffix
valid_issn=false; -- wrong length or improper character
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
else
valid_issn=is_valid_isxn(id, 8); -- validate issn
end


if nil ~= suffix then -- if there was a hyphen
if true == valid_issn then
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
lccn=prefix..suffix; -- reassemble the lccn
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
end
end
return lccn;
text = external_link_id({link = handler.link, label = handler.label,
end
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if false == valid_issn then
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
end
return text
end


--[[
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
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
Formats a link to Amazon.  Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
length = 9 then lccn[1] is lower case alpha
characters.  If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
length = 12 then lccn[1] and lccn[2] are both lower case alpha


]]
]]


local function lccn(lccn)
local function amazon(id, domain)
local handler = cfg.id_handlers['LCCN'];
local err_cat = ""
local err_cat = ''; -- presume that LCCN is valid
local id = lccn; -- local copy of the lccn


id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
local len = id:len(); -- get the length of the lccn
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
 
else
if 8 == len then
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
if check_isbn( id ) then -- see if asin value is isbn10
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
add_maint_cat ('ASIN');
end
elseif not is_set (err_cat) then
elseif 9 == len then -- LCCN should be adddddddd
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
end
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
elseif not id:match("^%u[%d%u]+$") then
err_cat =  ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
elseif 12 == len then -- LCCN should be aadddddddddd
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
end
end
if not is_set(domain) then
domain = "com";
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
domain = "co." .. domain;
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
end
local handler = cfg.id_handlers['ASIN'];
return external_link_id({link=handler.link,
label=handler.label, prefix=handler.prefix .. domain .. "/dp/",
id=id, encode=handler.encode, separator = handler.separator}) .. err_cat;
end


if not is_set (err_cat) and nil ~= lccn:find ('%s') then
--[[--------------------------< A R X I V >--------------------------------------------------------------------
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
end


return external_link_id({link = handler.link, label = handler.label,
See: http://arxiv.org/help/arxiv_identifier
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
end


--[[
format and error check arXiv identifierThere are three valid forms of the identifier:
Format PMID and do simple error checkingPMIDs are sequential numbers beginning at 1 and counting up.  This code checks the PMID to see that it
the first form, valid only between date codes 9108 and 0703 is:
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.
arXiv:<archive>.<class>/<date code><number><version>
]]
where:
 
<archive> is a string of alpha characters - may be hyphenated; no other punctuation
local function pmid(id)
<class> is a string of alpha characters - may be hyphenated; no other punctuation
local test_limit = 30000000; -- update this value as PMIDs approach
<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
local handler = cfg.id_handlers['PMID'];
first digit of YY for this form can only 9 and 0
local err_cat =  ''; -- presume that PMID is valid
<number> is a three-digit number
<version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented)
if id:match("[^%d]") then -- if PMID has anything but digits
the second form, valid from April 2007 through December 2014 is:
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
arXiv:<date code>.<number><version>
else -- PMID is only digits
where:
local id_num = tonumber(id); -- convert id to a number for range testing
<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
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
<number> is a four-digit number
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
<version> is a 1 or more digit number preceded with a lowercase v; no spaces
end
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
 
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
 
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date.  If embargo date is
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
|embargo= was not set in this cite.


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


local function is_embargoed (embargo)
local function arxiv (id, class)
if is_set (embargo) then
local handler = cfg.id_handlers['ARXIV'];
local lang = mw.getContentLanguage();
local year, month, version;
local good1, embargo_date, good2, todays_date;
local err_cat = '';
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
local text;
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
if good1 and good2 then -- if embargo date and today's date are good dates
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
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
return embargo; -- still embargoed
year = tonumber(year);
else
month = tonumber(month);
add_maint_cat ('embargo')
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
return ''; -- unset because embargo has expired
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
end
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") 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
return ''; -- |embargo= not set return empty string
end


--[[--------------------------< P M C >------------------------------------------------------------------------
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;


Format a PMC, do simple error checking, and check for embargoed articles.
if is_set (class) then
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
else
class = ''; -- empty string for concatenation
end
return text .. class;
end


The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
--[[
be linked to the article. If the embargo date is today or in the past, or if it is empty or omitted, then the
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
1. Remove all blanks.
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
3. If there is a hyphen in the string:
a. Remove it.
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
1. All these characters should be digits, and there should be six or less. (not done in this function)
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.


PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
Returns a normalized lccn for lccn() to validateThere is no error checking (step 3.b.1) performed in this function.
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC linkFunction 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
local function normalize_lccn (lccn)
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace


]]
if nil ~= string.find (lccn,'/') then
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end


local function pmc(id, embargo)
local prefix
local test_limit = 5000000; -- update this value as PMCs approach
local suffix
local handler = cfg.id_handlers['PMC'];
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
local err_cat =  ''; -- presume that PMC is valid
local text;


if id:match("[^%d]") then -- if PMC has anything but digits
if nil ~= suffix then -- if there was a hyphen
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
else -- PMC is only digits
lccn=prefix..suffix; -- reassemble the lccn
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?
return lccn;
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
end
return text;
end


-- Formats a DOI and checks for DOI errors.
--[[
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/


-- DOI names contain two parts: prefix and suffix separated by a forward slash.
length = 8 then all digits
--  Prefix: directory indicator '10.' followed by a registrant code
length = 9 then lccn[1] is lower case alpha
--  Suffix: character string of any length chosen by the registrant
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


-- This function checks a DOI name for: prefix/suffixIf the doi name contains spaces or endashes,
]]
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.
 
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


-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
local len = id:len(); -- get the length of the lccn


local function doi(id, inactive)
if 8 == len then
local cat = ""
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
local handler = cfg.id_handlers['DOI'];
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
local text;
if is_set(inactive) then
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
if is_set(inactive_year) then
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
else
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
end
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
elseif 9 == len then -- LCCN should be adddddddd
else
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
text = external_link_id({link = handler.link, label = handler.label,
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
end
inactive = ""
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
end
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
elseif 12 == len then -- LCCN should be aadddddddddd
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
end


if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
cat = ' ' .. set_error( 'bad_doi' );
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
end
end
return text .. inactive .. cat
 
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
end


-- Formats an OpenLibrary link, and checks for associated errors.
--[[
local function openlibrary(id)
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
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
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 handler = cfg.id_handlers['OL'];
]]


if ( code == "A" ) then
local function pmid(id)
return external_link_id({link=handler.link, label=handler.label,
local test_limit = 30000000; -- update this value as PMIDs approach
prefix=handler.prefix .. 'authors/OL',
local handler = cfg.id_handlers['PMID'];
id=id, separator=handler.separator, encode = handler.encode})
local err_cat = ''; -- presume that PMID is valid
elseif ( code == "M" ) then
return external_link_id({link=handler.link, label=handler.label,
if id:match("[^%d]") then -- if PMID has anything but digits
prefix=handler.prefix .. 'books/OL',
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
id=id, separator=handler.separator, encode = handler.encode})
else -- PMID is only digits
elseif ( code == "W" ) then
local id_num = tonumber(id); -- convert id to a number for range testing
return external_link_id({link=handler.link, label=handler.label,
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
prefix=handler.prefix .. 'works/OL',
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
id=id, separator=handler.separator, encode = handler.encode})
end
else
return external_link_id({link=handler.link, label=handler.label,
prefix=handler.prefix .. 'OL',
id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' );
end
end
return external_link_id({link = handler.link, label = handler.label,
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 >------------------------------------------------------


--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's dateIf embargo date is
 
in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because
Validate and format a usenet message idSimple error checking, looks for 'id-left@id-right' not enclosed in
|embargo= was not set in this cite.
'<' and/or '>' angle brackets.


]]
]]


local function message_id (id)
local function is_embargoed (embargo)
local handler = cfg.id_handlers['USENETID'];
if is_set (embargo) then
 
local lang = mw.getContentLanguage();
text = external_link_id({link = handler.link, label = handler.label,
local good1, embargo_date, good2, todays_date;
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
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
if good1 and good2 then -- if embargo date and today's date are good dates
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
return embargo; -- still embargoed
else
add_maint_cat ('embargo')
return ''; -- unset because embargo has expired
end
end
end
return ''; -- |embargo= not set return empty string
end
end


--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
--[[--------------------------< P M C >------------------------------------------------------------------------
 
Format a PMC, do simple error checking, and check for embargoed articles.
 
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
be linked to the article.  If the embargo date is today or in the past, or if it is empty or omitted, then the
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
 
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link.  Function is_embargoed ()
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.


This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
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
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.


]]
]]


local function set_titletype (cite_class, title_type)
local function pmc(id, embargo)
if is_set(title_type) then
local test_limit = 5000000; -- update this value as PMCs approach
if "none" == title_type then
local handler = cfg.id_handlers['PMC'];
title_type = ""; -- if |type=none then type parameter not displayed
local err_cat =  ''; -- presume that PMC is valid
local text;
 
if id:match("[^%d]") then -- if PMC has anything but digits
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
else -- PMC is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
end
end
return title_type; -- if |type= has been set to any other value use that value
end
end
 
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
if is_set (embargo) then -- is PMC is still embargoed?
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
return text;
end
end


--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
-- Formats a DOI and checks for DOI errors.


Removes irrelevant text and dashes from ISBN number
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
Similar to that used for Special:BookSources
--  Prefix: directory indicator '10.' followed by a registrant code
--  Suffix: character string of any length chosen by the registrant


]]
-- This function checks a DOI name for: prefix/suffix.  If the doi name contains spaces or endashes,
-- or, if it ends with a period or a comma, this function will emit a bad_doi error message.


local function clean_isbn( isbn_str )
-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
return isbn_str:gsub( "[^-0-9X]", "" );
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
end


--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
local function doi(id, inactive)
local cat = ""
local handler = cfg.id_handlers['DOI'];
local text;
if is_set(inactive) then
local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
if is_set(inactive_year) then
table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
else
table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year
end
inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
else
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
inactive = ""
end


Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
cat = ' ' .. set_error( 'bad_doi' );
]]
end
local function escape_lua_magic_chars (argument)
return text .. inactive .. cat
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
return argument;
end
end


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


Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
--[[--------------------------< O P E N L I B R A R Y >--------------------------------------------------------
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
 
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.
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'];


local function strip_apostrophe_markup (argument)
if ( code == "A" ) then
if not is_set (argument) then return argument; end
return external_link_id({link=handler.link, label=handler.label,
 
prefix=handler.prefix .. 'authors/OL',
while true do
id=id, separator=handler.separator, encode = handler.encode})
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
elseif ( code == "M" ) then
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
return external_link_id({link=handler.link, label=handler.label,
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
prefix=handler.prefix .. 'books/OL',
argument=argument:gsub("%'%'%'%'", "");
id=id, separator=handler.separator, encode = handler.encode})
elseif argument:match ("%'%'%'") then -- bold (3)
elseif ( code == "W" ) then
argument=argument:gsub("%'%'%'", "");
return external_link_id({link=handler.link, label=handler.label,
elseif argument:match ("%'%'") then -- italic (2)
prefix=handler.prefix .. 'works/OL',
argument=argument:gsub("%'%'", "");
id=id, separator=handler.separator, encode = handler.encode})
else
else
break;
return external_link_id({link=handler.link, label=handler.label,
end
prefix=handler.prefix .. 'OL',
id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' );
end
end
return argument; -- done
end
end


--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------


Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
 
Validate and format a usenet message id.  Simple error checking, looks for 'id-left@id-right' not enclosed in
'<' and/or '>' angle brackets.


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


local function make_coins_title (title, script)
local function message_id (id)
if is_set (title) then
local handler = cfg.id_handlers['USENETID'];
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
 
else
text = external_link_id({link = handler.link, label = handler.label,
title=''; -- if not set, make sure title is an empty string
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
end
if is_set (script) then
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
end  
else
script=''; -- if not set, make sure script is an empty string
return text
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 >------------------------------------------------
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------


Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
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 get_coins_pages (pages)
local function set_titletype (cite_class, title_type)
local pattern;
if is_set(title_type) then
if not is_set (pages) then return pages; end -- if no page numbers then we're done
if "none" == title_type then
title_type = ""; -- if |type=none then type parameter not displayed
while true do
end
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
return title_type; -- if |type= has been set to any other value use that value
if nil == pattern then break; end -- no more urls
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like?
return pages;
end


-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
local function remove_wiki_link( str )
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end));
end
end


-- Converts a hyphen to a dash
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end


--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
Removes irrelevant text and dashes from ISBN number
Similar to that used for Special:BookSources


Joins a sequence of strings together while checking for duplicate separation characters.
]]
 
local function clean_isbn( isbn_str )
return isbn_str:gsub( "[^-0-9X]", "" );
end
 
--[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >----------------------------------
 
Returns a string where all of lua's magic characters have been escaped.  This is important because functions like
string.gsub() treat their pattern and replace strings as patterns, not literal strings.
]]
local function escape_lua_magic_chars (argument)
argument = argument:gsub("%%", "%%%%"); -- replace % with %%
argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters
return argument;
end
 
--[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >--------------------------------
 
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata.
This function strips common patterns of apostrophe markup.  We presume that editors who have taken the time to
markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind.


]]
]]


local function safe_join( tbl, duplicate_char )
local function strip_apostrophe_markup (argument)
--[[
if not is_set (argument) then return argument; end
Note: we use string functions here, rather than ustring functions.
 
while true do
This has considerably faster performance and should work correctly as
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
long as the duplicate_char is strict ASCII.  The strings
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
in tbl may be ASCII or UTF8.
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
]]
argument=argument:gsub("%'%'%'%'", "");
elseif argument:match ("%'%'%'") then -- bold (3)
local str = ''; -- the output string
argument=argument:gsub("%'%'%'", "");
local comp = ''; -- what does 'comp' mean?
elseif argument:match ("%'%'") then -- italic (2)
local end_chr = '';
argument=argument:gsub("%'%'", "");
local trim;
else
for _, value in ipairs( tbl ) do
break;
if value == nil then value = ''; end
end
end
if str == '' then -- if output string is empty
return argument; -- done
str = value; -- assign value to it (first time through the loop)
end
elseif value ~= '' then
 
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
 
else
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
comp = value;
 
end
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
-- typically duplicate_char is sepc
of %27%27...
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
]]
--   Because individual string segments often (always?) begin with terminal punct for th
--   preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
end_chr = str:sub(-1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = str:sub(1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:sub(1,-3); -- remove them both
end
end


if trim then
local function make_coins_title (title, script)
if value ~= comp then -- value does not equal comp when value contains html markup
if is_set (title) then
local dup2 = duplicate_char;
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
else
title=''; -- if not set, make sure title is an empty string
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
end
else
if is_set (script) then
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
end
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
end
else
end
script=''; -- if not set, make sure script is an empty string
str = str .. value; --add it to the output string
end
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
end
return str;
return title .. script; -- return the concatenation
end
end


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


For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters.  When a name
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.
 
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
 
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
 
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
because the code editor gets confused between character insertion point and cursor position.


]]
]]


local function is_good_vanc_name (last, first)
local function get_coins_pages (pages)
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
local pattern;
add_vanc_error ();
if not is_set (pages) then return pages; end -- if no page numbers then we're done
return false; -- not a string of latin characters; Vancouver required Romanization
end;
while true do
return true;
pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url "
if nil == pattern then break; end -- no more urls
pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters
pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
end
pages = pages:gsub("[%[%]]", ""); -- remove the brackets
pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (&ndash; etc.) with hyphens; do we need to replace numerical entities like &#32; and the like?
return pages;
end
end


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


Attempts to convert names to initials in support of |name-list-format=vanc. 
-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end


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


Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
Joins a sequence of strings together while checking for duplicate separation characters.
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
 
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().


]]
]]


local function reduce_to_initials(first)
local function safe_join( tbl, duplicate_char )
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
--[[
local initials = {}
Note: we use string functions here, rather than ustring functions.
local i = 0; -- counter for number of initials
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
This has considerably faster performance and should work correctly as
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
long as the duplicate_char is strict ASCII. The strings
i = i + 1; -- bump the counter
in tbl may be ASCII or UTF8.
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
]]
end
return table.concat(initials) -- Vancouver format does not include spaces.
local str = ''; -- the output string
end
local comp = ''; -- what does 'comp' mean?
 
local end_chr = '';
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
local trim;
 
for _, value in ipairs( tbl ) do
Formats a list of people (e.g. authors / editors)
if value == nil then value = ''; end
 
]]
if str == '' then -- if output string is empty
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
else
comp = value;
end
-- typically duplicate_char is sepc
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
--  Because individual string segments often (always?) begin with terminal punct for th
--   preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
end_chr = str:sub(-1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = str:sub(1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:sub(1,-3); -- remove them both
end
end


local function list_people(control, people, etal)
if trim then
local sep;
if value ~= comp then -- value does not equal comp when value contains html markup
local namesep;
local dup2 = duplicate_char;
local format = control.format
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
local text = {}
else
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; --add it to the output string
end
end
return str;
end 
 
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
 
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.


if 'vanc' == format then -- Vancouver-like author/editor name styling?
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
sep = ','; -- name-list separator between authors is a comma
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
namesep = ' '; -- last/first separator is a space
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
else
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
sep = ';' -- name-list separator between authors is a semicolon
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
namesep = ', ' -- last/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end


if is_set(person.link) and ((nil ~= person.link:find("//")) or (nil ~= person.link:find("[%[%]]"))) then
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
one = one .. " " .. set_error( 'bad_authorlink' ) end -- url or wikilink in author link;
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
end
 
table.insert( text, one )
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
table.insert( text, sep_one )
because the code editor gets confused between character insertion point and cursor position.
end
 
end
]]


local count = #text / 2; -- (number of names + number of separators) divided by 2
local function is_good_vanc_name (last, first)
if count > 0 then
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za--ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
if count > 1 and is_set(lastauthoramp) and not etal then
add_vanc_error ();
text[#text-2] = " & "; -- replace last separator with ampersand text
return false; -- not a string of latin characters; Vancouver required Romanization
end
end;
text[#text] = nil; -- erase the last separator
return true;
end
local result = table.concat(text) -- construct list
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
end
return result, count
end
end


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


Generates a CITEREF anchor ID if we have at least one name or a dateOtherwise returns an empty string.
Attempts to convert names to initials in support of |name-list-format=vanc.   


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


local function anchor_id( options )
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.  This form is not
local id = table.concat( options ); -- concatenate names and year for CITEREF id
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
if is_set (id) then -- if concatenation is not an empty string
 
return "CITEREF" .. id; -- add the CITEREF portion
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
else
 
return ''; -- return an empty string; no reason to include CITEREF id in this citation
]]
 
local function reduce_to_initials(first)
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
local initials = {}
local i = 0; -- counter for number of initials
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
i = i + 1; -- bump the counter
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
end
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
end


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


Evaluates the content of author and editor name parameters for variations on the theme of et al.  If found,
Formats a list of people (e.g. authors / editors)
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
 
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal


]]
]]


local function name_has_etal (name, etal, nocat)
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here?  not used in this function
local sep;
local namesep;
local format = control.format
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
local text = {}


if is_set (name) then -- name can be nil in which case just return
if 'vanc' == format then -- Vancouver-like author/editor name styling?
local etal_pattern = "[;,]? *[\"']*%f[Ee][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
sep = ','; -- name-list separator between authors is a comma
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
namesep = ' '; -- last/first separator is a space
else
if name:match (etal_pattern) then -- variants on et al.
sep = ';' -- name-list separator between authors is a semicolon
name = name:gsub (etal_pattern, ''); -- if found, remove
namesep = ', ' -- last/first separator is <comma><space>
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
end
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
for i,person in ipairs(people) do
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if is_set(person.last) then
if not nocat then -- no categorization for |vauthors=
local mask = person.mask
add_maint_cat ('etal'); -- and add a category if not already added
local one
end
local sep_one = sep;
end
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("&mdash;",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
end
return name, etal; --
end
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
find |last4= and |last5= then the search is done.
This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.


When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned
local count = #text / 2; -- (number of names + number of separators) divided by 2
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration.  This keeps 'et al.' out of the
if count > 0 then
template's metadata.  When this occurs, the page is added to a maintenance category.
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
local result = table.concat(text) -- construct list
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
end
return result, count
end


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


local function extract_names(args, list_name)
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
local names = {}; -- table of names
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal=false; -- return value set to true when we find some form of et al. in an author parameter


local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );


last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
]]
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
local function anchor_id (namelist, year)
local names={}; -- a table for the one to four names and year
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
names[i] = v.last
if i == 4 then break end -- if four then done
end
table.insert (names, year); -- add the year at the end
local id = table.concat(names); -- concatenate names and year for CITEREF id
if is_set (id) then -- if concatenation is not an empty string
return "CITEREF" .. id; -- add the CITEREF portion
else
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end


if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
if 2 <= count then -- two missing names and we give up
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
return names, etal; -- all done, return our list of names
end


-- Populates ID table from arguments using configuration settings
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
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 >--------------------------------------------------------
Evaluates the content of author and editor name parameters for variations on the theme of et al.  If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.


Takes a table of IDs and turns it into a table of formatted ID outputs.
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal


]]
]]


local function build_id_list( id_list, options )
local function name_has_etal (name, etal, nocat)
local new_list, handler = {};


function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
if is_set (name) then -- name can be nil in which case just return
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
for k, v in pairs( id_list ) do
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
-- fallback to read-only cfg
handler = setmetatable( { ['id'] = v }, fallback(k) );
if handler.mode == 'external' then
if name:match (etal_pattern) then -- variants on et al.
table.insert( new_list, {handler.label, external_link_id( handler ) } );
name = name:gsub (etal_pattern, ''); -- if found, remove
elseif handler.mode == 'internal' then
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
if not nocat then -- no categorization for |vauthors=
elseif handler.mode ~= 'manual' then
add_maint_cat ('etal'); -- and add a category if not already added
error( cfg.messages['unknown_ID_mode'] );
end
elseif k == 'DOI' then
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
name = name:gsub (others_pattern, ''); -- if found, remove
elseif k == 'ARXIV' then
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
if not nocat then -- no categorization for |vauthors=
elseif k == 'ASIN' then
add_maint_cat ('etal'); -- and add a category if not already added
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );  
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISMN' then
table.insert( new_list, {handler.label, ismn( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
error( cfg.messages['unknown_manual_ID'] );
end
end
end
end
return name, etal; --  
function comp( a, b ) -- used in following table.sort()
return a[1] < b[1];
end
table.sort( new_list, comp );
for k, v in ipairs( new_list ) do
new_list[k] = v[2];
end
return new_list;
end
end
 


--[[--------------------------< C O I N S >--------------------------------------------------------------------
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
 
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
find |last4= and |last5= then the search is done.
 
This function emits an error message when there is a |firstn= without a matching |lastn=.  When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.


COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the
template's metadata.  When this occurs, the page is added to a maintenance category.


]]
]]


local function COinS(data, class)
local function extract_names(args, list_name)
if 'table' ~= type(data) or nil == next(data) then
local names = {}; -- table of names
return '';
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
 
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
 
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
 
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
if 2 <= count then -- two missing names and we give up
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last
table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link;
end
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; -- point to next args location
end
end
local ctx_ver = "Z39.88-2004";
return names, etal; -- all done, return our list of names
end
-- treat table strictly as an array with only set values.
 
local OCinSoutput = setmetatable( {}, {
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
__newindex = function(self, key, value)
 
if is_set(value) then
Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
any of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value to
end
the identifier list.  Emits redundant error message is more than one alias exists in args
end
 
});
]]
 
if in_array (class, {'citation', 'conference', 'interview', 'press release'}) and is_set(data.Periodical) then
local function extract_ids( args )
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
local id_list = {}; -- list of identifiers found in args
OCinSoutput["rft.genre"] = "article";
for k, v in pairs( cfg.id_handlers ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table
OCinSoutput["rft.jtitle"] = data.Periodical;
v = select_one( args, v.parameters, 'redundant_parameters' ); -- v.parameters is a table of aliases for k; here we pick one from args if present
OCinSoutput["rft.atitle"] = data.Title;
if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list
elseif in_array (class, {'arxiv', 'journal', 'news'}) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
if 'arxiv' == class then
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
else
OCinSoutput["rft.genre"] = "article";
end
OCinSoutput["rft.jtitle"] = data.Periodical;
OCinSoutput["rft.atitle"] = data.Title;
else
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
if is_set (data.Chapter) then
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter;
else
OCinSoutput["rft.genre"] = "book"
end
OCinSoutput["rft.btitle"] = data.Title;
end
end
return id_list;
end


OCinSoutput["rft.place"] = data.PublicationPlace;
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
OCinSoutput["rft.date"] = data.Date;
 
OCinSoutput["rft.series"] = data.Series;
Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs.
OCinSoutput["rft.volume"] = data.Volume;
 
OCinSoutput["rft.issue"] = data.Issue;
inputs:
OCinSoutput["rft.pages"] = data.Pages;
id_list – table of identifiers built by extract_ids()
OCinSoutput["rft.edition"] = data.Edition;
options – table of various template parameter values used to modify some manually handled identifiers
OCinSoutput["rft.pub"] = data.PublisherName;
 
]]
 
local function build_id_list( id_list, options )
local new_list, handler = {};
 
function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
for k, v in pairs( data.ID_list ) do
for k, v in pairs( id_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table
local id, value = cfg.id_handlers[k].COinS;
-- fallback to read-only cfg
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
handler = setmetatable( { ['id'] = v }, fallback(k) );
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
if handler.mode == 'external' then
table.insert( new_list, {handler.label, external_link_id( handler ) } );
elseif handler.mode == 'internal' then
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
elseif handler.mode ~= 'manual' then
error( cfg.messages['unknown_ID_mode'] );
elseif k == 'DOI' then
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
elseif k == 'ARXIV' then
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
elseif k == 'ASIN' then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );  
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' or k == 'OLA' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISMN' then
table.insert( new_list, {handler.label, ismn( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
else
OCinSoutput[ id ] = value;
error( cfg.messages['unknown_manual_ID'] );
end
end
end
end
local last, first;
function comp( a, b ) -- used in following table.sort()
for k, v in ipairs( data.Authors ) do
return a[1] < b[1];
last, first = v.last, v.first;
end
if k == 1 then -- for the first author name only
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
table.sort( new_list, comp );
OCinSoutput["rft.aulast"] = last;
for k, v in ipairs( new_list ) do
OCinSoutput["rft.aufirst"] = first;
new_list[k] = v[2];
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- otherwise use this form for the first name
end
else -- for all other authors
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
elseif is_set(last) then
OCinSoutput["rft.au"] = last;
end
end
end
end
OCinSoutput.rft_id = data.URL;
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
return new_list;
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver );  -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end
end
 


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


--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.


Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
]]
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.


Returns the language name and associated ISO639-1 code.  Because case of the source may be incorrect or different from the case that Wikimedia
local function COinS(data, class)
uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along
if 'table' ~= type(data) or nil == next(data) then
with the code.  When there is no match, we return the original language name string.
return '';
 
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
in the list will be found if that name is provided in the |language= parameter.  For example, if |language=Samaritan Aramaic, that name will be
found with the associated code 'sam', not an ISO639-1 code.  When names are found and the associated code is not two characters, this function
returns only the Wikimedia language name.
 
Adapted from code taken from Module:Check ISO 639-1.
 
]]
 
local function get_iso639_code (lang)
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
end
end
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
local ctx_ver = "Z39.88-2004";
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
-- treat table strictly as an array with only set values.
if langlc == mw.ustring.lower(name) then
local OCinSoutput = setmetatable( {}, {
if 2 ~= code:len() then -- ISO639-1 codes only
__newindex = function(self, key, value)
return name; -- so return the name but not the code
if is_set(value) then
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
end
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
end
});
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or
 
('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier
if 'arxiv' == class then -- set genre according to the type of citation template we are rendering
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
elseif 'conference' == class then
OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set)
elseif 'web' == class then
OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set)
else
OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles
end
OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only
if is_set (data.Map) then
OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical
else
OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles
end
-- these used onlu for periodicals
OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall
OCinSoutput["rft.chron"] = data.Chron; -- free-form date components
OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata


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.
elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes
 
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier
There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and
if 'report' == class or 'techreport' == class then -- cite report and cite techreport
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
OCinSoutput["rft.genre"] = "report";
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.
elseif 'conference' == class then -- cite conference when Periodical not set
 
OCinSoutput["rft.genre"] = "conference";
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
elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then
return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them.
if is_set (data.Chapter) then
 
OCinSoutput["rft.genre"] = "bookitem";
See Help talk:Citation Style_1#An ISO 639-1 language name test
OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title
 
else
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
if 'map' == class or 'interview' == class then
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.
OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview
 
else
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.
OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia
end
end
else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
OCinSoutput["rft.genre"] = "unknown";
end
OCinSoutput["rft.btitle"] = data.Title; -- book only
OCinSoutput["rft.place"] = data.PublicationPlace; -- book only
OCinSoutput["rft.series"] = data.Series; -- book only
OCinSoutput["rft.pages"] = data.Pages; -- book, journal
OCinSoutput["rft.edition"] = data.Edition; -- book only
OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation
else -- cite thesis
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier
OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported)
OCinSoutput["rft.degree"] = data.Degree; -- dissertation only
OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation
end
-- and now common parameters (as much as possible)
OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
if k == 'ISBN' then v = clean_isbn( v ) end
local id = cfg.id_handlers[k].COinS;
if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
elseif string.sub (id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords
OCinSoutput[ id ] = v;
elseif id then -- when cfg.id_handlers[k].COinS is not nil
OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v }; -- others; provide a url
end
end


--[[
for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all?
local id, value = cfg.id_handlers[k].COinS;
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
OCinSoutput[ id ] = value;
end
end
]]
]]
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = v.last, v.first;
if k == 1 then -- for the first author name only
if is_set(last)  and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name
OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation
OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name
end
else -- for all other authors
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation
elseif is_set(last) then
OCinSoutput["rft.au"] = last; -- book, journal, dissertation
end
end
end
OCinSoutput.rft_id = data.URL;
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


local function language_parameter (lang)
local code; -- the ISO639-1 two character code
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_table = {}; -- table made from the value assigned to |language=


names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------


for _, lang in ipairs (names_table) do -- reuse lang
Validates language names provided in |language= parameter if not an ISO639-1 code.  Handles the special case that is Norwegian where
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.


if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
Returns the language name and associated ISO639-1 code.  Because case of the source may be incorrect or different from the case that Wikimedia
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
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
end
with the code. When there is no match, we return the original language name string.
if is_set (name) then -- if Language specified a valid ISO639-1 code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if is_set (code) then
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
if 'en' ~= code then -- English not the language
add_prop_cat ('foreign_lang_source', {name, code})
end
else
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
code = #language_list -- reuse code as number of languages in the list
if 2 >= code then
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
elseif 2 < code then
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
if 'English' == name then
return ''; -- if one language and that language is English return an enpty string (no annotation)
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end


--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
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
in the list will be found if that name is provided in the |language= parameter.  For example, if |language=Samaritan Aramaic, that name will be
found with the associated code 'sam', not an ISO639-1 code.  When names are found and the associated code is not two characters, this function
returns only the Wikimedia language name.


Set style settings for CS1 citation templates. Returns separator and postscript settings
Adapted from code taken from Module:Check ISO 639-1.


]]
]]


local function set_cs1_style (ps)
local function get_iso639_code (lang)
if not is_set (ps) then -- unless explicitely set to something
if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
ps = '.'; -- terminate the rendered citation with a period
return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized
end
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() then -- ISO639-1 codes only
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
end
return '.', ps; -- separator is a full stop
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
end


--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
--[[--------------------------< 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.
 
There is an exception.  There are three ISO639-1 codes for Norewegian language variants.  There are two official variants: Norwegian Bokmål (code 'nb') and
Norwegian Nynorsk (code 'nn').  The third, code 'no',  is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless.  However, it appears
that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.


Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and
return 'Norwegian' when editors use |language=no.  We presume that editors don't know about the variants or can't descriminate between them.


]]
See Help talk:Citation Style_1#An ISO 639-1 language name test


local function set_cs2_style (ps, ref)
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
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.
ps = ''; -- make sure it isn't nil
end
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
return ',', ps, ref; -- separator is a comma
end


--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
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.
 
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
rendered style.


]]
]]


local function get_settings_from_cite_class (ps, ref, cite_class)
local function language_parameter (lang)
local sep;
local code; -- the ISO639-1 two character code
if (cite_class == "citation") then -- for citation templates (CS2)
local name; -- the language name
sep, ps, ref = set_cs2_style (ps, ref);
local language_list = {}; -- table of language names to be rendered
else -- not a citation template so CS1
local names_table = {}; -- table made from the value assigned to |language=
sep, ps = set_cs1_style (ps);
end


return sep, ps, ref -- return them all
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
end


--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
for _, lang in ipairs (names_table) do -- reuse lang


Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
if lang:match ('^%a%a%-') then -- strip ietf language tags from code
config.CitationClass from the template's #invoke: to establish style.
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
 
end
]]
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
 
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
local function set_style (mode, ps, ref, cite_class)
end
local sep;
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
if is_set (name) then -- if Language specified a valid ISO639-1 code
sep, ps, ref = set_cs2_style (ps, ref);
code = lang:lower(); -- save it
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
else
sep, ps = set_cs1_style (ps);
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
else -- anything but cs1 or cs2
end
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
if is_set (code) then
if 'none' == ps:lower() then -- if assigned value is 'none' then
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
ps = ''; -- set to empty string
if 'en' ~= code then -- English not the language
add_prop_cat ('foreign_lang_source', {name, code})
end
else
add_maint_cat ('unknown_lang'); -- add maint category if not already added
end
table.insert (language_list, name);
name = ''; -- so we can reuse it
end
end
return sep, ps, ref
code = #language_list -- reuse code as number of languages in the list
end
if 2 >= code then
 
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
elseif 2 < code then
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
if 'English' == name then
return ''; -- if one language and that language is English return an empty string (no annotation)
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end


Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
applying the pdf icon to external links.


returns true if file extension is one of the recognized extension, else false
Set style settings for CS1 citation templates. Returns separator and postscript settings


]=]
]]


local function is_pdf (url)
local function set_cs1_style (ps)
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
if not is_set (ps) then -- unless explicitely set to something
ps = '.'; -- terminate the rendered citation with a period
end
return '.', ps; -- separator is a full stop
end
end


--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------


Applies css style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
not have a matching url parameter.  If the format parameter is not set and the url contains a file extension that
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.


]]
]]


local function style_format (format, url, fmt_param, url_param)
local function set_cs2_style (ps, ref)
if is_set (format) then
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
format = wrap_style ('format', format); -- add leading space, parenthases, resize
ps = ''; -- make sure it isn't nil
if not is_set (url) then
end
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
if not is_set (ref) then -- if |ref= is not set
end
ref = "harv"; -- set default |ref=harv
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
end
return format;
return ',', ps, ref; -- separator is a comma
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 >------------------------
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
 
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
rendered style.
 
]]


Returns a number that may or may not limit the length of the author or editor name lists.
local function get_settings_from_cite_class (ps, ref, cite_class)
local sep;
if (cite_class == "citation") then -- for citation templates (CS2)
sep, ps, ref = set_cs2_style (ps, ref);
else -- not a citation template so CS1
sep, ps = set_cs1_style (ps);
end


When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
return sep, ps, ref -- return them all
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
end
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
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
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.
Establish basic style settings to be used when rendering the citation.  Uses |mode= if set and valid or uses
config.CitationClass from the template's #invoke: to establish style.


]]
]]


local function get_display_authors_editors (max, count, list_name, etal)
local function set_style (mode, ps, ref, cite_class)
if is_set (max) then
local sep;
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
max = count + 1; -- number of authors + 1 so display all author name plus et al.
sep, ps, ref = set_cs2_style (ps, ref);
etal = true; -- overrides value set by extract_names()
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
elseif max:match ('^%d+$') then -- if is a string of numbers
sep, ps = set_cs1_style (ps);
max = tonumber (max); -- make it a number
else -- anything but cs1 or cs2
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
add_maint_cat ('disp_auth_ed', list_name);
end
end
if 'none' == ps:lower() then -- if assigned value is 'none' then
else -- not a valid keyword or number
ps = ''; -- set to empty string
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset
end
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
end
return max, etal;
return sep, ps, ref
end
end


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


Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.  
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
abbreviation in the first characters of the parameter content.
applying the pdf icon to external links.


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


]]
]=]


local function extra_text_in_page_check (page, nopp)
local function is_pdf (url)
-- local good_pattern = '^P[^%.P%l]';
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
end
-- local bad_pattern = '^[Pp][Pp]';
 
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
 
Applies css style to |format=, |chapter-format=, etc.  Also emits an error message if the format parameter does
not have a matching url parameter.  If the format parameter is not set and the url contains a file extension that
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.


if is_set (nopp) then -- don't bother checking if |nopp= is set
]]
return;
end


if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
local function style_format (format, url, fmt_param, url_param)
add_maint_cat ('extra_text');
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parenthases, resize
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
return format;
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
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 >------------------------


--[[--------------------------< P A R S E _ V A U T H O R S _ V 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.


This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
|xxxxor-linkn= in args.  It then returns a table of assembled names just as extract_names() does.
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
some variant of the text 'et al.').


Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
the names in the name list followed by 'et al.'


This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
In all other cases, returns nil and the previous state of the 'etal' flag.


]]
]]


local function parse_vauthors_veditors (args, vparam, list_name)
local function get_display_authors_editors (max, count, list_name, etal)
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
if is_set (max) then
local v_name_table = {};
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
max = count + 1; -- number of authors + 1 so display all author name plus et al.
local last, first, link, mask;
etal = true; -- overrides value set by extract_names()
local corporate = false;
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cat ('disp_auth_ed', list_name);
end
else -- not a valid keyword or number
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset
end
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
return max, etal;
end


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)
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ();
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas


for i, v_name in ipairs(v_name_table) do
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.  
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
abbreviation in the first characters of the parameter content.
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name:match ('^%(%((.+)%)%)$')
corporate = true;
elseif string.find(v_name, "%s") then
    lastfirstTable = {}
    lastfirstTable = mw.text.split(v_name, "%s")
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
end
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ();
end
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
return names, etal; -- all done, return our list of names
end


--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
 
]]
 
local function extra_text_in_page_check (page)
-- local good_pattern = '^P[^%.P%l]';
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
-- local bad_pattern = '^[Pp][Pp]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
 
if not page:match (good_pattern) and (page:match (bad_pattern) or  page:match ('^[Pp]ages?')) then
add_maint_cat ('extra_text');
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
end


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


Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
similarly, |editorn= (and aliases) highest and |editors= lowest


When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
test which mimicks the test used in extract_names() when looking for a hole in the author name listThere may be a better
|xxxxor-linkn= in argsIt then returns a table of assembled names just as extract_names() does.
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.
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.


In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.


]]
]]


local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local function parse_vauthors_veditors (args, vparam, list_name)
local lastfirst = false;
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
if select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', 1 ) or -- do this twice incase we have a first 1 without a last1
local v_name_table = {};
select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', 2 ) then
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
lastfirst=true;
local last, first, link, mask;
end
local corporate = false;
 
 
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
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)
(is_set (vxxxxors) and is_set (xxxxors)) or
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
(true == lastfirst and is_set (xxxxors)) then
add_vanc_error ();
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas


if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
for i, v_name in ipairs(v_name_table) do
if is_set (vxxxxors) then return 2 end;
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
if is_set (xxxxors) then return 3 end;
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
last = v_name:match ('^%(%((.+)%)%)$')
end
corporate = true;
 
elseif string.find(v_name, "%s") then
 
    lastfirstTable = {}
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
    lastfirstTable = mw.text.split(v_name, "%s")
 
    first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
    last  = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
    if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials
true; else, emits an error message and returns false.
end
 
else
]]
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
 
last = v_name; -- last name or single corporate name?  Doesn't support multiword corporate names? do we need this?
local function is_valid_parameter_value (value, name, possible)
end
if not is_set (value) then
return true; -- an empty parameter is ok
if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
elseif in_array(value:lower(), possible) then
add_vanc_error ();
return true;
end
else
-- this from extract_names ()
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
return false
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
end
return names, etal; -- all done, return our list of names
end
end


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


--[[--------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.


Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
Only one of these appropriate three will be used.  The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
characters following the opening bracket obey the rules of a uri scheme (see check_url())The test will also find
similarly, |editorn= (and aliases) highest and |editors= lowest
external wikilinks that use protocol relative urls.
 
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
test which mimicks the test used in extract_names() when looking for a hole in the author name listThere may be a better
way to do this, I just haven't discovered what that way is.
 
Emits an error message when more than one xxxxor name source is provided.
 
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.


]]
]]


local function is_parameter_ext_wikilink (value)
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
if value:match ("%[%[%a+:") then -- if a wikilink with namespace (interwiki)
local lastfirst = false;
return false;
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
elseif value:match ("%[%a[%a%d%+%.%-]*:.*%]") or value:match ("%[//.*%]") then -- does the param value contain an external wikilink?
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
-- elseif value:match ("%[%a[%a%d%+%.%-]*:%S.*%]") or value:match ("%[//.*%]") then -- does the param value contain an external wikilink?
lastfirst=true;
return true;
else
return false;
end
end
end


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


--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if is_set (vxxxxors) then return 2 end;
if is_set (xxxxors) then return 3 end;
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
end


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


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


local function check_for_url (parameter_list)
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
local error_message = '';
of allowable values (yes, y, true, no, etc).  When the parameter value has not been assigned a value (missing or empty
for k, v in pairs (parameter_list) do -- for each parameter in the list
in the source template) the function refurns true.  If the parameter value is one of the list of allowed values returns
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
true; else, emits an error message and returns false.
if is_set(error_message) then -- once we've added the first portion of the error message ...
 
error_message=error_message .. ", "; -- ... add a comma space separator
]]
end
 
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
local function is_valid_parameter_value (value, name, possible)
end
if not is_set (value) then
end
return true; -- an empty parameter is ok
if is_set (error_message) then -- done looping, if there is an error message, display it
elseif in_array(value:lower(), possible) then
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
return true;
else
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
end
end
end
end




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


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


]]
]]


local function citation0( config, args)
local function terminate_name_list (name_list, sepc)
--[[
if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
Load Input Parameters
return name_list .. " "; -- don't add another
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
else
]]
return name_list .. sepc .. ' '; -- otherwise terninate the name list
local A = argument_wrapper( args );
end
end


local i
 
local PPrefix = A['PPrefix']
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
local PPPrefix = A['PPPrefix']
 
local NoPP = A['NoPP']
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
or formatted issue, or an empty string if neither are set.
PPPrefix = ''; -- unset these, prefix if used is in |page= or |pages=
 
PPrefix = '';
]]
else
NoPP = nil; -- unset, used as a flag later
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not is_set (volume) and not is_set (issue) then
return '';
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
end
local vol = '';
-- Pick out the relevant fields from the arguments. Different citation templates
if is_set (volume) then
-- define different field names for the same underlying things.
if (4 < mw.ustring.len(volume)) then
local author_etal;
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
else
local Authors;
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
local NameListFormat = A['NameListFormat'];
 
do -- to limit scope of selected
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
if 1 == selected then
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
end
end
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end


local Coauthors = A['Coauthors'];
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
local Others = A['Others'];


local editor_etal;
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
The return order is:
local Editors;
page, pages, sheet, sheets
 
Singular has priority over plural when both are provided.
 
]]


do -- to limit scope of selected
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if 1 == selected then
if is_set (sheet) then
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
if 'journal' == origin then
elseif 2 == selected then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
else
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
elseif 3 == selected then
end
Editors = A['Editors']; -- use content of |editors=
elseif is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
end
end


local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
local Translators; -- assembled trnaslators name list
 
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
if is_set (page) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif is_set(pages) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
return '', '', '', ''; -- return empty strings
NameListFormat = ''; -- anything else, set to empty string
end
end
 
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
 
This is the main function doing the majority of the citation formatting.


local Year = A['Year'];
]]
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local Date = A['Date'];
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
local Chapter = A['Chapter'];
local ScriptChapter = A['ScriptChapter'];
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
local Degree = A['Degree'];
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
local ArchiveURL = A['ArchiveURL'];
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local ChapterURL = A['ChapterURL'];
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];


local Series = A['Series'];
local function citation0( config, args)
local Volume = A['Volume'];
--[[  
local Issue = A['Issue'];
Load Input Parameters
local Position = '';
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
local Page = A['Page'];
]]
local Pages = hyphen_to_dash( A['Pages'] );
local A = argument_wrapper( args );
local At = A['At'];
local i


local Edition = A['Edition'];
-- Pick out the relevant fields from the arguments.  Different citation templates
local PublicationPlace = A['PublicationPlace']
-- define different field names for the same underlying things.
local Place = A['Place'];
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
local PublisherName = A['PublisherName'];
local Authors;
local RegistrationRequired = A['RegistrationRequired'];
local NameListFormat = A['NameListFormat'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end


local Via = A['Via'];
do -- to limit scope of selected
local AccessDate = A['AccessDate'];
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
local ArchiveDate = A['ArchiveDate'];
if 1 == selected then
local Agency = A['Agency'];
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
local DeadURL = A['DeadURL']
elseif 2 == selected then
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
DeadURL = ''; -- anything else, set to empty string
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
end
end
end


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


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


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


local LayFormat = A['LayFormat'];
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local LayURL = A['LayURL'];
local Translators; -- assembled translators name list
local LaySource = A['LaySource'];
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
local Transcript = A['Transcript'];
local TranscriptFormat = A['TranscriptFormat'];
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local TranscriptURL = A['TranscriptURL']  
local Contributors; -- assembled contributors name list
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
local Contribution = A['Contribution'];
 
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
local LastAuthorAmp = A['LastAuthorAmp'];
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
if 0 < #c then
if not is_set (Contribution) then -- |contributor= requires |contribution=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
end
end
local no_tracking_cats = A['NoTracking'];
else -- if not a book cite
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters?
no_tracking_cats = nil; -- set to empty string
table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message
end
end
 
Contribution = nil; -- unset
--these are used by cite interview
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];
 
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local anchor_year; -- used in the CITEREF identifier
local COinS_date; -- used in the COinS metadata
 
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text


--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
NameListFormat = ''; -- anything else, set to empty string
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
break; -- bail out if one is found
end
end
end
end


-- check for extra |page=, |pages= or |at= parameters.
local Year = A['Year'];
if is_set(Page) then
local PublicationDate = A['PublicationDate'];
if is_set(Pages) or is_set(At) then
local OrigYear = A['OrigYear'];
Page = Page .. " " .. set_error('extra_pages'); -- add error message
local Date = A['Date'];
Pages = ''; -- unset the others
local LayDate = A['LayDate'];
At = '';
------------------------------------------------- Get title data
end
local Title = A['Title'];
extra_text_in_page_check (Page, NoPP); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
local ScriptTitle = A['ScriptTitle'];
elseif is_set(Pages) then
local BookTitle = A['BookTitle'];
if is_set(At) then
local Conference = A['Conference'];
Pages = Pages .. " " .. set_error('extra_pages'); -- add error messages
local TransTitle = A['TransTitle'];
At = ''; -- unset
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
if is_set (TitleLink) and false == link_param_ok (TitleLink) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=;
end
end
extra_text_in_page_check (Pages, NoPP); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
end


-- both |publication-place= and |place= (|location=) allowed if different
local Chapter = A['Chapter'];
if not is_set(PublicationPlace) and is_set(Place) then
local ScriptChapter = A['ScriptChapter'];
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
end
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
local Degree = A['Degree'];
local Docket = A['Docket'];
--[[
local ArchiveFormat = A['ArchiveFormat'];
Parameter remapping for cite encyclopedia:
local ArchiveURL = A['ArchiveURL'];
When the citation has these parameters:
local URL = A['URL']
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
|encyclopedia and |article then map |encyclopedia to |title
local ChapterURL = A['ChapterURL'];
|encyclopedia then map |encyclopedia to |title
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter


|trans_title maps to |trans_chapter when |title is re-mapped
local Series = A['Series'];
|url maps to |chapterurl when |title is remapped
local Volume;
local Issue;
local Page;
local Pages;
local At;


All other combinations of |encyclopedia, |title, and |article are not modified
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
Volume = A['Volume'];
end
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = A['Issue'];
end
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = hyphen_to_dash( A['Pages'] );
At = A['At'];
end


]]
local Edition = A['Edition'];
local PublicationPlace = A['PublicationPlace']
local Place = A['Place'];
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end


local Encyclopedia = A['Encyclopedia'];
local Via = A['Via'];
 
local AccessDate = A['AccessDate'];
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
local ArchiveDate = A['ArchiveDate'];
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
local Agency = A['Agency'];
if is_set(Title) or is_set (ScriptTitle) then
local DeadURL = A['DeadURL']
if not is_set(Chapter) then
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
DeadURL = ''; -- anything else, set to empty string
ScriptChapter = ScriptTitle;
TransChapter = TransTitle;
ChapterURL = URL;
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
end
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset
TransTitle = '';
URL = '';
Format = '';
TitleLink = '';
ScriptTitle = '';
end
else -- |title not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Periodical = ''; -- redundant so unset
end
end
end
end


-- Special case for cite techreport.
local Language = A['Language'];
if (config.CitationClass == "techreport") then -- special case for cite techreport
local Format = A['Format'];
if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue'
local ChapterFormat = A['ChapterFormat'];
if not is_set(ID) then -- can we use ID for the "number"?
local DoiBroken = A['DoiBroken'];
ID = Issue; -- yes, use it
local ID = A['ID'];
Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
local ASINTLD = A['ASINTLD'];
else -- can't use ID so emit error message
local IgnoreISBN = A['IgnoreISBN'];
ID = ID .. " " .. set_error('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
end
IgnoreISBN = nil; -- anything else, set to empty string
end
end
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
 
local ID_list = extract_ids( args );
 
local Quote = A['Quote'];
 
local LayFormat = A['LayFormat'];
local LayURL = A['LayURL'];
local LaySource = A['LaySource'];
local Transcript = A['Transcript'];
local TranscriptFormat = A['TranscriptFormat'];
local TranscriptURL = A['TranscriptURL']
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL


-- special case for cite interview
local LastAuthorAmp = A['LastAuthorAmp'];
if (config.CitationClass == "interview") then
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
if is_set(Program) then
LastAuthorAmp = nil; -- set to empty string
ID = ' ' .. Program;
end
end
if is_set(Callsign) then
local no_tracking_cats = A['NoTracking'];
if is_set(ID) then
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
ID = ID .. sepc .. ' ' .. Callsign;
no_tracking_cats = nil; -- set to empty string
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
end


if is_set(Others) then
--these are used by cite interview
if is_set(TitleType) then
local Callsign = A['Callsign'];
Others = ' ' .. TitleType .. ' with ' .. Others;
local City = A['City'];
TitleType = '';
local Program = A['Program'];
else
 
Others = ' ' .. 'Interview with ' .. Others;
--local variables that are not cs1 parameters
end
local use_lowercase; -- controls capitalization of certain static text
else
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
Others = '(Interview)';
local anchor_year; -- used in the CITEREF identifier
end
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
end


-- special case for cite mailing list
-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
if (config.CitationClass == "mailinglist") then
local Mode = A['Mode'];
Periodical = A ['MailingList'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text


-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
--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 'conference' == config.CitationClass then
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if is_set(BookTitle) then
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
Chapter = Title;
no_tracking_cats = "true"; -- set no_tracking_cats
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
end
ChapterURL = URL;
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
ChapterURLorigin = URLorigin;
if this_page.text:match (v) then -- test page name against each pattern
URLorigin = '';
no_tracking_cats = "true"; -- set no_tracking_cats
ChapterFormat = Format;
break; -- bail out if one is found
TransChapter = TransTitle;
end
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
end


-- cite map oddities
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
local Cartography = "";
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
local Scale = "";
 
local Sheet = A['Sheet'] or '';
local NoPP = A['NoPP']  
local Sheets = A['Sheets'] or '';
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
if config.CitationClass == "map" then
NoPP = true;
Chapter = A['Map'];
else
ChapterURL = A['MapURL'];
NoPP = nil; -- unset, used as a flag later
TransChapter = A['TransMap'];
end
ChapterURLorigin = A:ORIGIN('MapURL');
 
ChapterFormat = A['MapFormat'];
if is_set(Page) then
if is_set(Pages) or is_set(At) then
Cartography = A['Cartography'];
Pages = ''; -- unset the others
if is_set( Cartography ) then
At = '';
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
end
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
Scale = A['Scale'];
elseif is_set(Pages) then
if is_set( Scale ) then
if is_set(At) then
Scale = sepc .. " " .. Scale;
At = ''; -- unset
end
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title


-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
|trans_title maps to |trans_chapter when |title is re-mapped
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
|url maps to |chapterurl when |title is remapped
local AirDate = A['AirDate'];
 
local SeriesLink = A['SeriesLink'];
All other combinations of |encyclopedia, |title, and |article are not modified
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};


-- do common parameters first
]]
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) then -- promote airdate or Began/Ended to date
if is_set (AirDate) then
Date = AirDate;
end
end


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


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


if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
-- Special case for cite techreport.
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
if (config.CitationClass == "techreport") then -- special case for cite techreport
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
if not is_set(ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
-- ID = ID .. " " .. set_error('redundant_parameters', '<code>&#124;id=</code> and <code>&#124;number=</code>');
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
end
end
URL = ''; -- unset
end
TransTitle = '';
end
ScriptTitle = '';
 
-- special case for cite interview
else -- now oddities that are cite serial
if (config.CitationClass == "interview") then
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
if is_set(Program) then
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
ID = ' ' .. Program;
if is_set (Series) and is_set (SeriesLink) then
end
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
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
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.
if is_set(Others) then
if 'arxiv' == config.CitationClass then
if is_set(TitleType) then
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
Others = ' ' .. TitleType .. ' with ' .. Others;
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
TitleType = '';
elseif is_set (Series) then -- series is an alias of version
else
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
Others = ' ' .. 'Interview with ' .. Others;
Series = ''; -- unset
end
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
else
end
Others = '(Interview)';
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
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
Chapter = '';
URL = '';
Format = '';
Page = ''; Pages = ''; At = '';
end
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
end


-- handle type parameter for those CS1 citations that have default values
-- special case for cite mailing list
 
if (config.CitationClass == "mailinglist") then
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
Periodical = A ['MailingList'];
TitleType = set_titletype (config.CitationClass, TitleType);
elseif 'mailinglist' == A:ORIGIN('Periodical') then
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
Periodical = ''; -- unset because mailing list is only used for cite mailing list
TitleType = Degree .. " thesis";
end
end
end


if is_set(TitleType) then -- if type parameter is specified
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
TitleType = " (" .. TitleType .. ")"; -- display it in parentheses
if 'conference' == config.CitationClass then
end
if is_set(BookTitle) then
 
Chapter = Title;
-- 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.
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
if not is_set (Date) then
ChapterURL = URL;
Date = Year; -- promote Year to Date
ChapterURLorigin = URLorigin;
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
URLorigin = '';
if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
ChapterFormat = Format;
Date = PublicationDate; -- promote PublicationDate to Date
TransChapter = TransTitle;
PublicationDate = ''; -- unset, no longer needed
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
end


if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
-- cite map oddities
 
local Cartography = "";
--[[
local Scale = "";
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
local Sheet = A['Sheet'] or '';
we get the date used in the metadata.
local Sheets = A['Sheets'] or '';
 
if config.CitationClass == "map" then
Date validation supporting code is in Module:Citation/CS1/Date_validation
Chapter = A['Map'];
]]
ChapterURL = A['MapURL'];
do -- create defined block to contain local variables error_message and mismatch
TransChapter = A['TransMap'];
local error_message = '';
ChapterURLorigin = A:ORIGIN('MapURL');
-- AirDate has been promoted to Date so not necessary to check it
ChapterFormat = A['MapFormat'];
anchor_year, COinS_date, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year});
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


if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
local mismatch = year_date_check (Year, Date)
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
if 0 == mismatch then -- |year= does not match a year-value in |date=
local AirDate = A['AirDate'];
if is_set (error_message) then -- if there is already an error message
local SeriesLink = A['SeriesLink'];
error_message = error_message .. ', '; -- tack on this additional message
if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then
end
table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))});
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
end
end
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
Date = AirDate;
end
end


if is_set(error_message) then
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
local Season = A['Season'];
end
local SeriesNumber = A['SeriesNumber'];
end -- end of do


-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
-- 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
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
Embargo = is_embargoed (Embargo); --
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
 
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if not is_set (Embargo) then -- if not embargoed or embargo has expired
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
end
end
 
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- Test if citation has no title
if not is_set(Title) and
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; is there a better way to do this?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
end
end
end
-- assemble a table of parts concatenated later into Series
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
if 'none' == Title and is_set(Periodical) and not (( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia))) then -- special case
Chapter = Title; -- promote title parameters to chapter
Title = ''; -- set title to empty string
ScriptChapter = ScriptTitle;
add_maint_cat ('untitled');
ChapterLink = TitleLink; -- alias episodelink
end
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


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


-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
if 'arxiv' == config.CitationClass then
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
-- is the article title, and Chapter is a section within the article. So, we remap
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
elseif is_set (Series) then -- series is an alias of version
local coins_chapter = Chapter; -- default assuming that remapping not required
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
local coins_title = Title; -- et tu
Series = ''; -- unset
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
end
end
end
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
-- this is the function call to COinS()
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
local OCinSoutput = COinS({
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
['Periodical'] = Periodical,
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
['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.
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
Chapter = '';
URL = '';
Format = '';
Page = ''; Pages = ''; At = '';
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
end


-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
-- handle type parameter for those CS1 citations that have default values
if 'newsgroup' == config.CitationClass then
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
if is_set (PublisherName) then
TitleType = set_titletype (config.CitationClass, TitleType);
PublisherName = '[[Usenet newsgroup|Newsgroup]]:&nbsp;' .. external_link( 'news:' .. PublisherName, PublisherName );
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
end
end
end
end


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


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


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


do -- do editor name list first because coauthors can modify control table
Date validation supporting code is in Module:Citation/CS1/Date_validation
maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
]]
-- Preserve old-style implicit et al.
do -- create defined block to contain local variables error_message and mismatch
if not is_set(maximum) and #e == 4 then
local error_message = '';
maximum = 3;
-- AirDate has been promoted to Date so not necessary to check it
table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
end
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date);


control.maximum = maximum;
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;  
local mismatch = year_date_check (Year, Date)
last_first_list, EditorCount = list_people(control, e, editor_etal);
if 0 == mismatch then -- |year= does not match a year-value in |date=
 
if is_set (error_message) then -- if there is already an error message
if is_set (Editors) then
error_message = error_message .. ', '; -- tack on this additional message
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
end
else
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
Editors = last_first_list; -- either an author name list or an empty string
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
end
end
end


if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then  
if is_set(error_message) then
EditorCount = 2; -- spoof to display (eds.) annotation
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
end
end
do -- now do translators
end -- end of do
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);


if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
control.lastauthoramp = nil;
-- 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
control.maximum = #a + 1;
Embargo = is_embargoed (Embargo); --
end
last_first_list = list_people(control, a, author_etal);


if is_set (Authors) then
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
if not is_set (Embargo) then -- if not embargoed or embargo has expired
if author_etal then
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
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
 
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- Test if citation has no title
if not is_set(Title) and
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
else
Authors = last_first_list; -- either an author name list or an empty string
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
end
end
end
if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end


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


if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
-- 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
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
end


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


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


--[[
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
do -- do-block to limit scope of last_first_list
if 'newsgroup' == config.CitationClass then
local last_first_list;
if is_set (PublisherName) then
local maximum = A['DisplayAuthors'];
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
 
maximum , author_etal = get_display_authors_editors (maximum, #a, 'authors', author_etal);
 
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = maximum,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via authorlinkn
};
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
end
end
last_first_list = list_people(control, a, author_etal);


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


end -- end of do
if 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


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


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


if is_set (Editors) then
control.maximum = maximum;
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
 
if is_set (Editors) then
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
Editors = last_first_list; -- either an author name list or an empty string
end
 
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
else
Editors = last_first_list; -- either an author name list or an empty string
end
end
do -- now do translators
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
end
do -- now do contributors
control.maximum = #c; -- number of contributors
Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);


if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
EditorCount = 2; -- spoof to display (eds.) annotation
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal, 'author');
 
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
end
else
Authors = last_first_list; -- either an author name list or an empty string
end
end -- end of do
 
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
end
end
]]


-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
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');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', 'url');
Format = style_format (Format, URL, 'format', 'url');
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
-- special case for chapter format so no error message or cat when chapter not supported
if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end


if  not is_set(URL) then --and
if  not is_set(URL) then --and
-- not is_set(ArchiveURL) then --and -- prevents format_missing_url error from registering
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty
-- not is_set(ConferenceURL) and -- TODO: keep this here? conference as part of cite web or cite podcast?
-- not is_set(TranscriptURL) then -- TODO: remove? |transcript-url= and |transcript= has separate test
-- Test if cite web or cite podcast |url= is missing or empty
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
end
Line 2,959: Line 3,277:
end
end


local OriginalURL, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
DeadURL = DeadURL:lower(); -- used later when assembling archived text
DeadURL = DeadURL:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
if is_set( ArchiveURL ) then
if is_set (URL) then
if is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalFormat = Format; -- and original |format=
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
Line 2,972: Line 3,291:
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
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
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalFormat = ChapterFormat; -- and original |format=
OriginalFormat = ChapterFormat; -- and original |format=
if 'no' ~= DeadURL then
if 'no' ~= DeadURL then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
end
end
Line 2,981: Line 3,301:
end
end


if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", 'arxiv'}) or
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
if is_set (Chapter) or is_set (TransChapter) or is_set (ChapterURL) or is_set (ScriptChapter) then -- chapter parameters not supported for these citation types
local chap_param;
table.insert( z.message_tail, { set_error( 'chapter_ignored', {A:ORIGIN ('Chapter')}, true ) } ); -- add error message
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
Chapter = ''; -- set them to empty string to be safe with concatenation
chap_param = A:ORIGIN ('Chapter')
elseif is_set (TransChapter) then
chap_param = A:ORIGIN ('TransChapter')
elseif is_set (ChapterURL) then
chap_param = A:ORIGIN ('ChapterURL')
elseif is_set (ScriptChapter) then
chap_param = A:ORIGIN ('ScriptChapter')
else is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
 
if is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
TransChapter = '';
ChapterURL = '';
ChapterURL = '';
ScriptChapter = '';
ScriptChapter = '';
ChapterFormat = '';
end
end
else -- otherwise, format chapter / article title
else -- otherwise, format chapter / article title
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin);
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
 
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
if is_set (Chapter) then
if is_set (Chapter) then
if 'map' == config.CitationClass and is_set (TitleType) then
if 'map' == config.CitationClass and is_set (TitleType) then
Line 2,997: Line 3,338:
end
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
end
end
Line 3,005: Line 3,348:
end
end


if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", "mailinglist", 'arxiv'}) or
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Line 3,035: Line 3,378:
if is_set(Title) then
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then  
if not is_set(TitleLink) and is_set(URL) then  
Title = external_link( URL, Title ) .. TransError .. Format;
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
URL = "";
URL = "";
Format = "";
Format = "";
Line 3,049: Line 3,392:
if is_set (Conference) then
if is_set (Conference) then
if is_set (ConferenceURL) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference );
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
end
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
Conference = sepc .. " " .. Conference .. ConferenceFormat;
Line 3,058: Line 3,401:
if not is_set(Position) then
if not is_set(Position) then
local Minutes = A['Minutes'];
local Minutes = A['Minutes'];
local Time = A['Time'];
if is_set(Minutes) then
if is_set(Minutes) then
if is_set (Time) then
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
else
local Time = A['Time'];
if is_set(Time) then
if is_set(Time) then
local TimeCaption = A['TimeCaption']
local TimeCaption = A['TimeCaption']
Line 3,076: Line 3,423:
Position = " " .. Position;
Position = " " .. Position;
At = '';
At = '';
end
if not is_set(Page) then
if is_set(Pages) then
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
Pages = ": " .. Pages;
elseif tonumber(Pages) ~= nil then
Pages = sepc .." " .. PPrefix .. Pages;
else
Pages = sepc .." " .. PPPrefix .. Pages;
end
end
else
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then
Page = ": " .. Page;
else
Page = sepc .." " .. PPrefix .. Page;
end
end
end


if 'map' == config.CitationClass then -- cite map oddity done after COinS call (and with other in-source locators)
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
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 "";
At = is_set(At) and (sepc .. " " .. At) or "";
Line 3,170: Line 3,467:
Edition = '';
Edition = '';
end
end
Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
 
Series = is_set(Series) and (sepc .. " " .. Series) or "";
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";


if is_set(Volume) then
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
if ( mw.ustring.len(Volume) > 4 )
  then Volume = sepc .." " .. Volume;
  else Volume = " <b>" .. hyphen_to_dash(Volume) .. "</b>";
end
end


------------------------------------ totally unrelated data
------------------------------------ totally unrelated data
Line 3,225: Line 3,517:


if is_set(Quote) then
if is_set(Quote) then
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' 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);
Quote = Quote:sub(2,-2); -- strip them off
end
end
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- CS1 does not supply terminal punctuation when |quote= is set
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
end
Line 3,241: Line 3,533:
if sepc ~= "." then arch_text = arch_text:lower() end
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
{ external_link( ArchiveURL, arch_text ) .. ArchiveFormat, ArchiveDate } );
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');    
Archived = Archived .. " " .. set_error('archive_missing_url');    
Line 3,248: Line 3,540:
local arch_text = cfg.messages['archived-dead'];
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if sepc ~= "." then arch_text = arch_text:lower() end
-- if 'usurped' == DeadURL then -- when original has unsuitable content do not link
if in_array (DeadURL, {'unfit', 'usurped'}) then
if in_array (DeadURL, {'unfit', 'usurped'}) then
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
else -- DeadURL is empty, 'yes', 'true', or 'y'
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'] ) .. OriginalFormat, ArchiveDate } ); -- format already styled
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
end
else
else
Line 3,276: Line 3,567:
end
end
if sepc == '.' then
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'] ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
else
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower() ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
end
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Line 3,286: Line 3,577:
if is_set(Transcript) then
if is_set(Transcript) then
if is_set(TranscriptURL) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript );
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
end
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
Line 3,360: Line 3,651:
-- not to keep reassigning to the same string variable over and over.
-- not to keep reassigning to the same string variable over and over.


local tcommon
local tcommon;
local tcommon2; -- used for book cite when |contributor= is set
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
if is_set(Others) then Others = Others .. sepc .. " " end
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,  
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,  
Language, Edition, Publisher, Agency, Volume, Issue}, sepc );
Language, Edition, Publisher, Agency, Volume}, sepc );
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
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
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
elseif is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume, Issue}, sepc );
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
Line 3,379: Line 3,680:
else -- all other CS1 templates
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
Volume, Issue, Others, Edition, Publisher, Agency}, sepc );
Volume, Others, Edition, Publisher, Agency}, sepc );
end
end
Line 3,390: Line 3,691:
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local text;
local pgtext = Position .. Sheet .. Page .. Pages .. At;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 
if is_set(Date) then
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
else -- neither of authors and editors set
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
else
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
end
end
end
if is_set(Authors) then
if is_set(Authors) then
if is_set(Coauthors) then
if is_set(Coauthors) then
local sep = '; ';
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
if 'vanc' == NameListFormat then
Authors = Authors .. ', ' .. Coauthors;
sep = ', ';
else
Authors = Authors .. '; ' .. Coauthors;
end
end
Authors = Authors .. sep .. Coauthors;
end
end
if is_set(Date) then
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
Date = " ("..Date..")" .. OrigYear .. sepc .. " "
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
elseif string.sub(Authors,-1,-1) == sepc then
Authors = Authors .. " "
else
Authors = Authors .. sepc .. " "
end
end
if is_set(Editors) then
if is_set(Editors) then
local in_text = " ";
local in_text = " ";
local post_text = "";
local post_text = "";
if is_set(Chapter) then
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
else
else
if EditorCount <= 1 then
if EditorCount <= 1 then
Line 3,419: Line 3,728:
end
end
end  
end  
if (sepc ~= '.') then in_text = in_text:lower() end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
Editors = in_text .. Editors .. post_text;
end
if (string.sub(Editors,-1,-1) == sepc) or (string.sub(Editors,-3,-1) == sepc .. ']]') then -- if last editor name ends with sepc char
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
Editors = Editors .. " "; -- don't add another
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
else
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Editors = Editors .. sepc .. " " -- otherwise terninate the editor list
Authors = by_text .. Authors; -- author follows title so tweak it here
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
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
end
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
elseif is_set(Editors) then
elseif is_set(Editors) then
if is_set(Date) then
if is_set(Date) then
Line 3,436: Line 3,751:
Editors = Editors .. ", " .. cfg.messages['editors'];
Editors = Editors .. ", " .. cfg.messages['editors'];
end
end
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
else
else
if EditorCount <= 1 then
if EditorCount <= 1 then
Line 3,444: Line 3,758:
end
end
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon}, sepc );
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
else
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
if config.CitationClass=="journal" and is_set(Periodical) then
text = safe_join( {Chapter, Place, tcommon}, sepc );
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
text = safe_join( {text, pgtext, Date, idcommon}, sepc );
else
else
text = safe_join( {Chapter, Place, tcommon, Date}, sepc );
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
end
end
end
end
Line 3,479: Line 3,784:
end
end
if is_set(Ref) and Ref:lower() ~= "none" then
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
local id = Ref
if ( "harv" == Ref ) then
if ('harv' == Ref ) then
local names = {} --table of last names & year
local namelist = {}; -- holds selected contributor, author, editor name list
if #a > 0 then
-- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
for i,v in ipairs(a) do
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
names[i] = v.last
 
if i == 4 then break end
if #c > 0 then -- if there is a contributor list
end
namelist = c; -- select it
elseif #e > 0 then
elseif #a > 0 then -- or an author list
for i,v in ipairs(e) do
namelist = a;
names[i] = v.last
elseif #e > 0 then -- or an editor list
if i == 4 then break end
namelist = e;
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 (namelist, year); -- go make the CITEREF anchor
id = anchor_id(names)
end
end
options.id = id;
options.id = id;
Line 3,514: Line 3,817:
local empty_span = '<span style="display:none;">&nbsp;</span>';
local empty_span = '<span style="display:none;">&nbsp;</span>';
-- Note: Using display: none on then COinS span breaks some clients.
-- Note: Using display: none on the COinS span breaks some clients.
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
text = text .. OCinS;
text = text .. OCinS;
Line 3,555: Line 3,858:
end
end


-- This is used by templates such as {{cite book}} to create the actual citation text.
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the first match.
 
Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the
replacement character.  That replacement character is not detected by this test though it is visible to readers
of the rendered citation.  This function will detect the replacement character when it is part of the wikisource.
 
Output of this function is an error message that identifies the character or the Unicode group that the character
belongs to along with its position in the parameter value.
 
]]
 
local function has_invisible_chars (param, v)
local position = '';
local i=1;
 
while cfg.invisible_chars[i] do
local char=cfg.invisible_chars[i][1] -- the character or group name
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position then
table.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('parameter', param), position}, true ) } ); -- add error message
return; -- and done with this parameter
end
i=i+1; -- bump our index
end
end
 
 
--[[--------------------------< Z . C I T A T I O N >----------------------------------------------------------
 
This is used by templates such as {{cite book}} to create the actual citation text.
 
]]
 
function z.citation(frame)
function z.citation(frame)
local pframe = frame:getParent()
local pframe = frame:getParent()
Line 3,618: Line 3,956:
end
end
end
end
-- if #suggestions == 0 then
-- suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
-- end
-- if suggestions[ k:lower() ] ~= nil then
-- error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
-- else
-- error_text, error_state = set_error( 'parameter_ignored', {k}, true );
-- end
end    
end    
if error_text ~= '' then
if error_text ~= '' then
Line 3,636: Line 3,966:
end
end
end
end
 
for k, v in pairs( args ) do
has_invisible_chars (k, v)
end
return citation0( config, args)
return citation0( config, args)
end
end


return z
return z
Anonymous user