Module:Lang: Difference between revisions
From Vigyanwiki
Template>Trappist the monk (per CfD;) |
Template>Gonnym (fixed bug in make_text_html() where & lrm; wasn't consistently added; fixed a lua error when trying to access "script_table[tscript][1]" with a nil value; refactored make_translit() and removed unreachable conditions; moved strings out of code to make code easier to read and strings easier to update; moving variable declarations near their assignments; various minor cleanup. All changes tested in /testcases.) |
||
Line 1: | Line 1: | ||
--[=[ | --[=[ | ||
Lua support for the {{ | Lua support for the {{Lang}}, {{Lang-xx}}, and {{Transl}} templates and | ||
support for other templates and modules. | |||
]=] | ]=] | ||
require('Module:No globals') | require('Module:No globals') | ||
local getArgs = require ('Module:Arguments').getArgs | local getArgs = require('Module:Arguments').getArgs | ||
local unicode = require ("Module:Unicode data") | local unicode = require("Module:Unicode data") -- for is_latin() and is_rtl() | ||
local lang_data = | 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 | 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_table = lang_data.lang_name_table.lang | ||
local lang_dep_table = lang_data.lang_name_table.lang_dep | local lang_dep_table = lang_data.lang_name_table.lang_dep | ||
local script_table = lang_data.lang_name_table.script | local script_table = lang_data.lang_name_table.script | ||
local override_table = lang_data.override | |||
local override_table = lang_data.override | |||
local | local namespace = mw.title.getCurrentTitle().namespace -- used for categorization | ||
local | local maintenance_categories = {} -- maintenance categories go here | ||
local maintenance_messages = {} -- and their messages go here | |||
local | local tracking_categories = { | ||
["CATEGORY_LANG_DEPRECATED"] = "Category:Lang and lang-xx using deprecated ISO 639 codes|%s", | |||
["CATEGORY_LANG_PROMOTED"] = "Category:Lang and lang-xx code promoted to ISO 639-1|%s", | |||
["ERROR_CATEGORY"] = "[[Category:%s template errors]]", | |||
} | |||
local | local language_categories = { | ||
["ENGLISH_TEXT"] = "[[Category:Articles containing explicitly cited %s-language text]]", | |||
["LANGUAGE_TEXT"] = "[[Category:Articles containing %s-language text]]", | |||
["LANGUAGES_COLLECTIVE_TEXT"] = "[[Category:Articles with text in %s]]", | |||
} | |||
local | local error_messages = { | ||
["CODE_DEPRECATED"] = "code: %s is deprecated", | |||
["CODE_PROMOTED"] = "code: %s promoted to code: %s", | |||
["CONFLICTING_LIT_TRANSLATION"] = "conflicting: {{{3}}} and |lit= or |translation=", | |||
["CONFLICTING_NAMED_AND_NAMED"] = "conflicting: |%s= and |%s=", | |||
["CONFLICTING_POSITIONAL_AND_NAMED"] = "conflicting: {{{%s}}} and |%s=", | |||
["INVALID_PROTO"] = "invalid |proto=", | |||
["INVALID_TRANSLIT_STD_VALUE"] = "invalid |translit-std=: %s", | |||
["MISSING_LANGUAGE_OR_SCRIPT_CODE"] = "missing language / script code", | |||
["MISSING_LANGUAGE_TAG"] = "missing language tag", | |||
["LANGUAGE_NOT_FOUND"] = "language: %s not found", | |||
["LANGUAGE_NOT_PROVIDED"] = "missing language name", | |||
["NO_TEXT"] = "no text", | |||
["ONLY_ONE_TYPE_ITALICS"] = "only one of |italic=, |italics=, or |i= can be specified", | |||
["REDUNDANT_REGION_TAG"] = "redundant region tag", | |||
["REDUNDANT_SCRIPT_TAG"] = "redundant script tag", | |||
["REDUNDANT_VARIANT_TAG"] = "redundant variant tag", | |||
["SCRIPT_NOT_SUPPOTED_FOR_CODE"] = "script: %s not supported for code: %s", | |||
["TEXT_HAS_MALFORMED_MARKUP"] = "text has malformed markup", | |||
["TEXT_HAS_ITALIC_MARKUP"] = "text has italic markup", | |||
["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"] = "unrecognized language / script code: %s", | |||
["UNRECOGNIZED_TRANSLITERATION_STANDARD"] = "unrecognized transliteration standard: %s", | |||
["UNRECOGNIZED_LANGUAGE_CODE"] = "unrecognized language code: %s", | |||
["UNRECOGNIZED_LANGUAGE_TAG"] = "unrecognized language tag: %s", | |||
["UNRECOGNIZED_PRIVATE_TAG"] = "unrecognized private tag: %s", | |||
["UNRECOGNIZED_VARIANT"] = "unrecognized variant: %s", | |||
["UNRECOGNIZED_SCRIPT_FOR_CODE"] = "unrecognized script: %s for code: %s", | |||
["UNRECOGNIZED_REGION_FOR_CODE"] = "unrecognized region: %s for code: %s", | |||
["UNRECOGNIZED_VARIANT_FOR_CODE"] = "unrecognized variant: %s for code: %s", | |||
["UNRECOGNIZED_VARIANT_FOR_CODE_SCRIPT_PAIR"] = "unrecognized variant: %s for code-script pair: %s-%s", | |||
["UNRECOGNIZED_VARIANT_FOR_CODE_REGION_PAIR"] = "unrecognized variant: %s for code-region pair: %s-%s", | |||
} | |||
local strings = { | |||
-- Template names -- | |||
["TEMPLATE_LANG_LANG_XX"] = "Lang and lang-xx", | |||
["TEMPLATE_LANG"] = "Lang", | |||
["TEMPLATE_LANG_XX"] = "Lang-xx", | |||
["TEMPLATE_TRANSL"] = "Transl", | |||
--[[-- | -- Error -- | ||
["ERROR_SPAN"] = '[%s] <span style="font-size: 100%%; font-style: normal;" class="error">Error: {{%s}}: %s ([[:Category:%s template errors|help]])</span>', | |||
["UNDEFINED"] = "undefined", | |||
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. | -- Maintenance -- | ||
["MAINTENANCE_SPAN"] = '<span class="lang-comment" style="font-style: normal; display: none; color: #33aa33; margin-left: 0.3em;">%s</span>', | |||
-- Lang_xx -- | |||
["LABEL_LANGUAGE"] = "%s: %s", | |||
["LABEL_TRANSLATION"] = ', <small>%s </small>'%s'', -- use HTML entities to avoid wiki markup confusion | |||
["LABEL_TRANSLIT"] = ", <small>%s: </small>%s", | |||
["LIT"] = "lit.", | |||
["LITERAL_TRANSLATION_ABBR"] = '<abbr title="literal translation">lit.</abbr>', | |||
["LITERAL_TRANSLATION_TEXT"] = "Literal translation", | |||
["ROMANIZATION_OF"] = "Romanization of %s", | |||
["ROMANIZED"] = "romanized", | |||
-- HTML lang -- | |||
["HTML_LANG_TAG"] = '%s<%s lang="%s" %s style="%s %s" %s>%s</%s>%s', | |||
["ASTERISK"] = "*", -- use numeric entity because plain asterisk confuses MediaWiki | |||
["DIR_ATTRIBUTE"] = 'dir="rtl"', | |||
["FONT_STYLE"] = "font-style: normal;", | |||
["FONT_SIZE"] = "font-size: %s;", | |||
["LTR_MARK"] = "‎", | |||
["TITLE_ATTRIBUTE_COLLECTIVE"] = 'title="%s collective text"', | |||
["TITLE_ATTRIBUTE_LANGUAGE"] = 'title="%s language text"', | |||
-- Transliteration -- | |||
["TRANSLIT_ITALIC"] = '<i lang="%s-Latn" title="%s">%s</i>', | |||
["TRANSLIT_SPAN_CODE"] = '<span style="font-style: %s" lang="%s-Latn" title="%s">%s</span>', | |||
["TRANSLIT_SPAN_NO_CODE"] = '<span title="%s">%s</span>', | |||
["TRANSLITERATION_STD_SCRIPT"] = "%s (%s script) transliteration", | |||
["TRANSLITERATION_STD_LANGUAGE"] = "%s (%s language) transliteration", | |||
["TRANSLITERATION_SCRIPT"] = "%s-script transliteration", | |||
["TRANSLITERATION_LANGUAGES"] = "%s transliteration", | |||
["TRANSLITERATION_LANGUAGE"] = "%s-language transliteration", | |||
["ROMANIZATION_LANGUAGES"] = "%s romanization", | |||
["ROMANIZATION_LANGUAGE"] = "%s-language romanization", | |||
} | |||
--[[ -------------------------- < 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. | |||
]] | ]] | ||
local function is_set( var ) | local function is_set(var) | ||
return not (var == nil or var == '') | return not (var == nil or var == '') | ||
end | end | ||
--[[--------------------------< I N V E R T | --[[ -------------------------- < I N V E R T _ I T A L I C S > -------------------------- | ||
This function attempts to invert the italic markup | This function attempts to invert the italic markup in args.text | ||
in args.text | by adding or removing leading and trailing italic markup in args.text. | ||
Like |italic=unset, |italic=invert disables automatic italic markup. | |||
This function expects that markup in args.text is complete and correct; if it is not, oddness may result. | Individual leading and 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, replacement of wiki markup is handled by a string.gsub() | |||
replacement table operating only on these separate elements. | |||
In the string.gsub() matching pattern, '.*' matches empty string as well as | |||
the three expected wiki markup patterns. | |||
This function expects that markup in args.text is complete and correct; | |||
if it is not, oddness may result. | |||
]] | ]] | ||
local function invert_italics (source) | local function invert_italics(source) | ||
source = source:gsub("%f[\']\'%f[^\']", ''') -- protect single quote marks from being interpreted as bold markup | |||
source = source:gsub ("%f[\']\'%f[^\']", ''') | |||
seg[1] = source:match ('^(\'\'+%f[^\']).+') or '' | local seg = {} | ||
seg[3] = source:match ('.+(%f[\']\'\'+)$') or '' | seg[1] = source:match('^(\'\'+%f[^\']).+') or '' -- get leading markup, if any; ignore single quote | ||
seg[3] = source:match('.+(%f[\']\'\'+)$') or '' -- get trailing markup, if any; ignore single quote | |||
if | if seg[1] ~= '' and seg[3] ~= '' then -- extract the 'text' | ||
seg[2] = source:match ('^\'\'+%f[^\'](.+)%f[\']\'\'+$') -- from between leading and trailing markup | seg[2] = source:match('^\'\'+%f[^\'](.+)%f[\']\'\'+$') -- from between leading and trailing markup | ||
elseif | elseif seg[1] ~= '' then | ||
seg[2] = source:match ('^\'\'+%f[^\'](.+)') -- following leading markup | seg[2] = source:match('^\'\'+%f[^\'](.+)') -- following leading markup | ||
elseif | elseif seg[3] ~= '' then | ||
seg[2] = source:match ('(.+)%f[\']\'\'+$') -- preceding trailing markup | seg[2] = source:match('(.+)%f[\']\'\'+$') -- preceding trailing markup | ||
else | else | ||
seg[2] = source -- when there is no markup | seg[2] = source -- when there is no markup | ||
end | end | ||
local invert_pattern_table = { -- leading/trailing markup add/remove/replace patterns | |||
[""] = "\'\'", -- empty string becomes italic markup | |||
["\'\'"] = "", -- italic markup becomes empty string | |||
["\'\'\'"] = "\'\'\'\'\'", -- bold becomes bold italic | |||
["\'\'\'\'\'"] = "\'\'\'", -- bold italic become bold | |||
} | |||
return table.concat (seg) | 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 | |||
return table.concat(seg) -- put it all back together and done | |||
end | end | ||
--[[--------------------------< V A L I D A T E _ I T A L I C > | --[[ -------------------------- < V A L I D A T E _ I T A L I C > -------------------------- | ||
Validates |italic= or |italics= assigned values. | |||
When |italic= is set and has an | When |italic= is set and has an acceptable assigned value, | ||
return the matching css font-style property value or, | |||
for the special case 'default', return nil. | for the special case 'default', return nil. | ||
When |italic= is not set, or has an unacceptible assigned value, return nil and a nil error message. | When |italic= is not set, or has an unacceptible assigned value, | ||
return nil and a nil error message. | |||
When both |italic= and |italics= are set, returns nil and a 'conflicting' error message. | When both |italic= and |italics= are set, returns nil | ||
and a 'conflicting' error message. | |||
The return value nil causes the calling lang, lang_xx, or transl function to set args.italic according to the template's | The return value nil causes the calling lang, lang_xx, or transl function to set | ||
defined default ('inherit' for {{ | args.italic according to the template's defined default | ||
the individual template's requirements, 'italic' for {{ | ('inherit' for {{Lang}}, 'inherit' or 'italic' for {{Lang-xx}} depending on | ||
and {{ | the individual template's requirements, 'italic' for {{Transl}}) | ||
or to the value appropriate to |script=, if set ({{Lang}} and {{Lang-xx}} only). | |||
Accepted values and the values that this function returns are are: | Accepted values and the values that this function returns are are: | ||
Line 116: | Line 211: | ||
]] | ]] | ||
local function validate_italic (args) | local function validate_italic(args) | ||
local count = 0 | local count = 0 | ||
for _, arg in pairs {'italic', 'italics', 'i'} do | for _, arg in pairs{'italic', 'italics', 'i'} do | ||
if args[arg] then | if args[arg] then | ||
count = count + 1 | count = count + 1 | ||
Line 127: | Line 220: | ||
if count > 1 then -- return nil and an error message if more than one is set | if count > 1 then -- return nil and an error message if more than one is set | ||
return nil, | return nil, error_messages["ONLY_ONE_TYPE_ITALICS"] | ||
end | end | ||
return properties[args.italic or args.italics or args.i], nil | local properties = { | ||
['yes'] = 'italic', | |||
['no'] = 'normal', | |||
['unset'] = 'inherit', | |||
['invert'] = 'invert', | |||
['default'] = nil, | |||
} | |||
return properties[args.italic or args.italics or args.i], nil -- return an appropriate value and a nil error message | |||
end | end | ||
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S > | --[=[ -------------------------- < V A L I D A T E _ C A T _ A R G S > -------------------------- | ||
Default behavior of the {{ | 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 default functionality may be suppressed by setting |nocat=yes or |cat=no. This function selects one of these two parameters | ||
to control categorization. | to control categorization. | ||
Line 153: | Line 254: | ||
]=] | ]=] | ||
local function validate_cat_args (args) | local function validate_cat_args(args) | ||
if not (args.nocat or args.cat) then -- both are nil, so categorize | if not (args.nocat or args.cat) then -- both are nil, so categorize | ||
return | return | ||
end | end | ||
if | local yesno = require('Module:Yesno') | ||
args.nocat = true | if yesno(args.cat) == false or yesno(args.nocat) == true 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. | else -- args.nocat is the parameter actually used. | ||
args.nocat = nil | args.nocat = nil | ||
end | end | ||
end | end | ||
--[[--------------------------< I N _ A R R A Y > | --[[ -------------------------- < I N _ A R R A Y > -------------------------- | ||
Whether needle is in haystack | Whether needle is in haystack | ||
Line 172: | Line 274: | ||
]] | ]] | ||
local function in_array ( needle, haystack ) | local function in_array(needle, haystack) | ||
if needle == nil then | if needle == nil then | ||
return false | return false | ||
end | end | ||
for n,v in ipairs( haystack ) do | |||
for n, v in ipairs(haystack) do | |||
if v == needle then | if v == needle then | ||
return n | return n | ||
end | end | ||
end | end | ||
return false | return false | ||
end | end | ||
--[[--------------------------< F O R M A T _ I E T F _ T A G > | --[[ -------------------------- < F O R M A T _ I E T F _ T A G > -------------------------- | ||
Prettify IETF tags to use recommended subtag formats: | |||
code: lower case | code: lower case | ||
script: sentence case | script: sentence case | ||
Line 193: | Line 296: | ||
variant: lower case | variant: lower case | ||
private: lower case prefixed with -x- | private: lower case prefixed with -x- | ||
]] | ]] | ||
local function format_ietf_tag (code, script, region, variant, private) | local function format_ietf_tag(code, script, region, variant, private) | ||
local out = {} | local out = {} | ||
if is_set (private) then | if is_set(private) then | ||
return | return string.format("%s-x-%s", code:lower(), private:lower()) -- if private, all other tags ignored | ||
end | end | ||
table.insert (out, code:lower()) | table.insert(out, code:lower()) | ||
if is_set (script) then | if is_set(script) then | ||
script = script:lower():gsub ('^%a', string.upper) | script = script:lower():gsub('^%a', string.upper) | ||
table.insert (out, script) | table.insert(out, script) | ||
end | end | ||
if is_set (region) then | if is_set(region) then | ||
table.insert (out, region:upper()) | table.insert(out, region:upper()) | ||
end | end | ||
if is_set (variant) then | if is_set(variant) then | ||
table.insert (out, variant:lower()) | table.insert(out, variant:lower()) | ||
end | end | ||
return table.concat (out, '-') | return table.concat(out, '-') | ||
end | end | ||
--[[--------------------------< G E T _ I E T F _ P A R T S > | --[[ -------------------------- < G E T _ I E T F _ P A R T S > -------------------------- | ||
Extracts and returns IETF language tag parts: | |||
primary language subtag (required) - 2 or 3 character IANA language code | primary language subtag (required) - 2 or 3 character IANA language code | ||
script subtag - four character IANA script code | script subtag - four character IANA script code | ||
Line 230: | Line 333: | ||
private subtag - x- followed by 1-8 alnum private code; only supported with the primary language tag | private subtag - x- followed by 1-8 alnum private code; only supported with the primary language tag | ||
Supported forms: | |||
lang lang-variant | lang lang-variant | ||
lang-script lang-script-variant | lang-script lang-script-variant | ||
Line 236: | Line 339: | ||
lang-script-region lang-script-region-variant | lang-script-region lang-script-region-variant | ||
lang-x-private | lang-x-private | ||
Each of lang, script, region, variant, and private, when used, must be valid. | |||
Languages with both two- and three-character code synonyms are promoted to the two-character synonym because | Languages with both two- and three-character code synonyms are promoted to the two-character synonym because | ||
Line 243: | Line 346: | ||
the synonymous three-character codes in the lang= attribute. | the synonymous three-character codes in the lang= attribute. | ||
For {{ | For {{Lang-xx}} templates, the parameters |script=, |region=, and |variant= are supported (not supported in {{Lang}} | ||
because those parameters are superfluous to the IETF subtags in |code=) | 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. | parts are returned as nil; the sixth returned item is an error message (if an error detected) or nil. | ||
See http://www.rfc-editor.org/rfc/bcp/bcp47.txt section 2.1 | |||
]] | ]] | ||
local function get_ietf_parts (source, args_script, args_region, args_variant) | local function get_ietf_parts(source, args_script, args_region, args_variant) | ||
local | if not is_set(source) then | ||
return nil, nil, nil, nil, nil, error_messages["MISSING_LANGUAGE_TAG"] | |||
end | |||
local pattern = { -- table of tables holding acceptable IETF tag patterns and short names of the IETF part captured by the pattern | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 1 - ll-Ssss-RR-variant (where variant is 4 digits) | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 2 - ll-Ssss-DDD-variant (where region is 3 digits and variant is 4 digits) | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 3 - ll-Ssss-RR-variant (where variant is 5-8 alnum characters) | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 4 - ll-Ssss-DDD-variant (where region is 3 digits and variant is 5-8 alnum characters) | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$', 's', 'v'}, -- 5 - ll-Ssss-variant (where variant is 4 digits) | |||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'v'}, -- 6 - ll-Ssss-variant (where variant is 5-8 alnum characters) | |||
{'^(%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 and 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 and variant is 5-8 alnum characters) | |||
{'^(%a%a%a?)%-(%d%d%d%d)$', 'v'}, -- 11 - ll-variant (where variant is 4 digits) | {'^(%a%a%a?)%-(%d%d%d%d)$', 'v'}, -- 11 - ll-variant (where variant is 4 digits) | ||
{'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$', 'v'}, -- 12 - ll-variant (where variant is 5-8 alnum characters) | {'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$', 'v'}, -- 12 - ll-variant (where variant is 5-8 alnum characters) | ||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR | {'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR | ||
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits) | {'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits) | ||
{'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss | {'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss | ||
{'^(%a%a%a?)%-(%a%a)$', 'r'}, -- 16 - ll-RR | {'^(%a%a%a?)%-(%a%a)$', 'r'}, -- 16 - ll-RR | ||
{'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits) | {'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits) | ||
{'^(%a%a%a?)$'}, -- 18 - ll | {'^(%a%a%a?)$'}, -- 18 - ll | ||
{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters) | {'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters) | ||
} | |||
local t = {} | local t = {} -- table of captures; serves as a translator between captured IETF tag parts and named variables | ||
local code, script, region, variant, private -- IETF tag parts | |||
for i, v in ipairs(pattern) do -- spin through the pattern table looking for a match | |||
local c1, c2, c3, c4 -- captures in the 'pattern' from the pattern table go here | |||
c1, c2, c3, c4 = source:match(pattern[i][1]) -- one or more captures set if source matches pattern[i]) | |||
if c1 then -- c1 always set on match | |||
code = c1 -- first capture is always code | |||
c1, c2, c3, c4 = source:match (pattern[i][1]) | t = { | ||
[pattern[i][2] or 'x'] = c2, -- fill the table of captures with the rest of the captures | |||
[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 | end | ||
if not code then | if not code then | ||
return nil, nil, nil, nil, nil, | return nil, nil, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_LANGUAGE_TAG"], source) -- don't know what we got but it is malformed | ||
end | end | ||
code = code:lower() | code = code:lower() -- ensure that we use and return lower case version of this | ||
local synonym_table = mw.loadData('Module:Lang/ISO 639 synonyms') -- ISO 639-2/639-2T code translation to 639-1 code | |||
if not (override_table[code] or lang_table[code] or synonym_table[code] or lang_dep_table[code]) then | if not (override_table[code] or lang_table[code] or synonym_table[code] or lang_dep_table[code]) then | ||
return nil, nil, nil, nil, nil, | return nil, nil, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_LANGUAGE_CODE"], code) -- invalid language code, don't know about the others (don't care?) | ||
end | end | ||
if synonym_table[code] then -- if 639-2/639-2T code has a 639-1 synonym | if synonym_table[code] then -- if 639-2/639-2T code has a 639-1 synonym | ||
table.insert ( | table.insert(maintenance_categories, string.format(tracking_categories["CATEGORY_LANG_PROMOTED"], code)) | ||
table.insert ( | table.insert(maintenance_messages, string.format(error_messages["CODE_PROMOTED"], code, synonym_table[code])) | ||
code = synonym_table[code] | code = synonym_table[code] -- use the synonym | ||
end | end | ||
if is_set (script) then | if is_set(script) then | ||
if is_set (args_script) then | if is_set(args_script) then | ||
return code, nil, nil, nil, nil, | return code, nil, nil, nil, nil, error_messages["REDUNDANT_SCRIPT_TAG"] -- both code with script and |script= not allowed | ||
end | end | ||
else | else | ||
script = args_script or '' | script = args_script or '' -- use args.script if provided | ||
end | end | ||
if is_set (script) then | if is_set(script) then | ||
script = script:lower() | script = script:lower() -- ensure that we use and return lower case version of this | ||
if not script_table[script] then | if not script_table[script] then | ||
return code, nil, nil, nil, nil, | return code, nil, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_SCRIPT_FOR_CODE"], script, code) -- language code ok, invalid script, don't know about the others (don't care?) | ||
end | end | ||
end | end | ||
local suppressed_table = lang_data.lang_name_table.suppressed | |||
if suppressed_table[script] then -- ensure that code-script does not use a suppressed script | if suppressed_table[script] then -- ensure that code-script does not use a suppressed script | ||
if in_array (code, suppressed_table[script]) then | if in_array(code, suppressed_table[script]) then | ||
return code, nil, nil, nil, nil, | return code, nil, nil, nil, nil, string.format(error_messages["SCRIPT_NOT_SUPPOTED_FOR_CODE"], script, code) -- language code ok, script is suppressed for this code | ||
end | end | ||
end | end | ||
if is_set (region) then | if is_set(region) then | ||
if is_set (args_region) then | if is_set(args_region) then | ||
return code, | return code, script, nil, nil, nil, error_messages["REDUNDANT_REGION_TAG"] -- both code with region and |region= not allowed | ||
end | end | ||
else | else | ||
region = args_region or '' | region = args_region or '' -- use args.region if provided | ||
end | end | ||
if is_set (region) then | if is_set(region) then | ||
region = region:lower() | region = region:lower() -- ensure that we use and return lower case version of this | ||
local region_table = lang_data.lang_name_table.region | |||
if not region_table[region] then | if not region_table[region] then | ||
return code, script, nil, nil, nil, | return code, script, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_REGION_FOR_CODE"], region, code) | ||
end | end | ||
end | end | ||
if is_set (variant) then | if is_set(variant) then | ||
if is_set (args_variant) then | if is_set(args_variant) then | ||
return code, | return code, script, region, nil, nil, error_messages["REDUNDANT_VARIANT_TAG"] -- both code with variant and |variant= not allowed | ||
end | end | ||
else | else | ||
variant = args_variant or '' | variant = args_variant or '' -- use args.variant if provided | ||
end | end | ||
if is_set (variant) then | if is_set(variant) then | ||
variant = variant:lower() | variant = variant:lower() -- ensure that we use and return lower case version of this | ||
local variant_table = lang_data.lang_name_table.variant | |||
if not variant_table[variant] then -- make sure variant is valid | if not variant_table[variant] then -- make sure variant is valid | ||
return code, script, region, nil, nil, | return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT"], variant) | ||
end -- does this duplicate/replace tests in lang() and lang_xx()? | 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 ( | if is_set(script) then -- if script set it must be part of the 'prefix' | ||
return code, script, region, nil, nil, | if not in_array(string.format("%s-%s", code, script), variant_table[variant]['prefixes']) then | ||
return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE_SCRIPT_PAIR"], variant, code, script) | |||
end | end | ||
elseif is_set (region) then -- if region set, there are some prefixes that require lang code and region (en-CA-newfound) | 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(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 ( | if not in_array(string.format("%s-%s", code, region), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound) | ||
return code, script, region, nil, nil, | return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE_REGION_PAIR"], variant, code, region) | ||
end | end | ||
end | end | ||
else | else | ||
if not in_array (code, variant_table[variant]['prefixes']) then | if not in_array(code, variant_table[variant]['prefixes']) then | ||
return code, script, region, nil, nil, | return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE"], variant, code) | ||
end | end | ||
end | end | ||
end | end | ||
if is_set (private) then | if is_set(private) then | ||
private = private:lower() | private = private:lower() -- ensure that we use and return lower case version of this | ||
if not override_table[ | if not override_table[string.format("%s-x-%s", code, private)] then -- make sure private tag is valid; note that index | ||
return code, script, region, | return code, script, region, variant, nil, string.format(error_messages["UNRECOGNIZED_PRIVATE_TAG"], private) | ||
end | end | ||
end | end | ||
return code, script, region, variant, private, nil | return code, script, region, variant, private, nil -- return the good bits; make sure that msg is nil | ||
end | end | ||
--[[--------------------------< M A K E _ E R R O R _ M S G > | --[[ -------------------------- < M A K E _ E R R O R _ M S G > -------------------------- | ||
Assembles an error message from template name, message text, | |||
help link, and error category. | |||
]] | ]] | ||
local function make_error_msg (msg, args, template) | local function make_error_msg(msg, args, template) | ||
local out = {} | local out = {} | ||
local category | |||
local category | |||
if | if template == strings["TEMPLATE_TRANSL"] then | ||
category | category = strings["TEMPLATE_TRANSL"] | ||
else | |||
category = strings["TEMPLATE_LANG_LANG_XX"] | |||
end | |||
if template then | |||
table.insert(out, string.format(strings["ERROR_SPAN"], args.text or strings["UNDEFINED"], template, msg, category)) | |||
else | else | ||
category = | local error_text = string.format(strings["ERROR_SPAN"], "", "", msg, category) | ||
error_text = error_text:gsub("%[] ", ""):gsub("{{}}: ", "") | |||
table.insert(out, error_text) | |||
end | end | ||
if (namespace == 0) and not args.nocat then -- only categorize in article space | |||
table.insert(out, string.format(tracking_categories["ERROR_CATEGORY"], category)) | |||
table.insert (out, | |||
end | end | ||
return table.concat (out) | return table.concat(out) | ||
end | end | ||
Makes a wikilink | --[=[ -------------------------- < M A K E _ W I K I L I N K > -------------------------- | ||
link is provided, returns a wikilink in the form [[L]] | |||
empty string. | 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) | local function make_wikilink(link, display) | ||
if is_set (link) then | if is_set(link) then | ||
if is_set (display) then | if is_set(display) then | ||
return | return string.format("[[%s|%s]]", link, display) | ||
else | else | ||
return | return string.format("[[%s]]", link) | ||
end | end | ||
else | else | ||
return '' | return '' | ||
end | end | ||
end | end | ||
--[[--------------------------< D I V _ M A R K U P _ A D D > | --[[ -------------------------- < D I V _ M A R K U P _ A D D > -------------------------- | ||
Adds <i> and </i> tags to list-item text or to implied <p>..</p> text. | |||
Mixed not supported. | |||
]] | ]] | ||
local function div_markup_add (text, style) | local function div_markup_add(text, style) | ||
local implied_p = {} | local implied_p = {} | ||
if text:find ('^\n[%*:;#]') then | if text:find('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text | ||
if 'italic' | if style == 'italic' then | ||
return mw.ustring.gsub (text, '(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>') | return mw.ustring.gsub(text, '(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>') -- insert <i> tags at each list item | ||
else | else | ||
return text | return text | ||
end | end | ||
end | end | ||
if text:find ('\n+') then -- look for any number of \n characters in text | if text:find('\n+') then -- look for any number of \n characters in text | ||
text = text:gsub ('([^\n])\n([^\n])', '%1 %2') | text = text:gsub('([^\n])\n([^\n])', '%1 %2') -- replace single newline characters with a space character which mimics MediaWiki | ||
if 'italic' | if style == 'italic' then | ||
text = text:gsub('[^\n]+', '<p><i>%1</i></p>') | text = text:gsub('[^\n]+', '<p><i>%1</i></p>') -- insert <p> and <i> tags at each implied <p> (two or more consecutive '\n\n' sequences) | ||
else | else | ||
text = text:gsub ('[^\n]+', '<p>%1</p>') | text = text:gsub('[^\n]+', '<p>%1</p>') -- insert <p> markup at each implied <p> | ||
text = text:gsub ('\n', '') | text = text:gsub('\n', '') -- strip newline characters | ||
end | end | ||
end | end | ||
return text | return text | ||
end | end | ||
--[[--------------------------< M A K E _ T E X T _ H T M L > | --[[ -------------------------- < M A K E _ T E X T _ H T M L > -------------------------- | ||
Add the | Add the HTML markup to text according to the type of content that it is: | ||
<div> tags for block content | <span> or <i> tags for inline content or <div> tags for block content. | ||
]] | ]] | ||
local function make_text_html (code, text, tag, rtl, style, size, language) | local function make_text_html(code, text, tag, rtl, style, size, language) | ||
local | local asterisk = "" | ||
if text:match('^%*') then | |||
asterisk = strings["ASTERISK"] -- move proto language text prefix outside of italic markup if any | |||
if text:match ('^%*') then | text = text:gsub('^%*', '') -- remove the asterisk from the text | ||
text = text:gsub ('^%*', '') | |||
end | end | ||
if 'span' | if tag == 'span' then -- default HTML tag for inline content | ||
if 'italic' | if style == 'italic' then -- but if italic | ||
tag = 'i' | tag = 'i' -- change to <i> tags | ||
end | end | ||
else -- must be div so go | else -- must be <div> so go | ||
text = div_markup_add (text, style) | text = div_markup_add(text, style) -- handle implied <p>, implied <p> with <i>, and list markup (*;:#) with <i> | ||
end | end | ||
local ltr = "" | |||
local dir_attribute = "" | |||
if rtl or unicode.is_rtl(text) then | if rtl or unicode.is_rtl(text) then | ||
dir_attribute = strings["DIR_ATTRIBUTE"] -- add direction attribute for right to left languages | |||
ltr = strings["LTR_MARK"] -- legacy; shouldn't be necessary because all of the rtl text is wrapped inside an HTML tag with dir="rtl" attribute | |||
-- make sure the browser knows that we're at the end of the rtl | |||
end | end | ||
if 'normal' | local font_style = "" | ||
if style == 'normal' then -- when |italic=no | |||
font_style = strings["FONT_STYLE"] -- override external markup, if any | |||
end | end | ||
if is_set (size) then -- when |size=<something> | local font_size = "" | ||
if is_set(size) then -- when |size=<something> | |||
font_size = string.format(strings["FONT_SIZE"], size) | |||
end | end | ||
if is_set (language) then | local title_attribute = "" | ||
if is_set(language) then | |||
if language:find ('languages') then | if language:find('languages') then | ||
title_attribute = string.format(strings["TITLE_ATTRIBUTE_COLLECTIVE"], language) -- for collective languages | |||
else | else | ||
title_attribute = string.format(strings["TITLE_ATTRIBUTE_LANGUAGE"], language) -- for individual languages | |||
end | end | ||
end | end | ||
local html = string.format(strings["HTML_LANG_TAG"], asterisk, tag, code, dir_attribute, font_style, font_size, title_attribute, text, tag, ltr) | |||
-- Prettify output | |||
html = html:gsub('style=" "', ""):gsub("%s+", " "):gsub(" >", ">"):gsub(' "', '"') -- remove empty style="" attribute; extra spaces for a cleaner tag; space before closing tag or double quote | |||
return | return html | ||
end | end | ||
--[=[-------------------------< M A K E _ C A T E G O R Y > | --[=[ -------------------------- < M A K E _ C A T E G O R Y > -------------------------- | ||
For individual language, <language>, returns: | For individual language, <language>, returns: | ||
Line 565: | Line 669: | ||
]=] | ]=] | ||
local function make_category (code, language_name, nocat, name_get) | local function make_category(code, language_name, nocat, name_get) | ||
if ((namespace ~= 0) or nocat) and not name_get then -- only categorize in article space | |||
return '' -- return empty string for concatenation | |||
if (( | |||
return '' | |||
end | end | ||
if language_name:find ('languages') then | if language_name:find('languages') then | ||
return | return string.format(language_categories["LANGUAGES_COLLECTIVE_TEXT"], language_name) | ||
end | end | ||
if 'en' | if code == 'en' then | ||
return string.format(language_categories["ENGLISH_TEXT"], language_name) -- falls back to English if regional name not available | |||
else | else | ||
return string.format(language_categories["LANGUAGE_TEXT"], language_name) | |||
end | end | ||
end | end | ||
--[[--------------------------< M A K E _ T R A N S L I T > | --[[ -------------------------- < M A K E _ T R A N S L I T > -------------------------- | ||
Return translit <i lang=xx-Latn>...</i> where xx is the language code; | |||
else return empty string. | |||
The value |script= is not used in {{ | The value |script= is not used in {{Transl}} for this purpose; instead it uses |code. | ||
are listed in the {{ | Because language scripts are listed in the {{Transl}} switches they are included in the data tables. | ||
at {{Language with name and transliteration}}. | The script parameter is introduced at {{Language with name and transliteration}}. | ||
If |script= is set, this function uses it in preference to code. | |||
To avoid confusion, in this module and the templates that use it, the transliteration script parameter is renamed | To avoid confusion, in this module and the templates that use it, the transliteration script parameter is renamed | ||
to be |translit-script= (in this function, tscript) | to be |translit-script= (in this function, tscript). | ||
This function is used by both lang_xx() and transl() | This function is used by both lang_xx() and transl() | ||
Line 606: | Line 703: | ||
transl() always provides language_name, translit, and one of code or tscript, never both; always provides style | transl() always provides language_name, translit, and one of code or tscript, never both; always provides style | ||
For {{transl}}, style only applies when a language code is provided | For {{transl}}, style only applies when a language code is provided. | ||
]] | ]] | ||
local function make_translit (code, language_name, translit, std, tscript, style) | local function make_translit(code, language_name, translit, std, tscript, style) | ||
local title_table = lang_data.translit_title_table -- table of transliteration standards and the language codes and scripts that apply to those standards | |||
std = std and std:lower() -- lower case for table indexing | |||
local title_table = lang_data.translit_title_table | local title_attribute | ||
if is_set ( | if is_set(std) then | ||
if not | if not title_table[std] then -- invalid standard, setup for error message | ||
return '' | |||
end | end | ||
if title_table[std][tscript] and script_table[tscript] then -- and if script for that standard is legitimate | |||
title_attribute = string.format(strings["TRANSLITERATION_STD_SCRIPT"], title_table[std][tscript:lower()], script_table[tscript][1]) -- add the appropriate text to the tool tip | |||
elseif title_table[std][code] then -- if language code is in the table (transl may not provide a language code) | |||
title_attribute = string.format(strings["TRANSLITERATION_STD_LANGUAGE"],title_table[std][code:lower()], language_name) -- add the appropriate text to the tool tip | |||
if title_table[std] | |||
else | else | ||
title_attribute = title_table[std]['default'] -- use the default if script not in std table | |||
end | end | ||
elseif title_table['no_std'][tscript] then | |||
elseif | title_attribute = title_table['no_std'][tscript] -- use translit-script if set | ||
elseif title_table['no_std'][code] then | |||
title_attribute = title_table['no_std'][code] -- use language code | |||
elseif is_set(tscript) then | |||
title_attribute = string.format(strings["TRANSLITERATION_SCRIPT"], language_name) -- write a script tool tip | |||
-- TODO: Conflicting with next section. Commenting out for now. | |||
-- elseif is_set(code) then | |||
-- if language_name:find('languages') then -- collective language names (plural 'languages' is part of the name) | |||
-- title_attribute = string.format(strings["TRANSLITERATION_LANGUAGES"], language_name) | |||
-- else -- individual and macro languages only | |||
-- title_attribute = string.format(strings["TRANSLITERATION_LANGUAGE"], language_name) | |||
-- end | |||
else -- when neither standard nor script specified | |||
if language_name:find('languages') then -- collective language names (plural 'languages' is part of the name) | |||
title_attribute = string.format(strings["ROMANIZATION_LANGUAGES"], language_name) | |||
else -- individual and macro languages only | |||
title_attribute = string.format(strings["ROMANIZATION_LANGUAGE"], language_name) | |||
end | end | ||
end | end | ||
if is_set(code) then -- when a language code is provided (always with {{Lang-xx}} templates, not always with {{Transl}}) | |||
if style then | |||
if is_set (code) | return string.format(strings["TRANSLIT_SPAN_CODE"], style, code, title_attribute, translit) -- non-standard style, construct a <span> tag for it | ||
else -- nil for the default italic style | |||
return string.format(strings["TRANSLIT_ITALIC"], code, title_attribute, translit) -- so use <i> tag | |||
end | |||
else | else | ||
return string.format(strings["TRANSLIT_SPAN_NO_CODE"], title_attribute, translit) -- when no language code: no lang= attribute, not italic ({{Transl}} only) | |||
end | end | ||
end | end | ||
--[[--------------------------< V A L I D A T E _ T E X T > | --[[ -------------------------- < 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 | This function checks the content of args.text and returns empty string if nothing is amiss else it returns an | ||
error message. | error message. The tests are for empty or missing text and for improper or disallowed use of apostrophe markup. | ||
Italic rendering is controlled by the |italic= template parameter so italic markup should never appear in args.text | Italic rendering is controlled by the |italic= template parameter so italic markup should never appear in args.text | ||
Line 694: | Line 766: | ||
]] | ]] | ||
local function validate_text (template, args) | local function validate_text(template, args) | ||
if not is_set (args.text) then | if not is_set(args.text) then | ||
return make_error_msg ( | return make_error_msg(error_messages["NO_TEXT"], args, template) | ||
end | end | ||
if args.text:find ("%f[\']\'\'\'\'%f[^\']") or args.text:find ("\'\'\'\'\'[\']+") then -- because we're looking, look for 4 | if args.text:find("%f[\']\'\'\'\'%f[^\']") or args.text:find("\'\'\'\'\'[\']+") then -- because we're looking, look for 4 apostrophes or 6+ apostrophes | ||
return make_error_msg ( | return make_error_msg(error_messages["TEXT_HAS_MALFORMED_MARKUP"], args, template) | ||
end | end | ||
local style = args.italic | local style = args.italic | ||
if (style ~= 'unset') and (style ~= 'invert') then | |||
if ('unset' | if args.text:find("%f[\']\'\'%f[^\']") or args.text:find("%f[\']\'\'\'\'\'%f[^\']") 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(error_messages["TEXT_HAS_ITALIC_MARKUP"], args, template) | ||
return make_error_msg ( | |||
end | end | ||
end | end | ||
Line 713: | Line 784: | ||
--[[--------------------------< R E N D E R _ M A I N T > | --[[ -------------------------- < R E N D E R _ M A I N T E N A N C E > -------------------------- | ||
Render maintenance messages and categories. | |||
]] | ]] | ||
local function | local function render_maintenance(nocat) | ||
local | local maintenance = {} | ||
if 0 < # | if 0 < #maintenance_messages then | ||
table.insert ( | table.insert(maintenance, string.format(strings["MAINTENANCE_SPAN"], table.concat(maintenance_messages, " "))) | ||
end | end | ||
if (0 < # | if (0 < #maintenance_categories) and (namespace == 0) and not nocat then -- when there are maintenance categories; article namespace only | ||
for _, | for _, category in ipairs(maintenance_categories) do | ||
table.insert ( | table.insert(maintenance, string.format("[[%s]]", category)) -- format and add the categories | ||
end | end | ||
end | end | ||
return table.concat ( | return table.concat(maintenance) | ||
end | end | ||
--[[--------------------------< P R O T O _ P R E F I X > | --[[ -------------------------- < P R O T O _ P R E F I X > -------------------------- | ||
For proto languages, text is prefixed with an asterisk. | |||
will be rendered outside of italic markup (if used). | We do that here as a flag for make_text_html() so that an asterisk will be | ||
do nothing | rendered outside of italic markup (if used). | ||
If the first character in text here is already an asterisk, we do nothing. | |||
proto_param is boolean or nil | proto_param is boolean or nil: | ||
regardless of language name | - true adds asterisk 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 asterisk. | |||
]] | ]] | ||
local function proto_prefix (text, language_name, proto_param) | local function proto_prefix(text, language_name, proto_param) | ||
if | if proto_param == false then -- when forced by |proto=no | ||
return text:gsub ('^%**', '') | return text:gsub('^%**', '') -- return text without asterisk prefix regardless of language name or existing asterisk prefix in text | ||
elseif (language_name:find ('^Proto%-') or (true == proto_param)) then -- language is a proto or forced by |proto=yes | elseif (language_name:find('^Proto%-') or (true == proto_param)) then -- language is a proto or forced by |proto=yes | ||
return text:gsub ('^%**', '*') | return text:gsub('^%**', '*') -- prefix proto-language text with an asterisk; also removes duplicate prefixing asterisks | ||
end | end | ||
return text:gsub ('^%*+', '*') | return text:gsub('^%*+', '*') -- return text unmolested except multiple asterisks reduced to one asterisk | ||
end | end | ||
--[[--------------------------< H A S _ P O E M _ T A G > | --[[ -------------------------- < H A S _ 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> strip marker because it is not possible for this code to know | |||
the content that will replace the | the content that will replace the strip marker. | ||
]] | ]] | ||
local function has_poem_tag (text) | local function has_poem_tag(text) | ||
return text:find ('\127[^\127]*UNIQ%-%-poem%-[%a%d]+%-QINU[^\127]*\127') and true or false | return text:find('\127[^\127]*UNIQ%-%-poem%-[%a%d]+%-QINU[^\127]*\127') and true or false | ||
end | end | ||
--[[--------------------------< H T M L _ T A G _ S E L E C T > | --[[ -------------------------- < H T M L _ T A G _ S E L E C T > -------------------------- | ||
Inspects content of and selectively trims text. | Inspects content of and selectively trims text. | ||
Returns text and the name of an appropriate HTML tag for text. | |||
If text contains: | If text contains: | ||
Line 787: | Line 858: | ||
\n: definition | \n: definition | ||
\n# ordered | \n# ordered | ||
trim all leading whitespace except | trim all leading whitespace except \n and trim all trailing whitespace | ||
If text contains <poem>...</poem> | If text contains <poem>...</poem> strip marker, return text unmodified and choose <div>..</div> tags because | ||
the | the strip marker is replaced with text wrapped in <div>..</div> tags. | ||
]] | ]] | ||
local function html_tag_select (text) | local function html_tag_select(text) | ||
local tag | local tag | ||
if has_poem_tag (text) then -- contains poem | if has_poem_tag(text) then -- contains <poem> strip marker (we can't know the content of that) | ||
tag = 'div' | 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 | elseif mw.text.trim(text):find('\n\n+') then -- contains implied <p> tags | ||
text = mw.text.trim (text) | text = mw.text.trim(text) -- trim leading and trailing whitespace characters | ||
tag = 'div' | 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 | elseif text:find('\n[%*:;%#]') then -- if text has list markup | ||
text = text:gsub ('^[\t\r\f ]*', ''):gsub ('%s*$', '') | text = text:gsub('^[\t\r\f ]*', ''):gsub('%s*$', '') -- trim all whitespace except leading newline character '\n' | ||
tag = 'div' | tag = 'div' -- must be <div> because <span> may not contain <ul>, <dd>, <dl>, <ol> tags (added later by MediaWiki) | ||
else | else | ||
text = mw.text.trim (text) | text = mw.text.trim(text) -- plain text | ||
tag = 'span' | tag = 'span' -- so <span> is fine | ||
end | end | ||
return text, tag | return text, tag | ||
end | end | ||
--[[--------------------------< V A L I D A T E _ P R O T O > | --[[ -------------------------- < 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 | 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= | true indicating that some other value has been assigned to |proto=. | ||
]] | ]] | ||
local function validate_proto (proto_param) | local function validate_proto(proto_param) | ||
if 'yes' | if proto_param == 'yes' then | ||
return true | return true | ||
elseif 'no' | elseif proto_param == 'no' then | ||
return false | return false | ||
elseif is_set (proto_param) then | elseif is_set(proto_param) then | ||
return nil, true | return nil, true -- |proto= something other than 'yes' or 'no' | ||
else | else | ||
return nil | return nil -- missing or empty | ||
end | end | ||
end | end | ||
--[[--------------------------< L A N G U A G E _ N A M E _ G E T > | --[[ -------------------------- < 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, cat) | local function language_name_get(ietf, code, cat) | ||
ietf = ietf:lower() | ietf = ietf:lower() -- ietf:lower() because format_ietf_tag() returns mixed case | ||
if override_table[ietf] then -- look for whole IETF tag in override table | if override_table[ietf] then -- look for whole IETF tag in override table | ||
return override_table[ietf][1] | |||
elseif override_table[code] then -- not there so try basic language code | elseif override_table[code] then -- not there so try basic language code | ||
return override_table[code][1] | |||
elseif lang_table[code] then -- shift to | elseif lang_table[code] then -- shift to IANA code/name table | ||
return lang_table[code][1] -- table entries sometimes have multiple names, always take the first one | |||
elseif lang_dep_table[code] then | elseif lang_dep_table[code] then | ||
if cat then | |||
table.insert(maintenance_categories, string.format(tracking_categories["CATEGORY_LANG_DEPRECATED"], code)) | |||
table.insert(maintenance_messages, string.format(error_messages["CODE_DEPRECATED"], code)) | |||
end | |||
return lang_dep_table[code][1] -- table entries sometimes have multiple names, always take the first one | |||
end | |||
end | |||
--[[ -------------------------- < L A N G _ A N D _ L A N G _ X X _ S H A R E D _ S E T U P > -------------------------- | |||
Shared code used by both {{Lang}} and {{Lang-xx}} templates to setup the parameters. | |||
Parameters required are the args passed to the template | |||
and the template name being called, which is used for error messages. | |||
Returns 6 parameters in this order: | |||
-- args | |||
-- script | |||
-- code | |||
-- language_name | |||
-- tag | |||
-- error_msg | |||
If error_msg returned is not nil, it should be returned back | |||
to the invoking function and not passed to make_error_msg() | |||
as it was already handled. | |||
]] | |||
local function lang_and_lang_xx_shared_setup(args, template) | |||
local msg = validate_text(template, args) -- ensure that |text= is set | |||
if is_set(msg) then -- msg is an already-formatted error message | |||
return nil, nil, nil, nil, nil, msg | |||
end | |||
local tag | |||
args.text, tag = html_tag_select(args.text) -- inspects text; returns appropriate HTML tag with text trimmed accordingly | |||
validate_cat_args(args) -- determine if categorization should be suppressed | |||
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 nil, nil, nil, nil, nil, make_error_msg(error_messages["INVALID_PROTO"], args, template) | |||
end | |||
local subtags = {} -- IETF subtags script, region, variant, and private | |||
local code -- the language code | |||
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(args.code, args.script, args.region, args.variant) -- private omitted because private | |||
if msg then | |||
return nil, nil, nil, nil, nil, make_error_msg(msg, args, template) | |||
end | |||
args.italic, msg = validate_italic(args) | |||
if msg then | |||
return nil, nil, nil, nil, nil, make_error_msg(msg, args, template) | |||
end | end | ||
if | if is_set(subtags.script) then -- if script set, override rtl setting | ||
if in_array(subtags.script, lang_data.rtl_scripts) then | |||
args.rtl = true -- script is an rtl script | |||
else | |||
args.rtl = false -- script is not an rtl script | |||
end | |||
end | end | ||
args.code = format_ietf_tag(code, subtags.script, subtags.region, subtags.variant, subtags.private) -- format to recommended subtag styles | |||
local language_name = language_name_get(args.code, code, true) -- get language name; try IETF tag first, then code without variant then code with variant | |||
args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk | |||
return args, subtags.script, code, language_name, tag, nil | |||
end | end | ||
--[[--------------------------< _ L A N G > | --[[ -------------------------- < _ 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> | <includeonly>{{#invoke:lang|lang}}</includeonly> | ||
Parameters are received from the template's frame (parent frame). | |||
]] | ]] | ||
local function _lang (args | local function _lang(args) | ||
local template = args.template or strings["TEMPLATE_LANG"] | |||
local template = args.template or | |||
if args[1] and args.code then | if args[1] and args.code then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "1", "code"), args, template) | ||
else | else | ||
args.code = args[1] or args.code | args.code = args[1] or args.code -- prefer args.code | ||
end | end | ||
if args[2] and args.text then | if args[2] and args.text then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "2", "text"), args, template) | ||
else | else | ||
args.text = args[2] or args.text | args.text = args[2] or args.text -- prefer args.text | ||
end | end | ||
-- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{Lang}}); copied from previous comment. | |||
args.script = nil | |||
args.region = nil | |||
args.variant = nil | |||
code, | local script -- IETF script | ||
local code -- the language code | |||
local language_name | |||
local tag -- HTML tag | |||
local error_msg | |||
args, script, code, language_name, tag, error_msg = lang_and_lang_xx_shared_setup(args, template) | |||
if | if error_msg then | ||
return | return error_msg | ||
end | end | ||
args.italic | if args.italic == nil then -- nil when |italic= absent or not set or |italic=default; args.italic controls | ||
if (script == 'latn') or -- script is latn | |||
(mw.language.getContentLanguage().code ~= code | |||
and not is_set(script) | |||
and not has_poem_tag(args.text) | |||
and unicode.is_Latin(args.text) | |||
if ('latn' | ) 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' | |||
else | else | ||
args. | args.italic = 'inherit' -- italic not set and script not latn; inherit current style | ||
end | end | ||
end | end | ||
args. | if args.italic == 'invert' and tag == 'span' then -- invert only supported for in-line content | ||
args.text = invert_italics(args.text) | |||
args.text = invert_italics (args.text) | |||
end | end | ||
args.text = proto_prefix (args.text, language_name, args.proto) | args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk | ||
table.insert (out, make_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size, language_name)) | local out = {} | ||
table.insert (out, make_category (code, language_name, args.nocat)) | table.insert(out, make_text_html(args.code, args.text, tag, args.rtl, args.italic, args.size, language_name)) | ||
table.insert (out, | table.insert(out, make_category(code, language_name, args.nocat)) | ||
table.insert(out, render_maintenance(args.nocat)) -- maintenance messages and categories | |||
return table.concat (out) | return table.concat(out) -- put it all together and done | ||
end | end | ||
--[[--------------------------< L A N G > | --[[ -------------------------- < 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> | <includeonly>{{#invoke:lang|lang}}</includeonly> | ||
Parameters are received from the template's frame (parent frame). | |||
]] | ]] | ||
local function lang (frame) | local function lang(frame) | ||
local args = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text | local args = getArgs(frame, { -- this code so that we can detect and handle wiki list markup in text | ||
valueFunc = function (key, value) | valueFunc = function(key, value) | ||
if 2 == | if key == 2 or key == 'text' then -- the 'text' parameter; do not trim white space | ||
return value | return value -- return untrimmed 'text' | ||
elseif value then -- all other values: if the value is not nil | elseif value then -- all other values: if the value is not nil | ||
value = mw.text.trim (value) | value = mw.text.trim(value) -- trim whitespace | ||
if '' | if value ~= '' then -- empty string when value was only whitespace | ||
return value | return value | ||
end | end | ||
end | end | ||
return nil | return nil -- value was empty or contained only whitespace | ||
end -- end of valueFunc | end -- end of valueFunc | ||
}) | }) | ||
return _lang (args) | return _lang(args) | ||
end | end | ||
--[[--------------------------< L A N G _ X X > | --[[ -------------------------- < L A N G _ X X > -------------------------- | ||
For the {{ | For the {{L-xx}} templates, the only parameter required to be set in the template is the language code. All | ||
other parameters can, usually should, be written in the template call. | other parameters can, usually should, be written in the template call. For {{Lang-xx}} templates for languages | ||
that can have multiple writing systems, it may be appropriate to set |script= as well. | that can have multiple writing systems, it may be appropriate to set |script= as well. | ||
For each {{ | For each {{Lang-xx}} template choose the appropriate entry-point function so that this function knows the default | ||
styling that should be applied to text. | styling that should be applied to text. | ||
Line 1,017: | Line 1,122: | ||
|variant = IANA variant code | |variant = IANA variant code | ||
|text = (required) the displayed text in language specified by code | |text = (required) the displayed text in language specified by code | ||
|link = boolean false ('no') does not link code- | |link = boolean false ('no') does not link code-specified language name to associated language article | ||
|rtl = boolean true ('yes') identifies the language specified by code as a right-to-left language | |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 | |nocat = boolean true ('yes') inhibits normal categorization; error categories are not affected | ||
|cat = boolian false ('no') opposite form of |nocat= | |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 | |italic = boolean true ('yes') renders displayed text in italic font; boolean false ('no') renders displayed text in normal font; not set renders according to args.initial_style_state | ||
|lit = text that is a literal translation of text | |lit = text that is a literal translation of text | ||
|label = 'none' to suppress all labeling (language name, 'translit.', 'lit.') | |label = 'none' to suppress all labeling (language name, 'translit.', 'lit.') | ||
any other text replaces language-name label - automatic wikilinking disabled | any other text replaces language-name label - automatic wikilinking disabled | ||
for those {{ | for those {{Lang-xx}} templates that support transliteration (those templates where |text= is not entirely latn script): | ||
|translit = text that is a transliteration of text | |translit = text that is a transliteration of text | ||
|translit-std = the standard that applies to the transliteration | |translit-std = the standard that applies to the transliteration | ||
|translit-script = ISO 15924 script name; falls back to code | |translit-script = ISO 15924 script name; falls back to code | ||
For {{ | For {{Lang-xx}}, the positional parameters are: | ||
{{{1}}} text | {{{1}}} text | ||
{{{2}}} transliterated text | {{{2}}} transliterated text | ||
{{{3}}} literal translation text | {{{3}}} literal translation text | ||
No other positional parameters are allowed. | |||
]] | ]] | ||
local function _lang_xx (args | local function _lang_xx(args) | ||
local template = args.template or strings["TEMPLATE_LANG_XX"] | |||
local template = args.template or | |||
if args[1] and args.text then | if args[1] and args.text then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "1", "text"), args, template) | ||
else | else | ||
args.text = args[1] or args.text | args.text = args[1] or args.text -- prefer args.text | ||
end | end | ||
if args[2] and args.translit then | if args[2] and args.translit then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "2", "translit"), args, template) | ||
else | else | ||
args.translit = args[2] or args.translit -- prefer args.translit | args.translit = args[2] or args.translit -- prefer args.translit | ||
end | end | ||
if args[3] and (args.translation or args.lit) then | if args[3] and (args.translation or args.lit) then | ||
return make_error_msg ( | return make_error_msg(error_messages["CONFLICTING_LIT_TRANSLATION"], args, template) | ||
elseif args.translation and args.lit then | elseif args.translation and args.lit then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_NAMED_AND_NAMED"], "lit", "translation"), args, template) | ||
else | else | ||
args.translation = args[3] or args.translation or args.lit | args.translation = args[3] or args.translation or args.lit -- prefer args.translation | ||
end | end | ||
if args.links and args.link then | if args.links and args.link then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["CONFLICTING_NAMED_AND_NAMED"], "links", "link"), args, template) | ||
else | else | ||
args.link = args.link or args.links | args.link = args.link or args.links -- prefer args.link | ||
end | end | ||
local script -- IETF script | |||
local code -- the language code | |||
local language_name | |||
local tag -- HTML tag | |||
local error_msg | |||
args, script, code, language_name, tag, error_msg = lang_and_lang_xx_shared_setup(args, template) | |||
if error_msg then | |||
if | return error_msg | ||
return | |||
end | end | ||
if | if args.italic == nil then -- args.italic controls | ||
if is_set ( | if is_set(script) then | ||
if 'latn' | if script == 'latn' then | ||
args.italic = 'italic' | args.italic = 'italic' -- |script=Latn; set for font-style: italic | ||
else | else | ||
args.italic = initial_style_state | args.italic = args["initial_style_state"] -- italic not set; script is not latn; set for font-style: <initial_style_state> | ||
end | end | ||
else | else | ||
args.italic = initial_style_state | args.italic = args["initial_style_state"] -- here when |italic= and |script= not set; set for font-style: <initial_style_state> | ||
end | end | ||
end | end | ||
args. | if args.italic == 'invert' then | ||
args.text = invert_italics(args.text) | |||
end | end | ||
local category_name = language_name -- category names retain IANA parenthetical disambiguators (if any) | |||
language_name = | language_name = language_name:gsub('%s+%b()', '') -- remove IANA parenthetical disambiguators or qualifiers from names that have them | ||
args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk | |||
local out = {} | |||
local label | |||
if args.label then | if args.label then | ||
if 'none' | if args.label ~= 'none' then | ||
label = args.label -- custom label | |||
end | end | ||
else | else | ||
if 'no' | if args.link == 'no' then | ||
label = language_name -- language name without wikilink | |||
else | else | ||
if language_name:find ('languages') then | if language_name:find('languages') then | ||
label = make_wikilink(language_name) -- collective language name uses simple wikilink | |||
elseif lang_data.article_name[code] then | elseif lang_data.article_name[code] then | ||
label = make_wikilink(lang_data.article_name[code][1], language_name) -- language name with wikilink from override data | |||
else | else | ||
label = make_wikilink(language_name .. ' language', language_name) -- language name with wikilink | |||
end | end | ||
end | end | ||
end | end | ||
table.insert(out, string.format(strings["LABEL_LANGUAGE"], label, 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) | |||
local translit_label | |||
if args.label ~= 'none' then | |||
local translit_script_name -- name associated with IANA (ISO 15924) script code | |||
if script_table[args['translit-script']] then -- when |translit-script= is set, try to use the script's name | if script_table[args['translit-script']] then -- when |translit-script= is set, try to use the script's name | ||
translit_script_name = script_table[args['translit-script'][1] | translit_script_name = script_table[args['translit-script']][1] | ||
else | else | ||
translit_script_name = language_name | translit_script_name = language_name -- fall back on language name | ||
end | end | ||
translit_title = mw.title.makeTitle (0, | |||
if translit_title.exists and ('no' | local translit_title = mw.title.makeTitle(0, string.format(strings["ROMANIZATION_OF"], translit_script_name)) -- make a title object | ||
if translit_title.exists and (args.link ~= 'no') then | |||
translit_label = make_wikilink(string.format(strings["ROMANIZATION_OF"], translit_script_name or language_name), strings["ROMANIZED"]) -- make a wikilink if there is an article to link to | |||
else | else | ||
translit_label = strings["ROMANIZED"] -- else plain text | |||
end | end | ||
end | end | ||
translit = make_translit (args.code, language_name, args.translit, args['translit-std'], args['translit-script']) | local translit = make_translit(args.code, language_name, args.translit, args['translit-std'], args['translit-script']) | ||
if is_set (translit) then | if is_set(translit) then | ||
table.insert (out, translit) | table.insert(out, string.format(strings["LABEL_TRANSLIT"], translit_label, translit)) | ||
else | else | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["INVALID_TRANSLIT_STD_VALUE"], args['translit-std']), args, template) | ||
end | end | ||
end | end | ||
if is_set (args.translation) then -- translation (not supported in {{ | if is_set(args.translation) then -- translation (not supported in {{Lang}}) | ||
local translation_label | |||
if | if args.label ~= 'none' then | ||
if args.link == 'no' then | |||
if 'no' | translation_label = strings["LITERAL_TRANSLATION_ABBR"] | ||
else | else | ||
translation_label = make_wikilink(strings["LITERAL_TRANSLATION_TEXT"], strings["LIT"]) | |||
end | end | ||
end | end | ||
table.insert (out, | table.insert(out, string.format(strings["LABEL_TRANSLATION"], translation_label, args.translation)) | ||
end | end | ||
table.insert (out, make_category (code, category_name, args.nocat)) | table.insert(out, make_category(code, category_name, args.nocat)) | ||
table.insert (out, | table.insert(out, render_maintenance(args.nocat)) -- maintenance messages and categories | ||
return table.concat (out) | return table.concat(out) -- put it all together and done | ||
end | end | ||
--[[--------------------------< L A N G _ X X _ A R G S _ G E T > | --[[ -------------------------- < 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 function lang_xx_args_get(frame) | ||
local args = getArgs(frame, | local args = getArgs(frame, { | ||
parentFirst = true, -- parameters in the template override parameters set in the {{#invoke:}} | |||
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}} | valueFunc = function(key, value) | ||
valueFunc = function (key, value) | if key == 1 then -- the 'text' parameter; do not trim white space | ||
if | return value -- return untrimmed 'text' | ||
return value | |||
elseif value then -- all other values: if the value is not nil | elseif value then -- all other values: if the value is not nil | ||
value = mw.text.trim (value) | value = mw.text.trim(value) -- trim whitespace | ||
if '' | if value ~= '' then -- empty string when value was only whitespace | ||
return value | return value | ||
end | end | ||
end | end | ||
return nil | return nil -- value was empty or contained only whitespace | ||
end -- end of valueFunc | end -- end of valueFunc | ||
}) | }) | ||
return args | return args | ||
end | end | ||
--[[--------------------------< L A N G _ X X _ I T A L I C > | --[[ -------------------------- < L A N G _ X X _ I T A L I C > -------------------------- | ||
Entry point for those {{ | Entry point for those {{Lang-xx}} templates that call lang_xx_italic(). | ||
Sets the initial style state to italic. | |||
]] | ]] | ||
local function lang_xx_italic (frame) | local function lang_xx_italic(frame) | ||
local args = lang_xx_args_get (frame) | local args = lang_xx_args_get(frame) | ||
initial_style_state = 'italic' | args["initial_style_state"] = 'italic' | ||
return _lang_xx (args) | return _lang_xx(args) | ||
end | end | ||
--[[--------------------------< _ L A N G _ X X _ I T A L I C > | --[[ -------------------------- < _ L A N G _ X X _ I T A L I C > -------------------------- | ||
Entry point ffrom another module. | Entry point ffrom another module. | ||
Sets the initial style state to italic. | |||
]] | ]] | ||
local function _lang_xx_italic (args) | local function _lang_xx_italic(args) | ||
initial_style_state = 'italic' | args["initial_style_state"] = 'italic' | ||
return _lang_xx (args) | return _lang_xx(args) | ||
end | end | ||
--[[--------------------------< L A N G _ X X _ I N H E R I T > | --[[ -------------------------- < L A N G _ X X _ I N H E R I T > -------------------------- | ||
Entry point for those {{ | Entry point for those {{Lang-xx}} templates that call lang_xx_inherit(). | ||
Sets the initial style state to inherit. | |||
]] | ]] | ||
local function lang_xx_inherit (frame) | local function lang_xx_inherit(frame) | ||
local args = lang_xx_args_get (frame) | local args = lang_xx_args_get(frame) | ||
initial_style_state = 'inherit' | args["initial_style_state"] = 'inherit' | ||
return _lang_xx (args) | return _lang_xx(args) | ||
end | end | ||
--[[--------------------------< _ L A N G _ X X _ I N H E R I T > | --[[ -------------------------- < _ L A N G _ X X _ I N H E R I T > -------------------------- | ||
Entry point from another module. | Entry point from another module. | ||
Sets the initial style state to inherit. | |||
]] | ]] | ||
local function _lang_xx_inherit (args) | local function _lang_xx_inherit(args) | ||
initial_style_state = 'inherit' | args["initial_style_state"] = 'inherit' | ||
return _lang_xx (args) | return _lang_xx(args) | ||
end | end | ||
--[[--------------------------< _ I S _ I E T F _ T A G > | --[[ -------------------------- < _ I S _ I E T F _ T A G > -------------------------- | ||
Returns true when a language name associated with IETF language tag exists; nil else. | 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 {{ | All code combinations supported by {{Lang}} and the {{Lang-xx}} templates are supported by this function. | ||
Module entry point from another module | Module entry point from another module. | ||
]] | ]] | ||
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 | local c, s, r, v, p, err -- code, script, region, variant, private, error message | ||
c, s, r, v, p, err = get_ietf_parts (tag) | 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 ((c and not err) and true) or nil -- return true when code portion has a value without error message; nil else | ||
end | end | ||
--[[--------------------------< I S _ I E T F _ T A G > | --[[ -------------------------- < I S _ I E T F _ T A G > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function is_ietf_tag (frame) | local function is_ietf_tag(frame) | ||
return _is_ietf_tag (getArgs(frame)[1]) | return _is_ietf_tag(getArgs(frame)[1]) -- args[1] is the IETF language tag to be tested; getArgs() so we also get parent frame | ||
end | end | ||
--[[--------------------------< _ N A M E _ F R O M _ T A G > | --[[ -------------------------- < _ N A M E _ F R O M _ T A G > -------------------------- | ||
Returns language name associated with IETF language tag if valid; error message else. | Returns language name associated with IETF language tag if valid; error message else. | ||
All code combinations supported by {{ | 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. | Set invoke's |link= parameter to yes to get wikilinked version of the language name. | ||
Module entry point from another module | Module entry point from another module. | ||
]] | ]] | ||
local function _name_from_tag (args) | local function _name_from_tag(args) | ||
local raw_code = args[1] -- save a copy of the input IETF subtag | |||
local raw_code = args[1] | |||
local | local subtags = {} -- IETF subtags script, region, variant, and private | ||
local code -- the language code | |||
local code | local msg -- gets an error message if IETF language tag is malformed or invalid | ||
local msg | code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(raw_code) | ||
validate_cat_args(args) | |||
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code) | |||
if msg then | if msg then | ||
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization | |||
return | args.nocat = nil | ||
end | |||
return make_error_msg(msg, args, args['template']) | |||
end | end | ||
raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private) | 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) | local language_name = language_name_get(raw_code, code) -- get language name; try IETF tag first, then code without variant then code with variant | ||
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()', '') | |||
local link = 'yes' == args['link'] -- make a boolean | |||
local label = args.label | |||
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, label) | 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], label or language_name) | 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', label or language_name) | 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 | ||
--[[--------------------------< N A M E _ F R O M _ T A G > | --[[ -------------------------- < N A M E _ F R O M _ T A G > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function name_from_tag (frame) | local function name_from_tag(frame) -- entry point from an {{#invoke:Lang|name_from_tag|<IETF tag>|link=<yes>|template=<template name>}} | ||
local args = getArgs(frame) -- getArgs() so we also get parent frame | |||
args["from_invoke"] = true | |||
return _name_from_tag(args) -- pass-on the args table | |||
end | end | ||
--[[--------------------------< _ T A G _ F R O M _ N A M E > | --[[ -------------------------- < _ T A G _ F R O M _ N A M E > -------------------------- | ||
Returns the | Returns the IETF language tag associated with the language name. | ||
according to the spelling in the source tables. | 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). | that disambiguator must be omitted (they are not present in the data name-to-tag tables). | ||
Module entry point from another module | Module entry point from another module. | ||
]] | ]] | ||
local function _tag_from_name (args) | local function _tag_from_name(args) | ||
local msg | local msg | ||
if args[1] and | if args[1] and args[1] ~= '' then | ||
local data = mw.loadData ('Module:Lang/tag from name') | local data = mw.loadData('Module:Lang/tag from name') -- get the reversed data tables | ||
local lang = args[1]:lower() | local lang = args[1]:lower() -- allow any-case for the language name (spelling must till be correct) | ||
local tag = data.rev_override_table[lang] or data.rev_lang_table[lang] or data.rev_lang_dep_table[lang] | 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 | if tag then | ||
return tag, true | return tag, true -- language name found so return tag and done; second return used by is_lang_name() | ||
else | else | ||
msg = | msg = string.format(error_messages["LANGUAGE_NOT_FOUND"], args[1]) -- language name not found, error message | ||
end | end | ||
else | else | ||
msg = | msg = error_messages["LANGUAGE_NOT_PROVIDED"] -- language name not provided, error message | ||
end | end | ||
validate_cat_args(args) | |||
if args. | if msg then | ||
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization | |||
args.nocat = nil | |||
end | |||
return make_error_msg(msg, args, args['template']) | |||
end | end | ||
end | end | ||
--[[--------------------------< T A G _ F R O M _ N A M E > | --[[ -------------------------- < T A G _ F R O M _ N A M E > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function tag_from_name (frame) | local function tag_from_name(frame) -- entry point from an {{#invoke:Lang|tag_from_name|<language name>|link=<yes>|template=<template name>}} | ||
local | local args = getArgs(frame) -- getArgs() so we also get parent frame | ||
return result | args["from_invoke"] = true | ||
local result, _ = _tag_from_name(args) -- pass-on the args table and suppress second return used by is_lang_name() | |||
return result | |||
end | end | ||
--[[--------------------------< I S _ L A N G _ N A M E > | --[[ -------------------------- < I S _ L A N G _ N A M E > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function is_lang_name (frame) | local function is_lang_name(frame) | ||
local _, result = _tag_from_name (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; | local _, result = _tag_from_name(getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; suppress second return used by tag_from_name() | ||
return result and true or nil | return result and true or nil | ||
end | end | ||
--[[--------------------------< _ T R A N S L > | --[[ -------------------------- < _ T R A N S L > -------------------------- | ||
Module entry point from another module | Module entry point from another module. | ||
]] | ]] | ||
local function _transl (args) | local function _transl(args) | ||
local title_table = lang_data.translit_title_table | local template = strings["TEMPLATE_TRANSL"] | ||
local title_table = lang_data.translit_title_table -- table of transliteration standards and the language codes and scripts that apply to those standards | |||
if is_set (args[3]) then | if is_set(args[3]) then -- [3] set when {{Transl|code|standard|text}} | ||
args.text = args[3] | args.text = args[3] -- get the transliterated text | ||
args.translit_std = args[2] and args[2]:lower() | args.translit_std = args[2] and args[2]:lower() -- get the standard; lower case for table indexing | ||
if not title_table[args.translit_std] then | if not title_table[args.translit_std] then | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["UNRECOGNIZED_TRANSLITERATION_STANDARD"], args.translit_std), args, template) | ||
end | end | ||
else | else | ||
if is_set (args[2]) then | if is_set(args[2]) then -- [2] set when {{Transl|code|text}} | ||
args.text = args[2] | args.text = args[2] -- get the transliterated text | ||
else | else | ||
if args[1] and args[1]:match ('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text? | if args[1] and args[1]:match('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text? | ||
return make_error_msg ( | return make_error_msg(error_messages["NO_TEXT"], args, template)-- args[1] is a code so we're missing text | ||
else | else | ||
args.text = args[1] | 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 ( | return make_error_msg(string.format(error_messages["MISSING_LANGUAGE_OR_SCRIPT_CODE"]), args, template) | ||
end | end | ||
end | end | ||
end | end | ||
if is_set (args[1]) then | if is_set(args[1]) then -- IANA language code used for HTML lang= attribute; or ISO 15924 script code | ||
if args[1]:match ('^%a%a%a?%a?$') then -- args[1] has correct form? | if args[1]:match('^%a%a%a?%a?$') then -- args[1] has correct form? | ||
args.code = args[1]:lower() | 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 | else | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"], args[1]), args, template) -- invalid language / script code | ||
end | end | ||
else | else | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["MISSING_LANGUAGE_OR_SCRIPT_CODE"]), args, template) -- missing language / script code so quit | ||
end | end | ||
args.italic, msg = validate_italic (args) | local msg | ||
args.italic, msg = validate_italic(args) | |||
if msg then | if msg then | ||
return make_error_msg (msg, args, | return make_error_msg(msg, args, template) | ||
end | end | ||
if | if args.italic == 'italic' then -- 'italic' when |italic=yes; because that is same as absent or not set and |italic=default | ||
args.italic = nil | args.italic = nil -- set to nil; | ||
end | end | ||
local language_name -- language name that matches language code; used for tool tip | |||
local script -- IANA script | |||
if override_table[args.code] then -- is code a language code defined in the override table? | if override_table[args.code] then -- is code a language code defined in the override table? | ||
language_name = override_table[args.code][1] | language_name = override_table[args.code][1] | ||
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables? | elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables? | ||
language_name = lang_table[args.code][1] | language_name = lang_table[args.code][1] | ||
elseif lang_dep_table[args.code] then -- is code a language code defined in the deprecated language code tables? | elseif lang_dep_table[args.code] then -- is code a language code defined in the deprecated language code tables? | ||
language_name = lang_dep_table[args.code][1] | language_name = lang_dep_table[args.code][1] | ||
elseif script_table[args.code] then -- if here, code is not a language code; is it a script code? | 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] | language_name = script_table[args.code][1] | ||
script = args.code | script = args.code -- code was an ISO 15924 script so use that instead | ||
args.code = '' | args.code = '' -- unset because not a language code | ||
else | else | ||
return make_error_msg ( | return make_error_msg(string.format(error_messages["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"], args.code), args, template) -- invalid language / script code | ||
end | end | ||
-- here only when all parameters passed to make_translit() are valid | -- here only when all parameters passed to make_translit() are valid | ||
return make_translit (args.code, language_name, args.text, args.translit_std, script, args.italic) | return make_translit(args.code, language_name, args.text, args.translit_std, script, args.italic) | ||
end | end | ||
--[[--------------------------< T R A N S L > | --[[ -------------------------- < T R A N S L > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function transl (frame) | local function transl(frame) | ||
return _transl (getArgs(frame)) | return _transl(getArgs(frame)) | ||
end | end | ||
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G > | --[[ -------------------------- < 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 | Returns category name associated with IETF language tag if valid; error message else. | ||
All code combinations supported by {{ | All code combinations supported by {{Lang}} and the {{Lang-xx}} templates are supported by this function. | ||
Module entry point from another module | Module entry point from another module. | ||
]] | ]] | ||
local function _category_from_tag (args) | local function _category_from_tag(args) | ||
local raw_code = args[1] -- save a copy of the input IETF subtag | |||
local raw_code = args[1] | |||
local | local subtags = {} -- IETF subtags script, region, variant, and private | ||
local code -- the language code | |||
local code | local msg -- gets an error message if IETF language tag is malformed or invalid | ||
local msg | code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(raw_code) | ||
validate_cat_args(args) | |||
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code) | |||
if msg then | if msg then | ||
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization | |||
return | args.nocat = nil | ||
end | |||
return make_error_msg(msg, args, args['template']) | |||
end | end | ||
raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private) | 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) | local category_name = language_name_get(raw_code, code) -- get language name; try IETF tag first, then code without variant then code with variant | ||
category_name = make_category (code, category_name, nil, true):gsub ('[%[%]]', '') | category_name = make_category(code, category_name, nil, true):gsub('[%[%]]', '') | ||
return category_name | if args.link then | ||
return string.format("[[:%s]]", category_name) | |||
else | |||
return category_name | |||
end | |||
end | end | ||
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G > | --[[ -------------------------- < C A T E G O R Y _ F R O M _ T A G > -------------------------- | ||
Module entry point from an {{#invoke:}} | Module entry point from an {{#invoke:}}. | ||
]] | ]] | ||
local function category_from_tag (frame) | local function category_from_tag(frame) -- entry point from an {{#invoke:Lang|category_from_tag|<IETF tag>|template=<template name>}} | ||
local args = getArgs(frame) -- getArgs() so we also get parent frame | |||
args["from_invoke"] = true | |||
return _category_from_tag(args) -- pass-on the args table, nothing else | |||
end | end | ||
--[[--------------------------< E X P O R T E D | --[[ -------------------------- < E X P O R T E D _ F U N C T I O N S > -------------------------- | ||
]] | ]] | ||
return { | return { | ||
category_from_tag = category_from_tag, | category_from_tag = category_from_tag, | ||
lang = lang, -- entry point for {{ | lang = lang, -- entry point for {{Lang}} | ||
lang_xx_inherit = lang_xx_inherit, -- entry points for {{ | lang_xx_inherit = lang_xx_inherit, -- entry points for {{Lang-??}} | ||
lang_xx_italic = lang_xx_italic, | lang_xx_italic = lang_xx_italic, | ||
is_ietf_tag = is_ietf_tag, | is_ietf_tag = is_ietf_tag, | ||
is_lang_name = is_lang_name, | is_lang_name = is_lang_name, | ||
tag_from_name = tag_from_name, -- returns | 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 | 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, -- entry point for {{Transl}} | ||
_category_from_tag = _category_from_tag, -- 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 | ||
Line 1,580: | Line 1,668: | ||
_name_from_tag = _name_from_tag, | _name_from_tag = _name_from_tag, | ||
_transl = _transl, | _transl = _transl, | ||
} |
Revision as of 19:41, 9 November 2020
Documentation for this module may be created at Module:Lang/doc
--[=[
Lua support for the {{Lang}}, {{Lang-xx}}, and {{Transl}} templates and
support for other templates and modules.
]=]
require('Module:No globals')
local getArgs = require('Module:Arguments').getArgs
local unicode = require("Module:Unicode data") -- for is_latin() and is_rtl()
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 override_table = lang_data.override
local namespace = mw.title.getCurrentTitle().namespace -- used for categorization
local maintenance_categories = {} -- maintenance categories go here
local maintenance_messages = {} -- and their messages go here
local tracking_categories = {
["CATEGORY_LANG_DEPRECATED"] = "Category:Lang and lang-xx using deprecated ISO 639 codes|%s",
["CATEGORY_LANG_PROMOTED"] = "Category:Lang and lang-xx code promoted to ISO 639-1|%s",
["ERROR_CATEGORY"] = "[[Category:%s template errors]]",
}
local language_categories = {
["ENGLISH_TEXT"] = "[[Category:Articles containing explicitly cited %s-language text]]",
["LANGUAGE_TEXT"] = "[[Category:Articles containing %s-language text]]",
["LANGUAGES_COLLECTIVE_TEXT"] = "[[Category:Articles with text in %s]]",
}
local error_messages = {
["CODE_DEPRECATED"] = "code: %s is deprecated",
["CODE_PROMOTED"] = "code: %s promoted to code: %s",
["CONFLICTING_LIT_TRANSLATION"] = "conflicting: {{{3}}} and |lit= or |translation=",
["CONFLICTING_NAMED_AND_NAMED"] = "conflicting: |%s= and |%s=",
["CONFLICTING_POSITIONAL_AND_NAMED"] = "conflicting: {{{%s}}} and |%s=",
["INVALID_PROTO"] = "invalid |proto=",
["INVALID_TRANSLIT_STD_VALUE"] = "invalid |translit-std=: %s",
["MISSING_LANGUAGE_OR_SCRIPT_CODE"] = "missing language / script code",
["MISSING_LANGUAGE_TAG"] = "missing language tag",
["LANGUAGE_NOT_FOUND"] = "language: %s not found",
["LANGUAGE_NOT_PROVIDED"] = "missing language name",
["NO_TEXT"] = "no text",
["ONLY_ONE_TYPE_ITALICS"] = "only one of |italic=, |italics=, or |i= can be specified",
["REDUNDANT_REGION_TAG"] = "redundant region tag",
["REDUNDANT_SCRIPT_TAG"] = "redundant script tag",
["REDUNDANT_VARIANT_TAG"] = "redundant variant tag",
["SCRIPT_NOT_SUPPOTED_FOR_CODE"] = "script: %s not supported for code: %s",
["TEXT_HAS_MALFORMED_MARKUP"] = "text has malformed markup",
["TEXT_HAS_ITALIC_MARKUP"] = "text has italic markup",
["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"] = "unrecognized language / script code: %s",
["UNRECOGNIZED_TRANSLITERATION_STANDARD"] = "unrecognized transliteration standard: %s",
["UNRECOGNIZED_LANGUAGE_CODE"] = "unrecognized language code: %s",
["UNRECOGNIZED_LANGUAGE_TAG"] = "unrecognized language tag: %s",
["UNRECOGNIZED_PRIVATE_TAG"] = "unrecognized private tag: %s",
["UNRECOGNIZED_VARIANT"] = "unrecognized variant: %s",
["UNRECOGNIZED_SCRIPT_FOR_CODE"] = "unrecognized script: %s for code: %s",
["UNRECOGNIZED_REGION_FOR_CODE"] = "unrecognized region: %s for code: %s",
["UNRECOGNIZED_VARIANT_FOR_CODE"] = "unrecognized variant: %s for code: %s",
["UNRECOGNIZED_VARIANT_FOR_CODE_SCRIPT_PAIR"] = "unrecognized variant: %s for code-script pair: %s-%s",
["UNRECOGNIZED_VARIANT_FOR_CODE_REGION_PAIR"] = "unrecognized variant: %s for code-region pair: %s-%s",
}
local strings = {
-- Template names --
["TEMPLATE_LANG_LANG_XX"] = "Lang and lang-xx",
["TEMPLATE_LANG"] = "Lang",
["TEMPLATE_LANG_XX"] = "Lang-xx",
["TEMPLATE_TRANSL"] = "Transl",
-- Error --
["ERROR_SPAN"] = '[%s] <span style="font-size: 100%%; font-style: normal;" class="error">Error: {{%s}}: %s ([[:Category:%s template errors|help]])</span>',
["UNDEFINED"] = "undefined",
-- Maintenance --
["MAINTENANCE_SPAN"] = '<span class="lang-comment" style="font-style: normal; display: none; color: #33aa33; margin-left: 0.3em;">%s</span>',
-- Lang_xx --
["LABEL_LANGUAGE"] = "%s: %s",
["LABEL_TRANSLATION"] = ', <small>%s </small>'%s'', -- use HTML entities to avoid wiki markup confusion
["LABEL_TRANSLIT"] = ", <small>%s: </small>%s",
["LIT"] = "lit.",
["LITERAL_TRANSLATION_ABBR"] = '<abbr title="literal translation">lit.</abbr>',
["LITERAL_TRANSLATION_TEXT"] = "Literal translation",
["ROMANIZATION_OF"] = "Romanization of %s",
["ROMANIZED"] = "romanized",
-- HTML lang --
["HTML_LANG_TAG"] = '%s<%s lang="%s" %s style="%s %s" %s>%s</%s>%s',
["ASTERISK"] = "*", -- use numeric entity because plain asterisk confuses MediaWiki
["DIR_ATTRIBUTE"] = 'dir="rtl"',
["FONT_STYLE"] = "font-style: normal;",
["FONT_SIZE"] = "font-size: %s;",
["LTR_MARK"] = "‎",
["TITLE_ATTRIBUTE_COLLECTIVE"] = 'title="%s collective text"',
["TITLE_ATTRIBUTE_LANGUAGE"] = 'title="%s language text"',
-- Transliteration --
["TRANSLIT_ITALIC"] = '<i lang="%s-Latn" title="%s">%s</i>',
["TRANSLIT_SPAN_CODE"] = '<span style="font-style: %s" lang="%s-Latn" title="%s">%s</span>',
["TRANSLIT_SPAN_NO_CODE"] = '<span title="%s">%s</span>',
["TRANSLITERATION_STD_SCRIPT"] = "%s (%s script) transliteration",
["TRANSLITERATION_STD_LANGUAGE"] = "%s (%s language) transliteration",
["TRANSLITERATION_SCRIPT"] = "%s-script transliteration",
["TRANSLITERATION_LANGUAGES"] = "%s transliteration",
["TRANSLITERATION_LANGUAGE"] = "%s-language transliteration",
["ROMANIZATION_LANGUAGES"] = "%s romanization",
["ROMANIZATION_LANGUAGE"] = "%s-language romanization",
}
--[[ -------------------------- < 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.
]]
local function is_set(var)
return not (var == nil or var == '')
end
--[[ -------------------------- < I N V E R T _ I T A L I C S > --------------------------
This function attempts to invert the italic markup in args.text
by adding or removing leading and trailing italic markup in args.text.
Like |italic=unset, |italic=invert disables automatic italic markup.
Individual leading and 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, replacement of wiki markup is handled by a string.gsub()
replacement table operating only on these separate elements.
In the string.gsub() matching pattern, '.*' matches empty string as well as
the three expected wiki markup patterns.
This function expects that markup in args.text is complete and correct;
if it is not, oddness may result.
]]
local function invert_italics(source)
source = source:gsub("%f[\']\'%f[^\']", ''') -- protect single quote marks from being interpreted as bold markup
local seg = {}
seg[1] = source:match('^(\'\'+%f[^\']).+') or '' -- get leading markup, if any; ignore single quote
seg[3] = source:match('.+(%f[\']\'\'+)$') or '' -- get trailing markup, if any; ignore single quote
if seg[1] ~= '' and seg[3] ~= '' then -- extract the 'text'
seg[2] = source:match('^\'\'+%f[^\'](.+)%f[\']\'\'+$') -- from between leading and trailing markup
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
local invert_pattern_table = { -- leading/trailing markup add/remove/replace patterns
[""] = "\'\'", -- empty string becomes italic markup
["\'\'"] = "", -- italic markup becomes empty string
["\'\'\'"] = "\'\'\'\'\'", -- bold becomes bold italic
["\'\'\'\'\'"] = "\'\'\'", -- bold italic become bold
}
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
return table.concat(seg) -- put it all back together and done
end
--[[ -------------------------- < V A L I D A T E _ I T A L I C > --------------------------
Validates |italic= or |italics= assigned values.
When |italic= is set and has an acceptable assigned value,
return the matching css font-style property value or,
for the special case 'default', return nil.
When |italic= is not set, or has an unacceptible assigned value,
return nil and a nil error message.
When both |italic= and |italics= are set, returns nil
and a 'conflicting' error message.
The return value nil causes the calling lang, lang_xx, or transl function to set
args.italic according to the template's defined default
('inherit' for {{Lang}}, 'inherit' or 'italic' for {{Lang-xx}} depending on
the individual template's requirements, 'italic' for {{Transl}})
or to the value appropriate to |script=, if set ({{Lang}} and {{Lang-xx}} only).
Accepted values and the values that this function returns are are:
nil - when |italic= absent or not set; returns nil
default - for completeness, should rarely if ever be used; returns nil
yes - force args.text to be rendered in italic font; returns 'italic'
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(args)
local count = 0
for _, arg in pairs{'italic', 'italics', 'i'} do
if args[arg] then
count = count + 1
end
end
if count > 1 then -- return nil and an error message if more than one is set
return nil, error_messages["ONLY_ONE_TYPE_ITALICS"]
end
local properties = {
['yes'] = 'italic',
['no'] = 'normal',
['unset'] = 'inherit',
['invert'] = 'invert',
['default'] = nil,
}
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
local yesno = require('Module:Yesno')
if yesno(args.cat) == false or yesno(args.nocat) == true 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
--[[ -------------------------- < I N _ A R R A Y > --------------------------
Whether needle is in haystack
]]
local function in_array(needle, haystack)
if needle == nil then
return false
end
for n, v in ipairs(haystack) do
if v == needle then
return n
end
end
return false
end
--[[ -------------------------- < F O R M A T _ I E T F _ T A G > --------------------------
Prettify IETF tags to use recommended subtag formats:
code: lower case
script: sentence case
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 string.format("%s-x-%s", code:lower(), private:lower()) -- if private, all other tags ignored
end
table.insert(out, code:lower())
if is_set(script) then
script = script:lower():gsub('^%a', string.upper)
table.insert(out, script)
end
if is_set(region) then
table.insert(out, region:upper())
end
if is_set(variant) then
table.insert(out, variant:lower())
end
return table.concat(out, '-')
end
--[[ -------------------------- < G E T _ I E T F _ P A R T S > --------------------------
Extracts and returns IETF language tag parts:
primary language subtag (required) - 2 or 3 character IANA language code
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
Supported forms:
lang lang-variant
lang-script lang-script-variant
lang-region lang-region-variant
lang-script-region lang-script-region-variant
lang-x-private
Each of lang, script, region, variant, and private, when used, must be valid.
Languages with both two- and three-character code synonyms are promoted to the two-character synonym because
the IANA registry file omits the synonymous three-character code; we cannot depend on browsers understanding
the synonymous three-character codes in the lang= attribute.
For {{Lang-xx}} templates, the parameters |script=, |region=, and |variant= are supported (not supported in {{Lang}}
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.
See http://www.rfc-editor.org/rfc/bcp/bcp47.txt section 2.1
]]
local function get_ietf_parts(source, args_script, args_region, args_variant)
if not is_set(source) then
return nil, nil, nil, nil, nil, error_messages["MISSING_LANGUAGE_TAG"]
end
local pattern = { -- table of tables holding acceptable IETF tag patterns and short names of the IETF part captured by the pattern
{'^(%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)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 2 - ll-Ssss-DDD-variant (where region is 3 digits and variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 3 - ll-Ssss-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 4 - ll-Ssss-DDD-variant (where region is 3 digits and variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$', 's', 'v'}, -- 5 - ll-Ssss-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'v'}, -- 6 - ll-Ssss-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$', 'r', 'v'}, -- 7 - ll-RR-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$', 'r', 'v'}, -- 8 - ll-DDD-variant (where region is 3 digits and variant is 4 digits)
{'^(%a%a%a?)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', '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?)$', 'r', 'v'}, -- 10 - ll-DDD-variant (where region is 3 digits and variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d%d)$', '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
local code, script, region, variant, private -- IETF tag parts
for i, v in ipairs(pattern) do -- spin through the pattern table looking for a match
local c1, c2, c3, c4 -- captures in the 'pattern' from the pattern table go here
c1, c2, c3, c4 = source:match(pattern[i][1]) -- one or more captures set if source matches pattern[i])
if c1 then -- c1 always set on match
code = c1 -- first capture is always code
t = {
[pattern[i][2] or 'x'] = c2, -- fill the table of captures with the rest of the captures
[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
return nil, nil, nil, nil, nil, string.format(error_messages["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
local synonym_table = mw.loadData('Module:Lang/ISO 639 synonyms') -- ISO 639-2/639-2T code translation to 639-1 code
if not (override_table[code] or lang_table[code] or synonym_table[code] or lang_dep_table[code]) then
return nil, nil, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_LANGUAGE_CODE"], code) -- invalid language code, don't know about the others (don't care?)
end
if synonym_table[code] then -- if 639-2/639-2T code has a 639-1 synonym
table.insert(maintenance_categories, string.format(tracking_categories["CATEGORY_LANG_PROMOTED"], code))
table.insert(maintenance_messages, string.format(error_messages["CODE_PROMOTED"], code, synonym_table[code]))
code = synonym_table[code] -- use the synonym
end
if is_set(script) then
if is_set(args_script) then
return code, nil, nil, nil, nil, error_messages["REDUNDANT_SCRIPT_TAG"] -- both code with script and |script= not allowed
end
else
script = args_script or '' -- use args.script if provided
end
if is_set(script) then
script = script:lower() -- ensure that we use and return lower case version of this
if not script_table[script] then
return code, nil, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_SCRIPT_FOR_CODE"], script, code) -- language code ok, invalid script, don't know about the others (don't care?)
end
end
local suppressed_table = lang_data.lang_name_table.suppressed
if suppressed_table[script] then -- ensure that code-script does not use a suppressed script
if in_array(code, suppressed_table[script]) then
return code, nil, nil, nil, nil, string.format(error_messages["SCRIPT_NOT_SUPPOTED_FOR_CODE"], script, code) -- language code ok, script is suppressed for this code
end
end
if is_set(region) then
if is_set(args_region) then
return code, script, nil, nil, nil, error_messages["REDUNDANT_REGION_TAG"] -- both code with region and |region= not allowed
end
else
region = args_region or '' -- use args.region if provided
end
if is_set(region) then
region = region:lower() -- ensure that we use and return lower case version of this
local region_table = lang_data.lang_name_table.region
if not region_table[region] then
return code, script, nil, nil, nil, string.format(error_messages["UNRECOGNIZED_REGION_FOR_CODE"], region, code)
end
end
if is_set(variant) then
if is_set(args_variant) then
return code, script, region, nil, nil, error_messages["REDUNDANT_VARIANT_TAG"] -- both code with variant and |variant= not allowed
end
else
variant = args_variant or '' -- use args.variant if provided
end
if is_set(variant) then
variant = variant:lower() -- ensure that we use and return lower case version of this
local variant_table = lang_data.lang_name_table.variant
if not variant_table[variant] then -- make sure variant is valid
return code, script, region, nil, nil, string.format(error_messages["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(string.format("%s-%s", code, script), variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE_SCRIPT_PAIR"], variant, 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(string.format("%s-%s", code, region), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE_REGION_PAIR"], variant, code, region)
end
end
else
if not in_array(code, variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, string.format(error_messages["UNRECOGNIZED_VARIANT_FOR_CODE"], variant, code)
end
end
end
if is_set(private) then
private = private:lower() -- ensure that we use and return lower case version of this
if not override_table[string.format("%s-x-%s", code, private)] then -- make sure private tag is valid; note that index
return code, script, region, variant, nil, string.format(error_messages["UNRECOGNIZED_PRIVATE_TAG"], private)
end
end
return code, script, region, variant, private, nil -- return the good bits; make sure that msg is nil
end
--[[ -------------------------- < M A K E _ E R R O R _ M S G > --------------------------
Assembles an error message from template name, message text,
help link, and error category.
]]
local function make_error_msg(msg, args, template)
local out = {}
local category
if template == strings["TEMPLATE_TRANSL"] then
category = strings["TEMPLATE_TRANSL"]
else
category = strings["TEMPLATE_LANG_LANG_XX"]
end
if template then
table.insert(out, string.format(strings["ERROR_SPAN"], args.text or strings["UNDEFINED"], template, msg, category))
else
local error_text = string.format(strings["ERROR_SPAN"], "", "", msg, category)
error_text = error_text:gsub("%[] ", ""):gsub("{{}}: ", "")
table.insert(out, error_text)
end
if (namespace == 0) and not args.nocat then -- only categorize in article space
table.insert(out, string.format(tracking_categories["ERROR_CATEGORY"], category))
end
return table.concat(out)
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 string.format("[[%s|%s]]", link, display)
else
return string.format("[[%s]]", link)
end
else
return ''
end
end
--[[ -------------------------- < D I V _ M A R K U P _ A D D > --------------------------
Adds <i> and </i> tags to list-item text or to implied <p>..</p> text.
Mixed not supported.
]]
local function div_markup_add(text, style)
local implied_p = {}
if text:find('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
if style == 'italic' then
return mw.ustring.gsub(text, '(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>') -- insert <i> tags 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 style == 'italic' then
text = text:gsub('[^\n]+', '<p><i>%1</i></p>') -- insert <p> and <i> tags at each implied <p> (two or more consecutive '\n\n' sequences)
else
text = text:gsub('[^\n]+', '<p>%1</p>') -- insert <p> markup at each implied <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 <div> tags for block content.
]]
local function make_text_html(code, text, tag, rtl, style, size, language)
local asterisk = ""
if text:match('^%*') then
asterisk = strings["ASTERISK"] -- move proto language text prefix outside of italic markup if any
text = text:gsub('^%*', '') -- remove the asterisk from the text
end
if tag == 'span' then -- default HTML tag for inline content
if style == 'italic' then -- but if italic
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
local ltr = ""
local dir_attribute = ""
if rtl or unicode.is_rtl(text) then
dir_attribute = strings["DIR_ATTRIBUTE"] -- add direction attribute for right to left languages
ltr = strings["LTR_MARK"] -- legacy; shouldn't be necessary because all of the rtl text is wrapped inside an HTML tag with dir="rtl" attribute
-- make sure the browser knows that we're at the end of the rtl
end
local font_style = ""
if style == 'normal' then -- when |italic=no
font_style = strings["FONT_STYLE"] -- override external markup, if any
end
local font_size = ""
if is_set(size) then -- when |size=<something>
font_size = string.format(strings["FONT_SIZE"], size)
end
local title_attribute = ""
if is_set(language) then
if language:find('languages') then
title_attribute = string.format(strings["TITLE_ATTRIBUTE_COLLECTIVE"], language) -- for collective languages
else
title_attribute = string.format(strings["TITLE_ATTRIBUTE_LANGUAGE"], language) -- for individual languages
end
end
local html = string.format(strings["HTML_LANG_TAG"], asterisk, tag, code, dir_attribute, font_style, font_size, title_attribute, text, tag, ltr)
-- Prettify output
html = html:gsub('style=" "', ""):gsub("%s+", " "):gsub(" >", ">"):gsub(' "', '"') -- remove empty style="" attribute; extra spaces for a cleaner tag; space before closing tag or double quote
return html
end
--[=[ -------------------------- < M A K E _ C A T E G O R Y > --------------------------
For individual language, <language>, returns:
[[Category:Articles containing <language>-language text]]
for English:
[[Category:Articles containing explicitly cited English-language text]]
for ISO 639-2 collective languages (and for 639-1 bh):
[[Category:Articles with text in <language> languages]]
]=]
local function make_category(code, language_name, nocat, name_get)
if ((namespace ~= 0) 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 string.format(language_categories["LANGUAGES_COLLECTIVE_TEXT"], language_name)
end
if code == 'en' then
return string.format(language_categories["ENGLISH_TEXT"], language_name) -- falls back to English if regional name not available
else
return string.format(language_categories["LANGUAGE_TEXT"], language_name)
end
end
--[[ -------------------------- < M A K E _ T R A N S L I T > --------------------------
Return translit <i lang=xx-Latn>...</i> where xx is the language code;
else return empty string.
The value |script= is not used in {{Transl}} for this purpose; instead it uses |code.
Because language scripts are listed in the {{Transl}} switches they are included in the data tables.
The script parameter is introduced at {{Language with name and transliteration}}.
If |script= is set, this function uses it in preference to code.
To avoid confusion, in this module and the templates that use it, the transliteration script parameter is renamed
to be |translit-script= (in this function, tscript).
This function is used by both lang_xx() and transl()
lang_xx() always provides code, language_name, and translit; may provide tscript; never provides style
transl() always provides language_name, translit, and one of code or tscript, never both; always provides style
For {{transl}}, style only applies when a language code is provided.
]]
local function make_translit(code, language_name, translit, std, tscript, style)
local title_table = lang_data.translit_title_table -- table of transliteration standards and the language codes and scripts that apply to those standards
std = std and std:lower() -- lower case for table indexing
local title_attribute
if is_set(std) then
if not title_table[std] then -- invalid standard, setup for error message
return ''
end
if title_table[std][tscript] and script_table[tscript] then -- and if script for that standard is legitimate
title_attribute = string.format(strings["TRANSLITERATION_STD_SCRIPT"], title_table[std][tscript:lower()], script_table[tscript][1]) -- add the appropriate text to the tool tip
elseif title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
title_attribute = string.format(strings["TRANSLITERATION_STD_LANGUAGE"],title_table[std][code:lower()], language_name) -- add the appropriate text to the tool tip
else
title_attribute = title_table[std]['default'] -- use the default if script not in std table
end
elseif title_table['no_std'][tscript] then
title_attribute = title_table['no_std'][tscript] -- use translit-script if set
elseif title_table['no_std'][code] then
title_attribute = title_table['no_std'][code] -- use language code
elseif is_set(tscript) then
title_attribute = string.format(strings["TRANSLITERATION_SCRIPT"], language_name) -- write a script tool tip
-- TODO: Conflicting with next section. Commenting out for now.
-- elseif is_set(code) then
-- if language_name:find('languages') then -- collective language names (plural 'languages' is part of the name)
-- title_attribute = string.format(strings["TRANSLITERATION_LANGUAGES"], language_name)
-- else -- individual and macro languages only
-- title_attribute = string.format(strings["TRANSLITERATION_LANGUAGE"], language_name)
-- end
else -- when neither standard nor script specified
if language_name:find('languages') then -- collective language names (plural 'languages' is part of the name)
title_attribute = string.format(strings["ROMANIZATION_LANGUAGES"], language_name)
else -- individual and macro languages only
title_attribute = string.format(strings["ROMANIZATION_LANGUAGE"], language_name)
end
end
if is_set(code) then -- when a language code is provided (always with {{Lang-xx}} templates, not always with {{Transl}})
if style then
return string.format(strings["TRANSLIT_SPAN_CODE"], style, code, title_attribute, translit) -- non-standard style, construct a <span> tag for it
else -- nil for the default italic style
return string.format(strings["TRANSLIT_ITALIC"], code, title_attribute, translit) -- so use <i> tag
end
else
return string.format(strings["TRANSLIT_SPAN_NO_CODE"], title_attribute, translit) -- when no language code: no lang= attribute, not italic ({{Transl}} only)
end
end
--[[ -------------------------- < 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
error message. The tests are for empty or missing text and for improper or disallowed use of apostrophe markup.
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)
if not is_set(args.text) then
return make_error_msg(error_messages["NO_TEXT"], args, template)
end
if args.text:find("%f[\']\'\'\'\'%f[^\']") or args.text:find("\'\'\'\'\'[\']+") then -- because we're looking, look for 4 apostrophes or 6+ apostrophes
return make_error_msg(error_messages["TEXT_HAS_MALFORMED_MARKUP"], args, template)
end
local style = args.italic
if (style ~= 'unset') and (style ~= 'invert') then
if args.text:find("%f[\']\'\'%f[^\']") or args.text:find("%f[\']\'\'\'\'\'%f[^\']") then -- italic but not bold, or bold italic
return make_error_msg(error_messages["TEXT_HAS_ITALIC_MARKUP"], args, template)
end
end
end
--[[ -------------------------- < R E N D E R _ M A I N T E N A N C E > --------------------------
Render maintenance messages and categories.
]]
local function render_maintenance(nocat)
local maintenance = {}
if 0 < #maintenance_messages then
table.insert(maintenance, string.format(strings["MAINTENANCE_SPAN"], table.concat(maintenance_messages, " ")))
end
if (0 < #maintenance_categories) and (namespace == 0) and not nocat then -- when there are maintenance categories; article namespace only
for _, category in ipairs(maintenance_categories) do
table.insert(maintenance, string.format("[[%s]]", category)) -- format and add the categories
end
end
return table.concat(maintenance)
end
--[[ -------------------------- < P R O T O _ P R E F I X > --------------------------
For proto languages, text is prefixed with an asterisk.
We do that here as a flag for make_text_html() so that an asterisk will be
rendered outside of italic markup (if used).
If the first character in text here is already an asterisk, we do nothing.
proto_param is boolean or nil:
- true adds asterisk 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 asterisk.
]]
local function proto_prefix(text, language_name, proto_param)
if proto_param == false then -- when forced by |proto=no
return text:gsub('^%**', '') -- return text without asterisk prefix regardless of language name or existing asterisk 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 an asterisk; also removes duplicate prefixing asterisks
end
return text:gsub('^%*+', '*') -- return text unmolested except multiple asterisks reduced to one asterisk
end
--[[ -------------------------- < H A S _ 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> strip marker because it is not possible for this code to know
the content that will replace the strip marker.
]]
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> strip marker, return text unmodified and choose <div>..</div> tags because
the strip marker 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> strip marker (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 proto_param == 'yes' then
return true
elseif proto_param == 'no' 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.
]]
local function language_name_get(ietf, code, cat)
ietf = ietf:lower() -- ietf:lower() because format_ietf_tag() returns mixed case
if override_table[ietf] then -- look for whole IETF tag in override table
return override_table[ietf][1]
elseif override_table[code] then -- not there so try basic language code
return override_table[code][1]
elseif lang_table[code] then -- shift to IANA code/name table
return 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(maintenance_categories, string.format(tracking_categories["CATEGORY_LANG_DEPRECATED"], code))
table.insert(maintenance_messages, string.format(error_messages["CODE_DEPRECATED"], code))
end
return lang_dep_table[code][1] -- table entries sometimes have multiple names, always take the first one
end
end
--[[ -------------------------- < L A N G _ A N D _ L A N G _ X X _ S H A R E D _ S E T U P > --------------------------
Shared code used by both {{Lang}} and {{Lang-xx}} templates to setup the parameters.
Parameters required are the args passed to the template
and the template name being called, which is used for error messages.
Returns 6 parameters in this order:
-- args
-- script
-- code
-- language_name
-- tag
-- error_msg
If error_msg returned is not nil, it should be returned back
to the invoking function and not passed to make_error_msg()
as it was already handled.
]]
local function lang_and_lang_xx_shared_setup(args, template)
local msg = validate_text(template, args) -- ensure that |text= is set
if is_set(msg) then -- msg is an already-formatted error message
return nil, nil, nil, nil, nil, msg
end
local tag
args.text, tag = html_tag_select(args.text) -- inspects text; returns appropriate HTML tag with text trimmed accordingly
validate_cat_args(args) -- determine if categorization should be suppressed
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 nil, nil, nil, nil, nil, make_error_msg(error_messages["INVALID_PROTO"], args, template)
end
local subtags = {} -- IETF subtags script, region, variant, and private
local code -- the language code
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(args.code, args.script, args.region, args.variant) -- private omitted because private
if msg then
return nil, nil, nil, nil, nil, make_error_msg(msg, args, template)
end
args.italic, msg = validate_italic(args)
if msg then
return nil, nil, nil, nil, nil, make_error_msg(msg, args, template)
end
if is_set(subtags.script) then -- if script set, override rtl setting
if in_array(subtags.script, lang_data.rtl_scripts) then
args.rtl = true -- script is an rtl script
else
args.rtl = false -- script is not an rtl script
end
end
args.code = format_ietf_tag(code, subtags.script, subtags.region, subtags.variant, subtags.private) -- format to recommended subtag styles
local language_name = language_name_get(args.code, code, true) -- get language name; try IETF tag first, then code without variant then code with variant
args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk
return args, subtags.script, code, language_name, tag, nil
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(args)
local template = args.template or strings["TEMPLATE_LANG"]
if args[1] and args.code then
return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "1", "code"), args, template)
else
args.code = args[1] or args.code -- prefer args.code
end
if args[2] and args.text then
return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "2", "text"), args, template)
else
args.text = args[2] or args.text -- prefer args.text
end
-- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{Lang}}); copied from previous comment.
args.script = nil
args.region = nil
args.variant = nil
local script -- IETF script
local code -- the language code
local language_name
local tag -- HTML tag
local error_msg
args, script, code, language_name, tag, error_msg = lang_and_lang_xx_shared_setup(args, template)
if error_msg then
return error_msg
end
if args.italic == nil then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if (script == 'latn') or -- script is latn
(mw.language.getContentLanguage().code ~= code
and not is_set(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
else
args.italic = 'inherit' -- italic not set and script not latn; inherit current style
end
end
if args.italic == 'invert' and tag == 'span' then -- invert only supported for in-line content
args.text = invert_italics(args.text)
end
args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk
local out = {}
table.insert(out, make_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_maintenance(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 key == 2 or key == 'text' then -- the 'text' parameter; do not trim white 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
--[[ -------------------------- < L A N G _ X X > --------------------------
For the {{L-xx}} templates, the only parameter required to be set in the template is the language code. All
other parameters can, usually should, be written in the template call. For {{Lang-xx}} templates for languages
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 knows the default
styling that should be applied to text.
For normal, upright style:
<includeonly>{{#invoke:lang|lang_xx_inherit|code=xx}}</includeonly>
For italic style:
<includeonly>{{#invoke:lang|lang_xx_italic|code=xx}}</includeonly>
All other parameters should be received from the template's frame (parent frame)
Supported parameters are:
|code = (required) the IANA language code
|script = IANA script code; especially for use with languages that use multiple writing systems
|region = IANA region code
|variant = IANA variant code
|text = (required) the displayed text in language specified by code
|link = boolean false ('no') does not link code-specified 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 args.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 templates where |text= is not entirely latn script):
|translit = text that is a transliteration of text
|translit-std = the standard that applies to the transliteration
|translit-script = ISO 15924 script name; falls back to code
For {{Lang-xx}}, the positional parameters are:
{{{1}}} text
{{{2}}} transliterated text
{{{3}}} literal translation text
No other positional parameters are allowed.
]]
local function _lang_xx(args)
local template = args.template or strings["TEMPLATE_LANG_XX"]
if args[1] and args.text then
return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "1", "text"), args, template)
else
args.text = args[1] or args.text -- prefer args.text
end
if args[2] and args.translit then
return make_error_msg(string.format(error_messages["CONFLICTING_POSITIONAL_AND_NAMED"], "2", "translit"), args, template)
else
args.translit = args[2] or args.translit -- prefer args.translit
end
if args[3] and (args.translation or args.lit) then
return make_error_msg(error_messages["CONFLICTING_LIT_TRANSLATION"], args, template)
elseif args.translation and args.lit then
return make_error_msg(string.format(error_messages["CONFLICTING_NAMED_AND_NAMED"], "lit", "translation"), args, template)
else
args.translation = args[3] or args.translation or args.lit -- prefer args.translation
end
if args.links and args.link then
return make_error_msg(string.format(error_messages["CONFLICTING_NAMED_AND_NAMED"], "links", "link"), args, template)
else
args.link = args.link or args.links -- prefer args.link
end
local script -- IETF script
local code -- the language code
local language_name
local tag -- HTML tag
local error_msg
args, script, code, language_name, tag, error_msg = lang_and_lang_xx_shared_setup(args, template)
if error_msg then
return error_msg
end
if args.italic == nil then -- args.italic controls
if is_set(script) then
if script == 'latn' then
args.italic = 'italic' -- |script=Latn; set for font-style: italic
else
args.italic = args["initial_style_state"] -- italic not set; script is not latn; set for font-style: <initial_style_state>
end
else
args.italic = args["initial_style_state"] -- here when |italic= and |script= not set; set for font-style: <initial_style_state>
end
end
if args.italic == 'invert' then
args.text = invert_italics(args.text)
end
local category_name = language_name -- category names retain IANA parenthetical disambiguators (if any)
language_name = language_name:gsub('%s+%b()', '') -- remove IANA parenthetical disambiguators or qualifiers from names that have them
args.text = proto_prefix(args.text, language_name, args.proto) -- prefix proto-language text with an asterisk
local out = {}
local label
if args.label then
if args.label ~= 'none' then
label = args.label -- custom label
end
else
if args.link == 'no' then
label = language_name -- language name without wikilink
else
if language_name:find('languages') then
label = make_wikilink(language_name) -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
label = make_wikilink(lang_data.article_name[code][1], language_name) -- language name with wikilink from override data
else
label = make_wikilink(language_name .. ' language', language_name) -- language name with wikilink
end
end
end
table.insert(out, string.format(strings["LABEL_LANGUAGE"], label, 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)
local translit_label
if args.label ~= 'none' then
local translit_script_name -- name associated with IANA (ISO 15924) script code
if script_table[args['translit-script']] then -- when |translit-script= is set, try to use the script's name
translit_script_name = script_table[args['translit-script']][1]
else
translit_script_name = language_name -- fall back on language name
end
local translit_title = mw.title.makeTitle(0, string.format(strings["ROMANIZATION_OF"], translit_script_name)) -- make a title object
if translit_title.exists and (args.link ~= 'no') then
translit_label = make_wikilink(string.format(strings["ROMANIZATION_OF"], translit_script_name or language_name), strings["ROMANIZED"]) -- make a wikilink if there is an article to link to
else
translit_label = strings["ROMANIZED"] -- else plain text
end
end
local translit = make_translit(args.code, language_name, args.translit, args['translit-std'], args['translit-script'])
if is_set(translit) then
table.insert(out, string.format(strings["LABEL_TRANSLIT"], translit_label, translit))
else
return make_error_msg(string.format(error_messages["INVALID_TRANSLIT_STD_VALUE"], args['translit-std']), args, template)
end
end
if is_set(args.translation) then -- translation (not supported in {{Lang}})
local translation_label
if args.label ~= 'none' then
if args.link == 'no' then
translation_label = strings["LITERAL_TRANSLATION_ABBR"]
else
translation_label = make_wikilink(strings["LITERAL_TRANSLATION_TEXT"], strings["LIT"])
end
end
table.insert(out, string.format(strings["LABEL_TRANSLATION"], translation_label, args.translation))
end
table.insert(out, make_category(code, category_name, args.nocat))
table.insert(out, render_maintenance(args.nocat)) -- maintenance messages and categories
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 key == 1 then -- the 'text' parameter; do not trim white 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
--[[ -------------------------- < L A N G _ X X _ I T A L I C > --------------------------
Entry point for those {{Lang-xx}} templates that call lang_xx_italic().
Sets the initial style state to italic.
]]
local function lang_xx_italic(frame)
local args = lang_xx_args_get(frame)
args["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)
args["initial_style_state"] = 'italic'
return _lang_xx(args)
end
--[[ -------------------------- < L A N G _ X X _ I N H E R I T > --------------------------
Entry point for those {{Lang-xx}} templates that call lang_xx_inherit().
Sets the initial style state to inherit.
]]
local function lang_xx_inherit(frame)
local args = lang_xx_args_get(frame)
args["initial_style_state"] = 'inherit'
return _lang_xx(args)
end
--[[ -------------------------- < _ L A N G _ X X _ I N H E R I T > --------------------------
Entry point from another module.
Sets the initial style state to inherit.
]]
local function _lang_xx_inherit(args)
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
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; getArgs() so we also 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 raw_code = args[1] -- save a copy of the input IETF subtag
local subtags = {} -- IETF subtags script, region, variant, and private
local code -- the language code
local msg -- gets an error message if IETF language tag is malformed or invalid
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(raw_code)
validate_cat_args(args)
if msg then
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization
args.nocat = nil
end
return make_error_msg(msg, args, args['template'])
end
raw_code = format_ietf_tag(code, subtags.script, subtags.region, subtags.variant, subtags.private) -- format to recommended subtag styles; private omitted because private
local language_name = language_name_get(raw_code, code) -- get language name; try IETF tag first, then code without variant then code with variant
language_name = language_name:gsub('%s+%b()', '') -- remove IANA parenthetical disambiguators or qualifiers from names that have them
local link = 'yes' == args['link'] -- make a boolean
local label = args.label
if link then -- when |link=yes, wikilink the language name
if language_name:find('languages') then
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
return language_name
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>}}
local args = getArgs(frame) -- getArgs() so we also get parent frame
args["from_invoke"] = true
return _name_from_tag(args) -- pass-on the args table
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)
local msg
if args[1] and args[1] ~= '' then
local data = mw.loadData('Module:Lang/tag from name') -- get the reversed data tables
local lang = args[1]:lower() -- allow any-case for the language name (spelling 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 = string.format(error_messages["LANGUAGE_NOT_FOUND"], args[1]) -- language name not found, error message
end
else
msg = error_messages["LANGUAGE_NOT_PROVIDED"] -- language name not provided, error message
end
validate_cat_args(args)
if msg then
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization
args.nocat = nil
end
return make_error_msg(msg, args, args['template'])
end
end
--[[ -------------------------- < 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 args = getArgs(frame) -- getArgs() so we also get parent frame
args["from_invoke"] = true
local result, _ = _tag_from_name(args) -- pass-on the args table and suppress second return used by is_lang_name()
return result
end
--[[ -------------------------- < I S _ L A N G _ N A M E > --------------------------
Module entry point from an {{#invoke:}}.
]]
local function is_lang_name(frame)
local _, result = _tag_from_name(getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; suppress second return used by tag_from_name()
return result and true or nil
end
--[[ -------------------------- < _ T R A N S L > --------------------------
Module entry point from another module.
]]
local function _transl(args)
local template = strings["TEMPLATE_TRANSL"]
local title_table = lang_data.translit_title_table -- table of transliteration standards and the language codes and scripts that apply to those standards
if is_set(args[3]) then -- [3] set when {{Transl|code|standard|text}}
args.text = args[3] -- get the transliterated text
args.translit_std = args[2] and args[2]:lower() -- get the standard; lower case for table indexing
if not title_table[args.translit_std] then
return make_error_msg(string.format(error_messages["UNRECOGNIZED_TRANSLITERATION_STANDARD"], args.translit_std), args, template)
end
else
if is_set(args[2]) then -- [2] set when {{Transl|code|text}}
args.text = args[2] -- get the transliterated text
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(error_messages["NO_TEXT"], args, template)-- 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(string.format(error_messages["MISSING_LANGUAGE_OR_SCRIPT_CODE"]), args, template)
end
end
end
if is_set(args[1]) then -- IANA language code used for HTML lang= attribute; or ISO 15924 script code
if args[1]:match('^%a%a%a?%a?$') then -- args[1] has correct form?
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(string.format(error_messages["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"], args[1]), args, template) -- invalid language / script code
end
else
return make_error_msg(string.format(error_messages["MISSING_LANGUAGE_OR_SCRIPT_CODE"]), args, template) -- missing language / script code so quit
end
local msg
args.italic, msg = validate_italic(args)
if msg then
return make_error_msg(msg, args, template)
end
if args.italic == 'italic' then -- 'italic' when |italic=yes; because that is same as absent or not set and |italic=default
args.italic = nil -- set to nil;
end
local language_name -- language name that matches language code; used for tool tip
local script -- IANA script
if override_table[args.code] then -- is code a language code defined in the override table?
language_name = override_table[args.code][1]
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables?
language_name = lang_table[args.code][1]
elseif lang_dep_table[args.code] then -- is code a language code defined in the deprecated language code tables?
language_name = lang_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(string.format(error_messages["UNRECOGNIZED_LANGUAGE_OR_SCRIPT_CODE"], args.code), args, template) -- invalid language / script code
end
-- here only when all parameters passed to make_translit() are valid
return make_translit(args.code, language_name, args.text, args.translit_std, script, args.italic)
end
--[[ -------------------------- < T R A N S L > --------------------------
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 raw_code = args[1] -- save a copy of the input IETF subtag
local subtags = {} -- IETF subtags script, region, variant, and private
local code -- the language code
local msg -- gets an error message if IETF language tag is malformed or invalid
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts(raw_code)
validate_cat_args(args)
if msg then
if not args.nocat and args["from_invoke"] then -- if called from an invoke and not manually set nocat to off, allow categorization
args.nocat = nil
end
return make_error_msg(msg, args, args['template'])
end
raw_code = format_ietf_tag(code, subtags.script, subtags.region, subtags.variant, subtags.private) -- format to recommended subtag styles; private omitted because private
local category_name = language_name_get(raw_code, code) -- get language name; try IETF tag first, then code without variant then code with variant
category_name = make_category(code, category_name, nil, true):gsub('[%[%]]', '')
if args.link then
return string.format("[[:%s]]", category_name)
else
return category_name
end
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>}}
local args = getArgs(frame) -- getArgs() so we also get parent frame
args["from_invoke"] = true
return _category_from_tag(args) -- pass-on the args table, nothing else
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_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,
}