imported>Xiplus
per EP, User:Vozhuo提供
imported>Tigerzeng
第1行: 第1行:
--[=[
--[=[ 基于英文维基2021年2月23日版本


Lua support for the {{lang}}, {{lang-xx}}, and {{transl}} templates and replacement of various supporting templates.  
Lua support for the {{lang}}, {{lang-xx}}, and {{transl}} templates and replacement of various supporting templates.  
第6行: 第6行:


require('Module:No globals');
require('Module:No globals');
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 lang_data = mw.loadData ('Module:Lang/data'); -- language name override and transliteration tool-tip tables
local lang_name_table = mw.loadData ('Module:Language/name/data');
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 namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
 
local this_wiki_lang = mw.language.getContentLanguage().code; -- get this wiki's language


local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
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 function page_exists (title)
    -- This function implements #ifexist
    local noError, titleObject = pcall (mw.title.new, title)
    if not noError then
        return false
    else
        if titleObject then
            return titleObject.exists
        else
            return false
        end
    end
end


--[[--------------------------< I S _ S E T >------------------------------------------------------------------
--[[--------------------------< I S _ S E T >------------------------------------------------------------------
第44行: 第41行:
local function is_set( var )
local function is_set( var )
return not (var == nil or var == '');
return not (var == nil or var == '');
end
--[[--------------------------< I S _ L A T N >----------------------------------------------------------------
Returns true if all of text argument is written using Latn script for letters, numbers and punctuationset; false 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:
[http://www.unicode.org/charts/PDF/U1D00.pdf Phonetic Extensions] U+1D00-U+1D7F (E1 B4 80 - E1 B5 BF)
[http://www.unicode.org/charts/PDF/U0250.pdf IPA Extensions] U+0250-U+02AF (C9 90 - CA AF)
[http://www.unicode.org/charts/PDF/U1D80.pdf Phonetic Extensions Supplement] U+1D80-U+1DBF (E1 B6 80 - E1 B6 BF)
{{lang}} is used inside <poem>...</poem> tags for song lyrics, poetry, etc.  <poem>...</poem> replaces newlines with
poem stripmarkers.  These have the form:
?'"`UNIQ--poem-67--QINU`"'?
where the '?' character is actually the delete character (U+007F, \127).  Including the '\n' (U+0010) and 'del' (U+007F)
characters in the latn character table allows {{lang}} to auto-italicize text within <poem>...</poem> tags.
]]
function p.is_latn (text)
local latn = table.concat (
{
'[', -- this is a set so include opening bracket
'\n\32-\127', -- C0 Controls and Basic Latin U+0020–U+007E (20 - 7E) + (U+0010 and U+007F <poem>...</poem> support)
'\194\160-\194\172', -- C1 Controls and Latin-1 Supplement U+00A0-U+00AC (C2 A0 - C2 AC)
'\195\128-\195\191', -- (skip shy) U+00C0–U+00FF (C3 80 - C3 BF)
'\196\128-\197\191', -- Latin Extended-A U+0100–U+017F (C4 80 - C5 BF)
'\198\128-\201\143', -- Latin Extended-B U+0180–U+024F (C6 80 - C9 8F)
'\225\184\128-\225\187\191', -- Latin Extended Additional U+1E00-U+1EFF (E1 B8 80 - E1 BB BF)
'\226\177\160-\226\177\191', -- Latin Extended-C U+2C60–U+2C7F (E2 B1 A0 - E2 B1 BF)
'\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)
'\239\172\128-\239\172\134', -- Alphabetic Presentaion Forms U+FB00-U+FB06 (EF AC 80 - EF AC 86)
'\239\188\129-\239\188\188', -- Halfwidth and Fullwidth Forms U+FF01-U+FF3C (EF BC 81 - EF BC BC)
'–', -- ndash
'—', -- mdash
'«', '»', -- guillemets commonly used in several 'Latn' languages
']', -- close the set
});
text = mw.text.decode (text, true); -- replace numeric and named html entities with their unicode characters
text = mw.ustring.gsub (text, '%[%[[^|]+|([^%]]+)%]%]', '%1'); -- remove the link and markup from complex wikilink in case interwiki to non-Latn wikipedia
return not is_set (mw.ustring.gsub (text, latn, '')); -- replace all latn characters with empty space; if result is all empty space, text is latn
end
end


第127行: 第68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
第142行: 第83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175行: 第116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 = {['yes'] = 'italic', ['no'] = 'normal', ['unset'] = 'inherit', ['invert'] = 'invert', ['default'] = nil};
local count = 0
for _, arg in pairs {'italic', 'italics', 'i'} do
if args[arg] then
count = count + 1
end
end
if count > 1 then -- return nil and an error message if more than one is set
return nil, '只能指定|italic=、|italics=或|i=中的一个';
end
return properties[args.italic or args.italics or args.i], nil; -- return an appropriate value and a nil error message
end
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------
Default behavior of the {{lang}} and {{lang-xx}} templates is to add categorization when the templates are used in mainspace.
This default functionality may be suppressed by setting |nocat=yes or |cat=no.  This function selects one of these two parameters
to control categorization.
Because having two parameters with 'opposite' names and 'opposite' values is confusing, this function accepts only affirmative
values for |nocat= and only negative values for |cat=; in both cases the 'other' sense (and non-sense) is not accepted and the
parameter is treated as if it were not set in the template.
Sets args.nocat to true if categorization is to be turned off; to nil if the default behavior should apply.
Accepted values for |nocat= are the text strings:
'yes', 'y', 'true', 't', on, '1' -- [[Module:Yesno]] returns logical true for all of these; false or nil else
for |cat=
'no', 'n', 'false', 'f', 'off', '0' -- [[Module:Yesno]] returns logical false for all of these; true or nil else
]=]


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
end
return properties[italic or italics], nil; -- return an appropriate value and a nil error message
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
end


第192行: 第172行:
]]
]]


local function in_array( needle, haystack )
local function in_array ( needle, haystack )
if needle == nil then
if needle == nil then
return false;
return false;
第212行: 第192行:
region: upper case
region: upper case
variant: lower case
variant: lower case
 
private: lower case prefixed with -x-
]]
]]


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


if is_set (private) then
return table.concat ({code:lower(), 'x', private:lower()}, '-'); -- if private, all other tags ignored
end
table.insert (out, code:lower());
table.insert (out, code:lower());
if is_set (script) then
if is_set (script) then
第242行: 第227行:
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261行: 第246行:
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.


第269行: 第254行:


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
第279行: 第260行:
end
end


if source:match ('^%a%a%a?%-%a%a%a%a%-%a%a%-%d%d%d%d$') then -- ll-Ssss-RR-variant (where variant is 4 digits)
local pattern = { -- table of tables holding acceptibe ietf tag patterns and short names of the ietf part captured by the pattern
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$');
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 1 - ll-Ssss-RR-variant (where variant is 4 digits)
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%-%d%d%d%d$') then -- ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 2 -  ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$');
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 3 -  ll-Ssss-RR-variant (where variant is 5-8 alnum characters)
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 4 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$', 's', 'v'}, -- 5 -  ll-Ssss-variant (where variant is 4 digits)
code, script, region, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
{'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', '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)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits)
{'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss
{'^(%a%a%a?)%-(%a%a)$', 'r'}, -- 16 - ll-RR
{'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits)
{'^(%a%a%a?)$'}, -- 18 - ll
{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters)
}


elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d%d$') then -- ll-Ssss-variant (where variant is 4 digits)
local t = {}; -- table of captures; serves as a translator between captured ietf tag parts and named variables
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$');
elseif source:match ('^%a%a%a?%-%a%a%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-Ssss-variant (where variant is 5-8 alnum characters)
code, script, variant = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');


elseif source:match ('^%a%a%a?%-%a%a%-%d%d%d%d$') then -- ll-RR-variant (where variant is 4 digits)
for i, v in ipairs (pattern) do -- spin through the pattern table looking for a match
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$');
local c1, c2, c3, c4; -- captures in the 'pattern' from the pattern table go here
elseif source:match ('^%a%a%a?%-%d%d%d%-%d%d%d%d$') then -- ll-DDD-variant (where region is 3 digits; variant is 4 digits)
code, region, variant = source:match ('^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$');
c1, c2, c3, c4 = source:match (pattern[i][1]); -- one or more captures set if source matches pattern[i])
elseif source:match ('^%a%a%a?%-%a%a%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-RR-variant (where variant is 5-8 alnum characters)
if c1 then -- c1 always set on match
code, region, variant = source:match ('^(%a%a%a?)%-(%a%a)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
code = c1; -- first capture is always code
elseif source:match ('^%a%a%a?%-%d%d%d%-[%a%d][%a%d][%a%d][%a%d][%a%d]+$') then -- ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
t = {
code, region, variant = source:match ('^(%a%a%a?)%-(%d%d%d)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
[pattern[i][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
elseif source:match ('^%a%a%a?%-%d%d%d%d$') then -- ll-variant (where variant is 4 digits)
[pattern[i][4] or 'x'] = c4, -- index name may be nil in pattern[i] table so "or 'x'" spoofs a name for this index in this table
code, variant = source:match ('^(%a%a%a?)%-(%d%d%d%d)$');
};
elseif source:match ('^%a%a%a?%-[%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?$') then -- ll-variant (where variant is 5-8 alnum characters)
script = t.s or ''; -- translate table contents to named variables;
code, variant = source:match ('^(%a%a%a?)%-([%a%d][%a%d][%a%d][%a%d][%a%d][%a%d]?[%a%d]?[%a%d]?)$');
region = t.r or ''; -- absent table entries are nil so set named ietf parts to empty string for concatenation
 
variant= t.v or '';
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%a%a$') then -- ll-Ssss-RR
private = t.p or '';
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$');
break; -- and done
elseif source:match ('^%a%a%a?%-%a%a%a%a%-%d%d%d$') then -- ll-Ssss-DDD (region is 3 digits)
end
code, script, region = source:match ('^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$');
end
 
elseif source:match ('^%a%a%a?%-%a%a%a%a$') then -- ll-Ssss
code, script = source:match ('^(%a%a%a?)%-(%a%a%a%a)$');
 
elseif source:match ('^%a%a%a?%-%a%a$') then -- ll-RR
code, region = source:match ('^(%a%a%a?)%-(%a%a)$');
elseif source:match ('^%a%a%a?%-%d%d%d$') then -- ll-DDD (region is 3 digits)
code, region = source:match ('^(%a%a%a?)%-(%d%d%d)$');


elseif source:match ('^%a%a%a?$') then -- ll
if not code then
code = source:match ('^(%a%a%a?)$');
 
elseif source:match ('^%a%a%a?%-x%-[%a%d][%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?[%a%d]?$') then -- ll-x-pppppppp)
code, private = source:match ('^(%a%a%a?)%-x%-([%a%d]+)$');
 
else
return nil, nil, nil, nil, nil, table.concat ({'无法识别的语言标签:', source}); -- don't know what we got but it is malformed
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
end
end
第332行: 第317行:
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, table.concat ({'无法识别的语言代码:', code}); -- invalid language code, don't know about the others (don't care?)
end
end
第352行: 第337行:
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, 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?)
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, table.concat ({'文本:', script, '不支持代码:', code}); -- language code ok, script is suppressed for this code
end
end
第372行: 第357行:
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, table.concat ({'无法识别的地区:', region, '用于代码:', code});
end
end
第387行: 第372行:
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, table.concat ({'无法识别的变体:', 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, table.concat ({'无法识别的变体:', variant, '用于代码-文本对:', code, '-', script});
end
elseif is_set (region) then -- if region set, there are some prefixes that require lang code and region (en-CA-newfound)
if not in_array (code, variant_table[variant]['prefixes']) then -- first see if lang code is all that's required (en-oxendict though en-GB-oxendict is preferred)
if not in_array (table.concat ({code, '-', region}), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
return code, script, region, nil, nil, table.concat ({'无法识别的变体:', variant, '用于代码-文本对:', code, '-', region});
end
end
end
else
else
if not in_array (code, lang_name_table.variant[variant]['prefixes']) then
if not in_array (code, variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'未识别的变体:', variant, '用于代码:', code});
return code, script, region, nil, nil, table.concat ({'无法识别的变体:', variant, '用于代码:', code});
end
end
end
end
第403行: 第394行:
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, table.concat ({'无法识别的私有标签:', private});
end
end
end
end
第421行: 第412行:
local category;
local category;
if 'transl' == template then
if 'Transl' == template then
category = 'transl';
category = 'Transl';
else
else
category = 'lang和lang-xx'
category = 'Lang和lang-xx'
end
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 ({'[', args.text or '未定义', '] '})); -- 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, table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">错误:{{', template, '}}:'}));
table.insert (out, msg);
table.insert (out, msg);
table.insert (out, table.concat ({'([[:Category:', category, '模板错误|帮助]])'}));
table.insert (out, table.concat ({'([[:Category:', category, '模板错误|帮助]])'}));
table.insert (out, '</span>');
table.insert (out, '</span>');
if (0 == namespace) and not is_set (args.nocat) then -- only categorize in article space
if (0 == namespace or 10 == namespace) and not args.nocat then -- categorize in article space (and template space to take care of broken usages)
table.insert (out, table.concat ({'[[Category:', category, '模板错误]]'}));
table.insert (out, table.concat ({'[[Category:', category, '模板错误]]'}));
end
end
第462行: 第453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 >--------------------------------------------------
 
adds <i> and </i> tags to list-item text or to implied <p>..</p> text.  mixed not supported
 
]]
 
local function div_markup_add (text, style)
local implied_p = {};
 
if text:find ('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
if 'italic' == style then
return mw.ustring.gsub (text, '(\n[%*:;#]+)([^\n]+)', '%1<i>%2</i>'); -- insert italic markup at each list item
else
return text;
end
end
 
if text:find ('\n+') then -- look for any number of \n characters in text
text = text:gsub ('([^\n])\n([^\n])', '%1 %2'); -- replace single newline characters with a space character which mimics mediawiki
 
if 'italic' == style then
text = text:gsub('[^\n]+', '<p><i>%1</i></p>'); -- insert p and italic markup tags at each impled p (two or more consecutive '\n\n' sequences)
else
text = text:gsub ('[^\n]+', '<p>%1</p>'); -- insert p markup at each impled p
text = text:gsub ('\n', ''); -- strip newline characters
end
end
 
return text;
end


TODO: add support for block: div tags instead of span tags; would need some sort of proper parameter to control the switch


For italic style, can't do ''{{lang|xx|text}}'' without using <span/> tags when text is italic because of -Latn, |italic=yes,
--[[--------------------------< M A K E _ T E X T _ H T M L >--------------------------------------------------
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:
Add the html markup to text according to the type of content that it is: <span> or <i> tags for inline content or
<i><span lang="xx">text</span></i>
<div> tags for block content


]]
]]


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 = {};
local style_added = '';
local style_added = '';


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, '&#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, table.concat ({'<', tag})); -- open the <i>, <span>, or <div> html tag
table.insert (span, ' dir="rtl"'); -- add direction attribute for right to left languages
table.insert (html, table.concat ({' lang="', code, '\"'})); -- add language attribute
 
if rtl or unicode.is_rtl(text) then
table.insert (html, ' dir="rtl"'); -- add direction attribute for right to left 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, ' 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505行: 第523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, 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, 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
第513行: 第531行:


if is_set (language) then
if is_set (language) then
table.insert (span, table.concat ({style_added, ' title=\"', language})); --start the title text
table.insert (html, table.concat ({style_added, ' title=\"', language})); --start the title text
if language:find ('languages') then
if language:find ('languages') then
table.insert (span, ' collective text\"'); -- for collective languages
table.insert (html, '汇集文本'); -- for collective languages
else
else
table.insert (span, ' language text\"'); -- for individual languages
table.insert (html, '文本'); -- for individual languages
end
end
table.insert (span, '>'); -- close the opening span tag
table.insert (html, '\">'); -- close the opening html tag
else
else
table.insert (span, table.concat ({style_added, '>'})); -- close the style attribute and close opening span tag
table.insert (html, table.concat ({style_added, '>'})); -- close the style attribute and close opening html tag
end
end
table.insert (span, text); -- insert the text
table.insert (html, text); -- insert the text
 
table.insert (html, table.concat ({'</', tag, '>'})); -- close the <i>, <span>, or <div> html tag


table.insert (span, '</span>'); -- close the <span> tag
if rtl then -- legacy; shouldn't be necessary because all of the rtl text is wrapped inside an html tag with dir="rtl" attribute
if 'italic' == style then
table.insert (html, '&lrm;'); -- make sure the browser knows that we're at the end of the rtl
table.insert (span, '</i>'); -- close italic style tag
end
if rtl then -- legacy; shouldn't be necessary because all of the rtl text is wrapped in <span dir="rtl">text</span>
table.insert (span, '&lrm;'); -- make sure the browser knows that we're at the end of the rtl
end
end
return table.concat (html); -- put it all together and done
return table.concat (span); -- put it all together and done
end
end


第609行: 第623行:
if is_set (code) then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
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
if not style then -- nil for the default italic style
table.insert (tout, "<span lang=\""); -- so use <span> tag
table.insert (tout, "<i lang=\""); -- so use <i> tag
else
else
table.insert (tout, table.concat ({'<span style=\"font-style:', style, '\" lang=\"'})); -- non-standard style, construct a span tag for it
table.insert (tout, table.concat ({'<span style=\"font-style: ', style, '\" lang=\"'})); -- non-standard style, construct a span tag for it
end
end
table.insert (tout, code);
table.insert (tout, code);
第624行: 第638行:
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
table.insert (tout, language_name); -- write a generic tool tip
if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
-- if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
-- table.insert (tout, '-language') -- skip this text (individual and macro languages only)
end
-- end
table.insert (tout, ' transliteration'); -- finish the tool tip
table.insert (tout, '羅馬化'); -- 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_table[std] then -- and if standard is legitimate
if title_table[std][tscript] then -- and if script for that standard is legitimate
if title_table[std][tscript] then -- and if script for that standard is legitimate
table.insert (tout, table.concat ({title_table[std][tscript:lower()], ' (', lang_name_table.script[tscript][1], ' script) transliteration'})); -- add the appropriate text to the tool tip
table.insert (tout, table.concat ({title_table[std][tscript:lower()], '', script_table[tscript][1], ')转写'})); -- add the appropriate text to the tool tip
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?
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?
第643行: 第657行:
if title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
if title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
table.insert (tout, table.concat ({title_table[std][code:lower()], ' (', lang_name_table.lang[code][1], ' language) transliteration'})); -- add the appropriate text to the tool tip
-- table.insert (tout, table.concat ({title_table[std][code:lower()], ' (', lang_table[code][1], ' language) transliteration'})); -- add the appropriate text to the tool tip
table.insert (tout, table.concat ({title_table[std][code:lower()], '(', language_name, ')转写'})); -- add the appropriate text to the tool tip
else -- code doesn't match
else -- code doesn't match
table.insert (tout, title_table[std]['default']); -- so use the standard's default
table.insert (tout, title_table[std]['default']); -- so use the standard's default
第654行: 第669行:
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
table.insert (tout, table.concat ({language_name, '-文字转写'})); -- write a script tool tip
elseif is_set (code) then
elseif is_set (code) then
if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
-- if not language_name:find ('languages') then -- collective language names (plural 'languages' is part of the name)
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
-- table.insert (tout, '-language') -- skip this text (individual and macro languages only)
end
-- end
table.insert (tout, ' transliteration'); -- finish the tool tip
table.insert (tout, '转写'); -- finish the tool tip
else
else
table.insert (tout, ' transliteration'); -- generic tool tip (can we ever get here?)
table.insert (tout, '转写'); -- generic tool tip (can we ever get here?)
end
end
end
end
第668行: 第683行:
table.insert (tout, '">');
table.insert (tout, '">');
table.insert (tout, translit);
table.insert (tout, translit);
if is_set (code) and not style then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
if is_set (code) and not style then -- when a language code is provided (always with {{lang-xx}} templates, not always with {{transl}})
table.insert (tout, "</span>"); -- close the span tag
table.insert (tout, "</i>"); -- close the italic tag
else
else
table.insert (tout, "</span>"); -- no language code so close the span tag
table.insert (tout, "</span>"); -- no language code so close the span tag
第677行: 第692行:




--[=[-------------------------< 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
第683行: 第698行:


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)
第696行: 第711行:
end
end


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


-- if ('unset' ~= args.italic) and ('unset' ~= args.italics) then -- allow italic markup when |italic=unset or |italics=unset
if ('unset' ~= style) and ('invert' ~=style) then
if ('unset' ~= style) and ('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
第717行: 第731行:
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
第724行: 第738行:
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
第736行: 第750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 / or inhibits
regardless of language name; nil does nothing; presumes that the value in text is correct but removes extra splac


]]
]]


local function proto_prefix (text, language_name)
local function proto_prefix (text, language_name, proto_param)
if language_name:find ('^Proto%-') and not text:find ('^*') then -- language is a proto and text does not already have leading splat
if false == proto_param then -- when forced by |proto=no
return table.concat ({'*', text}); -- prefix proto language text with a splat
return text:gsub ('^%**', ''); -- return text without splat prefix regardless of language name or existing splat prefix in text
elseif (language_name:find ('^Proto%-') or (true == proto_param)) then -- language is a proto or forced by |proto=yes
return text:gsub ('^%**', '*'); -- prefix proto-language text with a splat; also removes duplicate prefixing splats
end
end
return text;
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.
 
]]
 
local function html_tag_select (text)
local tag;
if has_poem_tag (text) then -- contains poem stripmarker (we can't know the content of that)
tag = 'div'; -- poem replacement is in div tags so lang must use div tags
elseif mw.text.trim (text):find ('\n\n+') then -- contains implied p tags
text = mw.text.trim (text); -- trim leading and trailing whitespace characters
tag = 'div'; -- must be div because span may not contain p tags (added later by MediaWiki); poem replacement is in div tags
elseif text:find ('\n[%*:;%#]') then -- if text has list markup
text = text:gsub ('^[\t\r\f ]*', ''):gsub ('%s*$', ''); -- trim all whitespace except leading newline character '\n'
tag = 'div'; -- must be div because span may not contain ul, dd, dl, ol tags (added later by MediaWiki)
else
text = mw.text.trim (text); -- plain text
tag = 'span'; -- so span is fine
end
return text, tag;
end
 
 
--[[--------------------------< V A L I D A T E _ P R O T O >--------------------------------------------------
 
validates value assigned to |proto=; permitted values are yes and no; yes returns as true, no returns as false,
empty string (or parameter omitted) returns as nil; any other value returns as nil with a second return value of
true indicating that some other value has been assigned to |proto=
 
]]
 
local function validate_proto (proto_param)
if 'yes' == proto_param then
return true;
elseif 'no' == proto_param then
return false;
elseif is_set (proto_param) then
return nil, true; -- |proto= something other than 'yes' or 'no'
else
return nil; -- missing or empty
end
end
 
 
--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------
 
common function to return language name from the data set according to IETF tag
 
returns language name if found in data tables; nil else
 
]]
 
local function language_name_get (ietf, code, cat)
ietf = ietf:lower(); -- ietf:lower() because format_ietf_tag() returns mixed case
local name; -- remains nil if not found
if override_table[ietf] then -- look for whole IETF tag in override table
name = override_table[ietf][1];
elseif override_table[code] then -- not there so try basic language code
name = override_table[code][1];
elseif lang_table[code] then -- shift to iana code/name table
name = lang_table[code][1]; -- table entries sometimes have multiple names, always take the first one
elseif lang_dep_table[code] then
-- if cat then
-- table.insert (maint_cats, table.concat ({'Lang and lang-xx using deprecated ISO 639 codes|', code}));
-- table.insert (maint_msgs, table.concat ({'code: ', code, ' is deprecated'}));
-- end
name = lang_dep_table[code][1]; -- table entries sometimes have multiple names, always take the first one
end
 
if lang_dep_table[code] and cat then -- because deprecated code may have been overridden to en.wiki preferred name
table.insert (maint_cats, table.concat ({'Lang和lang-xx使用弃用的ISO 639代码|', code}));
table.insert (maint_msgs, table.concat ({'代码:', code, '已弃用'}));
end
 
return name; -- name from data tables or nil
end
end




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


entry point for {{lang}}
entry point for {{lang}}
第758行: 第886行:
<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 'Lang';
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');
return make_error_msg ('冲突:{{{1}}} 和 |code=', args, template);
else
else
args.code = args[1] or args.code; -- prefer args.code
args.code = args[1] or args.code; -- prefer args.code
第777行: 第909行:


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');
return make_error_msg ('冲突:{{{2}}} 和 |text=', args, template);
else
else
args.text = args[2] or args.text; -- prefer args.text
args.text = args[2] or args.text; -- prefer args.text
end
if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
args.italic = 'unset';
end
end
msg = validate_text ('lang', args); -- ensure that |text= is set (italic test disabled for the time being)
msg = validate_text (template, args); -- ensure that |text= is set
if is_set (msg) then -- msg is an already-formatted error message
if is_set (msg) then -- msg is an already-formatted error message
return msg;
return msg;
end
end
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly


args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
return make_error_msg (table.concat ({'无效|proto=:', args.proto}), args, template);
end


code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (args.code); -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})
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');
return make_error_msg ( msg, args, template);
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');
return make_error_msg (msg, args, template);
end
 
if nil == args.italic then -- nil when |italic= absent or not set or |italic=default; args.italic controls
if ('latn' == subtags.script) or -- script is latn
(this_wiki_lang ~= code and not is_set (subtags.script) and not has_poem_tag (args.text) and unicode.is_Latin (args.text)) then -- text not this wiki's language, no script specified and not in poem markup but is wholly latn script (auto-italics)
args.italic = 'unset'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
else
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
end
end
end
第812行: 第956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); -- 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 ...
language_name = lang_data.override[table.concat ({code, '-x-', subtags.private})][1]; -- ... args.code does not get private subtag
elseif lang_data.override[code] then -- get the language name for categorization
language_name = lang_data.override[code][1] -- prefer language names taken from the override table
elseif lang_name_table.lang[code] then
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
end


if 'invert' == args.italic then
if 'invert' == args.italic and 'span' == tag then -- invert only supported for in-line content
args.text = invert_italics (args.text)
args.text = invert_italics (args.text)
end
end
 
-- 中文版特化部分:为非中文文字禁用繁简转换,中文文字和其他以汉字作为书写系统的汉语方言文字启用繁简转换。
-- 中文版特化部分:为非中文文字禁用繁简转换,中文文字和其他以汉字作为书写系统的汉语方言文字启用繁简转换。
if 'zh' == code then
if 'zh' == code then
第843行: 第980行:
end
end
args.text = proto_prefix (args.text, language_name); -- prefix proto-language text with a splat
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat


table.insert (out, make_text_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


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 >----------------------------------------------------------------------
entry point for {{lang}}
there should be no reason to set parameters in the {{lang}} {{#invoke:}}
<includeonly>{{#invoke:lang|lang}}</includeonly>
parameters are received from the template's frame (parent frame)
]]
local function lang (frame)
local args = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text
valueFunc = function (key, value)
if 2 == key or 'text' == key then -- the 'text' parameter; do not trim wite space
return value; -- return untrimmed 'text'
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
if '' ~= value then -- empty string when value was only whitespace
return value;
end
end
return nil; -- value was empty or contained only whitespace
end -- end of valueFunc
});
return _lang (args);
end
end


第859行: 第1,026行:
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-xx}} template choose the appropriate entry-point function so that this function knows the default
styling that should be applied to text.
styling that should be applied to text.


第871行: 第1,038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-xx}} templates that support transliteration (those templates where |text= is not entirely latn script):
|translit = text that is a transliteration of text
|translit = text that is a transliteration of text
|translit-std = the standard that applies to the transliteration
|translit-std = the standard that applies to the transliteration
第896行: 第1,064行:
]]
]]


local function _lang_xx (frame)
local function _lang_xx (args)
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908行: 第1,075行:
local translit_title;
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 'Lang-xx';


if args[1] and args.text then
if args[1] and args.text then
return make_error_msg ('冲突:{{{1}}} 和 &#124;text=', args, 'lang-xx');
return make_error_msg ('冲突:{{{1}}} 和 |text=', args, template);
else
else
args.text = args[1] or args.text; -- prefer args.text
args.text = args[1] or args.text; -- prefer args.text
end
end
msg = validate_text ('lang-xx', args); -- ensure that |text= is set, does not contain italic markup and is protected from improper bolding
msg = validate_text (template, args); -- ensure that |text= is set, does not contain italic markup and is protected from improper bolding
if is_set (msg) then
if is_set (msg) then
return msg;
return msg;
end
end
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly


if args[2] and args.translit then
if args[2] and args.translit then
return make_error_msg ('冲突:{{{2}}} 和 &#124;translit=', args, 'lang-xx');
return make_error_msg ('冲突:{{{2}}} 和 |translit=', args, template);
else
else
args.translit = args[2] or args.translit -- prefer args.translit
args.translit = args[2] or args.translit -- prefer args.translit
第927行: 第1,098行:
if args[3] and (args.translation or args.lit) then
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');
return make_error_msg ('冲突:{{{3}}} 和 |lit= or |translation=', args, template);
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');
return make_error_msg ('冲突:|lit= 和 |translation=', args, template);
else
else
args.translation = args[3] or args.translation or args.lit; -- prefer args.translation
args.translation = args[3] or args.translation or args.lit; -- prefer args.translation
第935行: 第1,106行:


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');
return make_error_msg ('冲突:|links= 和 |link=', args, template);
else
else
args.link = args.link or args.links; -- prefer args.link
args.link = args.link or args.links; -- prefer args.link
end
end
validate_cat_args (args); -- determine if categorization should be suppressed


args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
args.rtl = args.rtl == 'yes'; -- convert to boolean: 'yes' -> true, other values -> false
第945行: 第1,118行:


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');
return make_error_msg (msg, args, template);
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');
return make_error_msg (msg, args, template);
end
end


第973行: 第1,146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 (table.concat ({'无效 |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); -- 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1,002行: 第1,165行:
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
if lang_data.article_name[code] then
table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
table.insert (out, make_wikilink (lang_data.article_name[code][1], language_name)); -- language name with wikilink from override data
-- else
else
-- table.insert (out, make_wikilink (language_name .. ' language', language_name)); -- language name with wikilink
table.insert (out, make_wikilink (language_name)); -- language name with wikilink
-- end
end
end
end
table.insert (out, ':'); -- separator
table.insert (out, ':'); -- separator
第1,014行: 第1,177行:
args.text = invert_italics (args.text)
args.text = invert_italics (args.text)
end
end
 
-- 中文版特化部分:为非中文文字禁用繁简转换,中文文字和其他以汉字作为书写系统的汉语方言文字启用繁简转换。
-- 中文版特化部分:为非中文文字禁用繁简转换,中文文字和其他以汉字作为书写系统的汉语方言文字启用繁简转换。
if 'zh' == code then
if 'zh' == code then
第1,032行: 第1,195行:
end
end
args.text = proto_prefix (args.text, language_name); -- prefix proto-language text with a splat
args.text = proto_prefix (args.text, language_name, args.proto); -- prefix proto-language text with a splat


table.insert (out, make_text_span (args.code, args.text, args.rtl, args.italic, args.size))
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 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)
if is_set (args.translit) and not unicode.is_Latin (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
args.translit = '-{' .. args.translit .. '}-'
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'][1]];
else
else
translit_script_name = language_name; -- fall back on language name
translit_script_name = language_name; -- fall back on language name
第1,048行: 第1,210行:
translit_title = mw.title.makeTitle (0, table.concat ({translit_script_name, '羅馬化'})); -- make a title object
translit_title = mw.title.makeTitle (0, table.concat ({translit_script_name, '羅馬化'})); -- make a title object
if translit_title.exists and ('no' ~= args.link) then
if translit_title.exists and ('no' ~= args.link) then
table.insert (out, make_wikilink ((translit_script_name or language_name) .. '羅馬化', '转写')); -- make a wikilink if there is an article to link to
table.insert (out, make_wikilink ((translit_script_name or language_name) .. '羅馬化', '羅馬化')); -- make a wikilink if there is an article to link to
else
else
table.insert (out, '转写'); -- else define the abbreviation
table.insert (out, '羅馬化'); -- else plain text
end
end
table.insert (out, ':</small>'); -- close the small tag
table.insert (out, ':</small>'); -- close the small tag
第1,059行: 第1,221行:
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');
return make_error_msg (table.concat ({'invalid translit-std: \'', args['translit-std'] or '[missing]'}), args, template);
end
end
end
end
第1,081行: 第1,243行:


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
]]
local function lang_xx_args_get (frame)
local args = getArgs(frame,
{
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}}
valueFunc = function (key, value)
if 1 == key then -- the 'text' parameter; do not trim wite space
return value; -- return untrimmed 'text'
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
if '' ~= value then -- empty string when value was only whitespace
return value;
end
end
return nil; -- value was empty or contained only whitespace
end -- end of valueFunc
});
return args;
end
end


第1,090行: 第1,281行:
]]
]]


function p.lang_xx_italic (frame)
local function lang_xx_italic (frame)
local args = lang_xx_args_get (frame);
initial_style_state = 'italic';
initial_style_state = 'italic';
return _lang_xx (frame);
return _lang_xx (args);
end
 
 
--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------
 
Entry point ffrom another module.  Sets the initial style state to italic.
 
]]
 
local function _lang_xx_italic (args)
initial_style_state = 'italic';
return _lang_xx (args);
end
end


第1,102行: 第1,307行:
]]
]]


function p.lang_xx_inherit (frame)
local function lang_xx_inherit (frame)
local args = lang_xx_args_get (frame);
 
initial_style_state = 'inherit';
return _lang_xx (args);
end
 
 
--[[--------------------------< _ L A N G _ X X _ I N H E R I T >----------------------------------------------
 
Entry point from another module.  Sets the initial style state to inherit.
 
]]
 
local function _lang_xx_inherit (args)
initial_style_state = 'inherit';
initial_style_state = 'inherit';
return _lang_xx (frame);
return _lang_xx (args);
end
 
 
--[[--------------------------< _ I S _ I E T F _ T A G >------------------------------------------------------
 
Returns true when a language name associated with IETF language tag exists; nil else.  IETF language tag must be valid.
 
All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
 
Module entry point from another module
 
]]
 
local function _is_ietf_tag (tag) -- entry point when this module is require()d into another
local c, s, r, v, p, err; -- code, script, region, variant, private, error message
c, s, r, v, p, err = get_ietf_parts (tag); -- disassemble tag into constituent part and validate
 
return ((c and not err) and true) or nil; -- return true when code portion has a value without error message; nil else
end
 
 
--[[--------------------------< I S _ I E T F _ T A G >--------------------------------------------------------
 
Module entry point from an {{#invoke:}}
 
]]
 
local function is_ietf_tag (frame)
return _is_ietf_tag (getArgs (frame)[1]); -- args[1] is the ietf language tag to be tested; 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
end




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


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


All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
All code combinations supported by {{lang}} and the {{lang-xx}} templates are supported by this function.
Set invoke's |link= parameter to yes to get wikilinked version of the language name.
Module entry point from another module


]]
]]


function p.name_from_code (frame)
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 = 'yes' == 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 table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">错误:', template, msg, '</span>'});
end
end


if lang_data.override[raw_code:lower()] then -- look for whole IETF tag in override table (force lower case)
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 = lang_data.override[raw_code:lower()][1];
language_name = language_name_get (raw_code, code); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
elseif lang_data.override[code] then -- not there so try basic language code in override table
 
language_name = lang_data.override[code][1];
language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
elseif not is_set (subtags.variant) then
 
if lang_name_table.lang[code] then
if link then -- when |link=yes, wikilink the language name
language_name = lang_name_table.lang[code][1]; -- table entries sometimes have multiple names, always take the first one
if lang_data.article_name[code] then
language_name = make_wikilink (lang_data.article_name[code][1], label or language_name); -- language name with wikilink from override data
else
language_name = make_wikilink (language_name, 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'); -- 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 = '语言:' .. args[1] .. '未找到' -- language name not found, error message
end
end
else
msg = '缺少语言名称' -- language name not provided, error message
end
local template = '';
if args.template and '' ~= args.template then
template = table.concat ({'{{', args['template'], '}}: '}); -- make template name (if provided by the template)
end
end
return table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">错误:', template, msg, '</span>'});
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 >------------------------------------------------------


language_name = language_name:gsub ('%s+%b()', ''); -- remove IANA parenthetical disambiguators or qualifiers from names that have them
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
第1,168行: 第1,501行:


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');
return make_error_msg (table.concat ({'无法识别的转译标准:', args.translit_std}), args, 'Transl');
end
end
else
else
第1,175行: 第1,508行:
else
else
if args[1] and args[1]:match ('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text?
if args[1] and args[1]:match ('^%a%a%a?%a?$') then -- args[2] missing; is args[1] a code or its it the transliterated text?
return make_error_msg ('no text', args, 'transl'); -- args[1] is a code so we're missing text
return make_error_msg ('无文本', args, 'Transl'); -- args[1] is a code so we're missing text
else
else
args.text = args[1]; -- args[1] is not a code so we're missing that; assign args.text for error message
args.text = args[1]; -- args[1] is not a code so we're missing that; assign args.text for error message
return make_error_msg ('缺少语言/文字代码', args, 'transl');
return make_error_msg ('缺少语言/文字代码', args, 'Transl');
end
end
end
end
第1,187行: 第1,520行:
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); 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
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
end
end
else
else
return make_error_msg ('缺少语言/文字代码', args, 'transl'); -- missing language / script code so quit
return make_error_msg ('缺少语言/文字代码', args, 'Transl'); -- missing language / script code so quit
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, 'transl');
return make_error_msg (msg, args, 'Transl');
end
end
第1,202行: 第1,535行:
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][1];
elseif lang_name_table.lang[args.code] then -- is code a language code defined in the standard language code tables?
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables?
language_name = lang_name_table.lang[args.code][1];
language_name = lang_table[args.code][1];
elseif lang_name_table.script[args.code] then -- if here, code is not a language code; is it a script code?
elseif lang_dep_table[args.code] then -- is code a language code defined in the deprecated language code tables?
language_name = lang_name_table.script[args.code][1];
language_name = lang_dep_table[args.code][1];
elseif script_table[args.code] then -- if here, code is not a language code; is it a script code?
language_name = script_table[args.code][1];
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
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
end
end
-- here only when all parameters passed to make_translit() are valid
-- here only when all parameters passed to make_translit() are valid
第1,218行: 第1,553行:




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-xx}} templates are supported by this function.
 
Module entry point from another module
 
]]
 
local function _category_from_tag (args)
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = args[1]; -- save a copy of the input IETF subtag
local link = 'yes' == args['link']; -- make a boolean
local label = args.label;
local code; -- the language code
local msg; -- gets an error message if IETF language tag is malformed or invalid
local category_name = '';
code, subtags.script, subtags.region, subtags.variant, subtags.private, msg = get_ietf_parts (raw_code);
if msg then
local template = (args['template'] and table.concat ({'{{', args['template'], '}}: '})) or ''; -- make template name (if provided by the template)
return table.concat ({'<span style=\"font-size: 100%; font-style: normal;\" class=\"error\">错误:', template, msg, '</span>'});
end
 
raw_code = format_ietf_tag (code, subtags.script, subtags.region, subtags.variant, subtags.private); -- format to recommended subtag styles; private omitted because private
category_name = language_name_get (raw_code, code); -- get language name; try ietf tag first, then code w/o variant then code w/ variant
category_name = make_category (code, category_name, nil, true):gsub ('[%[%]]', '');
 
return category_name;
end
 
 
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------
 
Module entry point from an {{#invoke:}}
 
]]
 
local function category_from_tag (frame) -- entry point from an {{#invoke:Lang|category_from_tag|<ietf tag>|template=<template name>}}
return _category_from_tag (getArgs (frame)); -- pass-on the args table, nothing else; getArgs() so we also get parent frame
end
 
 
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
]]
 
return {
category_from_tag = category_from_tag,
lang = lang, -- entry point for {{lang}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_italic = lang_xx_italic,
is_ietf_tag = is_ietf_tag,
        is_ietf_tag_frame = is_ietf_tag_frame,
is_lang_name = is_lang_name,
tag_from_name = tag_from_name, -- returns ietf tag associated with language name
name_from_tag = name_from_tag, -- used for template documentation; possible use in ISO 639 name from code templates
transl = transl, -- entry point for {{transl}}
_category_from_tag = _category_from_tag, -- entry points when this module is require()d into other modules
_lang = _lang,
_lang_xx_inherit = _lang_xx_inherit,
_lang_xx_italic = _lang_xx_italic,
_is_ietf_tag = _is_ietf_tag,
get_ietf_parts = get_ietf_parts,
_tag_from_name = _tag_from_name,
_name_from_tag = _name_from_tag,
_transl = _transl,
};