Module:Lang

This module exists primarily to provide correct html markup for non-English language text where that text is used in the English Wikipedia. It has a secondary purpose of providing correct visual rendering for this non-English text. The module was developed to consolidate processing for {{Lang}}, the {{lang-??}} (most), and {{Transl}} templates into a single source and to use a clearly defined data set extracted from international standards. It provides error checking and reporting to ensure that the html rendered is correct for browsers and screen readers.

Other templates that get language name support from this module are:

• {{Native name}}

Data set

The data set is specified in Module:Language/name/data and its included data modules:

• language tag-and-name data
  • Module:Language/data/iana languages – from IANA language-subtag-registry file
  • Module:Language/data/ISO 639-3 – from sil.org UTF-8 Complete Code Tables Set
  • Module:Language/data/wp languages – sourcing for the data in this module is unknown
• language script data
  • Module:Language/data/iana scripts – from IANA language-subtag-registry file
• language region data
  • Module:Language/data/iana regions – from IANA language-subtag-registry file
• language variant data
  • Module:Language/data/iana variants – from IANA language-subtag-registry file
• suppressed-script data
  • Module:Language/data/iana suppressed scripts – from IANA language-subtag-registry file

The data set also includes supplementary data modules:

• override and other non-standard data
  • Module:Lang/data – For example, when IANA disagrees with ISO 639-3 or when the standard language name is cumbersome or contains information not suitable for use in article space, the override table can hold that language information
  • Module:Lang/ISO 639 synonyms – maps three character ISO 639-2, -2T, -3 codes to two character ISO 639-1 codes – from Codes for the Representation of Names of Languages
  • Module:Lang/name to tag – reversed language tag-and-name data so that the language name is the key and the language tag is the value

Error messages and categorization

Mainspace articles that have errors are placed in appropriate error categories:

• Category:lang and lang-xx template errors (2)
• Category:transl template errors (0)

Maintenance categories:

• Category:Lang and lang-xx code promoted to ISO 639-1 (0)

See also

MoS on foreign words:

• Wikipedia:Manual of Style/Text formatting § Foreign terms

---

--[=[
This is an experiment to see what is required to consolodate all of the myriad {{lang-xx}} templates
and their subtemplates into a single module with a data table

{{lang-es}} has parameters:
{{{1}}} text - required
{{{link}}} or {{{links}}} defaults to 'yes'
{{{lit}}} literal translation

{{language with name}} has parameters:
{{{1}}} iso language code - required
{{{2}}} language name in English - superfluous?
{{{3}}} text - required
{{{4}}} or {{{lit}}} literal translation
{{{link}}} or {{{links}}} set to 'no' disables '{{{2}} language' wikilinks
{{{rtl}}} passed through to {{lang}}
{{{nocat}}} passed through to {{lang}}

{{lang}} has parameters:
{{{1}}} iso language code - required
{{{2}}} text - required
{{{rtl}}} if set to any value, set rtl="rtl" attribute and inserts &lrm; after the </span> tag
{{{nocat}}} if set to any value, disables categorization

How it works now:
	1. {{lang-es}} receives text as {{{1}}} to which it adds italic markup, sets |links to {{{link}}} or {{{links}}} or yes, sets |lit to {{{lit}}}, and calls {{language with name}}.  {{{rtl}}} ignored for this example
	2. {{language with name}} renders [[Spanish language|Spanish]] ({{{links}}} not set) or Spanish ({{{links}}} set) and calls {{lang}}
	3. {{lang}} wraps the text in the <span lang="es">text</span> and adds categorization
]=]

require('Module:No globals');
local p = {};

local getArgs = require('Module:Arguments').getArgs;
local lang_name_table = require ('Module:Language/name/data');

local namespace = mw.title.getCurrentTitle().namespace;							-- used for categorization


--[[--------------------------< 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

]]

local function is_set( var )
	return not (var == nil or var == '');
end


--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------

Makes a wikilink; when both link and display text is provided, returns a wikilink in the form [[L|D]]; if only
link is provided, returns a wikilink in the form [[L]]; if neither are provided or link is omitted, returns an
empty string.

]=]

local function make_wikilink (link, display)
	if is_set (link) then
		if is_set (display) then
			return table.concat ({'[[', link, '|', display, ']]'});
		else
			return table.concat ({'[[', link, ']]'});
		end
	else
		return '';
	end
end


--[[--------------------------< M A K E _ T E X T _ S P A N >--------------------------------------------------

]]

local function make_text_span (code, text, rtl, italic, size)
	local span = {};

	table.insert (span, '<span lang="');										-- open <span> tag
	table.insert (span,  code);													-- language attribute
	table.insert (span, '"');
	if is_set (rtl) then
		table.insert (span, ' rtl="rtl"');										-- for right to left languages
	end
	if is_set (size) then														-- {{lang}} only
		table.insert (span, table.concat ({' style="font-size:', size, ';"'}))
	end
	table.insert (span, '>');													-- close the opening span tag
	if 'yes' == italic then
		table.insert (span, table.concat ({"''", text, "''"}));					-- text with italic markup
	else
		table.insert (span, text);												-- DEFAULT: text is not italicized
	end
	table.insert (span, '</span>');												-- close the span
	if is_set (rtl) then
		table.insert (span, '&lrm;');											-- make sure the browser knows that we're at the end of the rtl
	end
	
	return table.concat (span);													-- put it all together and done
end


--[[--------------------------< M A K E _ C A T E G O R Y >----------------------------------------------------

]]

local function make_category (code, language_name, nocat)
	local cat = {};
	
--	if (0 ~= namespace) or nocat then											-- only categorize in article space
--		return '';																-- return empty string for concatenation
--	end
	
	table.insert (cat, '[[Category:Articles containing ');
	
	if ('en' == code) or ('eng' == code) then
		table.insert (cat, 'explicitly cited English');
	elseif 'art' == code then
		table.insert (cat, 'constructed')
	else
		table.insert (cat, language_name);
	end
	
	table.insert (cat, '-language text]]');

	return table.concat (cat);	
end

--[=[-------------------------< L A N G >----------------------------------------------------------------------

{{#invoke:lang|lang|code={{{1}}}|text={{{2}}}|rtl={{{rtl}}}|size={{{size}}}|nocat={{{nocat}}}}}

]=]

function p.lang (frame)
	local args = getArgs(frame);
	
	local out = {};
	local language_name;
	if lang_name_table.lang[args.code] then
		language_name = lang_name_table.lang[args.code][1];						-- table entries sometimes have multiple names, always take the first one
	end
	
	if not is_set (language_name) then
		table.insert (out, '<span style="font-size:100%" class="error">error: unknown language code: ');
		table.insert (out, args.code);
		table.insert (out, '</span>');
		
		if 0 ~= namespace then														-- only categorize in article space
			table.insert (out, '[[Category:Articles containing unknown language template codes|');
			table.insert (out, args.code);
			table.insert (out, ']]');
		end
		return table.concat (out);												-- emit an error message and category
	end
	
	table.insert (out, make_text_span (args.code, args.text, args.rtl, nil, args.size));		-- italics set to nil here because not supporte by {{lang}}
	table.insert (out, make_category (args.code, language_name, args.nocat));
	return table.concat (out);													-- put it all together and done
	end


--[=[-------------------------< L A N G _ X X >----------------------------------------------------------------

{{#invoke:lang|lang_xx|code={{{1}}}|text={{{2}}}|link={{{links|{{{link}}}}}}|rtl={{{rtl}}}|nocat={{{nocat}}}|italic={{{italic}}}|translit={{{translit}}}|lit={{{lit}}}}}

]=]

function p.lang_xx (frame)
	local args = getArgs(frame);
	
	if not is_set (args.italic) then
		args.italic = 'yes';													-- DEFAULT for {{lang-xx}} templates is to italicize
	end
	
	args.size = nil;															-- size not supported in {{lang-xx}}
	
	local out = {};
	local language_name;
	if lang_name_table.lang[args.code] then
		language_name = lang_name_table.lang[args.code][1];						-- table entries sometimes have multiple names, always take the first one
	end
	
	if not is_set (language_name) then
		table.insert (out, '<span style="font-size:100%" class="error">error: unknown language code: ');
		table.insert (out, args.code);
		table.insert (out, '</span>');
		
		if 0 ~= namespace then														-- only categorize in article space
			table.insert (out, '[[Category:Articles containing unknown language template codes|');
			table.insert (out, args.code);
			table.insert (out, ']]');
		end
		return table.concat (out);												-- emit an error message and category
	end
	
	if 'no' == args.link then
		table.insert (out, language_name);										-- language name without wikilink
	else
		table.insert (out, make_wikilink (language_name .. ' language', language_name));	-- language name with wikilink
	end
	table.insert (out, ': ');													-- separator

	table.insert (out, make_text_span (args.code, args.text, args.rtl, args.italic, args.size))
	
	if is_set (args.lit) then													-- transliteration (not supported in {{lang}}); not supported in all {{lang-xx}}
		
	end
	if is_set (args.lit) then													-- translation (not supported in {{lang}})
		table.insert (out, ', <small>');
		table.insert (out, make_wikilink ('Literal translation', 'lit.'));
		table.insert (out, "&nbsp;</small>'");
		table.insert (out, args.lit);
		table.insert (out, "'");
	end
	
	table.insert (out, make_category (args.code, language_name, args.nocat));
	return table.concat (out);													-- put it all together and done
end

return p;