imported>Vozhuo
// Edit via Wikiplus
imported>Ericliu1912
依據編輯請求更新頁面 自Module:Lang/sandbox合并優枰版本90980088
 
(未显示10个用户的62个中间版本)
第1行: 第1行:
--[=[
--[=[


Lua support for the {{lang}}, {{lang-xx}}, and {{transl}} templates and replacement of various supporting templates.  
Lua support for the {{lang}}, {{langx}}, {{lang-??}}, and {{transliteration}} templates and replacement of various supporting templates.
 
-- 中文維基百科:加入了error_msgs,用於將所有報錯情形修改爲試圖顯示正常內容並附加預設不可見的錯誤報告。


]=]
]=]


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


local initial_style_state; -- set by lang_xx_inherit() and lang_xx_italic()
local getArgs = require ('Module:Arguments').getArgs;
local unicode = require ("Module:Unicode data"); -- for is_Latin() and is_rtl()
local yesno = require ('Module:Yesno');


local getArgs = require ('Module:Arguments').getArgs;
local sandbox = (mw.getCurrentFrame():getTitle():match ('/sandbox') or ''); -- when called from a sandbox template or module load sandbox data and sandbox configuration
local lang_name_table = mw.loadData ('Module:Language/name/data');
 
local lang_data = mw.loadData ('Module:Lang/data' .. sandbox); -- language name override and transliteration tool-tip tables
local lang_name_table = lang_data.lang_name_table; -- language codes, names, regions, scripts, suppressed scripts
local lang_table = lang_data.lang_name_table.lang;
local lang_dep_table = lang_data.lang_name_table.lang_dep;
local script_table = lang_data.lang_name_table.script;
local region_table = lang_data.lang_name_table.region;
local variant_table = lang_data.lang_name_table.variant;
local suppressed_table = lang_data.lang_name_table.suppressed;
local override_table = lang_data.override;


local synonym_table = mw.loadData ('Module:Lang/ISO 639 synonyms'); -- ISO 639-2/639-2T code translation to 639-1 code
local synonym_table = mw.loadData ('Module:Lang/ISO 639 synonyms'); -- ISO 639-2/639-2T code translation to 639-1 code


local lang_data = mw.loadData ('Module:Lang/data'); -- language name override and transliteration tool-tip tables
local cfg = mw.loadData ('Module:Lang/configuration' .. sandbox); -- for internationalization
 
local is_latn_data = mw.loadData ('Module:Lang/data/is latn data');
local sizeof_ranges_t = is_latn_data.sizeof_ranges_t;


local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
local content_lang = mw.language.getContentLanguage();
local this_wiki_lang_tag = content_lang.code; -- get this wiki's language tag
local this_wiki_lang_dir = content_lang:getDir(); -- get this wiki's language direction
local initial_style_state; -- set by lang_xx_normal() and lang_xx_italic()


local maint_cats = {}; -- maintenance categories go here
local maint_cats = {}; -- maintenance categories go here
local maint_msgs = {}; -- and their messages go here
local maint_msgs = {}; -- and their messages go here


local error_msgs = {}


--[[--------------------------< 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.
--[[--------------------------< M A K E _ E R R O R _ S P A N >--------------------------------------------------


]]
]]


local function is_set( var )
local function make_error_span (template, msg)
return not (var == nil or var == '');
return table.concat ({'<span class="error" style="font-size: 1em;">', cfg.misc_text_t.error, ':', template, msg, '</span>'})
end
 
local function make_lang_error_span (msg)
return table.concat ({'<span class="lang-comment lang-comment-error" style="font-style: normal; display: none; margin-left: 0.3em; color: #33aa33;">', msg, '</span>'})
end
end




--[[--------------------------< I S _ L A T N >----------------------------------------------------------------
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------


Returns true if all of text argument is written using Latn script for letters, numbers and punctuationset; false else.
Substitutes $1, $2, etc in <message> with data from <data_t>. Returns plain-text substituted string when
<data_t> not nil; returns <message> else.


For the purposes of this function, Latn script is characters less control characters from these Unicode 10.0 Character Code Charts:
]]
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] U+0020–U+007E (20 - 7E) + see note about <poem>...</poem> support
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] U+00A0-U+00AC, U+00C0–U+00FF (C2 A0 - C2 AC, C3 80 - C3 BF: \194\160-\194\172)
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] U+0100–U+017F (C4 80 - C5 BF)
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] U+0180–U+024F (C6 80 - C9 8F)
[http://www.unicode.org/charts/PDF/U1E00.pdf Latin Extended Additional] U+1E00-U+1EFF (E1 B8 80 - E1 BB BF)
[http://www.unicode.org/charts/PDF/U2C60.pdf Latin Extended-C] U+2C60–U+2C7F (E2 B1 A0 - E2 B1 BF)
[http://www.unicode.org/charts/PDF/UA720.pdf Latin Extended-D] U+A720-U+A7FF (EA 9C A0 - EA 9F BF)
[http://www.unicode.org/charts/PDF/UAB30.pdf Latin Extended-E] U+AB30-U+AB6F (EA AC B0 - EA AD AF)
[http://www.unicode.org/charts/PDF/UFB00.pdf Alphabetic Presentaion Forms] U+FB00-U+FB06 (EF AC 80 - EF AC 86)
[http://www.unicode.org/charts/PDF/UFF00.pdf Halfwidth and Fullwidth Forms] U+FF01-U+FF3C (EF BC 81 EF BC BC)


does not include:
local function substitute (message, data_t)
[http://www.unicode.org/charts/PDF/U1D00.pdf Phonetic Extensions] U+1D00-U+1D7F (E1 B4 80 - E1 B5 BF)
return data_t and mw.message.newRawMessage (message, data_t):plain() or message;
[http://www.unicode.org/charts/PDF/U0250.pdf IPA Extensions] U+0250-U+02AF (C9 90 - CA AF)
end
[http://www.unicode.org/charts/PDF/U1D80.pdf Phonetic Extensions Supplement] U+1D80-U+1DBF (E1 B6 80 - E1 B6 BF)


{{lang}} is used inside <poem>...</poem> tags for song lyrics, poetry, etc.  <poem>...</poem> replaces newlines with
 
poem stripmarkers.  These have the form:
--[[--------------------------< M A K E _ E R R O R _ M S G >--------------------------------------------------
?'"`UNIQ--poem-67--QINU`"'?
 
where the '?' character is actually the delete character (U+007F, \127).  Including the '\n' (U+0010) and 'del' (U+007F)
Assembles an error message from template name, message text, help link, and error category.
characters in the latn character table allows {{lang}} to auto-italicize text within <poem>...</poem> tags.


]]
]]


function p.is_latn (text)
local function make_error_msg (msg, args_t, template)
local latn = table.concat (
local category;
local text; -- handle the oddity that is {{langx}}
if cfg.templates_t.langxx == template then
text = args_t.text or args_t[1]; -- for {{lang-xx}}
else
text = args_t.text or args_t[2]; -- for {{lang}}, {{langx}}, and {{transliteration}}
end
 
if cfg.templates_t.transliteration == template then
category = cfg.make_error_msg_t.xlit_err_cat;
else
category = cfg.make_error_msg_t.lang_err_cat;
end
 
local category_link = ((0 == namespace or 10 == namespace) and not args_t.nocat) and substitute ('[[Category:$1]]', {category}) or '';
 
text = text or cfg.make_error_msg_t.undefined
if text == '' then
text = cfg.make_error_msg_t.empty
end
 
-- &#123;&#123;$3&#125;&#125; = {{$3}}
-- 防止特定情況下作爲模板展開
table.insert(error_msgs, substitute ('-{[$1]}-<span class="error" style="font-size: 1em; margin-left: 0.3em;">$2:&#123;&#123;$3&#125;&#125;:$4([[:Category:$5|$6]])</span>$7',
{
{
'[', -- this is a set so include opening bracket
text,
'\n\32-\127', -- C0 Controls and Basic Latin U+0020–U+007E (20 - 7E) + (U+0010 and U+007F <poem>...</poem> support)
cfg.misc_text_t.error,
'\194\160-\194\172', -- C1 Controls and Latin-1 Supplement U+00A0-U+00AC (C2 A0 - C2 AC)
template,
'\195\128-\195\191', -- (skip shy) U+00C0–U+00FF (C3 80 - C3 BF)
msg,
'\196\128-\197\191', -- Latin Extended-A U+0100–U+017F (C4 80 - C5 BF)
category,
'\198\128-\201\143', -- Latin Extended-B U+0180–U+024F (C6 80 - C9 8F)
cfg.misc_text_t.help,
'\225\184\128-\225\187\191', -- Latin Extended Additional U+1E00-U+1EFF (E1 B8 80 - E1 BB BF)
category_link
'\226\177\160-\226\177\191', -- Latin Extended-C U+2C60–U+2C7F (E2 B1 A0 - E2 B1 BF)
})
'\234\156\160-\234\159\191', -- Latin Extended-D U+A720-U+A7FF (EA 9C A0 - EA 9F BF)
)
'\234\172\176-\234\173\175', -- Latin Extended-E U+AB30-U+AB6F (EA AC B0 - EA AD AF)
return error_msgs[#error_msgs]
'\239\172\128-\239\172\134', -- Alphabetic Presentaion Forms U+FB00-U+FB06 (EF AC 80 - EF AC 86)
end
'\239\188\129-\239\188\188', -- Halfwidth and Fullwidth Forms U+FF01-U+FF3C (EF BC 81 - EF BC BC)
 
'–', -- ndash
 
'—', -- mdash
--[[--------------------------< P A R A M E T E R _ V A L I D A T E >------------------------------------------
'«', '»', -- guillemets commonly used in several 'Latn' languages
 
']', -- close the set
]]
});
 
local function parameter_validate (args_t, template)
local err_msg = cfg.parameter_validate_t.invalid_param;
 
local ret = {}
 
if cfg.templates_t.lang == template then -- for {{lang}}
for param, _ in pairs (args_t) do
if not cfg.known_params_t.params_lang_t[param] and -- unique {{lang}} parameters
not cfg.known_params_t.common_params_all_t[param] then -- common to all
table.insert(ret, substitute (err_msg, {param}))
end
end
elseif cfg.templates_t.langx == template then -- for {{langx}}
for param, _ in pairs (args_t) do
if not cfg.known_params_t.params_langx_t[param] and -- unique {{langx}} parameters
not cfg.known_params_t.params_x_t[param] and -- common to {{langx}} and {{lang-xx}}
not cfg.known_params_t.common_params_all_t[param] then -- common to all
table.insert(ret, substitute (err_msg, {param}))
end
end
elseif cfg.templates_t.langxx == template then -- for {{lang-xx}}
for param, _ in pairs (args_t) do
if not cfg.known_params_t.params_lang_xx_t[param] and -- unique {{lang-xx}} parameters
not cfg.known_params_t.params_x_t[param] and -- common to {{langx}} and {{lang-xx}}
not cfg.known_params_t.common_params_all_t[param] then -- common to all
table.insert(ret, substitute (err_msg, {param}))
end
end
end
 
if ret[1] then
return table.concat(ret, '、')
end
end
 
 
--[[--------------------------< 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.
 
]]


text = mw.text.decode (text, true); -- replace numeric and named html entities with their unicode characters
local function is_set (var)
text = mw.ustring.gsub (text, '%[%[[^|]+|([^%]]+)%]%]', '%1'); -- remove the link and markup from complex wikilink in case interwiki to non-Latn wikipedia
return not (var == nil or var == '');
return not is_set (mw.ustring.gsub (text, latn, '')); -- replace all latn characters with empty space; if result is all empty space, text is latn
end
end


第94行: 第172行:
This function attempts to invert the italic markup a args.text by adding/removing leading/trailing italic markup
This function attempts to invert the italic markup a args.text by adding/removing leading/trailing italic markup
in args.text.  Like |italic=unset, |italic=invert disables automatic italic markup.  Individual leading/trailing
in args.text.  Like |italic=unset, |italic=invert disables automatic italic markup.  Individual leading/trailing
apostrophes are converted to their html numeric entity equivalent so that the new italic markup doesn't become
apostrophes are converted to their HTML numeric entity equivalent so that the new italic markup doesn't become
bold markup inadvertently.
bold markup inadvertently.


第114行: 第192行:
local seg = {};
local seg = {};


source = source:gsub ("%f[\']\'%f[^\']", '&#38;'); -- protect single quote marks from being interpreted as bold markup
source = source:gsub ("%f[\']\'%f[^\']", '&#39;'); -- protect single quote marks from being interpreted as bold markup


seg[1] = source:match ('^(\'\'+%f[^\']).+') or ''; -- get leading markup, if any; ignore single quote
seg[1] = source:match ('^(\'\'+%f[^\']).+') or ''; -- get leading markup, if any; ignore single quote
seg[3] = source:match ('.+(%f[\']\'\'+)$') or ''; -- get trailing markup, if any; ignore single quote
seg[3] = source:match ('.+(%f[\']\'\'+)$') or ''; -- get trailing markup, if any; ignore single quote


if '' ~= seg[1] and '' ~= seg[3] then -- extract the 'text'  
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 '' ~= seg[1] then
elseif '' ~= seg[1] then
第129行: 第207行:
end
end


seg[1] = seg[1]:gsub (".*", invert_pattern_table, 1); -- replace leading markup according to pattern table
seg[1] = invert_pattern_table[seg[1]] or seg[1]; -- replace leading markup according to pattern table
seg[3] = seg[3]:gsub (".*", invert_pattern_table, 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
return table.concat (seg); -- put it all back together and done
第138行: 第216行:
--[[--------------------------< 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.
Validates |italic= or |italics= assigned values.


When |italic= is set and has an acceptible assigned value, return the matching css font-style property value or,
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 unacceptable 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 args.italic according to the template's
defined default ('inherit' for {{lang}}, 'inherit' or 'italic' for {{lang-xx}} depending on
defined default ('inherit' for {{lang}}, 'inherit' or 'italic' for {{lang-??}} depending on
the individual template's requirements, 'italic' for {{transl}}) or to the value appropriate to |script=, if set ({{lang}}
the individual template's requirements, 'italic' for {{transliteration}}) or to the value appropriate to |script=, if set ({{lang}}
and {{lang-xx}} only).
and {{lang-??}} only).


Accepted values and the values that this function returns are are:
Accepted values and the values that this function returns are are:
第162行: 第240行:
]]
]]


local function validate_italic (italic, italics)
local function validate_italic (args)
local properties = {['yes'] = 'italic', ['no'] = 'normal', ['unset'] = 'inherit', ['invert'] = 'invert', ['default'] = nil};
local properties = {[cfg.keywords_t.affirmative] = 'italic', [cfg.keywords_t.negative] = 'normal', [cfg.keywords_t.unset] = 'inherit', [cfg.keywords_t.invert] = 'invert', [cfg.keywords_t.default] = nil};
 
local count = 0
for _, arg in pairs {'italic', 'italics', 'i'} do
if args[arg] then
count = count + 1
end
end
 
return properties[args.italic or args.italics or args.i], count > 1 and cfg.validate_italic_t.multi_italic or nil
end
 
 
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------
 
Default behavior of the {{lang}} and {{lang-??}} templates is to add categorization when the templates are used in main space.
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
 
]=]


if italic and italics then -- return nil and an error message if both are set
local function validate_cat_args (args)
return nil, '冲突:&#124;italic= 和 &#124;italics=';
if not (args.nocat or args.cat) then -- both are nil, so categorize
return;
end
 
if false == yesno (args.cat) or true == yesno (args.nocat) then
args.nocat = true; -- set to true when args.nocat is affirmative; nil else (as if the parameter were not set in the template)
else -- args.nocat is the parameter actually used.
args.nocat = nil;
end
end
return properties[italic or italics], nil; -- return an appropriate value and a nil error message
end
end


第175行: 第288行:
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
--[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------


Whether needle is in haystack
Whether needle is in haystack.


]]
]]


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;
第194行: 第307行:
--[[--------------------------< 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:
Prettify IETF tags to use recommended subtag formats:
code: lower case
code: lower case
script: sentence case
script: sentence case
region: upper case
region: upper case
variant: lower case
variant: lower case
private: lower case prefixed with -x-


]]
]]


local function format_ietf_tag (code, script, region, variant)
local function format_ietf_tag (code, script, region, variant, private)
local out = {};
local out = {};
if is_set (private) then
return table.concat ({code:lower(), 'x', private:lower()}, '-'); -- if private, all other tags ignored
end


table.insert (out, code:lower());
table.insert (out, code:lower());
第214行: 第332行:
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
第225行: 第343行:
--[[--------------------------< 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:
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
region subtag - two-letter or three digit IANA region code
region subtag - two-letter or three digit IANA region code
variant subtag - four digit or 5-8 alnum variant 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
private subtag - x- followed by 1-8 alnum private code; only supported with the primary language tag


第237行: 第355行:
lang-region lang-region-variant
lang-region lang-region-variant
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
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
第245行: 第363行:
the synonymous three-character codes in the lang= attribute.
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}}
For {{lang-??}} 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.  Valid parts are returned as themselves; omitted parts are returned as empty strings, invalid
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
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 code;
local code, script, region, variant, private; -- IETF tag parts
local script = '';
local region = '';
local variant = '';
local private = '';


if not is_set (source) then
if not is_set (source) then
return nil, nil, nil, nil, nil, '缺少语言标签';
return nil, nil, nil, nil, nil, cfg.get_ietf_parts_t.missing_lang_tag;
end
end


if source:match ('^%a%a%a?%-%a%a%a%a%-%a%a%-%d%d%d%d$') then -- ll-Ssss-RR-variant (where variant is 4 digits)
local override = { -- 簡寫轉換爲正確的語言標籤
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$');
['pinyin'] = 'zh-Latn-pinyin', -- 漢語拼音
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%-%d%d%d%d$') then -- ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
['zhuyin'] = 'zh-Bopo', -- 注音符號
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$');
}
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-RR-variant (where variant is 5-8 alnum characters)
 
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
source = override[source] or source
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
 
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
local pattern = { -- table of tables holding acceptable IETF tag patterns and short names of the IETF part captured by the pattern
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$', '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)$', 's', 'r', 'v'}, -- 2 -  ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', '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; 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; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 9 -  ll-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 10 - ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
 
{'^(%a%a%a?)%-(%d%d%d%d)$', 'v'}, -- 11 - ll-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$', 'v'}, -- 12 - ll-variant (where variant is 5-8 alnum characters)


elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%d$') then -- ll-Ssss-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$');
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits)
elseif source:match ('^%a%a%a?%-%a%a%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-variant (where variant is 5-8 alnum characters)
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');


elseif source:match ('^%a%a%a?%-%a%a%-%d%d%d%d$') then -- ll-RR-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-%d%d%d%-%d%d%d%d$') then -- ll-DDD-variant (where region is 3 digits; variant is 4 digits)
code, region, variant = source:match ('^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-RR-variant (where variant is 5-8 alnum characters)
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
elseif source:match ('^%a%a%a?%-%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
code, region, variant = source:match ('^(%a%a%a?)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');


elseif source:match ('^%a%a%a?%-%d%d%d%d$') then -- ll-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a)$', 'r'}, -- 16 - ll-RR
code, variant = source:match ('^(%a%a%a?)%-(%d%d%d%d)$');
{'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits)
elseif source:match ('^%a%a%a?%-[%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?$') then -- ll-variant (where variant is 5-8 alnum characters)
code, variant = source:match ('^(%a%a%a?)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');


elseif source:match ('^%a%a%a?%-%a%a%a%a%-%a%a$') then -- ll-Ssss-RR
{'^(%a%a%a?)$'}, -- 18 - ll
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$');
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d$') then -- ll-Ssss-DDD (region is 3 digits)
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$');


elseif source:match ('^%a%a%a?%-%a%a%a%a$') then -- ll-Ssss
{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters)
code, script = source:match ('^(%a%a%a?)%-(%a%a%a%a)$');


elseif source:match ('^%a%a%a?%-%a%a$') then -- ll-RR
}
code, region = source:match ('^(%a%a%a?)%-(%a%a)$');
elseif source:match ('^%a%a%a?%-%d%d%d$') then -- ll-DDD (region is 3 digits)
code, region = source:match ('^(%a%a%a?)%-(%d%d%d)$');


elseif source:match ('^%a%a%a?$') then -- ll
local t = {}; -- table of captures; serves as a translator between captured IETF tag parts and named variables
code = source:match ('^(%a%a%a?)$');


elseif source:match ('^%a%a%a?%-x%-[%a%d][%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?$') then -- ll-x-pppppppp)
for i, v in ipairs (pattern) do -- spin through the pattern table looking for a match
code, private = source:match ('^(%a%a%a?)%-x%-([%a%d]+)$');
local c1, c2, c3, c4; -- captures in the 'pattern' from the pattern table go here


else
c1, c2, c3, c4 = source:match (pattern[i][1]); -- one or more captures set if source matches pattern[i])
return nil, nil, nil, nil, nil, table.concat ({'无法识别的语言标签:', source}); -- don't know what we got but it is malformed
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, substitute (cfg.get_ietf_parts_t.unrecog_tag, {source}); -- don't know what we got but it is malformed
end
end


code = code:lower(); -- ensure that we use and return lower case version of this
code = code:lower(); -- ensure that we use and return lower case version of this
 
if not (lang_data.override[code] or lang_name_table.lang[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, table.concat ({'无法识别的语言代码:', code}); -- invalid language code, don't know about the others (don't care?)
return nil, nil, nil, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_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 (maint_cats, table.concat ({'Lang和lang-xx代码升级为ISO 639-1|', code}));
table.insert (maint_cats, substitute (cfg.get_ietf_parts_t.maint_promo_cat, {code}));
table.insert (maint_msgs, table.concat ({'代码:', code, '升级为代码:', synonym_table[code]}));
table.insert (maint_msgs, substitute (cfg.get_ietf_parts_t.maint_promo_msg, {code, synonym_table[code]}));
code = synonym_table[code]; -- use the synonym
code = synonym_table[code]; -- use the synonym
end
end
第331行: 第457行:
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, '冗余文本标签'; -- both code with script and |script= not allowed
return code, nil, nil, nil, nil, cfg.get_ietf_parts_t.redundant_scr; -- both code with script and |script= not allowed
end
end
else
else
script = args_script or ''; -- use args.script if provided
script = args_script or ''; -- use args.script if provided
end  
end


if is_set (script) then
if is_set (script) then
script = script:lower(); -- ensure that we use and return lower case version of this
script = script:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.script[script] then
if not script_table[script] then
return code, nil, nil, nil, nil, table.concat ({'无法识别的文本:', script, '用于代码:', code}); -- language code ok, invalid script, don't know about the others (don't care?)
return code, nil, nil, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_scr_code, {script, code}); -- language code OK, invalid script, don't know about the others (don't care?)
end
end
end
end
if lang_name_table.suppressed[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, lang_name_table.suppressed[script]) then
if in_array (code, suppressed_table[script]) then
return code, nil, nil, nil, nil, table.concat ({'文本:', script, '不支持代码:', code}); -- language code ok, script is suppressed for this code
return code, nil, nil, nil, nil, substitute (cfg.get_ietf_parts_t.script_code, {script, code}); -- language code OK, script is suppressed for this code
end
end
end
end
第351行: 第477行:
if is_set (region) then
if is_set (region) then
if is_set (args_region) then
if is_set (args_region) then
return code, nil, nil, nil, nil, '冗余区域标签'; -- both code with region and |region= not allowed
return code, nil, nil, nil, nil, cfg.get_ietf_parts_t.redundant_reg; -- both code with region and |region= not allowed
end
end
else
else
region = args_region or ''; -- use args.region if provided
region = args_region or ''; -- use args.region if provided
end  
end


if is_set (region) then
if is_set (region) then
region = region:lower(); -- ensure that we use and return lower case version of this
region = region:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.region[region] then
if not region_table[region] then
return code, script, nil, nil, nil, table.concat ({'无法识别的地区:', region, '用于代码:', code});
return code, script, nil, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_reg_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, nil, nil, nil, nil, '冗余变体标签'; -- both code with variant and |variant= not allowed
return code, nil, nil, nil, nil, cfg.get_ietf_parts_t.redundant_var; -- both code with variant and |variant= not allowed
end
end
else
else
variant = args_variant or ''; -- use args.variant if provided
variant = args_variant or ''; -- use args.variant if provided
end  
end


if is_set (variant) then
if is_set (variant) then
variant = variant:lower(); -- ensure that we use and return lower case version of this
variant = variant:lower(); -- ensure that we use and return lower case version of this
if not lang_name_table.variant[variant] then -- make sure variant is valid
if not variant_table[variant] then -- make sure variant is valid
return code, script, region, nil, nil, table.concat ({'未识别的变体:', variant});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var, {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 is_set (script) then -- if script set it must be part of the 'prefix'
if not in_array (table.concat ({code, '-', script}), lang_name_table.variant[variant]['prefixes']) then
if not in_array (table.concat ({code, '-', script}), variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'未识别的变体:', variant, ' 用于代码-文本对', code, '-', script});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code_scr, {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 (table.concat ({code, '-', region}), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code_reg, {variant, code, region});
end
end
else -- cheap way to determine if there are prefixes; fonipa and others don't have prefixes; # operator always returns 0
if variant_table[variant]['prefixes'][1] and not in_array (code, variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code, {variant, code});
end
end
else
if not in_array (code, lang_name_table.variant[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'未识别的变体:', variant, '用于代码:', code});
end
end
end
end
end
 
if is_set (private) then
if is_set (private) then
private = private:lower(); -- ensure that we use and return lower case version of this
private = private:lower(); -- ensure that we use and return lower case version of this
if not lang_data.override[table.concat ({code, '-x-', private})] then -- make sure private tag is valid; note that index  
if not override_table[table.concat ({code, '-x-', private})] then -- make sure private tag is valid; note that index
return code, script, region, nil, nil, table.concat ({'无法识别的私有标签: ', private});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_pri, {private});
end
end
end
end
第397行: 第529行:
end
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 'transl' == template then
category = 'transl';
else
category = 'lang和lang-xx'
end
table.insert (out, table.concat ({'&#x5B;', args.text or '未定义', '&#x5D; '})); -- for error messages output args.text if available
table.insert (out, table.concat ({'<span style=\"font-size:100%; font-style:normal;\" class=\"error\">错误:{{', template, '}}:'}));
table.insert (out, msg);
table.insert (out, table.concat ({'([[:Category:', category, '模板错误|帮助]])'}));
table.insert (out, '</span>');
if (0 == namespace) and not is_set (args.nocat) then -- only categorize in article space
table.insert (out, table.concat ({'[[Category:', category, '模板错误]]'}));
end
return table.concat (out);
end


--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------
--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------
第449行: 第551行:




--[[--------------------------< M A K E _ T E X T _ S P A N >--------------------------------------------------
--[[--------------------------< D I V _ M A R K U P _ A D D >--------------------------------------------------


TODO: add support for block: div tags instead of span tags; would need some sort of proper parameter to control the switch
Adds <i> and </i> tags to list-item text or to implied <p>..</p> text. Mixed not supported.


For italic style, can't do ''{{lang|xx|text}}'' without using <span/> tags when text is italic because of -Latn, |italic=yes,
]]
or auto-italics because the wrapping wikimarkup produces this:
<i><i lang="xx">text</i></i>
which is later reduced to this:
<i>text</i>
This reduction happens in some sort of cleanup process outside the scope of this template/module.


Until or unless this is fixed italic text must be:
local function div_markup_add (text, style)
<i><span lang="xx">text</span></i>
if text:find ('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
if 'italic' == style then
return text:gsub ('(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>'); -- insert italic markup at each list item
else
return text;
end
end
 
if text:find ('\n+') then -- look for any number of \n characters in text
text = text:gsub ('([^\n])\n([^\n])', '%1 %2'); -- replace single newline characters with a space character which mimics MediaWiki
 
if 'italic' == style then
text = text:gsub('[^\n]+', '<p><i>%1</i></p>'); -- insert p and italic markup tags at each 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
 
 
--[[--------------------------< T I T L E _ W R A P P E R _ M A K E >------------------------------------------
 
Makes a <span title="<title text>"><content_text></span> or <div title="<title text>"><content_text></div> where
<title text> is in the tool-tip in the wiki's local language and <content_text> is non-local-language text in
HTML markup.  This because the lang= attribute applies to the content of its enclosing tag.
 
<tag> holds a string 'div' or 'span' used to choose the correct wrapping tag.
 
]]
 
local function title_wrapper_make (title_text, content_text, tag)
local wrapper_t = {};
 
table.insert (wrapper_t, table.concat ({'<', tag})); -- open opening wrapper tag
table.insert (wrapper_t, ' title=\"'); -- begin title attribute
table.insert (wrapper_t, title_text); -- add <title_text>
table.insert (wrapper_t, '\">'); -- end title attribute and close opening wrapper tag
table.insert (wrapper_t, content_text); -- add <content_text>
table.insert (wrapper_t, table.concat ({'</', tag, '>'})); -- add closing wrapper tag
 
return table.concat (wrapper_t); -- make a big string and done
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
 
The lang= attribute also applies to the content of the tag where it is placed so this is wrong because 'Spanish
language text' is English:
<i lang="es" title="Spanish language text">casa</i>
should be:
<span title="Spanish language text"><i lang="es">casa</i></span>
or for <div>...</div>:
<div title="Spanish language text"><div lang="es"><spanish-language-text></div></div>


]]
]]


local function make_text_span (code, text, rtl, style, size, language)
local function make_text_html (code, text, tag, rtl, style, size, language)
local span = {};
local html_t = {};
local style_added = '';
local style_added = '';
local wrapper_tag = tag; -- <tag> gets modified so save a copy for use when/if we create a wrapper span or div


if text:match ('^%*') then
if text:match ('^%*') then
table.insert (span, '&#42;'); -- move proto language text prefix outside of italic markup if any; use numeric entity because plan splat confuses MediaWiki
table.insert (html_t, '&#42;'); -- move proto language text prefix outside of italic markup if any; use numeric entity because plain splat confuses MediaWiki
text = text:gsub ('^%*', ''); -- remove the splat from the text
text = text:gsub ('^%*', ''); -- remove the splat from the text
end
end


if 'italic' == style then
if 'span' == tag then -- default HTML tag for inline content
table.insert (span, '<i>'); -- open italic style tag
if 'italic' == style 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
end
table.insert (span, table.concat ({'<span lang="'})); -- open <span> tag
table.insert (span, table.concat ({code, '\"'})); -- add language attribute


if rtl then
table.insert (html_t, table.concat ({'<', tag})); -- open the <i>, <span>, or <div> HTML tag
table.insert (span, ' dir="rtl"'); -- add direction attribute for right to left languages
code = code:gsub ('%-x%-.*', ''); -- strip private use subtag from code tag because meaningless outside of Wikipedia
table.insert (html_t, table.concat ({' lang="', code, '\"'})); -- add language attribute
 
if (rtl or unicode.is_rtl(text)) and ('ltr' == this_wiki_lang_dir) then -- text is right-to-left on a left-to-right wiki
table.insert (html_t, ' dir="rtl"'); -- add direction attribute for right-to-left languages
elseif not (rtl or unicode.is_rtl(text)) and ('rtl' == this_wiki_lang_dir) then -- text is left-to-right on a right-to-left wiki
table.insert (html_t, ' dir="ltr"'); -- add direction attribute for left-to-right languages
end
end


if 'normal' == style then -- when |italic=no
if 'normal' == style then -- when |italic=no
table.insert (span, ' style=\"font-style:normal;'); -- override external markup, if any
table.insert (html_t, ' style=\"font-style: normal;'); -- override external markup, if any
style_added = '\"'; -- remember that style attribute added and is not yet closed
style_added = '\"'; -- remember that style attribute added and is not yet closed
end
end
第492行: 第655行:
if is_set (size) then -- when |size=<something>
if is_set (size) then -- when |size=<something>
if is_set (style_added) then
if is_set (style_added) then
table.insert (span, table.concat ({' font-size:', size, ';'})); -- add when style attribute already inserted
table.insert (html_t, table.concat ({' font-size: ', size, ';'})); -- add when style attribute already inserted
else
else
table.insert (span, table.concat ({' style=\"font-size:', size, ';'})); -- create style attribute
table.insert (html_t, table.concat ({' style=\"font-size: ', size, ';'})); -- create style attribute
style_added = '\"'; -- remember that style attribute added and is not yet closed
style_added = '\"'; -- remember that style attribute added and is not yet closed
end
end
end
end


if is_set (language) then
table.insert (html_t, table.concat ({style_added, '>'})); -- close the opening HTML tag
table.insert (span, table.concat ({style_added, ' title=\"', language})); --start the title text
table.insert (html_t, text); -- insert the text
if language:find ('languages') then
 
table.insert (span, ' collective text\"'); -- for collective languages
table.insert (html_t, table.concat ({'</', tag, '>'})); -- close the 'text' <i>, <span>, or <div> HTML tag
else
 
table.insert (span, ' language text\"'); -- for individual languages
if is_set (language) then -- create a <title_text> string for the title= attribute in a wrapper span or div
end
local title_text;
table.insert (span, '>'); -- close the opening span tag
if 'zxx' == code then -- special case for this tag 'no linguistic content'
title_text = substitute ('$1$2', {language, cfg.make_text_html_t.zxx}); -- not a language so don't use 'language' in title text
elseif mw.ustring.find (language, '语系', 1, true) then
title_text = substitute ('$1$2', {language, cfg.make_text_html_t.collective}); -- for collective languages
else
title_text = substitute ('$1$2', {language, cfg.make_text_html_t.individual}); -- for individual languages
end
 
return title_wrapper_make (title_text, table.concat (html_t), wrapper_tag);
else
else
table.insert (span, table.concat ({style_added, '>'})); -- close the style attribute and close opening span tag
return table.concat (html_t);
end
end
table.insert (span, text); -- insert the text
end


table.insert (span, '</span>'); -- close the <span> tag
-- 中文版添加,实现#ifexist
if 'italic' == style then
local function page_exists (title)
table.insert (span, '</i>'); -- close italic style tag
local noError, titleObject = pcall (mw.title.new, title)
end
if not noError then
return false
if rtl then -- legacy; shouldn't be necessary because all of the rtl text is wrapped in <span dir="rtl">text</span>
else
table.insert (span, '&lrm;'); -- make sure the browser knows that we're at the end of the rtl
if titleObject then
return titleObject.exists
else
return false
end
end
end
return table.concat (span); -- put it all together and done
end
end


第530行: 第703行:
[[Category:Articles containing <language>-language text]]
[[Category:Articles containing <language>-language text]]


for English:
For English:
[[Category:Articles containing explicitly cited English-language text]]
[[Category:Articles containing explicitly cited English-language text]]
for artificial languages (code: art)
[[Category:Articles containing constructed-language text]]


for ISO 639-2 collective languages (and for 639-1 bh):
For ISO 639-2 collective languages (and for 639-1 bh):
[[Category:Articles with text from the <language> languages collective]]
[[Category:Articles with text in <language> languages]]
 
注意:此处有修改
 
对于中文(zh、zh-*):
 
如果[[Module:Lang/data]]没有额外定义变体名称(即取得的语言名称是「中文」),则返回以下分类:
[[Category:含有明确引用中文的条目]]
 
反之,则返回以下分类:
[[Category:含有<变体>的条目]]
 
对于非中文内容:
 
如果存在对应语言的分类,则返回以下分类:
[[Category:含有<语言>的条目]]
 
反之,则返回以下分类:
[[Category:含有非中文内容的条目]]


]=]
]=]


local function make_category (code, language_name, nocat)
local function make_category (code, language_name, nocat, name_get)
local cat = {};
if ((0 ~= namespace) or nocat) and not name_get then -- only categorize in article space
if (0 ~= namespace) or nocat then -- only categorize in article space
return ''; -- return empty string for concatenation
return ''; -- return empty string for concatenation
end
end
 
if language_name:find ('languages') then
-- 中文版无
return table.concat ({'[[Category:Articles with text from the ', language_name, ' collective]]'});
-- if mw.ustring.find (language_name, '语系', 1, true) then
end
-- return substitute ('[[$1 $2]]', {cfg.make_category_t.collective_cat, language_name});
-- end
table.insert (cat, '[[Category:含有');
 
if this_wiki_lang_tag == code and language_name == '中文' then -- 名稱必須是「中文」
if 'en' == code then
return substitute ('[[$1$2$3$4]]', { -- unique category name for the local language
table.insert (cat, 'explicitly cited English');
cfg.make_category_t.cat_prefix,
elseif 'art' == code then
cfg.make_category_t.explicit_cat,
table.insert (cat, 'constructed')
language_name,
cfg.make_category_t.cat_postfix,
});
elseif (page_exists (substitute ('$1$2$3', {
cfg.make_category_t.cat_prefix,
language_name,
cfg.make_category_t.cat_postfix,
}))) then
return substitute ('[[$1$2$3]]', { -- category for individual languages
cfg.make_category_t.cat_prefix,
language_name,
cfg.make_category_t.cat_postfix,
});
else
else
table.insert (cat, language_name);
return substitute ('[[$1$2$3]]', { -- 非中文内容
cfg.make_category_t.cat_prefix,
cfg.make_category_t.cat_nonezh,
cfg.make_category_t.cat_postfix,
});
end
end
table.insert (cat, '的条目]]');
return table.concat (cat);
end
end


第570行: 第768行:
--[[--------------------------< 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
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
The value |script= is not used in {{transliteration}} 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
are listed in the {{transliteration}} 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.
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()
第583行: 第781行:
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 {{transliteration}}, 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;
local title_t = lang_data.translit_title_table; -- table of transliteration standards and the language codes and scripts that apply to those standards
local tout = {};
local title_text = ''; -- tool tip text for title= attribute
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 (code) then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
if not style then -- nil for is the default italic style
table.insert (tout, "<span lang=\""); -- so use <span> tag
else
table.insert (tout, table.concat ({'<span style=\"font-style:', style, '\" lang=\"'})); -- non-standard style, construct a span tag for it
end
table.insert (tout, code);
table.insert (tout, "-Latn\" title=\""); -- transliterations are always Latin script
else
table.insert (tout, "<span title=\""); -- when no language code: no lang= attribute, not italic ({{transl}} only)
end
std = std and std:lower(); -- lower case for table indexing
std = std and std:lower(); -- lower case for table indexing
 
if not is_set (std) and not is_set (tscript) then -- when neither standard nor script specified
if not is_set (std) and not is_set (tscript) then -- when neither standard nor script specified
table.insert (tout, language_name); -- write a generic tool tip
title_text = language_name; -- write a generic tool tip
if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
title_text = substitute ('$1$2', {title_text, cfg.lang_xx_t.romanization}); -- 中文版添加
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
-- 中文版不需要
end
-- if not mw.ustring.find (language_name, 'languages', 1, true) then -- collective language names (plural 'languages' is part of the name)
table.insert (tout, ' transliteration'); -- finish the tool tip
-- title_text = substitute ('$1-$2', {title_text, cfg.misc_text_t.language}); -- skip this text (individual and macro languages only)
-- end
-- title_text = substitute ('$1 $2', {title_text, mw.ustring.lower (cfg.engvar_t[engvar]['romanisz_lc'])}); -- finish the tool tip; use romanization when neither script nor standard supplied
 
elseif is_set (std) and is_set (tscript) then -- when both are specified
elseif is_set (std) and is_set (tscript) then -- when both are specified
if title_table[std] then -- and if standard is legitimate
if title_t[std] then -- and if standard is legitimate
if title_table[std][tscript] then -- and if script for that standard is legitimate
if title_t[std][tscript] then -- and if script for that standard is legitimate
table.insert (tout, table.concat ({title_table[std][tscript:lower()], ' (', lang_name_table.script[tscript][1], ' script) transliteration'})); -- add the appropriate text to the tool tip
if script_table[tscript] then
title_text = substitute ('$1$2($3)$4', { -- add the appropriate text to the tool tip
title_text,
title_t[std][tscript:lower()],
script_table[tscript],
cfg.make_translit_t.transliteration,
});
else
title_text = title_text .. title_t[std]['default']; -- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?
end
else
else
table.insert (tout, title_table[std]['default']); -- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?
title_text = title_text .. title_t[std]['default']; -- use the default if script not in std table; TODO: maint cat? error message because script not found for this standard?
end
end
else
else
return ''; -- invalid standard, setup for error message
return translit
end
end


elseif is_set (std) then -- translit-script not set, use language code
elseif is_set (std) then -- translit-script not set, use language code
if not title_table[std] then return ''; end -- invalid standard, setup for error message
if not title_t[std] then
return translit
if title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
end
table.insert (tout, table.concat ({title_table[std][code:lower()], ' (', lang_name_table.lang[code][1], ' language) transliteration'})); -- add the appropriate text to the tool tip
 
if title_t[std][code] then -- if language code is in the table (transl may not provide a language code)
title_text = substitute ('$1$2($3)$4', { -- add the appropriate text to the tool tip
title_text,
title_t[std][code:lower()],
language_name,
cfg.make_translit_t.transliteration,
});
else -- code doesn't match
else -- code doesn't match
table.insert (tout, title_table[std]['default']); -- so use the standard's default
title_text = title_text .. title_t[std]['default']; -- so use the standard's default
end
end
else -- here if translit-script set but translit-std not set
else -- here if translit-script set but translit-std not set
if title_table['no_std'][tscript] then
if title_t['no_std'][tscript] then
table.insert (tout, title_table['no_std'][tscript]); -- use translit-script if set
title_text = title_text .. title_t['no_std'][tscript]; -- use translit-script if set
elseif title_table['no_std'][code] then
elseif title_t['no_std'][code] then
table.insert (tout, title_table['no_std'][code]); -- use language code
title_text = title_text .. title_t['no_std'][code]; -- use language code
else
else
if is_set (tscript) then
if is_set (tscript) then
table.insert (tout, table.concat ({language_name, '-script transliteration'})); -- write a script tool tip
title_text = substitute ('$1$2-$3$4', { -- write a script tool tip
elseif is_set (code) then
title_text,
if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
language_name,
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
cfg.make_translit_t.script,
end
cfg.make_translit_t.transliteration,
table.insert (tout, ' transliteration'); -- finish the tool tip
});
-- 中文版不需要
-- elseif is_set (code) then
-- if not mw.ustring.find (language_name, 'languages', 1, true) then -- collective language names (plural 'languages' is part of the name)
-- title_text = substitute ('$1-$2', { -- skip this text (individual and macro languages only)
-- title_text,
-- cfg.misc_text_t.language,
-- });
-- end
-- title_text = substitute ('$1 $2', { -- finish the tool tip
-- title_text,
-- cfg.make_translit_t.transliteration,
-- });
else
else
table.insert (tout, ' transliteration'); -- generic tool tip (can we ever get here?)
title_text = substitute ('$1$2', { -- generic tool tip (can we ever get here?)
title_text,
cfg.make_translit_t.transliteration,
});
end
end
end
end
end
end


table.insert (tout, '">');
local tag
table.insert (tout, translit);
if is_set (code) then -- when a language code is provided (always with {{lang-??}} templates, not always with {{transliteration}})
if is_set (code) and not style then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
code = code:match ('^(%a%a%a?)'); -- strip all subtags leaving only the language subtag
table.insert (tout, "</i>"); -- close the italic tag
if not style then -- 中文版默认不应用斜体
tag = '<span lang="%s-Latn">%s</span>'
else
tag = '<span style="font-style: %s" lang="%s-Latn">%s</span>' -- non-standard style, construct a span tag for it
tag = string.format(tag, style, "%s", "%s")
end
tag = string.format(tag, code, "%s")
else
tag = '<span>%s</span>' -- when no language code: no lang= attribute, not italic ({{transliteration}} only)
end
 
tag = string.format(tag, translit) -- add the translit text
if '' == title_text then -- when there is no need for a tool-tip
return tag; -- done
else
else
table.insert (tout, "</span>"); -- no language code so close the span tag
-- 中文版不需要
-- title_text = cfg.engvar_sel_t.gb == engvar and title_text:gsub ('([Rr]omani)z', '%1s') or title_text; -- gb eng when engvar specifies gb eng; us eng else
return title_wrapper_make (title_text, tag, 'span'); -- wrap with a tool-tip span and done
end
end
return table.concat (tout);
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. The tests are for empty or missing text and for improper or disallowed use of apostrophe markup.
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
either as ''itself''' or as '''''bold italic'''''.
either as ''itself'' or as '''''bold italic''''' unless |italic=unset or |italic=invert.


]=]
]]


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 ('无文本', args, template);
make_error_msg (cfg.validate_text_t.no_text, args, template)
args.text = ''
return
end
end


if args.text:find ("%f[\']\'\'\'\'%f[^\']") or args.text:find ("\'\'\'\'\'[\']+") then -- because we're looking, look for 4 appostrophes or 6+ appostrophes
if args.text:find ("%f[\']\'\'\'\'%f[^\']") or args.text:find ("\'\'\'\'\'[\']+") then -- because we're looking, look for 4 appostrophes or 6+ appostrophes
return make_error_msg ('文本有格式不正确的标记', args, template);
make_error_msg (cfg.validate_text_t.malformed_markup, args, template)
return
end
end


local style = args.italic or args.italics;
local style = args.italic or args.italics or args.i;


-- if ('unset' ~= args.italic) and ('unset' ~= args.italics) then -- allow italic markup when |italic=unset or |italics=unset
-- 中文版修改:|italic=no 和未指定 |italic= 時不檢查斜體標記
if ('unset' ~= style) and ('invert' ~=style) then
if style and (cfg.keywords_t.unset ~= style) and (cfg.keywords_t.negative ~= style) and (cfg.keywords_t.invert ~= style) then
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 ('文本有斜体标记', args, template);
make_error_msg (cfg.validate_text_t.italic_markup, args, template)
return
end
end
end
end
第692行: 第931行:
--[[--------------------------< R E N D E R _ M A I N T >------------------------------------------------------
--[[--------------------------< R E N D E R _ M A I N T >------------------------------------------------------


render mainenance messages and categories
Render mainenance messages and categories.


]]
]]


local function render_maint(nocat)
local function render_maint (nocat)
local maint = {};
local maint = {};
 
if 0 < #maint_msgs then -- when there are maintenance messages
if 0 < #maint_msgs then -- when there are maintenance messages
table.insert (maint, table.concat ({'<span class="lang-comment" style="font-style:normal; display:none; color:#33aa33; margin-left:0.3em">'})); -- opening <span> tag
table.insert (maint, table.concat ({'<span class="lang-comment" style="font-style: normal; display: none; color: #33aa33; margin-left: 0.3em;">'})); -- opening <span> tag
for _, msg in ipairs (maint_msgs) do
for _, msg in ipairs (maint_msgs) do
table.insert (maint, table.concat ({msg, ' '})); -- add message strings
table.insert (maint, table.concat ({msg, ''})); -- add message strings
end
end
table.insert (maint, '</span>'); -- close the span
table.insert (maint, '</span>'); -- close the span
end
end
 
if (0 < #maint_cats) and (0 == namespace) and not is_set (nocat) then -- when there are mainenance categories; article namespace only
if (0 < #maint_cats) and (0 == namespace) and not nocat then -- when there are maintenance categories; article namespace only
for _, cat in ipairs (maint_cats) do
for _, cat in ipairs (maint_cats) do
table.insert (maint, table.concat ({'[[Category:', cat, ']]'})); -- format and add the categories
table.insert (maint, table.concat ({'[[Category:', cat, ']]'})); -- format and add the categories
end
end
end
end
 
return table.concat (maint);
return table.concat (maint);
end
end
第719行: 第958行:
--[[--------------------------< 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 a splat. We do that here as a flag for make_text_span() so that a splat
For proto languages, text is prefixed with a splat. We do that here as a flag for make_text_html() so that a splat
will be rendered outside of italic markup (if used). If the first character in text here is already a splat, we
will be rendered outside of italic markup (if used). If the first character in text here is already a splat, we
do nothing
do nothing.
 
proto_param is boolean or nil; true adds splat prefix regardless of language name; false removes and inhibits
regardless of language name; nil does nothing; presumes that the value in text is correct but removes extra splac.
 
]]
 
local function proto_prefix (text, language_name, proto_param)
if false == proto_param then -- when forced by |proto=no
return text:gsub ('^%**', ''); -- return text without splat prefix regardless of language name or existing splat prefix in text
elseif (language_name:find ('^原始') or (true == proto_param)) then -- language is a proto or forced by |proto=yes
return text:gsub ('^%**', '*'); -- prefix proto-language text with a splat; also removes duplicate prefixing splats
end
 
return text:gsub ('^%*+', '*'); -- return text unmolested except multiple splats reduced to one splat
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 stripmarker because it is not possible for this code to know
the content that will replace the stripmarker.
 
]]
 
local function has_poem_tag (text)
return text:find ('\127[^\127]*UNIQ%-%-poem%-[%a%d]+%-QINU[^\127]*\127') and true or false;
end
 
 
--[[--------------------------< H T M L _ T A G _ S E L E C T >------------------------------------------------
 
Inspects content of and selectively trims text.  Returns text and the name of an appropriate HTML tag for text.
 
If text contains:
\n\n text has implied <p>..</p> tags - trim leading and trailing whitespace and return
If text begins with list markup:
\n* unordered
\n; definition
\n: definition
\n# ordered
trim all leading whitespace except  \n and trim all trailing whitespace
 
If text contains <poem>...</poem> stripmarker, return text unmodified and choose <div>..</div> tags because
the stripmarker is replaced with text wrapped in <div>..</div> tags.
 
If the text contains any actual <div>...</div> tags, then it's again returned unmodified and <div>...</div>
tags are used to wrap it, to prevent div/span inversion.
 
]]
 
local function html_tag_select (text)
local tag;
 
if has_poem_tag (text) then -- contains poem stripmarker (we can't know the content of that)
tag = 'div'; -- poem replacement is in div tags so lang must use div tags
elseif text:find ('<div') then -- reductive; if the text contains a div tag, we must use div tags
tag = 'div';
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 nil with <proto_param> as second
return value for use in error message.
 
]]
 
local function validate_proto (proto_param)
if cfg.keywords_t.affirmative == proto_param then
return true;
elseif cfg.keywords_t.negative == proto_param then
return false;
elseif is_set (proto_param) then
return nil, proto_param; -- |proto= something other than 'yes' or 'no'
else
return nil; -- missing or empty
end
end
 
 
--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------
 
Common function to return language name from the data set according to IETF tag.
 
Returns language name if found in data tables; nil else.


]]
]]


local function proto_prefix (text, language_name)
local function language_name_get (ietf, code, cat)
if language_name:find ('^Proto%-') and not text:find ('^*') then -- language is a proto and text does not already have leading splat
ietf = ietf:lower(); -- ietf:lower() because format_ietf_tag() returns mixed case
return table.concat ({'*', text}); -- prefix proto language text with a splat
 
local name; -- remains nil if not found
 
if override_table[ietf] then -- look for whole IETF tag in override table
name = override_table[ietf];
elseif override_table[code] then -- not there so try basic language tag
name = override_table[code];
elseif lang_table[code] then -- shift to IANA active tag/name table
name = lang_table[code];
elseif lang_dep_table[code] then -- try the IANA deprecated tag/name table
name = lang_dep_table[code];
end
end
 
return text;
if lang_dep_table[code] and cat then -- because deprecated code may have been overridden to en.wiki preferred name
table.insert (maint_cats, substitute (cfg.language_name_get_t.deprecated_cat, {code}));
table.insert (maint_msgs, substitute (cfg.language_name_get_t.deprecated_msg, {code}));
end
 
return name; -- name from data tables or nil
end
 
 
--[[--------------------------< T E X T _ S C R I P T _ M A T C H _ T E S T >----------------------------------
 
IETF script subtag should match the script of the <text>.  This module does not attempt to know all scripts and
what they look like.  It does know what Latn script looks like so when <text> is written using other than the Latn
script, the IETF script subtag, if present, should not be Latn.
 
Conversely, when <text> is written using the Latn script, the IETF script subtag, if present, should be Latn.
 
For the purposes of this test, Latf (Fraktur) and Latg (Gaelic) are considered to be equivalent to Latn because
unicode treats these two scripts as font-specific variants of Latn.
 
Returns an error message when mismatch detected; nil else.
 
]]
 
local function text_script_match_test (script, is_latn_text, pos, char)
local scripts_t = {['latf'] = true, ['latg'] = true, ['latn'] = true}; -- unicode 'latn' scripts; 'latf' and 'latg' are font variants so there are no Fraktur or Gaelic codepoints
if is_set (script) then -- don't bother with the rest of this if <script> is nil or empty string
script = script:lower(); -- lower case to index into <scripts_t>
if is_latn_text then -- when text is wholly Latn script
if not scripts_t[script] then -- but a non-Latn script is specified
return cfg.text_script_match_test_t.latn_txt_mismatch; -- emit an error message
end
else -- when text is not wholly Latn script
if scripts_t[script] then -- but a Latn script is specified
return substitute (cfg.text_script_match_test_t.latn_scr_mismatch, {pos, char}); -- emit an error message with position of first offending character
end
end
end
end
 
 
--[[--------------------------< B I N A R Y _ S E A R C H >---------------------------------------------------
 
conducts a binary search of <ranges_t> for a sub-range that holds <target>.
 
returns boolean true if a sub-range holding <target> is found; boolean false else.
 
]]
 
local function binary_search (target, ranges_t)
local idx_bot = 1; -- initialize to index of first key
local idx_top = sizeof_ranges_t; -- initialize to index of last key (number of keys)
 
if (target < ranges_t[idx_bot][1]) or (target > ranges_t[idx_top][2]) then -- invalid; target out of range
return; -- abandon
end
 
local idx_mid; -- calculated index of range midway between top index and bottom index
local flag = false; -- flag to tell us when we've evaluated last (highest) range in <ranges_t>
 
while 1 do
idx_mid = math.ceil ((idx_bot + idx_top) / 2); -- get the mid-point in the <ranges_t> sequence
if (target >= ranges_t[idx_mid][1]) and (target <= ranges_t[idx_mid][2]) then -- indexed range low value <= target <= indexed range high value
return true; -- we found the range that holds the <target> character; return true
 
elseif (target > ranges_t[idx_mid][2]) then -- is <target> > indexed range high value?
idx_bot = idx_mid; -- adjust <idx_bot> up
 
else -- here when <target> less than indexed range low value
idx_top = idx_mid - 1; -- adjust <idx_top> down
end
 
if flag then
break; -- here when we just evaluated the last range and <target> not found
end
 
if not flag and (idx_bot == idx_top) then -- set true just before we evaluate the last (highest) range in <ranges_t>
flag = true;
end
end
end
 
 
--[[--------------------------< I S _ L A T I N >--------------------------------------------------------------
 
compare <text> as codepoints to lists of known codepoints accepted as Latn script
 
returns boolean true and modified <text> when <text> is wrapped in accept-as-written markup
 
returns boolean true and <text> when codepoint is known
 
returns boolean false, <text>, non-Latn codepoint position in <text> (left to right), and the codepoint character
when codepoint is not known
 
TODO: when text has accept-as-written markup, return a non-boolean value to indicate that <text> is not wholly
latn script?  Use that return value to create non-Latn HTML lang= attribute because <text> isn't really
latn so lang=und (undetermined)? or instead, omit the -Latn subtag? (without -Latn need to force |italic=yes)
 
]]
 
local function is_latin (text, tag)
local count;
text, count = text:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-as-written markup if present
if 0 ~= count then
return true, text; -- markup present so assume that <text> is Latn-script
end
 
local pos = 0; -- position counter for error messaging
for codepoint in mw.ustring.gcodepoint (text) do -- fetch each code point
pos = pos + 1; -- bump the position counter
 
if not is_latn_data.singles_t[codepoint] and -- codepoint not found in the singles list?
not binary_search (codepoint, is_latn_data.ranges_t) and -- codepoint not a member of a listed range?
not (tag and is_latn_data.specials_t[codepoint] and is_latn_data.specials_t[codepoint][tag]) then -- not a language-specific codepoint?
return false, text, pos, mw.ustring.char (codepoint); -- codepoint not known; return false with codepoint position and character representation
end
end
return true, text; -- is known; return <text>
end
end




--[[--------------------------< L A N G >----------------------------------------------------------------------
--[[--------------------------< 处 理 中 文 文 本 转 换 >--------------------------------------------------------------
 
该函数用于判断输入的语言代码是否属于中文(包括汉语方言),并决定是否需要禁用繁简转换。
 
 
功能:
- 如果语言代码指定为无变体的中文代码 `zh-` 和其他以汉字作为书写系统的汉语方言文字(如粤语、吴语、赣语、文言文等),则返回原文本,不做任何修改。
- 如果语言代码不属于中文或为中文变体(以 `zh-` 开头),则在文本外添加 `-{}-`,以阻止繁简转换。
 
参数:
- `code` (string): 语言代码(如 `"zh"`、`"gan"`、`"yue"`、`"en"`)。
- `text` (string): 需要处理的文本。
 
返回值:
- (string) 处理后的文本。
 
]]
 
local function chinese_conversion(code, text)
-- 定义属于中文及相关方言的语言代码
local chinese_codes = { zh = true, gan = true, wuu = true, yue = true, lzh = true, hsn = true }
 
if chinese_codes[code] then
return text
else
return '-{' .. text .. '}-'
end
end
 
--[[--------------------------< _ L A N G >--------------------------------------------------------------------


entry point for {{lang}}
Entry point for {{lang}}.


there should be no reason to set parameters in the {{lang}} {{#invoke:}}
There should be no reason to set parameters in the {{lang}} {{#invoke:}}
<includeonly>{{#invoke:lang|lang}}</includeonly>
<includeonly>{{#invoke:lang|lang}}</includeonly>


parameters are recieved from the template's frame (parent frame)
Parameters are received from the template's frame (parent frame).


]]
]]


function p.lang (frame)
local function _lang (args)
local args = getArgs(frame);
local out = {};
local out = {};
local language_name; -- used to make category names
local language_name; -- used to make category names
local category_name; -- same as language_name except that it retains any parenthetical disambiguators (if any) from the data set
local subtags = {}; -- IETF subtags script, region, variant, and private
local subtags = {}; -- IETF subtags script, region, variant, and private
local code; -- the language code
local code; -- the language code
local msg; -- for error messages
local msg; -- for error messages
local tag = 'span'; -- initial value for make_text_html()
local template = args.template or cfg.templates_t.lang;
maint_cats = {}; -- initialize because when this module required into another module, these only declared once so only initialzed once
maint_msgs = {};
error_msgs = {}
validate_cat_args (args); -- determine if categorization should be suppressed


if args[1] and args.code then
if args[1] and args.code then
return make_error_msg ('冲突:{{{1}}} 和 &#124;code=', args, 'lang');
make_error_msg (substitute (cfg.lang_t.conflict_n_param, {'1', cfg.lang_t.conflict_n_param_types.code}), args, template)
else
args.code = args[1] or args.code; -- prefer args.code
end
end
args.code = args[1] or args.code; -- prefer args.code


if args[2] and args.text then
if args[2] and args.text then
return make_error_msg ('冲突:{{{2}}} 和 &#124;text=', args, 'lang');
make_error_msg (substitute (cfg.lang_t.conflict_n_param, {'2', cfg.lang_t.conflict_n_param_types.text}), args, template)
else
args.text = args[2] or args.text; -- prefer args.text
end
end
args.text = args[2] or args.text; -- prefer args.text
msg = validate_text ('lang', args); -- ensure that |text= is set  (italic test disabled for the time being)
 
if is_set (msg) then -- msg is an already-formatted error message
validate_text (template, args)
return msg;
 
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate HTML tag with text trimmed accordingly
 
args.rtl = args.rtl == cfg.keywords_t.affirmative; -- convert to boolean: 'yes' -> true, other values -> false
 
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
return make_error_msg (substitute (cfg.lang_t.invalid_proto, {msg}), args, template);
end
end
args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false


code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (args.code); -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (args.code); -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})


if msg then
if msg then
return make_error_msg ( msg, args, 'lang');
make_error_msg (msg, args, template)
msg = nil
code = code or ''
end
end


args.italic, msg = validate_italic (args.italic, args.italics);
local is_latn_text, pos, char;
is_latn_text, args.text, pos, char= is_latin (args.text, code); -- make a boolean
 
msg = text_script_match_test (subtags.script, is_latn_text, pos, char)
if msg then -- if an error detected then there is an error message
make_error_msg (msg, args, template)
msg = nil
end
 
args.italic, msg = validate_italic (args);
if msg then
if msg then
return make_error_msg (msg, args, 'lang');
make_error_msg (msg, args, template)
msg = nil
end
end


if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if ('latn' == subtags.script) or (p.is_latn (args.text) and 'en' ~= code) then -- script set to latn or text is wholly latn script but not rendering English
if ('latn' == subtags.script) or -- script is latn
args.italic = 'italic'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
(this_wiki_lang_tag ~= code and not is_set (subtags.script) and not has_poem_tag (args.text) and is_latn_text) then -- text not this wiki's language, no script specified and not in poem markup but is wholly latn script (auto-italics)
-- 中文版默认不应用斜体
args.italic = 'unset'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
else
else
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
end
end
end
end
 
if is_set (subtags.script) then -- if script set, override rtl setting
if is_set (subtags.script) then -- if script set, override rtl setting
if in_array (subtags.script, lang_data.rtl_scripts) then
if in_array (subtags.script, lang_data.rtl_scripts) then
第799行: 第1,319行:
end
end


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


if is_set (subtags.private) and lang_data.override[table.concat ({code, '-x-', subtags.private})] then -- look for private use tags; done this way because ...
if cfg.keywords_t.invert == args.italic and 'span' == tag then -- invert only supported for in-line content
language_name = lang_data.override[table.concat ({code, '-x-', subtags.private})][1]; -- ... args.code does not get private subtag
args.text = invert_italics (args.text)
elseif lang_data.override[code] then -- get the language name for categorization
language_name = lang_data.override[code][1] -- prefer language names taken from the override table
elseif lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end
end


if 'invert' == args.italic then
args.text = chinese_conversion (args.code, args.text) -- 中文版特化部分
args.text = invert_italics (args.text)
 
end
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat
args.text = proto_prefix (args.text, language_name); -- prefix proto-language text with a splat


table.insert (out, make_text_span (args.code, args.text, args.rtl, args.italic, args.size, language_name));
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, make_category (code, language_name, args.nocat));
table.insert (out, render_maint(args.nocat)); -- maintenance messages and categories
table.insert (out, render_maint (args.nocat)); -- maintenance messages and categories
 
if not args.noerror and error_msgs[1] then
table.insert(out, make_lang_error_span(table.concat(error_msgs)))
end


return table.concat (out); -- put it all together and done
return table.concat (out); -- put it all together and done
第823行: 第1,342行:




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


For the {{lang-xx}} templates, the only parameter required to be set in the template is the language code.  All
Parameters are received from the template's frame (parent frame).
other parameters can, usually should, be written in the template call.  For {{lang-xx}} templates for languages
 
]]
 
local function lang (frame)
local args_t = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text
valueFunc = function (key, value)
if 2 == key or 'text' == key then -- the 'text' parameter; do not trim wite space
return value; -- return untrimmed 'text'
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
if '' ~= value then -- empty string when value was only whitespace
return value;
end
end
return nil; -- value was empty or contained only whitespace
end -- end of valueFunc
});
 
args_t.fn = nil; -- unset because not supported but this function might have been called by {{lang|fn=lang|...}}
 
local msg = parameter_validate (args_t, cfg.templates_t.lang); -- verify that all supplied parameters are supported by {{lang-??}}
if args_t.noerror then
msg = ''
else
msg = msg and make_lang_error_span(make_error_msg(msg, args_t, cfg.templates_t.lang)) or ''
end
 
return _lang (args_t) .. msg
end
 
 
--[[--------------------------< T R A N S L A T I O N _ M A K E >----------------------------------------------
 
Stand-alone function to create literal translation of main text.
 
Also used by {{lang-x2}}.
 
]]
 
local function translation_make (args_t)
local translation_t = {','}; -- initialize output
 
if 'none' ~= args_t.label then -- if we want a label
table.insert (translation_t, '<small>'); -- open the <small> HTML tag
if cfg.keywords_t.negative == args_t.link then
table.insert (translation_t, cfg.translation_make_t.lit_xlation); -- unlinked form
else
table.insert (translation_t, make_wikilink (cfg.translation_make_t.lit_xlation)); -- linked form
end
table.insert (translation_t, ":</small>"); -- close the <small> HTML tag
end
table.insert (translation_t, table.concat ({'「', args_t.translation, '」'}));
return table.concat (translation_t); -- make a big string and done
end
 
 
--[[--------------------------< _ L A N G _ X X >--------------------------------------------------------------
 
For the {{lang-??}} 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-??}} 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 {{lang-xx}} template choose the appropriate entry-point function so that this function know the default
For each {{lang-??}} 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.


第841行: 第1,424行:
Supported parameters are:
Supported parameters are:
|code = (required) the IANA language code
|code = (required) the IANA language code
|script = IANA script code; especially for use with languages that use multiple writing systems; yields to the script subtag in |code= if present [not yet implemented]
|script = IANA script code; especially for use with languages that use multiple writing systems
|region = IANA region code
|region = IANA region code
|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') unlinks language specified by code to associated language article
|link = boolean false ('no') does not link code-spcified 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=
|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 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 {{lang-xx}} templates that support transliteration (those template where |text= is entirely latn script):
for those {{lang-??}} 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 {{lang-xx}}, the positional parameters are:
For {{lang-??}}, the positional parameters are:
{{{1}}} text
{{{1}}} text
{{{2}}} transliterated text
{{{2}}} transliterated text
第866行: 第1,450行:
]]
]]


local function _lang_xx (frame)
local function _lang_xx (args, base_template) -- base_template will be either of 'Langx' or 'Lang-xx'
local args = getArgs(frame, {parentFirst= true}); -- parameters in the template override parameters set in the {{#invoke:}}
local out = {};
local out = {};
local language_name; -- used to make display text, article links
local language_name; -- used to make display text, article links
第876行: 第1,459行:
local translit_script_name; -- name associated with IANA (ISO 15924) script code
local translit_script_name; -- name associated with IANA (ISO 15924) script code
local translit;
local translit;
local translit_title;
local msg; -- for error messages
local msg; -- for error messages
local tag = 'span'; -- initial value for make_text_html()
local template = args.template or base_template;


if args[1] and args.text then
maint_cats = {}; -- initialize because when this module required into another module, these only declared once so only initialzed once
return make_error_msg ('冲突:{{{1}}} 和 &#124;text=', args, 'lang-xx');
maint_msgs = {};
else
 
args.text = args[1] or args.text; -- prefer args.text
error_msgs = {}
 
local text_idx = (cfg.templates_t.langx == base_template) and 2 or 1; -- for {{langx}} 'text' positional parameter is '2'
local translit_idx = (cfg.templates_t.langx == base_template) and 3 or 2;
local xlate_idx = (cfg.templates_t.langx == base_template) and 4 or 3;
 
if args[text_idx] and args.text then
make_error_msg (substitute (cfg.lang_t.conflict_n_param, {text_idx, cfg.lang_t.conflict_n_param_types.text}), args, template)
end
end
args.text = args[text_idx] or args.text; -- prefer positional 'text' parameter
msg = validate_text ('lang-xx', args); -- ensure that |text= is set, does not contain italic markup and is protected from improper bolding
 
if is_set (msg) then
validate_text (template, args)
return msg;
 
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate HTML tag with text trimmed accordingly
 
if args[translit_idx] and args.translit then
make_error_msg (substitute (cfg.lang_t.conflict_n_param, {translit_idx, cfg.lang_t.conflict_n_param_types.translit}), args, template)
end
end
args.translit = args[translit_idx] or args.translit; -- prefer positional 'translit' parameter


if args[2] and args.translit then
if args[xlate_idx] and (args.translation or args.lit) then
return make_error_msg ('冲突:{{{2}}} 和 &#124;translit=', args, 'lang-xx');
make_error_msg (substitute (cfg.lang_xx_t.conflict_n_lit, {xlate_idx}), 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 ('冲突:{{{3}}} 和 &#124;lit= or &#124;translation=', args, 'lang-xx');
elseif args.translation and args.lit then
elseif args.translation and args.lit then
return make_error_msg ('冲突:&#124;lit= and &#124;translation=', args, 'lang-xx');
make_error_msg (cfg.lang_xx_t.conflict_lit, args, template)
else
args.translation = args[3] or args.translation or args.lit; -- prefer args.translation
end
end
args.translation = args[xlate_idx] or args.translation or args.lit; -- prefer positional 'translation' parameter


if args.links and args.link then
if args.links and args.link then
return make_error_msg ('冲突:&#124;links= and &#124;link=', args, 'lang-xx');
make_error_msg (cfg.lang_xx_t.conflict_link, args, template)
else
args.link = args.link or args.links; -- prefer args.link
end
end
args.link = args.link or args.links; -- prefer args.link


args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
validate_cat_args (args); -- determine if categorization should be suppressed
 
args.rtl = args.rtl == cfg.keywords_t.affirmative; -- convert to boolean: 'yes' -> true, other values -> false


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
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 -- if an error detected then there is an error message
if msg then -- if an error detected then there is an error message
return make_error_msg (msg, args, 'lang-xx');
make_error_msg (msg, args, template)
msg = nil
code = code or ''
end
 
if args.translit then
local latn, pos, char;
latn, args.translit, pos, char = is_latin (args.translit, (('' ~= subtags.private) and (code .. '-x-' .. subtags.private)) or code);
if not latn then
make_error_msg (substitute (cfg.lang_xx_t.translit_nonlatn, {pos, char}), args, template)
end
end
 
local is_latn_text, text, pos, char = is_latin (args.text, code); -- make a boolean
args.text = text; -- may have been modified (accept-as-written markup removed)
 
msg = text_script_match_test (subtags.script, is_latn_text, pos, char)
if msg then -- if an error detected then there is an error message
make_error_msg (msg, args, template)
msg = nil
end
end
 
args.italic, msg = validate_italic (args.italic, args.italics);
args.italic, msg = validate_italic (args);
if msg then
if msg then
return make_error_msg (msg, args, 'lang-xx');
make_error_msg (msg, args, template)
msg = nil
end
end


if nil == args.italic then -- args.italic controls
if cfg.templates_t.langx == base_template then -- auto-italics  for {{langx}} templates; adapted from {{lang}} (no support for poem tag)
if is_set (subtags.script) then
if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if 'latn' == subtags.script then
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
args.italic = 'italic'; -- |script=Latn; set for font-style:italic
end
else
 
args.italic = initial_style_state; -- italic not set; script is not latn; set for font-style:<initial_style_state>
else -- {{lang-xx}} does not do auto italics; retained for those wikis that don't support {{langx}}
end
if nil == args.italic then -- args.italic controls
else
args.italic = initial_style_state; -- here when |italic= and |script= not set; set for font-style:<initial_style_state>
args.italic = initial_style_state; -- here when |italic= and |script= not set; set for font-style:<initial_style_state>
end
end
end
end
 
if is_set (subtags.script) then -- if script set override rtl setting
if is_set (subtags.script) then -- if script set override rtl setting
if in_array (subtags.script, lang_data.rtl_scripts) then
if in_array (subtags.script, lang_data.rtl_scripts) then
第943行: 第1,552行:
end
end


args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant); -- format to recommended subtag styles
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
if is_set (subtags.private) and lang_data.override[table.concat ({code, '-x-', subtags.private})] then -- look for private use tags; done this way because ...
return make_error_msg (substitute (cfg.lang_t.invalid_proto, {args.proto}), args, template);
language_name = lang_data.override[table.concat ({code, '-x-', subtags.private})][1]; -- ... args.code does not get private subtag
elseif lang_data.override[args.code:lower()] then -- look for whole IETF tag in override table
language_name = lang_data.override[args.code:lower()][1]; -- args.code:lower() because format_ietf_tag() returns mixed case
elseif lang_data.override[code] then -- not there so try basic language code
language_name = lang_data.override[code][1];
elseif not is_set (subtags.variant) then
if lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end
else -- TODO: is this the right thing to do: take language display name from variants table?
if lang_name_table.variant[subtags.variant] then -- TODO: there is some discussion at Template talk:Lang about having a label parameter for use when variant name is not desired among other things
language_name = lang_name_table.variant[subtags.variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
end
end
end
args.code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles
language_name = language_name_get (args.code, code, true) or ''; -- get language name; try IETF tag first, then code w/o variant then code w/ variant


category_name = language_name; -- category names retain IANA parenthetical diambiguators (if any)
category_name = language_name; -- category names retain IANA parenthetical diambiguators (if any)
第969行: 第1,568行:
end
end
else
else
if 'no' == args.link then
if cfg.keywords_t.negative == args.link then
table.insert (out, language_name); -- language name without wikilink
table.insert (out, language_name); -- language name without wikilink
else
else
-- if language_name:find ('languages') then
-- 中文版不需要
table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
-- if mw.ustring.find (language_name, 'languages', 1, true) then
-- else
-- table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
-- table.insert (out, make_wikilink (language_name .. ' language', language_name)); -- language name with wikilink
-- elseif lang_data.article_name[args.code:lower()] then -- is IETF tag in article name over ride?
-- end
-- table.insert (out, make_wikilink (lang_data.article_name[args.code:lower()], language_name)); -- language name with wikilink from override data
if lang_data.article_name[code] then -- is language tag in article override
table.insert (out, make_wikilink (lang_data.article_name[code], language_name)); -- language name with wikilink from override data
else
table.insert (out, make_wikilink (language_name)); -- language name with wikilink
end
end
end
table.insert (out, ':'); -- separator
table.insert (out, ':'); -- separator
end
end


if 'invert' == args.italic then
if cfg.keywords_t.invert == args.italic then
args.text = invert_italics (args.text)
args.text = invert_italics (args.text)
end
end
args.text = proto_prefix (args.text, language_name); -- prefix proto-language text with a splat


table.insert (out, make_text_span (args.code, args.text, args.rtl, args.italic, args.size))
args.text = chinese_conversion (args.code, args.text) -- 中文版特化部分


if is_set (args.translit) and not p.is_latn (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat
 
table.insert (out, make_text_html (args.code, args.text, tag, args.rtl, args.italic, args.size, ('none' == args.label) and language_name or nil))
 
if is_set (args.translit) and not is_latn_text then -- transliteration; not supported when args.text is wholly latn text (this is an imperfect test)
table.insert (out, ','); -- comma to separate text from translit
table.insert (out, ','); -- comma to separate text from translit
if 'none' ~= args.label then
if 'none' ~= args.label then
table.insert (out, '<small>');
table.insert (out, '<small>');
if lang_name_table.script[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 = lang_name_table.script[args['translit-script'][1]];
translit_script_name = script_table[args['translit-script']];
else
else
translit_script_name = language_name; -- fall back on language name
translit_script_name = language_name; -- fall back on language name
end
end
translit_title = mw.title.makeTitle (0, table.concat ({translit_script_name, '罗马化'})); -- make a title object
 
if translit_title.exists and ('no' ~= args.link) then
local translit_title_obj = mw.title.makeTitle (0, substitute ('$2$1',{cfg.lang_xx_t.romanization, translit_script_name})); -- make a title object; no engvar, article titles use US spelling
table.insert (out, make_wikilink ((translit_script_name or language_name) .. '罗马化', '转写')); -- make a wikilink if there is an article to link to
if translit_title_obj.exists and (cfg.keywords_t.negative ~= args.link) then
table.insert (out, make_wikilink (substitute ('$2$1', {cfg.lang_xx_t.romanization, translit_script_name or language_name}),
substitute ('$1', {cfg.lang_xx_t.romanization})) .. ''); -- make a wikilink if there is an article to link to; engvar the display text
 
else
else
table.insert (out, '转写'); -- else define the abbreviation
table.insert (out, substitute ('$1:', {cfg.lang_xx_t.romanization})); -- else plain text per engvar
 
end
end
table.insert (out, '</small>'); -- close the small tag
table.insert (out, '</small>'); -- close the small tag
end
end
 
translit = make_translit (args.code, language_name, args.translit, args['translit-std'], args['translit-script'])
translit = make_translit (args.code, language_name, args.translit, args['translit-std'], args['translit-script'], nil)
if is_set (translit) then
if is_set (translit) then
table.insert (out, translit);
table.insert (out, translit);
else
else
return make_error_msg (table.concat ({'invalid translit-std: \'', args['translit-std'] or '[missing]'}), args, 'lang-xx');
make_error_msg (substitute ('$1:$2', {cfg.lang_xx_t.invalid_xlit_std, args['translit-std'] or '[missing]'}), args, template)
end
end
elseif is_set (args.translit) and is_latn_text then -- when creating a transliteration of Latn script <text>
make_error_msg (cfg.lang_xx_t.xlit_of_latn, args, template)
end
end
 
if is_set (args.translation) then -- translation (not supported in {{lang}})
if is_set (args.translation) then -- translation (not supported in {{lang}})
table.insert (out, ',');
table.insert (out, translation_make (args));
if 'none' ~= args.label then
table.insert (out, '<small>');
if 'no' == args.link then
table.insert (out, '直译');
else
table.insert (out, make_wikilink ('直译'));
end
table.insert (out, ":</small>");
end
table.insert (out, table.concat ({args.translation})); -- use html entities to avoid wiki markup confusion
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, render_maint(args.nocat)); -- maintenance messages and categories
table.insert (out, render_maint(args.nocat)); -- maintenance messages and categories
if not args.noerror and error_msgs[1] then
table.insert(out, make_lang_error_span(table.concat(error_msgs)))
end


return table.concat (out); -- put it all together and done
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.
Text positional parameters are not trimmed here but are selectively trimmed at html_tag_select().
]]
local function lang_xx_args_get (frame, base_template)
local args_t = getArgs(frame,
{
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}}
valueFunc = function (key, value)
if ((cfg.templates_t.langx == base_template) and 2 or 1) == key then -- the 'text' positional parameter; 1 for {{lang-??}}, 2 for {{langx}}; do not trim wite space
return value; -- return untrimmed 'text' positional parameter
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_t;
end
end


第1,038行: 第1,676行:
--[[--------------------------< 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 {{lang-xx}} templates that call lang_xx_italic(). Sets the initial style state to italic.
Entry point for those {{lang-??}} 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, cfg.templates_t.langxx);
args.fn = nil; -- unset because not supported but this function might have been called by {{lang|fn=lang_xx_italic|...}}
 
local msg = parameter_validate (args, cfg.templates_t.langxx); -- verify that all supplied parameters are supported by {{lang-??}}
 
if args.noerror then
msg = ''
else
msg = msg and make_lang_error_span(make_error_msg(msg, args, cfg.templates_t.langxx)) or ''
end
 
initial_style_state = args.italic_important and 'italic' or 'inherit'; -- 中文維基百科:忽略斜體(除非指定italic_important)
return _lang_xx (args, cfg.templates_t.langxx) .. msg .. '[[Category:使用Lang-xx模板的页面]]'
end
 
 
--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------
 
Entry point from another module. Sets the initial style state to italic.


]]
]]


function p.lang_xx_italic (frame)
local function _lang_xx_italic (args)
initial_style_state = 'italic';
initial_style_state = args.italic_important and 'italic' or 'inherit'; -- 中文維基百科:忽略斜體(除非指定italic_important)
return _lang_xx (frame);
return _lang_xx (args, cfg.templates_t.langxx);
end
end


第1,050行: 第1,711行:
--[[--------------------------< 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 {{lang-xx}} templates that call lang_xx_inherit(). Sets the initial style state to inherit.
Entry point for those {{lang-??}} 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, cfg.templates_t.langxx);
args.fn = nil; -- unset because not supported but this function might have been called by {{lang|fn=lang_xx_inherit|...}}
 
local msg = parameter_validate (args, cfg.templates_t.langxx); -- verify that all supplied parameters are supported by {{lang-??}}
 
if args.noerror then
msg = ''
else
msg = msg and make_lang_error_span(make_error_msg(msg, args, cfg.templates_t.langxx)) or ''
end
 
initial_style_state = 'inherit';
return _lang_xx (args, cfg.templates_t.langxx) .. msg .. '[[Category:使用Lang-xx模板的页面]]'
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.


]]
]]


function p.lang_xx_inherit (frame)
local function _lang_xx_inherit (args)
initial_style_state = 'inherit';
initial_style_state = 'inherit';
return _lang_xx (frame);
return _lang_xx (args, cfg.templates_t.langxx);
end
 
 
--[[--------------------------< _ L A N G X >------------------------------------------------------------------
 
Entry point from another module.
 
]]
 
local function _langx (args_t)
local langx_data = mw.loadData ('Module:Lang/langx'); -- get necessary data
local rtl_t = langx_data.rtl_t; -- get list of language tags for languages that are rendered right-to-left
local link_t = langx_data.link_t; -- get list of language tags for {{lang-??}} templates that set |link=<something>
local size_t = langx_data.size_t; -- get list of language tags for {{lang-??}} templates that set |size=<something>
 
error_msgs = {}
 
local msg = parameter_validate (args_t, cfg.templates_t.langx);
if msg then
make_error_msg (msg, args_t, cfg.templates_t.langx)
msg = nil
end
 
args_t.code = args_t[1] or args_t.code; -- get the language tag; must be {{{1}}} or |code=
if not args_t.code then
make_error_msg (cfg.get_ietf_parts_t.missing_lang_tag, args_t, cfg.templates_t.langx)
end
 
args_t.rtl = args_t.rtl or (rtl_t[args_t.code] and cfg.keywords_t.affirmative); -- prefer |rtl= in template call, use rtl_t else
args_t.link = args_t.link or link_t[args_t.code]; -- prefer |link= in template call, use link_t felse
args_t.size = args_t.size or size_t[args_t.code]; -- prefer |size= in template call, use size_t else
 
args_t[1] = nil; -- unset to mimic {{lang-??}} templates which set |code=xx
 
if not args_t.noerror and error_msgs[1] then
msg = make_lang_error_span(table.concat(error_msgs))
end
 
local lang_subtag = args_t.code; -- use only the base language subtag for unsupported tag test; some args_t.code are modified by |script= etc
return _lang_xx (args_t, cfg.templates_t.langx) .. (msg or '')
end
end




--[[--------------------------< N A M E _ F R O M _ C O D E >--------------------------------------------------
--[[--------------------------< L A N G X >--------------------------------------------------------------------
 
Entry point for {{langx}}.


Returns language name associated with IETF language tag if valid; empty string else.
this function calls _lang_xx() to render non-English text. The {{lang-??}} templates have three positional paramters
but {{langx}} has four:


All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
|  1 |  2 |  3 |  4
{{lang-xx |<text> |<transl> |<xlate> }}
{{langx |<tag> |<text> |<transl> |<xlate> }}
 
The calls to lang_xx_args_get() and _lang_xx() use 'Langx' as a flag for those functions to select the proper
positional parameters.
 
{{lang-??}} depends on the calling template to select 'inherit' or 'italic' to establish the default rendering.
 
{{langx}} can't do that.  The initial version of {{langx}} relied on a list of language tags (inherit_t in ~/langx)
scraped from those {{lang-??}} templates that call lang_xx_inherit() to render text in upright font. langx() now
uses auto-italics code adapted from {{lang}} (doesn't support poem tags).
 
]]
 
local function langx (frame)
local args_t = lang_xx_args_get (frame, cfg.templates_t.langx); -- get the arguments; 'Langx' is the <base_template> used to decide which positional param is 'text', 'translit', 'lit'
 
return _langx (args_t);
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-??}} templates are supported by this function.
 
Module entry point from another module.


]]
]]


function p.name_from_code (frame)
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; also get parent frame
end
 
 
--[[--------------------------< I S _ I E T F _ T A G _ F R A M E >--------------------------------------------
 
Module entry point from an {{#invoke:}}; same as is_ietf_tag() except does not get parameters from the parent
(template) frame.  This function not useful when called by {{lang|fn=is_ietf_tag_frame|<tag>}} because <tag>
is in the parent frame.
 
]]
 
local function is_ietf_tag_frame (frame)
return _is_ietf_tag (getArgs (frame, {frameOnly = true,})[1]); -- args[1] is the IETF language tag to be tested; do not get parent frame
end
 
 
--[[--------------------------< _ N A M E _ F R O M _ T A G >--------------------------------------------------
 
Returns language name associated with IETF language tag if valid; error message else.
 
All code combinations supported by {{lang}} and the {{lang-??}} templates are supported by this function.
 
Set invoke's |link= parameter to yes to get wikilinked version of the language name.
 
Module entry point from another module.
 
]]
 
local function _name_from_tag (args)
local subtags = {}; -- IETF subtags script, region, variant, and private
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = (frame.args and frame.args[1]) or frame; -- save a copy of the input
local raw_code = args[1]; -- save a copy of the input IETF subtag
local link = cfg.keywords_t.affirmative == args['link']; -- make a boolean
local label = args.label;
local code; -- the language code
local code; -- the language code
local msg; -- holds an error message (not used here) if IETF language tag is malformed or invalid
local msg; -- gets an error message if IETF language tag is malformed or invalid
local language_name = '';
local language_name = '';


code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code);
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code);
if msg then
if msg then
return '';
local template = (args['template'] and table.concat ({'{{', args['template'], '}}:'})) or ''; -- make template name (if provided by the template)
return make_error_span (template, msg);
end
 
raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles; private omitted because private
language_name = language_name_get (raw_code, code); -- get language name; try IETF tag first, then code w/o variant then code w/ variant
 
if 'yes' ~= args.raw then
language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
end
end


if lang_data.override[raw_code:lower()] then -- look for whole IETF tag in override table (force lower case)
if link then -- when |link=yes, wikilink the language name
language_name = lang_data.override[raw_code:lower()][1];
if mw.ustring.find (language_name, '语系', 1, true) then
elseif lang_data.override[code] then -- not there so try basic language code in override table
language_name = make_wikilink (language_name, label); -- collective language name uses simple wikilink
language_name = lang_data.override[code][1];
elseif lang_data.article_name[raw_code:lower()] then -- is IETF tag in article name override?
elseif not is_set (subtags.variant) then
language_name = make_wikilink (lang_data.article_name[raw_code:lower()], label or language_name); -- language name with wikilink from override data
if lang_name_table.lang[code] then
elseif lang_data.article_name[code] then -- is language tag in article name override?
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
language_name = make_wikilink (lang_data.article_name[code], label or language_name); -- language name with wikilink from override data
else
language_name = make_wikilink (language_name, label or language_name); -- language name with wikilink
end
end
else -- TODO: is this the right thing to do: take language display name from variants table?
end
if lang_name_table.variant[subtags.variant] then -- TODO: there is some discussion at Template talk:Lang about having a label parameter for use when variant name is not desired among other things
 
language_name = lang_name_table.variant[subtags.variant]['descriptions'][1]; -- table entries sometimes have multiple names, always take the first one
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>}}
return _name_from_tag (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame
end
 
 
--[[--------------------------< _ T A G _ F R O M _ N A M E >--------------------------------------------------
 
Returns the IETF language tag associated with the language name.  Spelling of language name must be correct
according to the spelling in the source tables.  When a standard language name has a parenthetical disambiguator,
that disambiguator must be omitted (they are not present in the data name-to-tag tables).
 
Module entry point from another module.
 
]]
 
local function _tag_from_name (args) -- entry point from another module
local msg;
 
if args[1] and '' ~= args[1] then
local data = mw.loadData ('Module:Lang/tag from name' .. sandbox); -- get the reversed data tables TODO: change when going live
local lang = args[1]:lower(); -- allow any-case for the language name (speeling must till be correct)
local tag = data.rev_override_table[lang] or data.rev_lang_table[lang] or data.rev_lang_dep_table[lang]; -- get the code; look first in the override then in the standard
 
if tag then
return tag, true; -- language name found so return tag and done; second return used by is_lang_name()
else
msg = substitute (cfg.tag_from_name_t.lang_not_found, {args[1]}); -- language name not found, error message
end
end
else
msg = cfg.tag_from_name_t.missing_lang_name; -- language name not found, error message
end
end


language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
local template = '';
if args.template and '' ~= args.template then
template = table.concat ({'{{', args['template'], '}}:'}); -- make template name (if provided by the template)
end
return make_error_span (template, msg);
 
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 result, _ = _tag_from_name (getArgs(frame)) -- pass-on the args table, nothing else; getArgs() so we also get parent frame; supress second return used by is_lang_name()
return result;
end
 
 
--[[--------------------------< I S _ L A N G _ N A M E >------------------------------------------------------
 
Module entry point from an {{#invoke:}}.


return language_name;
]]


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; supress second return used by tag_from_name()
return result and true or nil;
end
end




--[[--------------------------< T R A N S L >------------------------------------------------------------------
--[[--------------------------< _ T R A N S L >----------------------------------------------------------------


Prospective replacement for the template {{transl}}
Module entry point from another module.


]]
]]


function p.transl (frame)
local function _transl (args)
local args = getArgs(frame); -- no {{#invoke:}} parameters
local title_table = lang_data.translit_title_table; -- table of transliteration standards and the language codes and scripts that apply to those standards
local title_table = lang_data.translit_title_table; -- table of transliteration standards and the language codes and scripts that apply to those standards
local language_name; -- language name that matches language code; used for tool tip
local language_name; -- language name that matches language code; used for tool tip
local translit; -- translitterated text to display
local translit; -- transliterated text to display
local script; -- IANA script
local script; -- IANA script
local msg; -- for when called functions return an error message
local msg; -- for when called functions return an error message
local template = args.template or cfg.templates_t.transliteration;
maint_cats = {}; -- initialize because when this module required into another module, these only declared once so only initialzed once
maint_msgs = {};
error_msgs = {}


if is_set (args[3]) then -- [3] set when {{transl|code|standard|text}}
if is_set (args[3]) then -- [3] set when {{transliteration|code|standard|text}}
args.text = args[3]; -- get the transliterated 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
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 (table.concat ({'无法识别的转译标准:', args.translit_std}), args, 'transl');
make_error_msg (substitute (cfg.transl_t.unrecog_xlit_std, {args.translit_std}), args, template)
args.translit_std = nil
end
end
else
else
if is_set (args[2]) then -- [2] set when {{transl|code|text}}
if is_set (args[2]) then -- [2] set when {{transliteration|code|text}}
args.text = args[2]; -- get the transliterated text
args.text = args[2]; -- get the transliterated text
else
else
if args[1] and args[1]:match ('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text?
if args[1] and (args[1]:match ('^%a%a%a?%a?$') or -- args[2] missing; is args[1] a language or script tag or is it the transliterated text?
return make_error_msg ('no text', args, 'transl'); -- args[1] is a code so we're missing text
args[1]:match ('^%a%a%a?%-x%-')) then -- or is args[1] a private-use tag
make_error_msg (cfg.transl_t.no_text, args, template) -- args[1] is a code so we're missing text
args.text = ''
else
else
args.text = args[1]; -- args[1] is not a code so we're missing that; assign args.text for error message
make_error_msg (cfg.transl_t.missing_lang_scr, args, template)
return make_error_msg ('缺少语言/文字代码', args, 'transl');
args.text = ''
end
end
end
end
end
end


if is_set (args[1]) then -- IANA language code used for html lang= attribute; or ISO 15924 script code
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?$') then -- args[1] has correct form?
if args[1]:match ('^%a%a%a?%a?$') or args[1]:match ('^%a%a%a?%-x%-') 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
args.code = args[1]:lower(); -- use the language/script code; only (2, 3, or 4 alpha characters) or private-use; lower case because table indexes are lower case
else
else
return make_error_msg (table.concat ({'无法识别的语言/文字代码:', args[1]}), args, 'transl'); -- invalid language / script code
make_error_msg (substitute (cfg.transl_t.unrecog_lang_scr, {args[1]}), args, template) -- invalid language / script code
args.code = ''
end
end
else
else
return make_error_msg ('缺少语言/文字代码', args, 'transl'); -- missing language / script code so quit
make_error_msg (cfg.transl_t.missing_lang_scr, args, template) -- missing language / script code
args.code = ''
end
end


args.italic, msg = validate_italic (args.italic, args.italics);
local is_latn_text, pos, char;
is_latn_text, args.text, pos, char= is_latin (args.text, args.code); -- is latn text? strip accept-as-written markup
if not is_latn_text then -- when text is not latn
make_error_msg (substitute (cfg.lang_xx_t.translit_nonlatn, {pos, char}), args, template)
end
 
 
args.italic, msg = validate_italic (args);
if msg then
if msg then
return make_error_msg (msg, args, 'transl');
make_error_msg (msg, args, template)
msg = nil
end
end
 
if 'italic' == args.italic then -- 'italic' when |italic=yes; because that is same as absent or not set and |italic=default
if 'italic' == args.italic then -- 'italic' when |italic=yes; because that is same as absent or not set and |italic=default
args.italic = nil; -- set to nil;  
args.italic = nil; -- set to nil;
end
end


if lang_data.override[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 = lang_data.override[args.code][1];
language_name = override_table[args.code];
elseif lang_name_table.lang[args.code] then -- is code a language code defined in the standard language code tables?
args.code = args.code:match ('^%a%a%a?'); -- if private use, strip all but language subtag
language_name = lang_name_table.lang[args.code][1];
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables?
elseif lang_name_table.script[args.code] then -- if here, code is not a language code; is it a script code?
language_name = lang_table[args.code];
language_name = lang_name_table.script[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];
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];
script = args.code; -- code was an ISO 15924 script so use that instead
script = args.code; -- code was an ISO 15924 script so use that instead
args.code = ''; -- unset because not a language code
args.code = ''; -- unset because not a language code
else
else
return make_error_msg (table.concat ({'无法识别的语言/文字代码:', args.code}), args, 'transl'); -- invalid language / script code
make_error_msg (substitute (cfg.transl_t.unrecog_lang_scr, {args.code}), args, template) -- invalid language / script code
language_name = args.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);
 
if not args.noerror and error_msgs[1] then
msg = make_lang_error_span(table.concat(error_msgs))
end
 
return make_translit (args.code, language_name, args.text, args.translit_std, script, args.italic) .. (msg or '')
end
end




return p;
--[[--------------------------< 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-??}} templates are supported by this function.
 
Module entry point from another module.
 
]]
 
local function _category_from_tag (args_t)
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = args_t[1]; -- save a copy of the input IETF subtag
local link = cfg.keywords_t.affirmative == args_t.link; -- make a boolean
local label = args_t.label;
local code; -- the language code
local msg; -- gets an error message if IETF language tag is malformed or invalid
local category_name = '';
 
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code);
if msg then
local template = (args_t.template and table.concat ({'{{', args_t.template, '}}:'})) or ''; -- make template name (if provided by the template)
return make_error_span (template, msg);
end
 
raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles; private omitted because private
category_name = language_name_get (raw_code, code); -- get language name; try IETF tag first, then code w/o variant then code w/ variant
category_name = make_category (code, category_name, nil, true):gsub ('[%[%]]', '');
 
if link then
return table.concat ({'[[:', 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>}}
return _category_from_tag (getArgs (frame)); -- pass-on the args table, nothing else; getArgs() so we also get parent frame
end
 
 
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
]]
 
return {
category_from_tag = category_from_tag, -- frame entry points when this module is #invoke:ed into templates/wikitext
lang = lang, -- entry point for {{lang}}
langx = langx, -- entry point for {{langx}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_italic = lang_xx_italic,
is_ietf_tag = is_ietf_tag,
is_ietf_tag_frame = is_ietf_tag_frame,
is_lang_name = is_lang_name,
tag_from_name = tag_from_name, -- returns IETF tag associated with language name
name_from_tag = name_from_tag, -- used for template documentation; possible use in ISO 639 name from code templates
transl = transl, -- entry point for {{transliteration}}
 
_category_from_tag = _category_from_tag, -- API entry points when this module is require()d into other modules
_lang = _lang,
_langx = _langx,
_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,
_translation_make = translation_make,
};