Module:Citation/CS1

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
}

-- Whether variable is set or not
function is_set( var )
	return not (var == nil or var == '');
end

-- First set variable or nil if none
function first_set(...)
	local list = {...};
	for _, var in pairs(list) do
		if is_set( var ) then
			return var;
		end
	end
end

-- Whether needle is in haystack
function inArray( 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

--[[
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.
]]
function deprecated_parameter()
	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, { seterror( 'deprecated_params', {}, true ) } );		-- add error message
	end
end

-- Populates numbered arguments in a message string using an argument table.
function substitute( msg, args )
	return args and mw.message.newRawMessage( msg, args ):plain() or msg;
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.

]]

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;
]]

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 inArray (lang, {'ar', 'bs', 'dv', 'el', 'fa', 'hy', 'ja', 'ko', 'ku', 'he', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then
				table.insert( z.properties_cats, 'CS1 uses ' .. name .. '-language script ('..lang..')');	-- categorize in language-specific categories
			else
				table.insert( z.properties_cats, 'CS1 uses foreign language script');	-- use this category as a catchall until language-specific category is available
			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.
]]

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 _ 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().

]]

function wrap_style (key, str)
	if not is_set( str ) then
		return "";
	elseif inArray( key, { 'italic-title', 'trans-italic-title' } ) then
		str = safeforitalics( str );
	end

	return substitute( cfg.presentation[key], {str} );
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().

]]

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

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

]]

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

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

Parameters in the whitelist can have three values:
	true - active, supported parameters
	false - deprecated, supported parameters
	nil - unsupported parameters
]]
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 ();				-- 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 ();				-- parameter is deprecated but still supported
		return true;
	end
	
	return false;								-- Not supported because not found or name is set to nil
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.

]]
function errorcomment( content, hidden )
	return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content );
end

--[[
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.
]]
function seterror( 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 inArray( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
			and z.error_ids['citation_missing_title'] then
		return '', false;
	end
	
	message = table.concat({ prefix, message, suffix });
	
	if raw == true then
		return message, error_state.hidden;
	end		
		
	return errorcomment( message, error_state.hidden );
end

-- Formats a wiki style external link
function externallinkid(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 "&nbsp;",
		options.prefix, url_string, options.suffix or "",
		mw.text.nowiki(options.id)
	);
end

-- Formats a wiki style internal link
function internallinkid(options)
	return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
		options.link, options.label, options.separator or "&nbsp;",
		options.prefix, options.id, options.suffix or "",
		mw.text.nowiki(options.id)
	);
end

-- Format an external link with error checking
function externallink( URL, label, source )
	local error_str = "";
	if not is_set( label ) then
		label = URL;
		if is_set( source ) then
			error_str = seterror( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " );
		else
			error( cfg.messages["bare_url_no_origin"] );
		end			
	end
	if not checkurl( URL ) then
		error_str = seterror( 'bad_url', {}, false, " " ) .. error_str;
	end
	return table.concat({ "[", URL, " ", safeforurl( label ), "]", error_str });
end