Разлика помеѓу преработките на „Модул:Lang“

Додадени 19.032 бајти ,  пред 29 дена
Вратена во иста состојба како на 26 мај 2021 00.46 ч.
(Revert на скриптата на најстарата.)
Ознаки: Рачно отповикување Отповикано
(Вратена во иста состојба како на 26 мај 2021 00.46 ч.)
Ознака: Рачно отповикување
 
require('Module:No globals');
local p = {};
 
local initial_style_state; -- set by lang_xx_normal() and lang_xx_italic()
 
local getArgs = require ('Module:Arguments').getArgs;
local lang_name_tableunicode = mw.loadDatarequire ('"Module:Language/name/Unicode data'"); -- for is_latin() and is_rtl()
local yesno = require ('Module:Yesno');
 
local synonym_table = mw.loadData ('Module:Lang/ISO 639 synonyms'); -- ISO 639-2/639-2T code translation to 639-1 code
 
local lang_data = mw.loadData ('Module:Lang/data'); -- language name override and transliteration tool-tip tables
local lang_name_table = lang_data.lang_name_table; -- language codes, names, regions, scripts, suppressed scripts
local lang_table = lang_data.lang_name_table.lang;
local lang_dep_table = lang_data.lang_name_table.lang_dep;
local script_table = lang_data.lang_name_table.script;
local region_table = lang_data.lang_name_table.region;
local variant_table = lang_data.lang_name_table.variant;
local suppressed_table = lang_data.lang_name_table.suppressed;
local override_table = lang_data.override;
 
local synonym_table = mw.loadData ('Module:Lang/ISO 639 synonyms'); -- ISO 639-2/639-2T code translation to 639-1 code
 
local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
 
local this_wiki_lang = mw.language.getContentLanguage().code; -- get this wiki's language
 
local initial_style_state; -- set by lang_xx_normal() and lang_xx_italic()
 
local maint_cats = {}; -- maintenance categories go here
 
 
--[[--------------------------< I SN V E R T _ LI T A TL NI C S >----------------------------------------------------------------
 
This function attempts to invert the italic markup a args.text by adding/removing leading/trailing italic markup
Returns true if all of text argument is written using Latn script for letters, numbers and punctuationset; false else.
in args.text. Like |italic=unset, |italic=invert disables automatic italic markup. Individual leading/trailing
apostrophes are converted to their html numeric entity equivalent so that the new italic markup doesn't become
bold markup inadvertently.
 
Leading and trailing wiki markup is extracted from args.text into separate table elements. Addition, removal,
For the purposes of this function, Latn script is characters less control characters from these Unicode 10.0 Character Code Charts:
replacement of wiki markup is handled by a string.gsub() replacement table operating only on these separate elements.
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] U+0020–U+007E (20 - 7E) + see note about <poem>...</poem> support
In the string.gsub() matching pattern, '.*' matches empty string as well as the three expected wiki markup patterns.
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] U+00A0-U+00AC, U+00C0–U+00FF (C2 A0 - C2 AC, C3 80 - C3 BF: \194\160-\194\172)
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] U+0100–U+017F (C4 80 - C5 BF)
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] U+0180–U+024F (C6 80 - C9 8F)
[http://www.unicode.org/charts/PDF/U1E00.pdf Latin Extended Additional] U+1E00-U+1EFF (E1 B8 80 - E1 BB BF)
[http://www.unicode.org/charts/PDF/U2C60.pdf Latin Extended-C] U+2C60–U+2C7F (E2 B1 A0 - E2 B1 BF)
[http://www.unicode.org/charts/PDF/UA720.pdf Latin Extended-D] U+A720-U+A7FF (EA 9C A0 - EA 9F BF)
[http://www.unicode.org/charts/PDF/UAB30.pdf Latin Extended-E] U+AB30-U+AB6F (EA AC B0 - EA AD AF)
[http://www.unicode.org/charts/PDF/UFB00.pdf Alphabetic Presentaion Forms] U+FB00-U+FB06 (EF AC 80 - EF AC 86)
[http://www.unicode.org/charts/PDF/UFF00.pdf Halfwidth and Fullwidth Forms] U+FF01-U+FF3C (EF BC 81 EF BC BC)
 
This function expects that markup in args.text is complete and correct; if it is not, oddness may result.
does not include:
[http://www.unicode.org/charts/PDF/U1D00.pdf Phonetic Extensions] U+1D00-U+1D7F (E1 B4 80 - E1 B5 BF)
[http://www.unicode.org/charts/PDF/U0250.pdf IPA Extensions] U+0250-U+02AF (C9 90 - CA AF)
[http://www.unicode.org/charts/PDF/U1D80.pdf Phonetic Extensions Supplement] U+1D80-U+1DBF (E1 B6 80 - E1 B6 BF)
 
{{lang}} is used inside <poem>...</poem> tags for song lyrics, poetry, etc. <poem>...</poem> replaces newlines with
poem stripmarkers. These have the form:
?'"`UNIQ--poem-67--QINU`"'?
where the '?' character is actually the delete character (U+007F, \127). Including the '\n' (U+0010) and 'del' (U+007F)
characters in the latn character table allows {{lang}} to auto-italicize text within <poem>...</poem> tags.
 
]]
 
local function is_latninvert_italics (textsource)
local invert_pattern_table = { -- leading/trailing markup add/remove/replace patterns
local latn = table.concat (
[""]="\'\'", -- empty string becomes italic markup
{
'["\'\'"]="", -- this is a setitalic somarkup includebecomes openingempty bracketstring
["\'\'\'"]="\'\'\'\'\'", -- bold becomes bold italic
'\n\32-\127', -- C0 Controls and Basic Latin U+0020–U+007E (20 - 7E) + (U+0010 and U+007F <poem>...</poem> support)
["\'\194'\160-'\194'\172'"]="\'\'\'", -- C1bold Controls and Latin-1 Supplement U+00A0-U+00AC (C2 A0 -italic C2become AC)bold
};
'\195\128-\195\191', -- (skip shy) U+00C0–U+00FF (C3 80 - C3 BF)
local seg = {};
'\196\128-\197\191', -- Latin Extended-A U+0100–U+017F (C4 80 - C5 BF)
 
'\198\128-\201\143', -- Latin Extended-B U+0180–U+024F (C6 80 - C9 8F)
source = source:gsub ("%f[\']\'%f[^\']", '&#39;'); -- protect single quote marks from being interpreted as bold markup
'\225\184\128-\225\187\191', -- Latin Extended Additional U+1E00-U+1EFF (E1 B8 80 - E1 BB BF)
 
'\226\177\160-\226\177\191', -- Latin Extended-C U+2C60–U+2C7F (E2 B1 A0 - E2 B1 BF)
seg[1] = source:match ('^(\'\'+%f[^\']).+') or ''; -- get leading markup, if any; ignore single quote
'\234\156\160-\234\159\191', -- Latin Extended-D U+A720-U+A7FF (EA 9C A0 - EA 9F BF)
seg[3] = source:match ('.+(%f[\']\'\'+)$') or ''; -- get trailing markup, if any; ignore single quote
'\234\172\176-\234\173\175', -- Latin Extended-E U+AB30-U+AB6F (EA AC B0 - EA AD AF)
 
'\239\172\128-\239\172\134', -- Alphabetic Presentaion Forms U+FB00-U+FB06 (EF AC 80 - EF AC 86)
if '' ~= seg[1] and '' ~= seg[3] then -- extract the 'text'
'\239\188\129-\239\188\188', -- Halfwidth and Fullwidth Forms U+FF01-U+FF3C (EF BC 81 - EF BC BC)
seg[2] = source:match ('^\'\'+%f[^\'](.+)%f[\']\'\'+$') -- from between leading and trailing markup
']', -- close the set
elseif '' ~= seg[1] then
});
seg[2] = source:match ('^\'\'+%f[^\'](.+)') -- following leading markup
elseif '' ~= seg[3] then
seg[2] = source:match ('(.+)%f[\']\'\'+$') -- preceding trailing markup
else
seg[2] = source -- when there is no markup
end
 
seg[1] = invert_pattern_table[seg[1]] or seg[1]; -- replace leading markup according to pattern table
seg[3] = invert_pattern_table[seg[3]] or seg[3]; -- replace leading markup according to pattern table
 
textreturn = mwtable.text.decodeconcat (text, trueseg); -- replaceput numericit andall namedback htmltogether entities with their unicodeand charactersdone
text = mw.ustring.gsub (text, '%[%[[^|]+|([^%]]+)%]%]', '%1'); -- remove the link and markup from complex wikilink in case interwiki to non-Latn wikipedia
return not is_set (mw.ustring.gsub (text, latn, '')); -- replace all latn characters with empty space; if result is all empty space, text is latn
end
 
no - force args.text to be rendered in normal font; returns 'normal'
unset - disables font control so that font-style applied to text is dictated by markup inside or outside the template; returns 'inherit'
invert - disables font control so that font-style applied to text is dictated by markup outside or inverted inside the template; returns 'invert'
 
]]
 
local function validate_italic (italic, italicsargs)
local properties = {['yes'] = 'italic', ['no'] = 'normal', ['unset'] = 'inherit', ['invert'] = 'invert', ['default'] = nil};
local count = 0
for _, arg in pairs {'italic', 'italics', 'i'} do
if args[arg] then
count = count + 1
end
end
 
if italiccount and> italics1 then -- return nil and an error message if bothmore than one areis set
return nil, 'conflicting:only &#124;one of |italic=, and &#124;|italics=, or |i= can be specified';
end
return properties[args.italic or args.italics or args.i], nil; -- return an appropriate value and a nil error message
end
 
 
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------
 
Default behavior of the {{lang}} and {{lang-xx}} templates is to add categorization when the templates are used in mainspace.
This default functionality may be suppressed by setting |nocat=yes or |cat=no. This function selects one of these two parameters
to control categorization.
 
Because having two parameters with 'opposite' names and 'opposite' values is confusing, this function accepts only affirmative
values for |nocat= and only negative values for |cat=; in both cases the 'other' sense (and non-sense) is not accepted and the
parameter is treated as if it were not set in the template.
 
Sets args.nocat to true if categorization is to be turned off; to nil if the default behavior should apply.
 
Accepted values for |nocat= are the text strings:
'yes', 'y', 'true', 't', on, '1' -- [[Module:Yesno]] returns logical true for all of these; false or nil else
for |cat=
'no', 'n', 'false', 'f', 'off', '0' -- [[Module:Yesno]] returns logical false for all of these; true or nil else
 
]=]
 
local function validate_cat_args (args)
if not (args.nocat or args.cat) then -- both are nil, so categorize
return;
end
if false == yesno (args.cat) or true == yesno (args.nocat) then
args.nocat = true; -- set to true when args.nocat is affirmative; nil else (as if the parameter were not set in the template)
else -- args.nocat is the parameter actually used.
args.nocat = nil;
end
end
 
]]
 
local function in_array ( needle, haystack )
if needle == nil then
return false;
region: upper case
variant: lower case
private: lower case prefixed with -x-
 
]]
 
local function format_ietf_tag (code, script, region, variant, private)
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());
if is_set (script) then
script subtag - four character IANA script code
region subtag - two-letter or three digit IANA region code
variant subtag - four digit or 5-8 alnum variant code; only one variant subtag supported
private subtag - x- followed by 1-8 alnum private code; only supported with the primary language tag
 
because those parameters are superfluous to the IETF subtags in |code=)
 
returns six values; all lower case. Valid parts are returned as themselves; omitted parts are returned as empty strings, invalid
parts are returned as nil; the sixth returned item is an error message (if an error detected) or nil.
 
 
local function get_ietf_parts (source, args_script, args_region, args_variant)
local code, script, region, variant, private; -- ietf tag parts
local code;
local script = '';
local region = '';
local variant = '';
local private = '';
 
if not is_set (source) then
end
 
local pattern = { -- table of tables holding acceptibe ietf tag patterns and short names of the ietf part captured by the pattern
if source:match ('^%a%a%a?%-%a%a%a%a%-%a%a%-%d%d%d%d$') then -- ll-Ssss-RR-variant (where variant is 4 digits)
code, script, region, variant = source:match ({'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 1 - ll-Ssss-RR-variant (where variant is 4 digits);
elseif source:match ( {'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$'), then 's', 'r', 'v'}, -- 2 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
code, script, region, variant = source:match ({'^(%a%a%a?)%-(%a%a%a%a)%-(%da%d%da)%-(%dw%dw%dw%dw%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 3 - ll-Ssss-RR-variant (where variant is 5-8 alnum characters);
elseif source:match ( {'^(%a%a%a?)%-(%a%a%a%a)%-(%ad%a%-[%ad%d][)%a-(%d][w%aw%d][w%aw%d][w%aw?%d]+w?%w?)$'), then 's', 'r', 'v'}, -- 4 - ll-Ssss-RRDDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
elseif source:match ( {'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+)$'), then's', 'v'}, -- 5 - ll-Ssss-DDD-variant (where regionvariant is 34 digits; variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'v'}, -- 6 - ll-Ssss-variant (where variant is 5-8 alnum characters)
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
{'^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$', 'r', 'v'}, -- 7 - ll-RR-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$', 'r', 'v'}, -- 8 - ll-DDD-variant (where region is 3 digits; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 9 - ll-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 10 - ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d%d)$', 'v'}, -- 11 - ll-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$', 'v'}, -- 12 - ll-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits)
{'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss
{'^(%a%a%a?)%-(%a%a)$', 'r'}, -- 16 - ll-RR
{'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits)
{'^(%a%a%a?)$'}, -- 18 - ll
{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters)
}
 
local t = {}; -- table of captures; serves as a translator between captured ietf tag parts and named variables
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%d$') then -- ll-Ssss-variant (where variant is 4 digits)
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-%a%a%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-variant (where variant is 5-8 alnum characters)
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
 
for i, v in ipairs (pattern) do -- spin through the pattern table looking for a match
elseif source:match ('^%a%a%a?%-%a%a%-%d%d%d%d$') then -- ll-RR-variant (where variant is 4 digits)
local c1, c2, c3, c4; -- captures in the 'pattern' from the pattern table go here
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-%d%d%d%-%d%d%d%d$') then -- ll-DDD-variant (where region is 3 digits; variant is 4 digits)
codec1, regionc2, variantc3, c4 = source:match ('^(%a%a%a?pattern[i][1])%; -(%d%d%d)%-(%d%d%d%d one or more captures set if source matches pattern[i])$');
if c1 then -- c1 always set on match
elseif source:match ('^%a%a%a?%-%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-RR-variant (where variant is 5-8 alnum characters)
code = c1; -- first capture is always code
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
t = {
elseif source:match ('^%a%a%a?%-%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
[pattern[i][2] or 'x'] = c2, -- fill the table of captures with the rest of the captures
code, region, variant = source:match ('^(%a%a%a?)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
[pattern[i][3] or 'x'] = c3, -- take index names from pattern table and assign sequential captures
[pattern[i][4] or 'x'] = c4, -- index name may be nil in pattern[i] table so "or 'x'" spoofs a name for this index in this table
};
script = t.s or ''; -- translate table contents to named variables;
region = t.r or ''; -- absent table entries are nil so set named ietf parts to empty string for concatenation
variant= t.v or '';
private = t.p or '';
break; -- and done
end
end
 
if not code then
elseif source:match ('^%a%a%a?%-%d%d%d%d$') then -- ll-variant (where variant is 4 digits)
code, variant = source:match ('^(%a%a%a?)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-variant (where variant is 5-8 alnum characters)
code, variant = source:match ('^(%a%a%a?)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
 
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%a%a$') then -- ll-Ssss-RR
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$');
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d$') then -- ll-Ssss-DDD (region is 3 digits)
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$');
 
elseif source:match ('^%a%a%a?%-%a%a%a%a$') then -- ll-Ssss
code, script = source:match ('^(%a%a%a?)%-(%a%a%a%a)$');
 
elseif source:match ('^%a%a%a?%-%a%a$') then -- ll-RR
code, region = source:match ('^(%a%a%a?)%-(%a%a)$');
elseif source:match ('^%a%a%a?%-%d%d%d$') then -- ll-DDD (region is 3 digits)
code, region = source:match ('^(%a%a%a?)%-(%d%d%d)$');
 
elseif source:match ('^%a%a%a?$') then -- ll
code = source:match ('^(%a%a%a?)$');
 
elseif source:match ('^%a%a%a?%-x%-[%a%d][%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?$') then -- ll-x-pppppppp)
code, private = source:match ('^(%a%a%a?)%-x%-([%a%d]+)$');
 
else
return nil, nil, nil, nil, nil, table.concat ({'unrecognized language tag: ', source}); -- don't know what we got but it is malformed
end
code = code:lower(); -- ensure that we use and return lower case version of this
if not (lang_data.overrideoverride_table[code] or lang_name_table.langlang_table[code] or synonym_table[code] or lang_dep_table[code]) then
return nil, nil, nil, nil, nil, table.concat ({'unrecognized language code: ', code}); -- invalid language code, don't know about the others (don't care?)
end
if is_set (script) then
script = script:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.scriptscript_table[script] then
return code, nil, nil, nil, nil, table.concat ({'unrecognized script: ', script, ' for code: ', code}); -- language code ok, invalid script, don't know about the others (don't care?)
end
end
if lang_name_table.suppressedsuppressed_table[script] then -- ensure that code-script does not use a suppressed script
if in_array (code, lang_name_table.suppressedsuppressed_table[script]) then
return code, nil, nil, nil, nil, table.concat ({'script: ', script, ' not supported for code: ', code}); -- language code ok, script is suppressed for this code
end
if is_set (region) then
region = region:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.regionregion_table[region] then
return code, script, nil, nil, nil, table.concat ({'unrecognized region: ', region, ' for code: ', code});
end
if is_set (variant) then
variant = variant:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.variantvariant_table[variant] then -- make sure variant is valid
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant});
end -- does this duplicate/replace tests in lang() and lang_xx()?
if is_set (script) then -- if script set it must be part of the 'prefix'
if not in_array (table.concat ({code, '-', script}), lang_name_table.variantvariant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code-script pair: ', code, '-', script});
end
elseif is_set (region) then -- if region set, there are some prefixes that require lang code and region (en-CA-newfound)
if not in_array (code, variant_table[variant]['prefixes']) then -- first see if lang code is all that's required (en-oxendict though en-GB-oxendict is preferred)
if not in_array (table.concat ({code, '-', region}), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code-region pair: ', code, '-', region});
end
end
else
if not in_array (code, lang_name_table.variantvariant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code: ', code});
end
if is_set (private) then
private = private:lower(); -- ensure that we use and return lower case version of this
if not lang_data.overrideoverride_table[table.concat ({code, '-x-', private})] then -- make sure private tag is valid; note that index
return code, script, region, nil, nil, table.concat ({'unrecognized private tag: ', private});
end
local category;
if 'translTransl' == template then
category = 'translTransl';
else
category = 'langLang and lang-xx'
end
table.insert (out, table.concat ({'&#x5B;[', args.text or 'undefined', '&#x5D;] '})); -- for error messages output args.text if available
table.insert (out, table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">errorError: {{', template, '}}: '}));
table.insert (out, msg);
table.insert (out, table.concat ({' ([[:Category:', category, ' template errors|help]])'}));
table.insert (out, '</span>');
if (0 == namespace or 10 == namespace) and not is_set (args.nocat) then -- only categorize in article space (and template space to take care of broken usages)
table.insert (out, table.concat ({'[[Category:', category, ' template errors]]'}));
end
 
 
--[[--------------------------< MD AI K EV _ TM EA XR TK _ SU P _ A ND D >--------------------------------------------------
 
adds <i> and </i> tags to list-item text or to implied <p>..</p> text. mixed not supported
TODO: add support for block: div tags instead of span tags; would need some sort of proper parameter to control the switch
 
]]
For italic style, can't do ''{{lang|xx|text}}'' without using <span/> tags when text is italic because of -Latn, |italic=yes,
 
or auto-italics because the wrapping wikimarkup produces this:
local function div_markup_add (text, style)
<i><i lang="xx">text</i></i>
local implied_p = {};
which is later reduced to this:
 
<i>text</i>
if text:find ('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
This reduction happens in some sort of cleanup process outside the scope of this template/module.
if 'italic' == style then
return mw.ustring.gsub (text, '(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>'); -- insert italic markup at each list item
else
return text;
end
end
 
if text:find ('\n+') then -- look for any number of \n characters in text
text = text:gsub ('([^\n])\n([^\n])', '%1 %2'); -- replace single newline characters with a space character which mimics mediawiki
 
if 'italic' == style then
text = text:gsub('[^\n]+', '<p><i>%1</i></p>'); -- insert p and italic markup tags at each impled p (two or more consecutive '\n\n' sequences)
else
text = text:gsub ('[^\n]+', '<p>%1</p>'); -- insert p markup at each impled p
text = text:gsub ('\n', ''); -- strip newline characters
end
end
 
return text;
end
 
 
--[[--------------------------< M A K E _ T E X T _ H T M L >--------------------------------------------------
 
Add the html markup to text according to the type of content that it is: <span> or <i> tags for inline content or
Until or unless this is fixed italic text must be:
<div> tags for block content
<i><span lang="xx">text</span></i>
 
]]
 
local function make_text_spanmake_text_html (code, text, tag, rtl, style, size, language)
local spanhtml = {};
local style_added = '';
 
if text:match ('^%*') then
table.insert (spanhtml, '&#42;'); -- move proto language text prefix outside of italic markup if any; use numeric entity because planplain splat confuses MediaWiki
text = text:gsub ('^%*', ''); -- remove the spatsplat from the text
end
 
if 'span' == tag then -- default html tag for inline content
if 'italic' == style then
table.insert (span,if '<i>italic'); == style then -- openbut italicif style tagitalic
tag = 'i'; -- change to <i> tags
end
else -- must be div so go
text = div_markup_add (text, style); -- handle implied <p>, implied <p> with <i>, and list markup (*;:#) with <i>
end
table.insert (span, table.concat ({'<span lang="'})); -- open <span> tag
table.insert (span, table.concat ({code, '\"'})); -- add language attribute
 
table.insert (html, table.concat ({'<', tag})); -- open the <i>, <span>, or <div> html tag
if rtl then
table.insert (spanhtml, table.concat ({' dirlang="rtl', code, '\"'})); -- add directionlanguage attribute for right to left languages
 
if rtl or unicode.is_rtl(text) then
table.insert (html, ' dir="rtl"'); -- add direction attribute for right to left languages
end
 
if 'normal' == style then -- when |italic=no
table.insert (spanhtml, ' style=\"font-style: normal;'); -- override external markup, if any
style_added = '\"'; -- remember that style attribute added and is not yet closed
end
if is_set (size) then -- when |size=<something>
if is_set (style_added) then
table.insert (spanhtml, table.concat ({' font-size: ', size, ';'})); -- add when style attribute already inserted
else
table.insert (spanhtml, table.concat ({' style=\"font-size: ', size, ';'})); -- create style attribute
style_added = '\"'; -- remember that style attribute added and is not yet closed
end
end
 
if is_set (language) then
table.insert (span, table.concat ({style_added, '>'})); -- close the style attribute and close opening span tag
table.insert (spanhtml, texttable.concat ({style_added, ' title=\"', language})); --start insertthe thetitle text
if language:find ('languages') then
table.insert (html, ' collective text'); -- for collective languages
else
table.insert (html, '-language text'); -- for individual languages
end
table.insert (html, '\">'); -- close the opening html tag
else
table.insert (html, table.concat ({style_added, '>'})); -- close the style attribute and close opening html tag
end
table.insert (html, text); -- insert the text
 
table.insert (spanhtml, table.concat ({'</span', tag, '>'})); -- close the <i>, <span>, or <div> html tag
 
if 'italic' == style then
if rtl then -- legacy; shouldn't be necessary because all of the rtl text is wrapped inside an html tag with dir="rtl" attribute
table.insert (span, '</i>'); -- close italic style tag
table.insert (html, '&lrm;'); -- make sure the browser knows that we're at the end of the rtl
end
return table.concat (html); -- put it all together and done
if rtl then -- legacy; shouldn't be necessary because all of the rtl text is wrapped in <span dir="rtl">text</span>
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
 
[[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):
[[Category:Articles with text from thein <language> languages collective]]
 
]=]
 
local function make_category (code, language_name, nocat, name_get)
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
end
 
if language_name:find ('languages') then
return table.concat ({'[[Category:Articles with text from thein ', language_name, ' collective]]'});
end
table.insert (cat, '[[Category:Articles containing ');
 
if 'en' == code then
table.insert (cat, 'explicitly cited English' .. language_name); -- falls back to English if regional name not available
elseif 'art' == code then
table.insert (cat, 'constructed')
else
table.insert (cat, language_name);
table.insert (cat, '-language text]]');
 
return table.concat (cat);
end
 
if is_set (code) then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
if not style then -- nil for is the default italic style
table.insert (tout, "<i lang=\""); -- so use <i> tag
else
table.insert (tout, table.concat ({'<span style=\"font-style: ', style, '\" lang=\"'})); -- non-standard style, construct a span tag for it
end
table.insert (tout, code);
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
end
table.insert (tout, ' transliterationromanization'); -- finish the tool tip; use romanization when neither script nor standard supplied
elseif is_set (std) and is_set (tscript) then -- when both are specified
if title_table[std] then -- and if standard is legitimate
if title_table[std][tscript] then -- and if script for that standard is legitimate
table.insert (tout, table.concat ({title_table[std][tscript:lower()], ' (', lang_name_table.scriptscript_table[tscript][1], ' script) transliteration'})); -- add the appropriate text to the tool tip
else
table.insert (tout, title_table[std]['default']); -- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?
if title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
-- table.insert (tout, table.concat ({title_table[std][code:lower()], ' (', lang_name_table.langlang_table[code][1], ' language) transliteration'})); -- add the appropriate text to the tool tip
table.insert (tout, table.concat ({title_table[std][code:lower()], ' (', language_name, ' language) transliteration'})); -- add the appropriate text to the tool tip
else -- code doesn't match
table.insert (tout, title_table[std]['default']); -- so use the standard's default
table.insert (tout, '">');
table.insert (tout, translit);
if is_set (code) and not style then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
table.insert (tout, "</i>"); -- close the italic tag
else
 
 
--[=[--------------------------< V A L I D A T E _ T E X T >----------------------------------------------------
 
This function checks the content of args.text and returns empty string if nothing is amiss else it returns an
 
Italic rendering is controlled by the |italic= template parameter so italic markup should never appear in args.text
either as ''itself''' or as '''''bold italic''''' unless |italic=unset or |italic=invert.
 
]=]
 
local function validate_text (template, args)
end
 
local style = args.italic;
if 'lang-xx' == template then -- for the time being, this error checking does not apply to {{lang}}
 
if ('unset' ~= args.italic) and ('unset' ~= args.italics) then -- allow italic markup when |italic=unset or |italics=unset
if ('unset' ~= style) and ('invert' ~=style) then
if args.text:match ("%f[\']\'\'[^\']+\'\'%f[^\']") or args.text:match ("\'\'\'\'\'[^\']+\'\'\'\'\'") then -- italic but not bold, or bold italic
if args.text:find ("%f[\']\'\'%f[^\']") or args.text:find ("%f[\']\'\'\'\'\'%f[^\']") then -- italic but not bold, or bold italic
return make_error_msg ('text has italic markup', args, template);
return make_error_msg ('text has italic markup', args, template);
end
end
end
if 0 < #maint_msgs then -- when there are maintenance messages
table.insert (maint, table.concat ({'<span class="lang-comment" style="font-style: normal; display: none; color: #33aa33; margin-left: 0.3em;">'})); -- opening <span> tag
for _, msg in ipairs (maint_msgs) do
table.insert (maint, table.concat ({msg, ' '})); -- add message strings
end
if (0 < #maint_cats) and (0 == namespace) and not is_set (nocat) then -- when there are mainenancemaintenance categories; article namespace only
for _, cat in ipairs (maint_cats) do
table.insert (maint, table.concat ({'[[Category:', cat, ']]'})); -- format and add the categories
--[[--------------------------< P R O T O _ P R E F I X >------------------------------------------------------
 
for proto languages, text is prefixed with a splat. We do that here as a flag for make_text_spanmake_text_html() so that a splat
will be rendered outside of italic markup (if used). If the first character in text here is already a splat, we
do nothing
 
proto_param is boolean or nil; true adds splat prefix regardless of language name; false removes and / or inhibits
regardless of language name; nil does nothing; presumes that the value in text is correct but removes extra splac
 
]]
 
local function proto_prefix (text, language_name, proto_param)
if false == proto_param then -- when forced by |proto=no
if language_name:find ('^Proto%-') and not text:find ('^*') then -- language is a proto and text does not already have leading splat
return table.concattext:gsub ({'^%**', text}''); -- return text without splat prefix protoregardless of language textname withor aexisting splat prefix in text
elseif (language_name:find ('^Proto%-') or (true == proto_param)) then -- language is a proto or forced by |proto=yes
return text:gsub ('^%**', '*'); -- prefix proto-language text with a splat; also removes duplicate prefixing splats
end
return text:gsub ('^%*+', '*'); -- return text unmolested except multiple splats reduced to one splat
return text;
end
 
 
--[[--------------------------< LH A NS _ P O E M _ T A G >----------------------------------------------------------------------
 
looks for a poem strip marker in text; returns true when found; false else
 
auto-italic detection disabled when text has poem stripmarker because it is not possible for this code to know
the content that will replace the stripmarker.
 
]]
 
local function has_poem_tag (text)
return text:find ('\127[^\127]*UNIQ%-%-poem%-[%a%d]+%-QINU[^\127]*\127') and true or false;
end
 
 
--[[--------------------------< H T M L _ T A G _ S E L E C T >------------------------------------------------
 
Inspects content of and selectively trims text. Returns text and the name of an appropriate html tag for text.
 
If text contains:
\n\n text has implied <p>..</p> tags - trim leading and trailing whitespace and return
If text begins with list markup:
\n* unordered
\n; definition
\n: definition
\n# ordered
trim all leading whitespace except \n and trim all trailing whitespace
 
If text contains <poem>...</poem> stripmarker, return text unmodified and choose <div>..</div> tags because
the stripmarker is replaced with text wrapped in <div>..</div> tags.
 
]]
 
local function html_tag_select (text)
local tag;
if has_poem_tag (text) then -- contains poem stripmarker (we can't know the content of that)
tag = 'div'; -- poem replacement is in div tags so lang must use div tags
elseif mw.text.trim (text):find ('\n\n+') then -- contains implied p tags
text = mw.text.trim (text); -- trim leading and trailing whitespace characters
tag = 'div'; -- must be div because span may not contain p tags (added later by MediaWiki); poem replacement is in div tags
elseif text:find ('\n[%*:;%#]') then -- if text has list markup
text = text:gsub ('^[\t\r\f ]*', ''):gsub ('%s*$', ''); -- trim all whitespace except leading newline character '\n'
tag = 'div'; -- must be div because span may not contain ul, dd, dl, ol tags (added later by MediaWiki)
else
text = mw.text.trim (text); -- plain text
tag = 'span'; -- so span is fine
end
return text, tag;
end
 
 
--[[--------------------------< V A L I D A T E _ P R O T O >--------------------------------------------------
 
validates value assigned to |proto=; permitted values are yes and no; yes returns as true, no returns as false,
empty string (or parameter omitted) returns as nil; any other value returns as nil with a second return value of
true indicating that some other value has been assigned to |proto=
 
]]
 
local function validate_proto (proto_param)
if 'yes' == proto_param then
return true;
elseif 'no' == proto_param then
return false;
elseif is_set (proto_param) then
return nil, true; -- |proto= something other than 'yes' or 'no'
else
return nil; -- missing or empty
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 if found in data tables; nil else
 
]]
 
local function language_name_get (ietf, code, cat)
ietf = ietf:lower(); -- ietf:lower() because format_ietf_tag() returns mixed case
local name; -- remains nil if not found
if override_table[ietf] then -- look for whole IETF tag in override table
name = override_table[ietf][1];
elseif override_table[code] then -- not there so try basic language code
name = override_table[code][1];
elseif lang_table[code] then -- shift to iana code/name table
name = lang_table[code][1]; -- table entries sometimes have multiple names, always take the first one
elseif lang_dep_table[code] then
-- if cat then
-- table.insert (maint_cats, table.concat ({'Lang and lang-xx using deprecated ISO 639 codes|', code}));
-- table.insert (maint_msgs, table.concat ({'code: ', code, ' is deprecated'}));
-- end
name = lang_dep_table[code][1]; -- table entries sometimes have multiple names, always take the first one
end
 
if lang_dep_table[code] and cat then -- because deprecated code may have been overridden to en.wiki preferred name
table.insert (maint_cats, table.concat ({'Lang and lang-xx using deprecated ISO 639 codes|', code}));
table.insert (maint_msgs, table.concat ({'code: ', code, ' is deprecated'}));
end
 
return name; -- name from data tables or nil
end
 
 
--[[--------------------------< _ L A N G >--------------------------------------------------------------------
 
entry point for {{lang}}
<includeonly>{{#invoke:lang|lang}}</includeonly>
 
parameters are recievedreceived from the template's frame (parent frame)
 
]]
 
local function p.lang_lang (frameargs)
local args = getArgs(frame);
local out = {};
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 code; -- the language code
local msg; -- for error messages
local tag = 'span'; -- initial value for make_text_html()
local template = args.template or 'Lang';
 
validate_cat_args (args); -- determine if categorization should be suppressed
 
if args[1] and args.code then
return make_error_msg ('conflicting: {{{1}}} and &#124;|code=', args, 'lang'template);
else
args.code = args[1] or args.code; -- prefer args.code
 
if args[2] and args.text then
return make_error_msg ('conflicting: {{{2}}} and &#124;|text=', args, 'lang'template);
else
args.text = args[2] or args.text; -- prefer args.text
end
msg = validate_text ('lang'template, args); -- ensure that |text= is set (italic test disabled for the time being)
if is_set (msg) then -- msg is an already-formatted error message
return msg;
end
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly
 
args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
 
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
return make_error_msg (table.concat ({'invalid |proto=: ', args.proto}), args, template);
end
 
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (args.code); -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})
 
if msg then
return make_error_msg ( msg, args, 'lang'template);
end
 
args.italic, msg = validate_italic (args.italic, args.italics);
if msg then
return make_error_msg (msg, args, 'lang'template);
end
 
if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if ('latn' == subtags.script) or (is_latn (args.text) and 'en' ~= code) then -- script set to latn or text is wholly latn script but not rendering English
(this_wiki_lang ~= code and not is_set (subtags.script) and not has_poem_tag (args.text) and unicode.is_Latin (args.text)) then -- text not this wiki's language, no script specified and not in poem markup but is wholly latn script (auto-italics)
args.italic = 'italic'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
args.italic = 'italic'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
else
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
end
 
args.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 (args.code, code, true); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
 
if 'invert' == args.italic and 'span' == tag then -- invert only supported for in-line content
if is_set (subtags.private) and lang_data.override[table.concat ({code, '-x-', subtags.private})] then -- look for private use tags; done this way because ...
args.text = invert_italics (args.text)
language_name = lang_data.override[table.concat ({code, '-x-', subtags.private})][1]; -- ... args.code does not get private subtag
elseif lang_data.override[code] then -- get the language name for categorization
language_name = lang_data.override[code][1] -- prefer 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
 
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat
 
table.insert (out, make_text_spanmake_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size, language_name));
table.insert (out, make_category (code, language_name, args.nocat));
table.insert (out, render_maint(args.nocat)); -- maintenance messages and categories
 
return table.concat (out); -- put it all together and done
end
 
 
--[[--------------------------< L A N G >----------------------------------------------------------------------
 
entry point for {{lang}}
 
there should be no reason to set parameters in the {{lang}} {{#invoke:}}
<includeonly>{{#invoke:lang|lang}}</includeonly>
 
parameters are received from the template's frame (parent frame)
 
]]
 
local function lang (frame)
local args = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text
valueFunc = function (key, value)
if 2 == key or 'text' == key then -- the 'text' parameter; do not trim wite space
return value; -- return untrimmed 'text'
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
if '' ~= value then -- empty string when value was only whitespace
return value;
end
end
return nil; -- value was empty or contained only whitespace
end -- end of valueFunc
});
 
return _lang (args);
end
 
that can have multiple writing systems, it may be appropriate to set |script= as well.
 
For each {{lang-xx}} template choose the appropriate entry-point function so that this function knowknows the default
styling that should be applied to text.
 
Supported parameters are:
|code = (required) the IANA language code
|script = IANA script code; especially for use with languages that use multiple writing systems; yields to the script subtag in |code= if present [not yet implemented]
|region = IANA region code
|variant = IANA variant code
|text = (required) the displayed text in language specified by code
|link = boolean false ('no') unlinksdoes languagenot specified bylink code-spcified language name to associated language article
|rtl = boolean true ('yes') identifies the language specified by code as a right-to-left language
|nocat = boolean true ('yes') inhibits normal categorization; error categories are not affected
|cat = boolian false ('no') opposite form of |nocat=
|italic = boolean true ('yes') renders displayed text in italic font; boolean false ('no') renders displayed text in normal font; not set renders according to initial_style_state
|lit = text that is a literal translation of text
|label = 'none' to suppress all labeling (language name, 'translit.', 'lit.')
any other text replaces language-name label - automatic wikilinking disabled
for those {{lang-xx}} templates that support transliteration (those templatetemplates where |text= is not entirely latn script):
|translit = text that is a transliteration of text
|translit-std = the standard that applies to the transliteration
]]
 
local function _lang_xx (frameargs)
local args = getArgs(frame, {parentFirst= true}); -- parameters in the template override parameters set in the {{#invoke:}}
local out = {};
local language_name; -- used to make display text, article links
local translit_title;
local msg; -- for error messages
local tag = 'span'; -- initial value for make_text_html()
local template = args.template or 'Lang-xx';
 
if args[1] and args.text then
return make_error_msg ('conflicting: {{{1}}} and &#124;|text=', args, 'lang-xx'template);
else
args.text = args[1] or args.text; -- prefer args.text
end
msg = validate_text ('lang-xx'template, args); -- ensure that |text= is set, does not contain italic markup and is protected from improper bolding
if is_set (msg) then
return msg;
end
 
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly
 
if args[2] and args.translit then
return make_error_msg ('conflicting: {{{2}}} and &#124;|translit=', args, 'lang-xx'template);
else
args.translit = args[2] or args.translit -- prefer args.translit
if args[3] and (args.translation or args.lit) then
return make_error_msg ('conflicting: {{{3}}} and &#124;|lit= or &#124;|translation=', args, 'lang-xx'template);
elseif args.translation and args.lit then
return make_error_msg ('conflicting: &#124;|lit= and &#124;|translation=', args, 'lang-xx'template);
else
args.translation = args[3] or args.translation or args.lit; -- prefer args.translation
 
if args.links and args.link then
return make_error_msg ('conflicting: &#124;|links= and &#124;|link=', args, 'lang-xx'template);
else
args.link = args.link or args.links; -- prefer args.link
end
 
validate_cat_args (args); -- determine if categorization should be suppressed
 
args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
 
if msg then -- if an error detected then there is an error message
return make_error_msg (msg, args, 'lang-xx'template);
end
args.italic, msg = validate_italic (args.italic, args.italics);
if msg then
return make_error_msg (msg, args, 'lang-xx'template);
end
 
end
 
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant); -- format to recommended subtag styles
if msg then
return make_error_msg (table.concat ({'invalid |proto=: ', args.proto}), args, template);
if is_set (subtags.private) and lang_data.override[table.concat ({code, '-x-', subtags.private})] then -- look for private use tags; done this way because ...
language_name = lang_data.override[table.concat ({code, '-x-', subtags.private})][1]; -- ... args.code does not get private subtag
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
 
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, true); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
 
category_name = language_name; -- category names retain IANA parenthetical diambiguators (if any)
if language_name:find ('languages') then
table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
table.insert (out, make_wikilink (lang_data.article_name[code][1], language_name)); -- language name with wikilink from override data
else
table.insert (out, make_wikilink (language_name .. ' language', language_name)); -- language name with wikilink
end
 
if 'invert' == args.italic then
args.text = proto_prefix (args.text, language_name); -- prefix proto-language text with a splat
args.text = invert_italics (args.text)
end
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat
 
table.insert (out, make_text_spanmake_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size, ('none' == args.label) and language_name or nil))
 
if is_set (args.translit) and not is_latnunicode.is_Latin (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
table.insert (out, ', '); -- comma to separate text from translit
if 'none' ~= args.label then
table.insert (out, '<small>');
if lang_name_table.scriptscript_table[args['translit-script']] then -- when |translit-script= is set, try to use the script's name
translit_script_name = lang_name_table.scriptscript_table[args['translit-script'][1]];
else
translit_script_name = language_name; -- fall back on language name
translit_title = mw.title.makeTitle (0, table.concat ({'Romanization of ', translit_script_name})); -- make a title object
if translit_title.exists and ('no' ~= args.link) then
table.insert (out, make_wikilink ('Romanization of ' .. translit_script_name or language_name, 'translit.romanized') .. ':'); -- make a wikilink if there is an article to link to
else
table.insert (out, '<abbr title="transliteration">translit.</abbr>romanized:'); -- else define theplain abbreviationtext
end
table.insert (out, '&nbsp;</small>'); -- close the small tag
table.insert (out, translit);
else
return make_error_msg (table.concat ({'invalid translit-std: \'', args['translit-std'] or '[missing]'}), args, 'lang-xx'template);
end
end
table.insert (out, make_wikilink ('Literal translation', 'lit.'));
end
table.insert (out, "&nbspthinsp;</small>");
end
table.insert (out, table.concat ({"'"&#39;', args.translation, "'"&#39;'})); -- use html entities to avoid wiki markup confusion
end
 
return table.concat (out); -- put it all together and done
end
 
 
--[[--------------------------< L A N G _ X X _ A R G S _ G E T >----------------------------------------------
 
common function to get args table from {{lang-??}} templates
 
returns table of args
 
]]
 
local function lang_xx_args_get (frame)
local args = getArgs(frame,
{
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}}
valueFunc = function (key, value)
if 1 == key then -- the 'text' parameter; do not trim wite space
return value; -- return untrimmed 'text'
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
if '' ~= value then -- empty string when value was only whitespace
return value;
end
end
return nil; -- value was empty or contained only whitespace
end -- end of valueFunc
});
 
return args;
end
 
]]
 
local function p.lang_xx_italic (frame)
local args = lang_xx_args_get (frame);
initial_style_state = 'italic';
return _lang_xx (args);
end
 
 
--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------
 
Entry point ffrom another module. Sets the initial style state to italic.
 
]]
 
local function _lang_xx_italic (args)
initial_style_state = 'italic';
return _lang_xx (frameargs);
end
 
]]
 
local function p.lang_xx_inherit (frame)
local args = lang_xx_args_get (frame);
 
initial_style_state = 'inherit';
return _lang_xx (frameargs);
end
 
 
--[[--------------------------< N_ L A MN EG _ FX R O MX _ CI ON DH E R I T >--------------------------------------------------
 
Entry point from another module. Sets the initial style state to inherit.
Returns language name associated with IETF language tag if valid; empty string else.
 
]]
 
local function _lang_xx_inherit (args)
initial_style_state = 'inherit';
return _lang_xx (args);
end
 
 
--[[--------------------------< _ I S _ I E T F _ T A G >------------------------------------------------------
 
Returns true when a language name associated with IETF language tag exists; nil else. IETF language tag must be valid.
 
All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
 
Module entry point from another module
 
]]
 
local function _is_ietf_tag (tag) -- entry point when this module is require()d into another
function p.name_from_code (frame)
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
 
return ((c and not err) and true) or nil; -- return true when code portion has a value without error message; nil else
end
 
 
--[[--------------------------< I S _ I E T F _ T A G >--------------------------------------------------------
 
Module entry point from an {{#invoke:}}
 
]]
 
local function is_ietf_tag (frame)
return _is_ietf_tag (getArgs (frame)[1]); -- args[1] is the ietf language tag to be tested; also get parent frame
end
 
 
--[[--------------------------< I S _ I E T F _ T A G _ F R A M E >--------------------------------------------
 
Module entry point from an {{#invoke:}}; same as is_ietf_tag() except does not get parameters from the parent
(template) frame. This function not useful when called by {{lang|fn=is_ietf_tag_frame|<tag>}} because <tag>
is in the parent frame.
 
]]
 
local function is_ietf_tag_frame (frame)
return _is_ietf_tag (getArgs (frame, {frameOnly = true,})[1]); -- args[1] is the ietf language tag to be tested; do not get parent frame
end
 
 
--[[--------------------------< _ N A M E _ F R O M _ T A G >--------------------------------------------------
 
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.
 
Set invoke's |link= parameter to yes to get wikilinked version of the language name.
 
Module entry point from another module
 
]]
 
local function _name_from_tag (args)
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = (frame.args and frame.args[1]) or frame; -- 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; -- holdsgets an error message (not used here) 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 '';
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
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); -- 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 = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
language_name = lang_data.override[code][1];
 
elseif not is_set (subtags.variant) then
if link then -- when |link=yes, wikilink the language name
if lang_name_table.lang[code] then
if language_name:find ('languages') then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
language_name = make_wikilink (language_name, label); -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
language_name = make_wikilink (lang_data.article_name[code][1], label or language_name); -- language name with wikilink from override data
else
language_name = make_wikilink (language_name .. ' language', label or language_name); -- language name with wikilink
end
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
return language_name;
language_name = lang_name_table.variant[subtags.variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
end
 
 
--[[--------------------------< N A M E _ F R O M _ T A G >----------------------------------------------------
 
Module entry point from an {{#invoke:}}
 
]]
 
local function name_from_tag (frame) -- entry point from an {{#invoke:Lang|name_from_tag|<ietf tag>|link=<yes>|template=<template name>}}
return _name_from_tag (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame
end
 
 
--[[--------------------------< _ T A G _ F R O M _ N A M E >--------------------------------------------------
 
Returns the ietf language tag associated with the language name. Spelling of language name must be correct
according to the spelling in the source tables. When a standard language name has a parenthetical disambiguator,
that disambiguator must be omitted (they are not present in the data name-to-tag tables).
 
Module entry point from another module
 
]]
 
local function _tag_from_name (args) -- entry point from another module
local msg;
 
if args[1] and '' ~= args[1] then
local data = mw.loadData ('Module:Lang/tag from name'); -- get the reversed data tables TODO: change when going live
local lang = args[1]:lower(); -- allow any-case for the language name (speeling must till be correct)
local tag = data.rev_override_table[lang] or data.rev_lang_table[lang] or data.rev_lang_dep_table[lang]; -- get the code; look first in the override then in the standard
 
if tag then
return tag, true; -- language name found so return tag and done; second return used by is_lang_name()
else
msg = 'language: ' .. args[1] .. ' not found' -- language name not found, error message
end
else
msg = 'missing language name' -- language name not provided, error message
end
 
local template = '';
language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
if args.template and '' ~= args.template then
template = table.concat ({'{{', args['template'], '}}: '}); -- make template name (if provided by the template)
end
return table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">Error: ', template, msg, '</span>'});
end
 
return language_name;
 
--[[--------------------------< T A G _ F R O M _ N A M E >----------------------------------------------------
 
Module entry point from an {{#invoke:}}
 
]]
 
local function tag_from_name (frame) -- entry point from an {{#invoke:Lang|tag_from_name|<language name>|link=<yes>|template=<template name>}}
local result, _ = _tag_from_name (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; supress second return used by is_lang_name()
return result;
end
 
 
--[[--------------------------< TI RS _ L A N SG L_ N A M E >------------------------------------------------------------------
 
Module entry point from an {{#invoke:}}
Prospective replacement for the template {{transl}}
 
]]
 
local function p.translis_lang_name (frame)
local _, result = _tag_from_name (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; supress second return used by tag_from_name()
local args = getArgs(frame); -- no {{#invoke:}} parameters
return result and true or nil;
end
 
 
--[[--------------------------< _ T R A N S L >----------------------------------------------------------------
 
Module entry point from another module
 
]]
 
local function _transl (args)
local title_table = lang_data.translit_title_table; -- table of transliteration standards and the language codes and scripts that apply to those standards
local language_name; -- language name that matches language code; used for tool tip
local translit; -- translitteratedtransliterated text to display
local script; -- IANA script
local msg; -- for when called functions return an error message
 
if not title_table[args.translit_std] then
return make_error_msg (table.concat ({'unrecognized transliteration standard: ', args.translit_std}), args, 'translTransl');
end
else
else
if args[1] and args[1]:match ('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text?
return make_error_msg ('no text', args, 'translTransl'); -- args[1] is a code so we're missing text
else
args.text = args[1]; -- args[1] is not a code so we're missing that; assign args.text for error message
return make_error_msg ('missing language / script code', args, 'translTransl');
end
end
args.code = args[1]:lower(); -- use the language/script code; only (2, 3, or 4 alpha characters); lower case because table indexes are lower case
else
return make_error_msg (table.concat ({'unrecognized language / script code: ', args[1]}), args, 'translTransl'); -- invalid language / script code
end
else
return make_error_msg ('missing language / script code', args, 'translTransl'); -- missing language / script code so quit
end
 
args.italic, msg = validate_italic (args.italic, args.italics);
if msg then
return make_error_msg (msg, args, 'translTransl');
end
end
 
if lang_data.overrideoverride_table[args.code] then -- is code a language code defined in the override table?
language_name = lang_data.overrideoverride_table[args.code][1];
elseif lang_name_table.langlang_table[args.code] then -- is code a language code defined in the standard language code tables?
language_name = lang_name_table.langlang_table[args.code][1];
elseif lang_name_table.scriptlang_dep_table[args.code] then -- if here,is code is not a language code; isdefined itin athe scriptdeprecated language code tables?
language_name = lang_name_table.scriptlang_dep_table[args.code][1];
elseif script_table[args.code] then -- if here, code is not a language code; is it a script code?
language_name = script_table[args.code][1];
script = args.code; -- code was an ISO 15924 script so use that instead
args.code = ''; -- unset because not a language code
else
return make_error_msg (table.concat ({'unrecognized language / script code: ', args.code}), args, 'translTransl'); -- invalid language / script code
end
-- here only when all parameters passed to make_translit() are valid
 
 
--[[--------------------------< T R A N S L >------------------------------------------------------------------
return p;
 
Module entry point from an {{#invoke:}}
 
]]
 
local function transl (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 category_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
category_name = language_name_get (raw_code, code); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
category_name = make_category (code, category_name, nil, true):gsub ('[%[%]]', '');
 
return category_name;
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
 
 
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
 
return {
category_from_tag = category_from_tag,
lang = lang, -- entry point for {{lang}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_italic = lang_xx_italic,
is_ietf_tag = is_ietf_tag,
is_ietf_tag_frame = is_ietf_tag_frame,
is_lang_name = is_lang_name,
tag_from_name = tag_from_name, -- returns ietf tag associated with language name
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}}
_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_italic = _lang_xx_italic,
_is_ietf_tag = _is_ietf_tag,
get_ietf_parts = get_ietf_parts,
_tag_from_name = _tag_from_name,
_name_from_tag = _name_from_tag,
_transl = _transl,
};