Difference between revisions of "Module:Citation/CS1"
From Γνωσιακή Βάση Υπηρεσιών και Διαδικασιών του Δημοσίου Τομέα
m (Εισήχθη 1 αναθεώρηση) |
Mandravinus (talk | contribs) m (Εισήχθη 1 αναθεώρηση) |
(No difference)
| |
Latest revision as of 14:27, 5 February 2018
Documentation for this module may be created at Module:Citation/CS1/doc
local z = {
error_categories = {}; -- for categorizing citations that contain errors
error_ids = {};
message_tail = {};
maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance
}
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {}; -- talbe of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
--[[--------------------------< I S _ S E T >------------------------------------------------------------------
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string.
This function is global because it is called from both this module and from Date validation
]]
function is_set( var )
return not (var == nil or var == '');
end
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
First set variable or nil if none
]]
local function first_set(...)
local list = {...};
for _, var in pairs(list) do
if is_set( var ) then
return var;
end
end
end
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
Whether needle is in haystack
]]
local function in_array( needle, haystack )
if needle == nil then
return false;
end
for n,v in ipairs( haystack ) do
if v == needle then
return n;
end
end
return false;
end
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
Populates numbered arguments in a message string using an argument table.
]]
local function substitute( msg, args )
return args and mw.message.newRawMessage( msg, args ):plain() or msg;
end
--[[--------------------------< E R R O R _ C O M M E N T >----------------------------------------------------
Wraps error messages with css markup according to the state of hidden.
]]
local function error_comment( content, hidden )
return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
end
--[[--------------------------< S E T _ E R R O R >--------------------------------------------------------------
Sets an error condition and returns the appropriate error message. The actual placement of the error message in the output is
the responsibility of the calling function.
]]
local function set_error( error_id, arguments, raw, prefix, suffix )
local error_state = cfg.error_conditions[ error_id ];
prefix = prefix or "";
suffix = suffix or "";
if error_state == nil then
error( cfg.messages['undefined_error'] );
elseif is_set( error_state.category ) then
table.insert( z.error_categories, error_state.category );
end
local message = substitute( error_state.message, arguments );
message = message .. " ([[" .. cfg.messages['help page link'] ..
"#" .. error_state.anchor .. "|" ..
cfg.messages['help page label'] .. "]])";
z.error_ids[ error_id ] = true;
if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
and z.error_ids['citation_missing_title'] then
return '', false;
end
message = table.concat({ prefix, message, suffix });
if raw == true then
return message, error_state.hidden;
end
return error_comment( message, error_state.hidden );
end
--[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------
Adds a category to z.maintenance_cats using names from the configuration file with additional text if any.
]]
local function add_maint_cat (key, arguments)
table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table
end
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
]]
local function add_prop_cat (key, arguments)
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
Determines whether a URL string is valid.
At present the only check is whether the string appears to be prefixed with a URI scheme. It is not determined whether
the URI scheme is valid or whether the URL is otherwise well formed.
]]
local function check_url( url_str )
return url_str:sub(1,2) == "//" or url_str:match( "^[^/]*:" ) ~= nil; -- Protocol-relative or URL scheme
end
--[[--------------------------< S A F E _ F O R _ I T A L I C S >----------------------------------------------
Protects a string that will be wrapped in wiki italic markup '' ... ''
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 safe_for_italics( str )
if not is_set(str) then
return str;
else
if str:sub(1,1) == "'" then str = "<span />" .. str; end
if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
-- Remove newlines as they break italics.
return str:gsub( '\n', ' ' );
end
end
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
Escape sequences for content that will be used for URL descriptions
]]
local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
end
return str:gsub( '[%[%]\n]', {
['['] = '[',
[']'] = ']',
['\n'] = ' ' } );
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
argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason
this function is similar to but separate from wrap_msg().
]]
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
return substitute( cfg.presentation[key], {str} );
end
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
Format an external link with error checking
]]
local function external_link( URL, label, source )
local error_str = "";
if not is_set( label ) then
label = URL;
if is_set( source ) then
error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
else
error( cfg.messages["bare_url_no_origin"] );
end
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {}, false, " " ) .. error_str;
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end
--[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
Formats a wiki style external link
]]
local function external_link_id(options)
local url_string = options.id;
if options.encode == true or options.encode == nil then
url_string = mw.uri.encode( url_string );
end
return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
options.link, options.label, options.separator or " ",
options.prefix, url_string, options.suffix or "",
mw.text.nowiki(options.id)
);
end
--[[
Categorize and emit an error message when the citation contains one or more deprecated parameters. Because deprecated parameters (currently |month=,
|coauthor=, and |coauthors=) aren't related to each other and because these parameters may be concatenated into the variables used by |date= and |author#= (and aliases)
details of which parameter caused the error message are not provided. Only one error message is emitted regardless of the number of deprecated parameters in the citation.
]]
local function deprecated_parameter(name)
if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a
Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
end
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.
Call this function for chapter titles, for website titles, etc; not for book titles.
]]
local function kern_quotes (str)
local cap='';
local cap2='';
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if is_set (cap) then
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
if is_set (cap) then
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
return str;
end
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.
|script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon:
|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
|script-title=ja : *** ***
|script-title=ja: *** ***
|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
The prefix is checked for validity. If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
is not added. At this time there is no error message for this condition.
At this writing, only |script-title= is supported. It is anticipated that additional parameters will be created to use this function.
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
local function format_script_value (script_value)
local lang=''; -- initialize to empty string
local name;
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not is_set (lang) then
return ''; -- script_value was just the prefix so return empty string
end
-- if we get this far we have prefix and script
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'hy', 'ja', 'ka', 'ko', 'ku', 'he', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
add_prop_cat ('script_with_name', {name, lang})
else
add_prop_cat ('script')
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
return script_value;
end
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
wrapped in <bdi> tags.
]]
local function script_concatenate (title, script)
if is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
return title;
end
--[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
configuration taking one argument. Supports lower case text for {{citation}} templates. Additional text taken
from citation_config.messages - the reason this function is similar to but separate from wrap_style().
]]
local function wrap_msg (key, str, lower)
if not is_set( str ) then
return "";
end
if true == lower then
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
str = substitute( msg, {str} ); -- including template text
return str;
else
return substitute( cfg.messages[key], {str} );
end
end
--[[--------------------------< S E L E C T _ O N E >----------------------------------------------------------
Chooses one matching parameter from a list of parameters to consider
Generates an error if more than one match is present.
]]
local function select_one( args, possible, error_condition, index )
local value = nil;
local selected = '';
local error_list = {};
if index ~= nil then index = tostring(index); end
-- Handle special case of "#" replaced by empty string
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
for _, v in ipairs( possible ) do
if index ~= nil then
v = v:gsub( "#", index );
end
if is_set(args[v]) then
if value ~= nil and selected ~= v then
table.insert( error_list, v );
else
value = args[v];
selected = v;
end
end
end
if #error_list > 0 then
local error_str = "";
for _, k in ipairs( error_list ) do
if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
error_str = error_str .. wrap_style ('parameter', k);
end
if #error_list > 1 then
error_str = error_str .. cfg.messages['parameter-final-separator'];
else
error_str = error_str .. cfg.messages['parameter-pair-separator'];
end
error_str = error_str .. wrap_style ('parameter', selected);
table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } );
end
return value, selected;
end
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
Format the three chapter parameters: |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
parameter (chapter_url_source used for error messages).
]]
local function format_chapter_title (chapter, transchapter, chapterurl, chapter_url_source)
local chapter_error = '';
if not is_set (chapter) then
chapter = ''; -- just to be safe for concatenation
if is_set (transchapter) then
chapter = wrap_style ('trans-quoted-title', transchapter);
chapter_error = " " .. set_error ('trans_missing_chapter');
end
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
end
return chapter .. chapter_error;
else -- here when chapter is set
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
chapter = wrap_style ('quoted-title', chapter);
if is_set (transchapter) then
transchapter = wrap_style ('trans-quoted-title', transchapter);
chapter = chapter .. ' ' .. transchapter;
end
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter); -- adds bare_url_missing_title error if appropriate
end
end
return chapter;
end
--[[
Argument wrapper. This function provides support for argument
mapping defined in the configuration file so that multiple names
can be transparently aliased to single internal variable.
]]
local function argument_wrapper( args )
local origin = {};
return setmetatable({
ORIGIN = function( self, k )
local dummy = self[k]; --force the variable to be loaded.
return origin[k];
end
},
{
__index = function ( tbl, k )
if origin[k] ~= nil then
return nil;
end
local args, list, v = args, cfg.aliases[k];
if type( list ) == 'table' then
v, origin[k] = select_one( args, list, 'redundant_parameters' );
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
end
elseif list ~= nil then
v, origin[k] = args[list], list;
else
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
end
-- Empty strings, not nil;
if v == nil then
v = cfg.defaults[k] or '';
origin[k] = '';
end
tbl = rawset( tbl, k, v );
return v;
end,
});
end
--[[
Looks for a parameter's name in the whitelist.
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
local function validate( name )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
-- Normal arguments
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- Not supported because not found or name is set to nil
end
-- Formats a wiki style internal link
local function internal_link_id(options)
return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
options.link, options.label, options.separator or " ",
options.prefix, options.id, options.suffix or "",
mw.text.nowiki(options.id)
);
end
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
DOES NOT yet support MMMM YYYY or any of the date ranges.
]]
local function nowrap_date (date)
local cap='';
local cap2='';
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
date = substitute (cfg.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s*%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s*%d%d%d%d$") then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
return date;
end
--[[--------------------------< IS _ V A L I D _ I S X N >-----------------------------------------------------
ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn().
If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes,
spaces and other non-isxn characters.
]]
local function is_valid_isxn (isxn_str, len)
local temp = 0;
isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58
len = len+1; -- adjust to be a loop counter
for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58)
temp = temp + 10*( len - i ); -- it represents 10 decimal
else
temp = temp + tonumber( string.char(v) )*(len-i);
end
end
return temp % 11 == 0; -- returns true if calculation result is zero
end
--[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------
Determines whether an ISBN string is valid
]]
local function check_isbn( isbn_str )
if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
local len = isbn_str:len();
if len ~= 10 and len ~= 13 then
return false;
end
if len == 10 then
if isbn_str:match( "^%d*X?$" ) == nil then return false; end
return is_valid_isxn(isbn_str, 10);
else
local temp = 0;
if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979
isbn_str = { isbn_str:byte(1, len) };
for i, v in ipairs( isbn_str ) do
temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) );
end
return temp % 10 == 0;
end
end
--[[--------------------------< I S S N >----------------------------------------------------------------------
Validate and format an issn. This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four
digits with a space. When that condition occurred, the resulting link looked like this:
|issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
This code now prevents that by inserting a hyphen at the issn midpoint. It also validates the issn for length and makes sure that the checkdigit agrees
with the calculated value. Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn
error message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits.
]]
local function issn(id)
local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate
local handler = cfg.id_handlers['ISSN'];
local text;
local valid_issn = true;
id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn
if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position
valid_issn=false; -- wrong length or improper character
else
valid_issn=is_valid_isxn(id, 8); -- validate issn
end
if true == valid_issn then
id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
else
id = issn_copy; -- if not valid, use the show the invalid issn with error message
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if false == valid_issn then
text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid
end
return text
end
--[[--------------------------< A M A Z O N >------------------------------------------------------------------
Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
]]
local function amazon(id, domain)
local err_cat = ""
if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
else
if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X)
if check_isbn( id ) then -- see if asin value is isbn10
add_maint_cat ('ASIN');
elseif not is_set (err_cat) then
err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10
end
elseif not id:match("^%u[%d%u]+$") then
err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
end
end
if not is_set(domain) then
domain = "com";
elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
domain = "co." .. domain;
elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
end
local handler = cfg.id_handlers['ASIN'];
return external_link_id({link = handler.link,
label=handler.label , prefix="//www.amazon."..domain.."/dp/",id=id,
encode=handler.encode, separator = handler.separator}) .. err_cat;
end
--[[--------------------------< A R X I V >--------------------------------------------------------------------
See: http://arxiv.org/help/arxiv_identifier
format and error check arXiv identifier. There are three valid forms of the identifier:
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 handler = cfg.id_handlers['ARXIV'];
local year, month, version;
local err_cat = '';
local text;
if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version
year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month
((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years)
((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)?
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version
year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$");
year = tonumber(year);
month = tonumber(month);
if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years)
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message
end
else
err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format
end
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
if is_set (class) then
class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
else
class = ''; -- empty string for concatenation
end
return text .. class;
end
--[[
lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
1. Remove all blanks.
2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
3. If there is a hyphen in the string:
a. Remove it.
b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
1. All these characters should be digits, and there should be six or less. (not done in this function)
2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function.
]]
local function normalize_lccn (lccn)
lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace
if nil ~= string.find (lccn,'/') then
lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it
end
local prefix
local suffix
prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix
if nil ~= suffix then -- if there was a hyphen
suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6
lccn=prefix..suffix; -- reassemble the lccn
end
return lccn;
end
--[[
Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the
rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
length = 8 then all digits
length = 9 then lccn[1] is lower case alpha
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
length = 12 then lccn[1] and lccn[2] are both lower case alpha
]]
local function lccn(lccn)
local handler = cfg.id_handlers['LCCN'];
local err_cat = ''; -- presume that LCCN is valid
local id = lccn; -- local copy of the lccn
id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes)
local len = id:len(); -- get the length of the lccn
if 8 == len then
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits)
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
end
elseif 9 == len then -- LCCN should be adddddddd
if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
end
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
elseif 12 == len then -- LCCN should be aadddddddddd
if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern
err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message
end
else
err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message
end
if not is_set (err_cat) and nil ~= lccn:find ('%s') then
err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
--[[
Format PMID and do simple error checking. PMIDs are sequential numbers beginning at 1 and counting up. This code checks the PMID to see that it
contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.
]]
local function pmid(id)
local test_limit = 30000000; -- update this value as PMIDs approach
local handler = cfg.id_handlers['PMID'];
local err_cat = ''; -- presume that PMID is valid
if id:match("[^%d]") then -- if PMID has anything but digits
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
else -- PMID is only digits
local id_num = tonumber(id); -- convert id to a number for range testing
if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries
err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
end
end
return external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
--[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------
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.
]]
local function is_embargoed (embargo)
if is_set (embargo) then
local lang = mw.getContentLanguage();
local good1, embargo_date, good2, todays_date;
good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
good2, todays_date = pcall( lang.formatDate, lang, 'U' );
if good1 and good2 then -- if embargo date and today's date are good dates
if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future?
return embargo; -- still embargoed
else
add_maint_cat ('embargo')
return ''; -- unset because embargo has expired
end
end
end
return ''; -- |embargo= not set return empty string
end
--[[--------------------------< P M C >------------------------------------------------------------------------
Format a PMC, do simple error checking, and check for embargoed articles.
The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
be linked to the article. If the embargo date is today or in the past, or if it is empty or omitted, then the
PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation
has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link. Function is_embargoed ()
returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string.
PMCs are sequential numbers beginning at 1 and counting up. This code checks the PMC to see that it contains only digits and is less
than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued.
]]
local function pmc(id, embargo)
local test_limit = 5000000; -- update this value as PMCs approach
local handler = cfg.id_handlers['PMC'];
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
if is_set (embargo) then -- is PMC is still embargoed?
text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
else
text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat;
end
return text;
end
-- Formats a DOI and checks for DOI errors.
-- DOI names contain two parts: prefix and suffix separated by a forward slash.
-- 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.
-- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash,
-- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names.
local function doi(id, inactive)
local 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
if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma
cat = ' ' .. set_error( 'bad_doi' );
end
return text .. inactive .. cat
end
-- Formats an OpenLibrary link, and checks for associated errors.
local function openlibrary(id)
local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
local handler = cfg.id_handlers['OL'];
if ( code == "A" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/authors/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "M" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix="http://openlibrary.org/books/OL",id=id, separator=handler.separator,
encode = handler.encode})
elseif ( code == "W" ) then
return external_link_id({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/works/OL",id=id, separator=handler.separator,
encode = handler.encode})
else
return external_link_id({link=handler.link, label=handler.label,
prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator,
encode = handler.encode}) ..
' ' .. set_error( 'bad_ol' );
end
end
--[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
'<' and/or '>' angle brackets.
]]
local function message_id (id)
local handler = cfg.id_handlers['USENETID'];
text = external_link_id({link = handler.link, label = handler.label,
prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid
end
return text
end
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
]]
local function set_titletype (cite_class, title_type)
if is_set(title_type) then
if "none" == title_type then
title_type = ""; -- if |type=none then type parameter not displayed
end
return title_type; -- if |type= has been set to any other value use that value
end
return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation
end
--[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
Removes irrelevant text and dashes from ISBN number
Similar to that used for Special:BookSources
]]
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 strip_apostrophe_markup (argument)
if not is_set (argument) then return argument; end
while true do
if argument:match ("%'%'%'%'%'") then -- bold italic (5)
argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it
elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4)
argument=argument:gsub("%'%'%'%'", "");
elseif argument:match ("%'%'%'") then -- bold (3)
argument=argument:gsub("%'%'%'", "");
elseif argument:match ("%'%'") then -- italic (2)
argument=argument:gsub("%'%'", "");
else
break;
end
end
return argument; -- done
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)
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)
if is_set (title) then
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
else
title=''; -- if not set, make sure title is an empty string
end
if is_set (script) then
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
else
script=''; -- if not set, make sure script is an empty string
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
return title .. script; -- return the concatenation
end
--[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------
Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
]]
local function get_coins_pages (pages)
local pattern;
if not is_set (pages) then return pages; end -- if no page numbers then we're done
while true do
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 (– etc.) with hyphens; do we need to replace numerical entities like   and the like?
return pages;
end
-- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
local function remove_wiki_link( str )
return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
end));
end
-- Converts a hyphen to a dash
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
Joins a sequence of strings together while checking for duplicate separation characters.
]]
local function safe_join( tbl, duplicate_char )
--[[
Note: we use string functions here, rather than ustring functions.
This has considerably faster performance and should work correctly as
long as the duplicate_char is strict ASCII. The strings
in tbl may be ASCII or UTF8.
]]
local str = ''; -- the output string
local comp = ''; -- what does 'comp' mean?
local end_chr = '';
local trim;
for _, value in ipairs( tbl ) do
if value == nil then value = ''; end
if str == '' then -- if output string is empty
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string)
else
comp = value;
end
-- typically duplicate_char is sepc
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
-- Because individual string segments often (always?) begin with terminal punct for th
-- preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
end_chr = str:sub(-1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = str:sub(1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:sub(1,-3); -- remove them both
end
end
if trim then
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; --add it to the output string
end
end
return str;
end
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and past it here
because the code editor gets confused between character insertion point and cursor position.
]]
local function is_good_vanc_name (last, first)
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
if true ~= Page_in_vanc_error_cat then -- if we haven't been here before then set a sticky flag
Page_in_vanc_error_cat=true; -- so that if there are more than one error the category is added only once
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
end
return false; -- not a string of latin characters; Vancouver required Romanization
end;
return true;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-format=vanc.
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
]]
local function reduce_to_initials(first)
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
local initials = {}
local i = 0; -- counter for number of initials
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
i = i + 1; -- bump the counter
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
Formats a list of people (e.g. authors / editors)
]]
local function list_people(control, people, etal)
local sep;
local namesep;
local format = control.format
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
local text = {}
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = ','; -- name-list separator between authors is a comma
namesep = ' '; -- last/first separator is a space
else
sep = ';' -- name-list separator between authors is a semicolon
namesep = ', ' -- last/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("—",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if is_good_vanc_name (one, first) then -- and name is all Latin characters
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
if is_set(person.link) and ((nil ~= person.link:find("//")) or (nil ~= person.link:find("[%[%]]"))) then
one = one .. " " .. set_error( 'bad_authorlink' ) end -- url or wikilink in author link;
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
local count = #text / 2;
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & ";
end
text[#text] = nil;
end
local result = table.concat(text) -- construct list
if etal then
local etal_text = cfg.messages['et al'];
result = result .. " " .. etal_text;
end
return result, count
end
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
]]
local function anchor_id( options )
local id = table.concat( options ); -- 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
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
find |last4= and |last5= then the search is done.
This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the
template's metadata. When this occurs, the page is added to a maintenance category.
]]
local function extract_names(args, list_name)
local names = {}; -- table of names
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
local pattern = ",? *'*[Ee][Tt] *[Aa][Ll][%.']*$" -- variations on the 'et al' theme
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
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 );
local name = tostring(last);
if name:match (pattern) then -- varients on et al.
last = name:gsub (pattern, ''); -- if found, remove
etal = true;
end
name = tostring(first);
if name:match (pattern) then -- varients on et al.
first = name:gsub (pattern, ''); -- if found, remove
etal = true;
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}; -- add this name to our names list
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
if true == etal then
add_maint_cat ('etal');
end
return names, etal; -- all done, return our list of names
end
-- Populates ID table from arguments using configuration settings
local function extract_ids( args )
local id_list = {};
for k, v in pairs( cfg.id_handlers ) do
v = select_one( args, v.parameters, 'redundant_parameters' );
if is_set(v) then id_list[k] = v; end
end
return id_list;
end
--[[--------------------------< B U I L D _ I D _ L I S T >--------------------------------------------------------
Takes a table of IDs and turns it into a table of formatted ID outputs.
]]
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( id_list ) do
-- fallback to read-only cfg
handler = setmetatable( { ['id'] = v }, fallback(k) );
if handler.mode == 'external' then
table.insert( new_list, {handler.label, external_link_id( handler ) } );
elseif handler.mode == 'internal' then
table.insert( new_list, {handler.label, internal_link_id( handler ) } );
elseif handler.mode ~= 'manual' then
error( cfg.messages['unknown_ID_mode'] );
elseif k == 'DOI' then
table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
elseif k == 'ARXIV' then
table.insert( new_list, {handler.label, arxiv( v, options.Class ) } );
elseif k == 'ASIN' then
table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
elseif k == 'LCCN' then
table.insert( new_list, {handler.label, lccn( v ) } );
elseif k == 'OL' then
table.insert( new_list, {handler.label, openlibrary( v ) } );
elseif k == 'PMC' then
table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
elseif k == 'PMID' then
table.insert( new_list, {handler.label, pmid( v ) } );
elseif k == 'ISSN' then
table.insert( new_list, {handler.label, issn( v ) } );
elseif k == 'ISBN' then
local ISBN = internal_link_id( handler );
if not check_isbn( v ) and not is_set(options.IgnoreISBN) then
ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" );
end
table.insert( new_list, {handler.label, ISBN } );
elseif k == 'USENETID' then
table.insert( new_list, {handler.label, message_id( v ) } );
else
error( cfg.messages['unknown_manual_ID'] );
end
end
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
-- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse
-- the citation information.
local function COinS(data, class)
if 'table' ~= type(data) or nil == next(data) then
return '';
end
local ctx_ver = "Z39.88-2004";
-- treat table strictly as an array with only set values.
local OCinSoutput = setmetatable( {}, {
__newindex = function(self, key, value)
if is_set(value) then
rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
end
end
});
if is_set(data.Chapter) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
OCinSoutput["rft.genre"] = "bookitem";
OCinSoutput["rft.atitle"] = data.Chapter;
OCinSoutput["rft.btitle"] = data.Title;
elseif is_set(data.Periodical) then
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal";
if 'arxiv' == class then
OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
else
OCinSoutput["rft.genre"] = "article";
end
OCinSoutput["rft.jtitle"] = data.Periodical;
OCinSoutput["rft.atitle"] = data.Title;
else
OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
OCinSoutput["rft.genre"] = "book"
OCinSoutput["rft.btitle"] = data.Title;
end
OCinSoutput["rft.place"] = data.PublicationPlace;
OCinSoutput["rft.date"] = data.Date;
OCinSoutput["rft.series"] = data.Series;
OCinSoutput["rft.volume"] = data.Volume;
OCinSoutput["rft.issue"] = data.Issue;
OCinSoutput["rft.pages"] = data.Pages;
OCinSoutput["rft.edition"] = data.Edition;
OCinSoutput["rft.pub"] = data.PublisherName;
for k, v in pairs( data.ID_list ) do
local id, value = cfg.id_handlers[k].COinS;
if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
if string.sub( id or "", 1, 4 ) == 'info' then
OCinSoutput["rft_id"] = table.concat{ id, "/", v };
else
OCinSoutput[ id ] = value;
end
end
local last, first;
for k, v in ipairs( data.Authors ) do
last, first = v.last, v.first;
if k == 1 then
if is_set(last) then
OCinSoutput["rft.aulast"] = last;
end
if is_set(first) then
OCinSoutput["rft.aufirst"] = first;
end
end
if is_set(last) and is_set(first) then
OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
elseif is_set(last) then
OCinSoutput["rft.au"] = last;
end
end
OCinSoutput.rft_id = data.URL;
OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage };
OCinSoutput = setmetatable( OCinSoutput, nil );
-- sort with version string always first, and combine.
table.sort( OCinSoutput );
table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004"
return table.concat(OCinSoutput, "&");
end
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Validates language names provided in |language= parameter if not an ISO639-1 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
uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along
with the code. When there is no match, we return the original language name string.
mw.language.fetchLanguageNames() 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
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() then -- ISO639-1 codes only
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
--[[--------------------------< 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.
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
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
the page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way.
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas.
]]
local function language_parameter (lang, namespace)
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=
local unrec_cat = false -- flag so that we only add unrecognized category once
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
for _, lang in ipairs (names_table) do -- reuse lang
if 0 == namespace and (('en' == lang:lower()) or ('english' == lang:lower())) then
add_maint_cat ('english');
end
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
end
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 0 == namespace and 'en' ~= code then -- is this page main / article space and English not the language?
add_prop_cat ('foreign_lang_source', {name, code})
end
elseif false == unrec_cat then
unrec_cat = true; -- only add this category once
add_maint_cat (unknown_lang);
end
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
return (" " .. wrap_msg ('language', name)); -- wrap with '(in ...)'
end
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
Set style settings for CS1 citation templates. Returns separator and postscript settings
]]
local function set_cs1_style (ps)
if not is_set (ps) then -- unless explicitely set to something
ps = '.'; -- terminate the rendered citation with a period
end
return '.', ps; -- separator is a full stop
end
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
]]
local function set_cs2_style (ps, ref)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = ''; -- make sure it isn't nil
end
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
return ',', ps, ref; -- separator is a comma
end
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
rendered style.
]]
local function get_settings_from_cite_class (ps, ref, cite_class)
local sep;
if (cite_class == "citation") then -- for citation templates (CS2)
sep, ps, ref = set_cs2_style (ps, ref);
else -- not a citation template so CS1
sep, ps = set_cs1_style (ps);
end
return sep, ps, ref -- return them all
end
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
config.CitationClass from the template's #invoke: to establish style.
]]
local function set_style (mode, ps, ref, cite_class)
local sep;
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
sep, ps, ref = set_cs2_style (ps, ref);
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
sep, ps = set_cs1_style (ps);
else -- anything but cs1 or cs2
if is_set (mode) then
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'mode', mode}, true ) } ); -- add error message
end
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
if 'none' == ps:lower() then -- if assigned value is 'none' then
ps = ''; -- set to empty string
end
return sep, ps, ref
end
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Determines if a url has the file extension is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
applying the pdf icon to external links.
returns true if file extension is one of the recognized extension, else false
]=]
local function is_pdf (url)
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
end
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does
not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.
]]
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format:upper()); -- force upper case, add leading space, parenthases, resize
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
end
elseif is_pdf (url) then -- format is not set so if url is a pdf file then
format = wrap_style ('format', 'PDF'); -- set format to pdf
else
format = ''; -- empty string for concatenation
end
return format;
end
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
Returns a number that may or may not limit the length of the author or editor name lists.
When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
some variant of the text 'et al.').
When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
the names in the name list followed by 'et al.'
In all other cases, returns nil and the previous state of the 'etal' flag.
]]
local function get_display_authors_editors (max, count, list_name, etal)
if is_set (max) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
max = count + 1; -- number of authors + 1 so display all author name plus et al.
etal = true; -- overrides value set by extract_names()
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cat ('disp_auth_ed', list_name);
end
else -- not a valid keyword or number
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset
end
elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category
max = count + 1; -- number of authors + 1
end
return max, etal;
end
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
This is the main function doing the majority of the citation
formatting.
]]
local function citation0( config, args)
--[[
Load Input Parameters
The argument_wrapper facilitates the mapping of multiple
aliases to single internal variable.
]]
local A = argument_wrapper( args );
local i
local PPrefix = A['PPrefix']
local PPPrefix = A['PPPrefix']
if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end
-- Pick out the relevant fields from the arguments. Different citation templates
-- define different field names for the same underlying things.
local Authors = A['Authors'];
local author_etal;
local a, author_etal = extract_names( args, 'AuthorList' );
local Coauthors = A['Coauthors'];
local Others = A['Others'];
local Editors = A['Editors'];
local editor_etal;
local e, editor_etal = extract_names( args, 'EditorList' );
local NameListFormat = A['NameListFormat']; -- replaces |author-format= and |editor-format=
if is_set (NameListFormat) and ('vanc' ~= NameListFormat) then -- only accepted value for this parameter is 'vanc'
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'name-list-format', NameListFormat}, true ) } ); -- not vanc so add error message
NameListFormat = ''; -- set to empty string
end
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local Date = A['Date'];
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
local Chapter = A['Chapter'];
local ChapterLink = A['ChapterLink']; -- deprecated
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 Volume = A['Volume'];
local Issue = A['Issue'];
local Position = '';
local Page = A['Page'];
local Pages = hyphen_to_dash( A['Pages'] );
local At = A['At'];
local Edition = A['Edition'];
local PublicationPlace = A['PublicationPlace']
local Place = A['Place'];
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
local SubscriptionRequired = A['SubscriptionRequired'];
local Via = A['Via'];
local AccessDate = A['AccessDate'];
local ArchiveDate = A['ArchiveDate'];
local Agency = A['Agency'];
local DeadURL = A['DeadURL']
local Language = A['Language'];
local Format = A['Format'];
local ChapterFormat = A['ChapterFormat'];
local DoiBroken = A['DoiBroken'];
local ID = A['ID'];
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
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
local LastAuthorAmp = A['LastAuthorAmp'];
local no_tracking_cats = A['NoTracking'];
--these are used by cite interview
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];
--local variables that are not cs1 parameters
local 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 sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (A['Mode']:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
break; -- bail out if one is found
end
end
end
-- check for extra |page=, |pages= or |at= parameters.
if is_set(Page) then
if is_set(Pages) or is_set(At) then
Page = Page .. " " .. set_error('extra_pages'); -- add error message
Pages = ''; -- unset the others
At = '';
end
elseif is_set(Pages) then
if is_set(At) then
Pages = Pages .. " " .. set_error('extra_pages'); -- add error messages
At = ''; -- unset
end
end
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title
|trans_title maps to |trans_chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped
All other combinations of |encyclopedia, |title, and |article are not modified
TODO: script-title to script-chapter if and when we support script-chapter
]]
local Encyclopedia = A['Encyclopedia'];
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
if is_set(Title) then
if not is_set(Chapter) then
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
TransChapter = TransTitle;
ChapterURL = URL;
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset
TransTitle = ''; -- redundant so unset
URL = ''; -- redundant so unset
Format = ''; -- redundant so unset
end
else -- |title not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Periodical = ''; -- redundant so unset
end
end
end
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue'
if not is_set(ID) then -- can we use ID for the "number"?
ID = Issue; -- yes, use it
Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
else -- can't use ID so emit error message
ID = ID .. " " .. set_error('redundant_parameters', '<code>|id=</code> and <code>|number=</code>');
end
end
end
-- special case for cite interview
if (config.CitationClass == "interview") then
if is_set(Program) then
ID = ' ' .. Program;
end
if is_set(Callsign) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. Callsign;
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
else
Others = '(Interview)';
end
end
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
end
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if 'conference' == config.CitationClass then
if is_set(BookTitle) then
Chapter = Title;
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
ChapterURL = URL;
ChapterURLorigin = URLorigin;
URLorigin = '';
ChapterFormat = Format;
TransChapter = TransTitle;
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
end
elseif 'speech' ~= config.CitationClass then
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
-- cite map oddities
local Cartography = "";
local Scale = "";
local Sheet = A['Sheet'] or '';
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
Chapter = A['Map'];
ChapterURL = A['MapURL'];
TransChapter = A['TransMap'];
ChapterURLorigin = A:ORIGIN('MapURL');
ChapterFormat = A['MapFormat'];
Cartography = A['Cartography'];
if is_set( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
Scale = A['Scale'];
if is_set( Scale ) then
Scale = sepc .. " " .. Scale;
end
end
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local Began = A['Began']; -- these two are deprecated because the module understands date ranges
local Ended = A['Ended'];
local SeriesLink = A['SeriesLink'];
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
if is_set(Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) then -- promote airdate or Began/Ended to date
if is_set (AirDate) then
Date = AirDate;
elseif is_set (Began) then -- deprecated
if Began:match('%s') or Ended:match('%s') then -- so we don't create errors: if either has spaces then
Date = Began .. ' – ' .. Ended; -- use spaced ndash as separator
else
Date = Began .. '–' .. Ended; -- elsewise no spaces
end
end
end
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Chapter = Title; -- promote title parameters to chapter
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURLorigin = A:ORIGIN('URL');
Title = Series; -- promote series to title
TitleLink = SeriesLink;
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
end
URL = ''; -- unset
TransTitle = ''; -- unset
else -- now oddities that are cite serial
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
end
Series = wrap_style ('italic-title', Series); -- series is italicized
end
end
-- end of {{cite episode}} stuff
-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
if 'arxiv' == config.CitationClass then
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
end
if first_set (AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']) then
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
AccessDate= ''; -- set these to empty string; not supported in cite arXiv
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
Chapter = '';
URL = '';
Format = '';
Page = ''; Pages = ''; At = '';
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
end
end
if is_set(TitleType) then -- if type parameter is specified
TitleType = " (" .. 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 is_set(Date) then
local Month = A['Month'];
if is_set(Month) then
Date = Month .. " " .. Date;
end
elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
end
end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
--[[
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
we get the date used in the metadata.
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message and mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
anchor_year, COinS_date, error_message = dates({['accessdate']=AccessDate, ['archivedate']=ArchiveDate, ['date']=Date, ['doi_brokendate']=DoiBroken,
['embargo']=Embargo, ['laydate']=LayDate, ['publicationdate']=PublicationDate, ['year']=Year});
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
local mismatch = year_date_check (Year, Date)
if 0 == mismatch then -- |year= does not match a year-value in |date=
if is_set (error_message) then -- if there is already an error message
error_message = error_message .. ', '; -- tack on this additional message
end
error_message = error_message .. '|year= / |date= mismatch';
elseif 1 == mismatch then -- |year= matches year-value in |date=
add_maint_cat ('date_year');
end
end
if is_set(error_message) then
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
end -- end of do
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
Embargo = is_embargoed (Embargo); --
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if not is_set (Embargo) then -- if not embargoed or embargo has expired
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
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
table.insert( z.message_tail, { set_error( 'citation_missing_title', {}, true ) } );
end
if 'none' == Title and is_set(Periodical) and not (( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia))) then -- special case
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
-- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
-- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
-- is the article title, and Chapter is a section within the article. So, we remap
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
end
end
-- this is the function call to COinS()
local OCinSoutput = COinS({
['Periodical'] = Periodical,
['Chapter'] = strip_apostrophe_markup (coins_chapter), -- Chapter stripped of bold / italic wikimarkup
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
['PublicationPlace'] = PublicationPlace,
['Date'] = first_set(COinS_date, Date), -- COinS_date has correctly formatted date if Date is valid; any reason to keep Date here? Should we be including invalid dates in metadata?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = get_coins_pages (first_set(Sheet, Sheets, Page, Pages, At)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['URL'] = first_set( URL, ChapterURL ),
['Authors'] = a,
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
end
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName = '[[Newsgroup]]: ' .. external_link( 'news:' .. PublisherName, PublisherName );
end
end
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
do -- do-block to limit scope of LastFirstAuthors
local LastFirstAuthors;
local Maximum = A['DisplayAuthors'];
Maximum , author_etal = get_display_authors_editors (Maximum, #a, 'authors', author_etal);
local 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 the coauthor field is also used, prevent ampersand and et al. formatting.
if is_set(Coauthors) then
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
LastFirstAuthors = list_people(control, a, author_etal);
if is_set (Authors) then
if is_set (LastFirstAuthors) then -- if both author name styles
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'authors') .. ' and ' .. wrap_style ('parameter', 'last')}, true ) } ); -- add error message
Authors = LastFirstAuthors; -- TODO: is this correct or should we use |authors= instead?
end
else
Authors = LastFirstAuthors; -- 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
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
if not is_set(Editors) then
local Maximum = A['DisplayEditors'];
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 = {
format = NameListFormat, -- empty string or 'vanc'
maximum = Maximum,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
};
Editors, EditorCount = list_people(control, e, editor_etal);
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
else
EditorCount = 1;
end
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', 'url');
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
if not is_set(URL) then --and
-- not is_set(ArchiveURL) then --and -- prevents format_missing_url error from registering
-- not is_set(ConferenceURL) and -- TODO: keep this here? conference as part of cite web or cite podcast?
-- not is_set(TranscriptURL) then -- TODO: remove? |transcript-url= and |transcript= has separate test
-- Test if cite web or cite podcast |url= is missing or empty
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
-- Test if accessdate is given without giving a URL
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test?
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
end
local OriginalURL, 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
if is_set( ArchiveURL ) then
if is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalFormat = Format; -- and original |format=
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
end
elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalFormat = ChapterFormat; -- and original |format=
if 'no' ~= DeadURL then
ChapterURL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
end
end
end
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", 'arxiv'}) or
('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)then -- chapter parameters not supported for these citation types
table.insert( z.message_tail, { set_error( 'chapter_ignored', {}, true ) } ); -- add error message
Chapter = ''; -- set to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
end
else -- otherwise, format chapter / article title
Chapter = format_chapter_title (Chapter, TransChapter, ChapterURL, ChapterURLorigin);
if is_set (Chapter) then
if 'map' == config.CitationClass and is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType;
end
Chapter = Chapter .. ChapterFormat .. sepc .. ' ';
end
end
-- Format main title.
if is_set(TitleLink) and is_set(Title) then
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
end
if in_array(config.CitationClass, {"web","news","journal","pressrelease","podcast", "newsgroup", "mailinglist", 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
Title = wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = wrap_style ('trans-italic-title', TransTitle);
end
TransError = "";
if is_set(TransTitle) then
if is_set(Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. set_error( 'trans_missing_title' );
end
end
Title = Title .. TransTitle;
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title ) .. TransError .. Format;
URL = "";
Format = "";
else
Title = Title .. TransError;
end
end
if is_set(Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
if is_set (Conference) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
end
if not is_set(Position) then
local Minutes = A['Minutes'];
if is_set(Minutes) then
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
local Time = A['Time'];
if is_set(Time) then
local TimeCaption = A['TimeCaption']
if not is_set(TimeCaption) then
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
TimeCaption = TimeCaption:lower();
end
end
Position = " " .. TimeCaption .. " " .. Time;
end
end
else
Position = " " .. Position;
At = '';
end
if not is_set(Page) then
if is_set(Pages) then
if is_set(Periodical) and
not 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
if 'map' == config.CitationClass then -- cite map oddity done after COinS call (and with other in-source locators)
if is_set (Sheet) or is_set (Sheets) then
local err_msg1 = 'sheet=, |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=, |pages=, |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 "";
Position = is_set(Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
local Section = A['Section'];
local Sections = A['Sections'];
local Inset = A['Inset'];
if is_set( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
if is_set( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif is_set( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
At = At .. Inset .. Section;
end
if is_set (Language) then
Language = language_parameter (Language, this_page.namespace); -- format, categories (article namespace only), name from ISO639-1, etc
else
Language=""; -- language not specified so make sure this is an empty string;
end
Others = is_set(Others) and (sepc .. " " .. Others) or "";
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
Edition = is_set(Edition) and (" " .. wrap_msg ('edition', Edition)) or "";
Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
if is_set(Volume) then
if ( mw.ustring.len(Volume) > 4 )
then Volume = sepc .." " .. Volume;
else Volume = " <b>" .. hyphen_to_dash(Volume) .. "</b>";
end
end
------------------------------------ totally unrelated data
if is_set(Via) then
Via = " " .. wrap_msg ('via', Via);
end
--[[
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.
]]
if in_array(SubscriptionRequired:lower(), {'yes', 'true', 'y'}) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif in_array(RegistrationRequired:lower(), {'yes', 'true', 'y'}) then
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
end
if is_set(AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
-- neither of these work; don't know why; it seems that substitute() isn't being called
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if is_set(ID) then ID = sepc .." ".. ID; end
if "thesis" == config.CitationClass and is_set(Docket) then
ID = sepc .." Docket ".. Docket .. ID;
end
if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin );
end
if is_set(Quote) then
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then
Quote = Quote:sub(2,-2);
end
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; -- CS1 does not supply terminal punctuation when |quote= is set
end
local Archived
if is_set(ArchiveURL) then
if not is_set(ArchiveDate) then
ArchiveDate = set_error('archive_missing_date');
end
if "no" == DeadURL then
local arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
{ external_link( ArchiveURL, arch_text ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');
end
elseif is_set(OriginalURL) then
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'] ) .. OriginalFormat, ArchiveDate } ); -- format already styled
else
local arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( arch_text,
{ set_error('archive_missing_url'), ArchiveDate } );
end
elseif is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Archived = ""
end
local Lay = '';
if is_set(LayURL) then
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
if is_set(LaySource) then
LaySource = " – ''" .. safe_for_italics(LaySource) .. "''";
else
LaySource = "";
end
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'] ) .. LayFormat .. LaySource .. LayDate
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower() ) .. LayFormat .. LaySource .. LayDate
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
end
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
end
local Publisher;
if is_set(Periodical) and
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = PublicationPlace .. ": " .. PublisherName;
else
Publisher = PublisherName;
end
elseif is_set(PublicationPlace) then
Publisher= PublicationPlace;
else
Publisher = "";
end
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
else
Publisher = PublicationDate;
end
end
if is_set(Publisher) then
Publisher = " (" .. Publisher .. ")";
end
else
if is_set(PublicationDate) then
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
end
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
elseif is_set(PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Publisher = PublicationDate;
end
end
-- Several of the above rely upon detecting this as nil, so do it last.
if is_set(Periodical) then
if is_set(Title) or is_set(TitleNote) then
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)
else
Periodical = wrap_style ('italic-title', Periodical)
end
end
--[[
Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
if is_set (Conference) then -- and if |event= is set
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
end
end
-- Piece all bits together at last. Here, all should be non-nil.
-- We build things this way because it is more efficient in LUA
-- not to keep reassigning to the same string variable over and over.
local tcommon
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
Language, Edition, Publisher, Agency, Volume, Issue}, sepc );
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume, Issue}, sepc );
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
end
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume, Issue, Others, Edition, Publisher, Agency}, sepc );
end
if #ID_list > 0 then
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
else
ID_list = ID;
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Page .. Pages .. At;
if is_set(Authors) then
if is_set(Coauthors) then
local sep = '; ';
if 'vanc' == NameListFormat then
sep = ', ';
end
Authors = Authors .. sep .. Coauthors;
end
if is_set(Date) then
Date = " ("..Date..")" .. OrigYear .. sepc .. " "
elseif string.sub(Authors,-1,-1) == sepc then
Authors = Authors .. " "
else
Authors = Authors .. sepc .. " "
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) then
in_text = in_text .. cfg.messages['in'] .. " "
else
if EditorCount <= 1 then
post_text = ", " .. cfg.messages['editor'];
else
post_text = ", " .. cfg.messages['editors'];
end
end
if (sepc ~= '.') then in_text = in_text:lower() end
Editors = in_text .. Editors .. post_text;
if (string.sub(Editors,-1,-1) == sepc) or (string.sub(Editors,-3,-1) == sepc .. ']]') then -- if last editor name ends with sepc char
Editors = Editors .. " "; -- don't add another
else
Editors = Editors .. sepc .. " " -- otherwise terninate the editor list
end
end
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
elseif is_set(Editors) then
if is_set(Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
else
Editors = Editors .. ", " .. cfg.messages['editors'];
end
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
else
if EditorCount <= 1 then
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
else
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon}, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
else
if is_set(Date) then
if ( string.sub(tcommon,-1,-1) ~= sepc )
then Date = sepc .." " .. Date .. OrigYear
else Date = " " .. Date .. OrigYear
end
end
if config.CitationClass=="journal" and is_set(Periodical) then
text = safe_join( {Chapter, Place, tcommon}, sepc );
text = safe_join( {text, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Place, tcommon, Date}, sepc );
text = safe_join( {text, pgtext, idcommon}, sepc );
end
end
if is_set(PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1,-sepc:len()-1);
end
text = safe_join( {text, PostScript}, sepc );
-- Now enclose the whole thing in a <span/> element
local options = {};
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
options.class = "citation " .. config.CitationClass;
else
options.class = "citation";
end
if is_set(Ref) and Ref:lower() ~= "none" then
local id = Ref
if ( "harv" == Ref ) then
local names = {} --table of last names & year
if #a > 0 then
for i,v in ipairs(a) do
names[i] = v.last
if i == 4 then break end
end
elseif #e > 0 then
for i,v in ipairs(e) do
names[i] = v.last
if i == 4 then break end
end
end
names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation
id = anchor_id(names)
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
z.error_categories = {};
text = set_error('empty_citation');
z.message_tail = {};
end
if is_set(options.id) then
text = '<span id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
else
text = '<span class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
end
local empty_span = '<span style="display:none;"> </span>';
-- Note: Using display: none on then COinS span breaks some clients.
local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
text = text .. OCinS;
if #z.message_tail ~= 0 then
text = text .. " ";
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if i == #z.message_tail then
text = text .. error_comment( v[1], v[2] );
else
text = text .. error_comment( v[1] .. "; ", v[2] );
end
end
end
end
if #z.maintenance_cats ~= 0 then
text = text .. ' <span class="citation-comment" style="display:none; color:#33aa33">';
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. v .. ' ([[:Category:' .. v ..'|link]])';
end
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
end
no_tracking_cats = no_tracking_cats:lower();
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
end
return text
end
-- This is used by templates such as {{cite book}} to create the actual citation text.
function z.citation(frame)
local pframe = frame:getParent()
local validation;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ...
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ...
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code
end
dates = validation.dates; -- imported functions
year_date_check = validation.year_date_check;
local args = {};
local suggestions = {};
local error_text, error_state;
local config = {};
for k, v in pairs( frame.args ) do
config[k] = v;
args[k] = v;
end
for k, v in pairs( pframe.args ) do
if v ~= '' then
if not validate( k ) then
error_text = "";
if type( k ) ~= 'string' then
-- Exclude empty numbered parameters
if v:match("%S+") ~= nil then
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
elseif validate( k:lower() ) then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
else
if #suggestions == 0 then
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
end
if suggestions[ k:lower() ] ~= nil then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
end
end
if error_text ~= '' then
table.insert( z.message_tail, {error_text, error_state} );
end
end
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then
args[k] = v;
end
end
return citation0( config, args)
end
return z
