Module:Lang: Difference between revisions

Add links
Browse history interactively
← Older editNewer edit →
Content deleted Content added
No edit summary
sync from sandbox;
Line 186: Line 186:
region: upper case
region: upper case
variant: lower case
variant: lower case
private: lower case prefixed with -x-

]]
]]


local function format_ietf_tag (code, script, region, variant)
local function format_ietf_tag (code, script, region, variant, private)
local out = {};
local out = {};


if is_set (private) then
return table.concat ({code:lower(), 'x', private:lower()}, '-'); -- if private, all other tags ignored
end
table.insert (out, code:lower());
table.insert (out, code:lower());
if is_set (script) then
if is_set (script) then
Line 432: Line 437:
if is_set (link) then
if is_set (link) then
if is_set (display) then
if is_set (display) then
return table.concat ({'[[wikipedia:', link, '|', display, ']]'});
return table.concat ({'[[', link, '|', display, ']]'});
else
else
return table.concat ({'[[wikipedia', link, '|', link, ']]'});
return table.concat ({'[[', link, ']]'});
end
end
else
else
Line 522: Line 527:
table.insert (html, table.concat ({style_added, ' title=\"', language})); --start the title text
table.insert (html, table.concat ({style_added, ' title=\"', language})); --start the title text
if language:find ('languages') then
if language:find ('languages') then
table.insert (html, ' collective text\"'); -- for collective languages
table.insert (html, ' collective text'); -- for collective languages
else
else
table.insert (html, ' language text\"'); -- for individual languages
table.insert (html, ' language text'); -- for individual languages
end
end
table.insert (html, '>'); -- close the opening html tag
table.insert (html, '\">'); -- close the opening html tag
else
else
table.insert (html, table.concat ({style_added, '>'})); -- close the style attribute and close opening html tag
table.insert (html, table.concat ({style_added, '>'})); -- close the style attribute and close opening html tag
Line 549: Line 554:
[[Category:Articles containing explicitly cited English-language text]]
[[Category:Articles containing explicitly cited English-language text]]
for artificial languages (code: art)
[[Category:Articles containing constructed-language text]]

for ISO 639-2 collective languages (and for 639-1 bh):
for ISO 639-2 collective languages (and for 639-1 bh):
[[Category:Articles with text from the <language> languages collective]]
[[Category:Articles with text from the <language> languages collective]]
Line 557: Line 559:
]=]
]=]


local function make_category (code, language_name, nocat)
local function make_category (code, language_name, nocat, name_get)
local cat = {};
local cat = {};
local retval;

if (0 ~= namespace) or nocat then -- only categorize in article space
if ((0 ~= namespace) or nocat) and not name_get then -- only categorize in article space
return ''; -- return empty string for concatenation
return ''; -- return empty string for concatenation
end
end

if language_name:find ('languages') then
if language_name:find ('languages') then
return table.concat ({'[[Category:Articles with text from the ', language_name, ' collective]]'});
retval = table.concat ({'[[Category:Articles with text from the ', language_name, ' collective]]'});
-- return table.concat ({'[[Category:Articles with text from ', language_name, ']]'});
-- retval = table.concat ({'[[Category:Articles with text from ', language_name, ']]'}); -- proposed version at Wikipedia:Categories_for_discussion/Log/2020_August_18#Category:Articles_with_text_from_the_Afro-Asiatic_languages_collective
retval = name_get and retval:gsub ('[%[%]]', '') or retval; -- when called from category_from_tag() strip wikilink markup to return plain-text category name
return retval;
end
end
table.insert (cat, '[[Category:Articles containing ');
table.insert (cat, '[[Category:Articles containing ');

if 'en' == code then
if 'en' == code then
table.insert (cat, 'explicitly cited English');
table.insert (cat, 'explicitly cited English');
elseif 'art' == code then
table.insert (cat, 'constructed')
else
else
table.insert (cat, language_name);
table.insert (cat, language_name);
Line 581: Line 584:
table.insert (cat, '-language text]]');
table.insert (cat, '-language text]]');


return table.concat (cat);
retval = table.concat (cat);
retval = name_get and retval:gsub ('[%[%]]', '') or retval; -- when called from category_from_tag() strip wikilink markup to return plain-text category name
return retval
end
end


Line 827: Line 832:
end
end



--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------

common function to return language name from the data set according to IETF tag

returns language name

]]

local function language_name_get (ietf, code, variant)
if lang_data.override[ietf:lower()] then -- look for whole IETF tag in override table
return lang_data.override[ietf:lower()][1]; -- ietf:lower() because format_ietf_tag() returns mixed case
elseif lang_data.override[code] then -- not there so try basic language code
return lang_data.override[code][1];
elseif not is_set (variant) then -- shift to main code/name tables
if lang_name_table.lang[code] then
return lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end
else -- TODO: is this the right thing to do: take language display name from variants table?
if lang_name_table.variant[variant] then -- TODO: there is some discussion at Template talk:Lang about having a label parameter for use when variant name is not desired among other things
return lang_name_table.variant[variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
end
end
end


--[[--------------------------< _ L A N G >--------------------------------------------------------------------
--[[--------------------------< _ L A N G >--------------------------------------------------------------------
Line 842: Line 871:
local out = {};
local out = {};
local language_name; -- used to make category names
local language_name; -- used to make category names
local category_name; -- same as language_name except that it retains any parenthetical disambiguators (if any) from the data set
local subtags = {}; -- IETF subtags script, region, variant, and private
local subtags = {}; -- IETF subtags script, region, variant, and private
local code; -- the language code
local code; -- the language code
Line 904: Line 934:
end
end


args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant); -- format to recommended subtag styles; private omitted because private
args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles
language_name = language_name_get (args.code, code, subtags.variant); -- get language name; try ietf tag first, then code w/o variant then code w/ variant

subtags.private = subtags.private and table.concat ({code, '-x-', subtags.private}) or nil; -- assemble a complete private ietf subtag; args.code does not get private subtag

if is_set (subtags.private) and lang_data.override[subtags.private] then -- get the language name for categorization
language_name = lang_data.override[subtags.private][1]; -- first look for private use tag language name
elseif lang_data.override[code] then
language_name = lang_data.override[code][1] -- then language names taken from the override table
elseif lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end


if 'invert' == args.italic and 'span' == tag then -- invert only supported for in-line content
if 'invert' == args.italic and 'span' == tag then -- invert only supported for in-line content
Line 1,091: Line 1,112:
end
end


args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant); -- format to recommended subtag styles
args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles
language_name = language_name_get (args.code, code, subtags.variant); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
subtags.private = subtags.private and table.concat ({code, '-x-', subtags.private}) or nil; -- assemble a complete private ietf subtag; args.code does not get private subtag

if is_set (subtags.private) and lang_data.override[subtags.private] then -- get the language name for categorization
language_name = lang_data.override[subtags.private][1]; -- first look for private use tag language name
elseif lang_data.override[args.code:lower()] then -- look for whole IETF tag in override table
language_name = lang_data.override[args.code:lower()][1]; -- args.code:lower() because format_ietf_tag() returns mixed case
elseif lang_data.override[code] then -- not there so try basic language code
language_name = lang_data.override[code][1];
elseif not is_set (subtags.variant) then
if lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end
else -- TODO: is this the right thing to do: take language display name from variants table?
if lang_name_table.variant[subtags.variant] then -- TODO: there is some discussion at Template talk:Lang about having a label parameter for use when variant name is not desired among other things
language_name = lang_name_table.variant[subtags.variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
end
end


category_name = language_name; -- category names retain IANA parenthetical diambiguators (if any)
category_name = language_name; -- category names retain IANA parenthetical diambiguators (if any)
Line 1,139: Line 1,143:
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat


table.insert (out, make_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size))
table.insert (out, make_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size, nil))


if is_set (args.translit) and not unicode.is_Latin (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
if is_set (args.translit) and not unicode.is_Latin (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
Line 1,280: Line 1,284:


local function _is_ietf_tag (tag) -- entry point when this module is require()d into another
local function _is_ietf_tag (tag) -- entry point when this module is require()d into another
local c, s, r, v, p, err; -- code, script, region, private, error message
local c, s, r, v, p, err; -- code, script, region, variant, private, error message
c, s, r, v, p, err = get_ietf_parts (tag); -- disassemble tag into constituent part and validate
c, s, r, v, p, err = get_ietf_parts (tag); -- disassemble tag into constituent part and validate


Line 1,298: Line 1,302:




--[[--------------------------< _ N A M E _ F R O M _ C O D E >------------------------------------------------
--[[--------------------------< _ N A M E _ F R O M _ T A G >--------------------------------------------------


Returns language name associated with IETF language tag if valid; empty string else.
Returns language name associated with IETF language tag if valid; error message else.


All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
Line 1,314: Line 1,318:
local raw_code = args[1]; -- save a copy of the input IETF subtag
local raw_code = args[1]; -- save a copy of the input IETF subtag
local link = 'yes' == args['link']; -- make a boolean
local link = 'yes' == args['link']; -- make a boolean
local label = args.label;
local code; -- the language code
local code; -- the language code
local msg; -- gets an error message if IETF language tag is malformed or invalid
local msg; -- gets an error message if IETF language tag is malformed or invalid
Line 1,324: Line 1,329:
end
end


raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles; private omitted because private
if lang_data.override[raw_code:lower()] then -- look for whole IETF tag in override table (force lower case)
language_name = language_name_get (raw_code, code, subtags.variant); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
language_name = lang_data.override[raw_code:lower()][1];
elseif lang_data.override[code] then -- not there so try basic language code in override table
language_name = lang_data.override[code][1];
elseif not is_set (subtags.variant) then
if lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end
else -- TODO: is this the right thing to do: take language display name from variants table?
if lang_name_table.variant[subtags.variant] then -- TODO: there is some discussion at Template talk:Lang about having a label parameter for use when variant name is not desired among other things
language_name = lang_name_table.variant[subtags.variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
end
end


language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
Line 1,342: Line 1,336:
if link then -- when |link=yes, wikilink the language name
if link then -- when |link=yes, wikilink the language name
if language_name:find ('languages') then
if language_name:find ('languages') then
language_name = make_wikilink (language_name); -- collective language name uses simple wikilink
language_name = make_wikilink (language_name, label); -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
elseif lang_data.article_name[code] then
language_name = make_wikilink (lang_data.article_name[code][1], language_name); -- language name with wikilink from override data
language_name = make_wikilink (lang_data.article_name[code][1], label or language_name); -- language name with wikilink from override data
else
else
language_name = make_wikilink (language_name .. ' language', language_name); -- language name with wikilink
language_name = make_wikilink (language_name .. ' language', label or language_name); -- language name with wikilink
end
end
end
end


return language_name;
return language_name;

end
end


Line 1,501: Line 1,494:
local function transl (frame)
local function transl (frame)
return _transl (getArgs(frame));
return _transl (getArgs(frame));
end


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

Returns category name associated with IETF language tag if valid; error message else

All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.

Module entry point from another module

]]

local function _category_from_tag (args)
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = args[1]; -- save a copy of the input IETF subtag
local link = 'yes' == args['link']; -- make a boolean
local label = args.label;
local code; -- the language code
local msg; -- gets an error message if IETF language tag is malformed or invalid
local language_name = '';
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code);
if msg then
local template = (args['template'] and table.concat ({'{{', args['template'], '}}: '})) or ''; -- make template name (if provided by the template)
return table.concat ({'<span style=\"font-size:100%; font-style:normal;\" class=\"error\">error: ', template, msg, '</span>'});
end

raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles; private omitted because private
language_name = language_name_get (raw_code, code, subtags.variant); -- get language name; try ietf tag first, then code w/o variant then code w/ variant

return make_category (code, language_name, nil, true)
end


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

Module entry point from an {{#invoke:}}

]]

local function category_from_tag (frame) -- entry point from an {{#invoke:Lang|category_from_tag|<ietf tag>|template=<template name>}}
return _category_from_tag (getArgs (frame)); -- pass-on the args table, nothing else; getArgs() so we also get parent frame
end
end


Line 1,508: Line 1,544:


return {
return {
category_from_tag = category_from_tag,
lang = lang, -- entry point for {{lang}}
lang = lang, -- entry point for {{lang}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
Line 1,516: Line 1,553:
name_from_tag = name_from_tag, -- used for template documentation; possible use in ISO 639 name from code templates
name_from_tag = name_from_tag, -- used for template documentation; possible use in ISO 639 name from code templates
transl = transl, -- entry point for {{transl}}
transl = transl, -- entry point for {{transl}}

_lang = _lang, -- entry points when this module is require()d into other modules
_category_from_tag = _category_from_tag, -- entry points when this module is require()d into other modules
_lang = _lang,
_lang_xx_inherit = _lang_xx_inherit,
_lang_xx_inherit = _lang_xx_inherit,
_lang_xx_italic = _lang_xx_italic,
_lang_xx_italic = _lang_xx_italic,
Retrieved from "https://en.seminaverbi.bibleget.io/wiki/Module:Lang"