Module:Lang: Difference between revisions

m 1 revision imported
m 1 revision imported: template update
 
(6 intermediate revisions by 4 users not shown)
Line 1: Line 1:
--[=[
--[=[


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.  


]=]
]=]


require('Module:No globals');
require('strict');


local getArgs = require ('Module:Arguments').getArgs;
local getArgs = require ('Module:Arguments').getArgs;
local unicode = require ("Module:Unicode data"); -- for is_latin() and is_rtl()
local unicode = require ("Module:Unicode data"); -- for is_Latin() and is_rtl()
local yesno = require ('Module:Yesno');
local yesno = require ('Module:Yesno');


Line 22: Line 22:


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 cfg = mw.loadData ('Module:Lang/configuration' .. (mw.getCurrentFrame():getTitle():match ('/sandbox') or '')); -- for internationalization


local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
local namespace = mw.title.getCurrentTitle().namespace; -- used for categorization
Line 33: Line 35:
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
--[[--------------------------< M A K E _ E R R O R _ S P A N >--------------------------------------------------
]]
local function make_error_span (template, msg)
return table.concat ({'<span style="color:#d33">', cfg.misc_text_t.error, ': ', template, msg, '</span>'})
end
--[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
Substitutes $1, $2, etc in <message> with data from <data_t>. Returns plain-text substituted string when
<data_t> not nil; returns <message> else.
]]
local function substitute (message, data_t)
return data_t and mw.message.newRawMessage (message, data_t):plain() or message;
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_t, template)
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 '';
return substitute ('[$1] <span style="color:#d33">$2: {{$3}}: $4 ([[:Category:$5|$6]])</span>$7',
{
text or cfg.make_error_msg_t.undefined,
cfg.misc_text_t.error,
template,
msg,
category,
cfg.misc_text_t.help,
category_link
})
end
--[[--------------------------< P A R A M E T E R _ V A L I D A T E >------------------------------------------
]]
local function parameter_validate (args_t, template)
local err_msg = cfg.parameter_validate_t.invalid_param;
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
return substitute (err_msg, {param}); -- <param> not found so abandon
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
return substitute (err_msg, {param}); -- <param> not found so abandon
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
return substitute (err_msg, {param}); -- <param> not found so abandon
end
end
end
end




--[[--------------------------< I S _ S E T >------------------------------------------------------------------
--[[--------------------------< 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.
Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not
an empty string.


]]
]]


local function is_set( var )
local function is_set (var)
return not (var == nil or var == '');
return not (var == nil or var == '');
end
end
Line 94: Line 187:
--[[--------------------------< 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 acceptible assigned value, return the matching css font-style property value or,
Line 104: Line 197:


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:
Line 119: Line 212:


local function validate_italic (args)
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
local count = 0
Line 129: Line 222:


if count > 1 then -- return nil and an error message if more than one is set  
if count > 1 then -- return nil and an error message if more than one is set  
return nil, 'only one of |italic=, |italics=, or |i= can be specified';
return nil, cfg.validate_italic_t.multi_italic;
end
end
Line 138: Line 231:
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------
--[=[--------------------------< V A L I D A T E _ C A T _ A R G S >----------------------------------------------------------


Default behavior of the {{lang}} and {{lang-xx}} templates is to add categorization when the templates are used in mainspace.
Default behavior of the {{lang}} and {{lang-??}} 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
This default functionality may be suppressed by setting |nocat=yes or |cat=no.  This function selects one of these two parameters
to control categorization.
to control categorization.
Line 170: Line 263:
--[[--------------------------< 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;
Line 189: Line 282:
--[[--------------------------< 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
Line 225: Line 318:
--[[--------------------------< 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
Line 239: Line 332:
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
Line 245: Line 338:
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; all lower case.  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.
 
]]
]]


Line 259: Line 352:


if not is_set (source) then
if not is_set (source) then
return nil, nil, nil, nil, nil, 'missing language tag';
return nil, nil, nil, nil, nil, cfg.get_ietf_parts_t.missing_lang_tag;
end
end


Line 314: Line 407:


if not code then
if not code then
return nil, nil, nil, nil, nil, table.concat ({'unrecognized language tag: ', source}); -- don't know what we got but it is malformed
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


Line 320: Line 413:
if not (override_table[code] or lang_table[code] or synonym_table[code] or lang_dep_table[code]) then
if not (override_table[code] or lang_table[code] or synonym_table[code] or lang_dep_table[code]) then
return nil, nil, nil, nil, nil, table.concat ({'unrecognized language code: ', 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 and lang-xx code promoted to ISO 639-1|', code}));
table.insert (maint_cats, substitute (cfg.get_ietf_parts_t.maint_promo_cat, {code}));
table.insert (maint_msgs, table.concat ({'code: ', code, ' promoted to code: ', 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
Line 331: Line 424:
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, 'redundant script tag'; -- 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
Line 340: Line 433:
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 script_table[script] then
if not script_table[script] then
return code, nil, nil, nil, nil, table.concat ({'unrecognized script: ', script, ' for code: ', code}); -- language code ok, invalid script, don't know about the others (don't care?)
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 suppressed_table[script] then -- ensure that code-script does not use a suppressed script
if suppressed_table[script] then -- ensure that code-script does not use a suppressed script
if in_array (code, suppressed_table[script]) then
if in_array (code, suppressed_table[script]) then
return code, nil, nil, nil, nil, table.concat ({'script: ', script, ' not supported for code: ', 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
Line 351: Line 444:
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, 'redundant region tag'; -- 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
Line 360: Line 453:
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 region_table[region] then
if not region_table[region] then
return code, script, nil, nil, nil, table.concat ({'unrecognized region: ', region, ' for code: ', code});
return code, script, nil, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_reg_code, {region, code});
end
end
end
end
Line 366: Line 459:
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, 'redundant variant tag'; -- 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
Line 375: Line 468:
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 variant_table[variant] then -- make sure variant is valid
if not variant_table[variant] then -- make sure variant is valid
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', 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}), variant_table[variant]['prefixes']) then
if not in_array (table.concat ({code, '-', script}), variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code-script pair: ', code, '-', script});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code_scr, {variant, code, script});
end
end
elseif is_set (region) then -- if region set, there are some prefixes that require lang code and region (en-CA-newfound)
elseif is_set (region) then -- if region set, there are some prefixes that require lang code and region (en-CA-newfound)
if not in_array (code, variant_table[variant]['prefixes']) then -- first see if lang code is all that's required (en-oxendict though en-GB-oxendict is preferred)
if not in_array (code, variant_table[variant]['prefixes']) then -- first see if lang code is all that's required (en-oxendict though en-GB-oxendict is preferred)
if not in_array (table.concat ({code, '-', region}), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
if not in_array (table.concat ({code, '-', region}), variant_table[variant]['prefixes']) then -- now try for lang code and region (en-CA-newfound)
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code-region pair: ', code, '-', region});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code_reg, {variant, code, region});
end
end
end
end
else -- cheap way to determine if there are prefixes; fonipa and others don't have prefixes; # operator always returns 0
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
if variant_table[variant]['prefixes'][1] and not in_array (code, variant_table[variant]['prefixes']) then
return code, script, region, nil, nil, table.concat ({'unrecognized variant: ', variant, ' for code: ', code});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_var_code, {variant, code});
end
end
end
end
Line 397: Line 490:
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 override_table[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 ({'unrecognized private tag: ', private});
return code, script, region, nil, nil, substitute (cfg.get_ietf_parts_t.unrecog_pri, {private});
end
end
end
end
Line 403: Line 496:
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 and lang-xx'
end
table.insert (out, table.concat ({'[', args.text or 'undefined', '] '})); -- for error messages output args.text if available
table.insert (out, table.concat ({'<span style=\"color:#d33\">Error: {{', template, '}}: '}));
table.insert (out, msg);
table.insert (out, table.concat ({' ([[:Category:', category, ' template errors|help]])'}));
table.insert (out, '</span>');
if (0 == namespace or 10 == namespace) and not args.nocat then -- categorize in article space (and template space to take care of broken usages)
table.insert (out, table.concat ({'[[Category:', category, ' template errors]]'}));
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 >----------------------------------------------------
Line 457: Line 520:
--[[--------------------------< D I V _ M A R K U P _ A D D >--------------------------------------------------
--[[--------------------------< D I V _ M A R K U P _ A D D >--------------------------------------------------


adds <i> and </i> tags to list-item text or to implied <p>..</p> text. mixed not supported
Adds <i> and </i> tags to list-item text or to implied <p>..</p> text. Mixed not supported.


]]
]]


local function div_markup_add (text, style)
local function div_markup_add (text, style)
local implied_p = {};
if text:find ('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
if text:find ('^\n[%*:;#]') then -- look for list markup; list markup must begin at start of text
if 'italic' == style then
if 'italic' == style then
Line 484: Line 545:


return text;
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= attibute 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
end


Line 491: Line 576:
Add the html markup to text according to the type of content that it is: <span> or <i> tags for inline content or
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
<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_html (code, text, tag, rtl, style, size, language)
local function make_text_html (code, text, tag, rtl, style, size, language)
local html = {};
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 (html, '&#42;'); -- move proto language text prefix outside of italic markup if any; use numeric entity because plain 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
Line 511: Line 605:
end
end


table.insert (html, table.concat ({'<', tag})); -- open the <i>, <span>, or <div> html tag
table.insert (html_t, table.concat ({'<', tag})); -- open the <i>, <span>, or <div> html tag
code = code:gsub ('%-x%-.*', ''); -- strip private use subtag from code tag because meaningless outside of wikipedia
code = code:gsub ('%-x%-.*', ''); -- strip private use subtag from code tag because meaningless outside of wikipedia
table.insert (html, table.concat ({' lang="', code, '\"'})); -- add language attribute
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
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, ' dir="rtl"'); -- add direction attribute for right-to-left languages
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
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, ' dir="ltr"'); -- add direction attribute for left-to-right languages
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 (html, ' 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
Line 528: Line 622:
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 (html, 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 (html, 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 (html, table.concat ({style_added, ' title=\"', language})); -- start the title text
table.insert (html_t, text); -- insert the text
if 'zxx' == code then -- special case for this tag
 
table.insert (html, ' text'); -- not a language so don't use 'language' in title text
table.insert (html_t, table.concat ({'</', tag, '>'})); -- close the 'text' <i>, <span>, or <div> html tag
elseif mw.ustring.find (language, 'languages', 1, true) then
 
table.insert (html, ' collective text'); -- for collective languages
if is_set (language) then -- create a <title_text> string for the title= attribute in a wrapper span or div
else
local title_text;
table.insert (html, '-language text'); -- for individual languages
if 'zxx' == code then -- special case for this tag 'no linguistic content'
end
title_text = substitute ('$1 $2', {language, cfg.make_text_html_t.zxx}); -- not a language so don't use 'language' in title text
table.insert (html, '\">'); -- close the opening html tag
elseif mw.ustring.find (language, 'languages', 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 (html, table.concat ({style_added, '>'})); -- close the style attribute and close opening html tag
return table.concat (html_t);
end
end
table.insert (html, text); -- insert the text
table.insert (html, table.concat ({'</', tag, '>'})); -- close the <i>, <span>, or <div> html tag
return table.concat (html); -- put it all together and done
end
end


Line 561: Line 656:
[[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 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 in <language> languages]]
[[Category:Articles with text in <language> languages]]


Line 570: Line 665:


local function make_category (code, language_name, nocat, name_get)
local function make_category (code, language_name, nocat, name_get)
local cat = {};
local retval;
if ((0 ~= namespace) or nocat) and not name_get then -- only categorize in article space
if ((0 ~= namespace) or nocat) and not name_get then -- only categorize in article space
return ''; -- return empty string for concatenation
return ''; -- return empty string for concatenation
Line 578: Line 670:


if mw.ustring.find (language_name, 'languages', 1, true) then
if mw.ustring.find (language_name, 'languages', 1, true) then
return table.concat ({'[[Category:Articles with text in ', language_name, ']]'});
return substitute ('[[$1 $2]]', {cfg.make_category_t.collective_cat, language_name});
end
end
table.insert (cat, '[[Category:Articles containing ');
if this_wiki_lang_tag == code then
 
return substitute ('[[$1 $2 $3-$4]]', { -- unique category name for the local language
if 'en' == code then
cfg.make_category_t.cat_prefix,
table.insert (cat, 'explicitly cited ' .. language_name); -- falls back to English if regional name not available
cfg.make_category_t.explicit_cat,
language_name,
cfg.make_category_t.cat_postfix,
});
else
else
table.insert (cat, language_name);
return substitute ('[[$1 $2-$3]]', { -- category for individual languages
cfg.make_category_t.cat_prefix,
language_name,
cfg.make_category_t.cat_postfix,
});
end
end
table.insert (cat, '-language text]]');
return table.concat (cat);
end
end


Line 597: Line 692:
--[[--------------------------< 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()
Line 610: Line 705:
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, engvar)
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 the default italic style
table.insert (tout, "<i lang=\""); -- so use <i> tag
else
table.insert (tout, table.concat ({'<span style=\"font-style: ', style, '\" lang=\"'})); -- non-standard style, construct a span tag for it
end
table.insert (tout, code);
table.insert (tout, "-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 mw.ustring.find (language_name, 'languages', 1, true) then -- collective language names (plural 'languages' is part of the name)
if not mw.ustring.find (language_name, 'languages', 1, true) then -- collective language names (plural 'languages' is part of the name)
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
title_text = substitute ('$1-$2', {title_text, cfg.misc_text_t.language}); -- skip this text (individual and macro languages only)
end
end
table.insert (tout, ' romanization'); -- finish the tool tip; use romanization when neither script nor standard supplied
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
if script_table[tscript] then
if script_table[tscript] then
table.insert (tout, table.concat ({title_table[std][tscript:lower()], ' (', script_table[tscript], ' script) transliteration'})); -- add the appropriate text to the tool tip
title_text = substitute ('$1$2 ($3 $4) $5', { -- add the appropriate text to the tool tip
title_text,
title_t[std][tscript:lower()],
script_table[tscript],
cfg.make_translit_t.script,
cfg.make_translit_t.transliteration,
});
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
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
Line 654: Line 744:


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 ''; end -- invalid standard, setup for error message
if title_table[std][code] then -- if language code is in the table (transl may not provide a language code)
if title_t[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()], ' (', language_name, ' language) transliteration'})); -- add the appropriate text to the tool tip
title_text = substitute ('$1$2 ($3 $4) $5', { -- add the appropriate text to the tool tip
title_text,
title_t[std][code:lower()],
language_name,
cfg.misc_text_t.language,
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
title_text,
language_name,
cfg.make_translit_t.script,
cfg.make_translit_t.transliteration,
});
 
elseif is_set (code) then
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)
if not mw.ustring.find (language_name, 'languages', 1, true) then -- collective language names (plural 'languages' is part of the name)
table.insert (tout, '-language') -- skip this text (individual and macro languages only)
title_text = substitute ('$1-$2', { -- skip this text (individual and macro languages only)
title_text,
cfg.misc_text_t.language,
});
end
end
table.insert (tout, ' transliteration'); -- finish the tool tip
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 -- nil for the default italic style
tag = '<i lang="%s-Latn">%s</i>'
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
else
table.insert (tout, "</span>"); -- no language code so close the span tag
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
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


Line 694: Line 819:


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
Line 703: Line 828:
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 ('no text', args, template);
return make_error_msg (cfg.validate_text_t.no_text, args, template);
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 ('text has malformed markup', args, template);
return make_error_msg (cfg.validate_text_t.malformed_markup, args, template);
end
end


local style = args.italic;
local style = args.italic;


if ('unset' ~= style) and ('invert' ~=style) then
if (cfg.keywords_t.unset ~= 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 ('text has italic markup', args, template);
return make_error_msg (cfg.validate_text_t.italic_markup, args, template);
end
end
end
end
Line 722: Line 847:
--[[--------------------------< 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 = {};
Line 749: Line 874:
--[[--------------------------< 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_html() 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
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
regardless of language name; nil does nothing; presumes that the value in text is correct but removes extra splac.


]]
]]
Line 771: Line 896:
--[[--------------------------< H A S _ P O E M _ T A G >------------------------------------------------------
--[[--------------------------< H A S _ P O E M _ T A G >------------------------------------------------------


looks for a poem strip marker in text; returns true when found; false else
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
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.
the content that will replace the stripmarker.


Line 798: Line 923:
If text contains <poem>...</poem> stripmarker, return text unmodified and choose <div>..</div> tags because  
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.
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.


]]
]]
Line 806: Line 934:
if has_poem_tag (text) then -- contains poem stripmarker (we can't know the content of that)
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
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
elseif mw.text.trim (text):find ('\n\n+') then -- contains implied p tags
text = mw.text.trim (text); -- trim leading and trailing whitespace characters
text = mw.text.trim (text); -- trim leading and trailing whitespace characters
Line 823: Line 953:
--[[--------------------------< V A L I D A T E _ P R O T O >--------------------------------------------------
--[[--------------------------< V A L I D A T E _ P R O T O >--------------------------------------------------


validates value assigned to |proto=; permitted values are yes and no; yes returns as true, no returns as false,
Validates value assigned to |proto=; permitted values are yes and no; yes returns as true, no returns as false,
empty string (or parameter omitted) returns as nil; any other value returns as nil with a second return value of
empty string (or parameter omitted) returns as nil; any other value returns nil with <proto_param> as second
true indicating that some other value has been assigned to |proto=
return value for use in error message.


]]
]]


local function validate_proto (proto_param)
local function validate_proto (proto_param)
if 'yes' == proto_param then
if cfg.keywords_t.affirmative == proto_param then
return true;
return true;
elseif 'no' == proto_param then
elseif cfg.keywords_t.negative == proto_param then
return false;
return false;
elseif is_set (proto_param) then
elseif is_set (proto_param) then
return nil, true; -- |proto= something other than 'yes' or 'no'
return nil, proto_param; -- |proto= something other than 'yes' or 'no'
else
else
return nil; -- missing or empty
return nil; -- missing or empty
Line 844: Line 974:
--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------
--[[--------------------------< L A N G U A G E _ N A M E _ G E T >--------------------------------------------


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


returns language name if found in data tables; nil else
Returns language name if found in data tables; nil else.


]]
]]
Line 866: Line 996:


if lang_dep_table[code] and cat then -- because deprecated code may have been overridden to en.wiki preferred name
if lang_dep_table[code] and cat then -- because deprecated code may have been overridden to en.wiki preferred name
table.insert (maint_cats, table.concat ({'Lang and lang-xx using deprecated ISO 639 codes|', code}));
table.insert (maint_cats, substitute (cfg.language_name_get_t.deprecated_cat, {code}));
table.insert (maint_msgs, table.concat ({'code: ', code, ' is deprecated'}));
table.insert (maint_msgs, substitute (cfg.language_name_get_t.deprecated_msg, {code}));
end
end


return name; -- name from data tables or nil
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)
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}); -- emit an error message with position of first offending character
end
end
end
end
--[[--------------------------< I S _ L A T I N >--------------------------------------------------------------
Created because unicode does not have Latin theta 'θ' character.  The Greek 'θ' is, apparently, commonly used
in certain romanizations.  This function attempts to discover if <text> script is Latn with Greek 'θ' or some
other script with Greek 'θ'.
when <text> is or has Greek 'θ':
for {{lang}}, {{langx}}, and {{lang-??}}, returns boolean true when <text>:
has theta and all other characters are Latn
has theta as the only character, <script> is Latn
for {{transliteration}}, returns boolean true when <text>:
has theta and all other characters are Latn
has theta as the only character
]]
local function is_latin (text, script, transl)
if mw.ustring.find (text, 'θ', 1, true) then -- does <text> contain 'θ'?
text = text:gsub ('θ', ''); -- remove theta from <text>
if 0 == text:len() then -- will be zero if theta was the only character in <text>
if transl then -- not nil for {{transliteration}}; assume Latin theta because this is 'transliteration' template
return true;
end
return (script and ('latn' == script:lower())) or false; -- {{lang}}, {{langx}}, and {{lang-??}}; true when script is Latn; false else
end
return unicode.is_Latin (text); -- return true when all characters in modified <text> are Latn script; false else
end
return unicode.is_Latin (text); -- return true when all characters in <text> are Latn script; false else
end
end


Line 876: Line 1,071:
--[[--------------------------< _ L A N G >--------------------------------------------------------------------
--[[--------------------------< _ 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 received from the template's frame (parent frame)
Parameters are received from the template's frame (parent frame).


]]
]]
Line 893: Line 1,088:
local msg; -- for error messages
local msg; -- for error messages
local tag = 'span'; -- initial value for make_text_html()
local tag = 'span'; -- initial value for make_text_html()
local template = args.template or 'Lang';
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 = {};
validate_cat_args (args); -- determine if categorization should be suppressed
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 ('conflicting: {{{1}}} and |code=', args, template);
return make_error_msg (substitute (cfg.lang_t.conflict_n_param, {'1', cfg.lang_t.conflict_n_param_types.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
Line 904: Line 1,102:


if args[2] and args.text then
if args[2] and args.text then
return make_error_msg ('conflicting: {{{2}}} and |text=', args, template);
return make_error_msg (substitute (cfg.lang_t.conflict_n_param, {'2', cfg.lang_t.conflict_n_param_types.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
end
 
msg = validate_text (template, args); -- ensure that |text= is set
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
Line 916: Line 1,114:
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly
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 == 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
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
if msg then
return make_error_msg (table.concat ({'invalid |proto=: ', args.proto}), args, template);
return make_error_msg (substitute (cfg.lang_t.invalid_proto, {msg}), args, template);
end
end


Line 926: Line 1,124:


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


Line 936: Line 1,141:
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 -- script is latn
if ('latn' == subtags.script) or -- script is latn
(this_wiki_lang_tag ~= 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)
(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)
args.italic = 'italic'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
args.italic = 'italic'; -- DEFAULT for {{lang}} templates is upright; but if latn script set for font-style:italic
else
else
Line 954: Line 1,159:
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
language_name = language_name_get (args.code, code, true); -- get language name; try ietf tag first, then code w/o variant then code w/ variant


if 'invert' == args.italic and 'span' == tag then -- invert only supported for in-line content
if cfg.keywords_t.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
Line 962: Line 1,167:
table.insert (out, make_text_html (args.code, args.text, tag, 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
Line 970: Line 1,175:
--[[--------------------------< L A N G >----------------------------------------------------------------------
--[[--------------------------< 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 received from the template's frame (parent frame)
Parameters are received from the template's frame (parent frame).


]]
]]


local function lang (frame)
local function lang (frame)
local args = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text
local args_t = getArgs (frame, { -- this code so that we can detect and handle wiki list markup in text
valueFunc = function (key, value)
valueFunc = function (key, value)
if 2 == key or 'text' == key then -- the 'text' parameter; do not trim wite space
if 2 == key or 'text' == key then -- the 'text' parameter; do not trim wite space
Line 994: Line 1,199:
});
});


return _lang (args);
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 msg then
return make_error_msg (msg, args_t, cfg.templates_t.lang); -- when template has unsupported params, abandon with error message
end
 
return _lang (args_t);
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, substitute ('<abbr title="$1">$2</abbr>', {cfg.translation_make_t.lit_xlation, cfg.translation_make_t.lit_abbr})); -- unlinked form
else
table.insert (translation_t, make_wikilink (cfg.translation_make_t.lit_xlation, cfg.translation_make_t.lit_abbr)); -- linked form
end
table.insert (translation_t, "&thinsp;</small>"); -- close the <small> html tag
end
table.insert (translation_t, table.concat ({'&#39;', args_t.translation, '&#39;'})); -- use html entities to avoid wiki markup confusion
return table.concat (translation_t); -- make a big string and done
end
end




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


For the {{lang-xx}} templates, the only parameter required to be set in the template is the language code.  All
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-xx}} templates for languages
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 knows 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.


Line 1,029: Line 1,266:
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 templates where |text= is not 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
Line 1,042: Line 1,279:
]]
]]


local function _lang_xx (args)
local function _lang_xx (args, base_template) -- base_template will be either of 'Langx' or 'Lang-xx'
local out = {};
local out = {};
local language_name; -- used to make display text, article links
local language_name; -- used to make display text, article links
Line 1,051: Line 1,288:
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 tag = 'span'; -- initial value for make_text_html()
local template = args.template or 'Lang-xx';
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 ('conflicting: {{{1}}} and |text=', args, template);
maint_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
return make_error_msg (substitute (cfg.lang_t.conflict_n_param, {translit_idx, cfg.lang_t.conflict_n_param_types.text}), args, template);
else
else
args.text = args[1] or args.text; -- prefer args.text
args.text = args[text_idx] or args.text; -- prefer positional 'text' parameter
end
end
 
msg = validate_text (template, 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
Line 1,069: Line 1,312:
args.text, tag = html_tag_select (args.text); -- inspects text; returns appropriate html tag with text trimmed accordingly
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[translit_idx] and args.translit then
return make_error_msg ('conflicting: {{{2}}} and |translit=', args, template);
return make_error_msg (substitute (cfg.lang_t.conflict_n_param, {translit_idx, cfg.lang_t.conflict_n_param_types.translit}), args, template);
 
else
else
args.translit = args[2] or args.translit -- prefer args.translit
args.translit = args[translit_idx] or args.translit -- prefer positional 'translit' parameter
end
 
if args.translit then
local latn, pos = is_latin (args.translit, nil, true);
if not latn then
return make_error_msg (substitute (cfg.lang_xx_t.translit_nonlatn, {pos}), args, template);
end
end
end
 
if args[3] and (args.translation or args.lit) then
args.engvar = cfg.engvar_sel_t[args.engvar] or cfg.default_engvar; -- |engvar= when valid; cfg.default_engvar else
return make_error_msg ('conflicting: {{{3}}} and |lit= or |translation=', args, template);
 
if args[xlate_idx] and (args.translation or args.lit) then
return make_error_msg (substitute (cfg.lang_xx_t.conflict_n_lit, {translit_idx}), args, template);
elseif args.translation and args.lit then
elseif args.translation and args.lit then
return make_error_msg ('conflicting: |lit= and |translation=', args, template);
return make_error_msg (cfg.lang_xx_t.conflict_lit, args, template);
else
else
args.translation = args[3] or args.translation or args.lit; -- prefer args.translation
args.translation = args[xlate_idx] or args.translation or args.lit; -- prefer positional 'translation' parameter
end
end


if args.links and args.link then
if args.links and args.link then
return make_error_msg ('conflicting: |links= and |link=', args, template);
return make_error_msg (cfg.lang_xx_t.conflict_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
Line 1,091: Line 1,344:
validate_cat_args (args); -- determine if categorization should be suppressed
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 == 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
Line 1,099: Line 1,352:
end
end
local is_latn_text, pos = is_latin (args.text, subtags.script); -- make a boolean
msg = text_script_match_test (subtags.script, is_latn_text, pos)
if msg then -- if an error detected then there is an error message
return make_error_msg (msg, args, template);
end
args.italic, msg = validate_italic (args);
args.italic, msg = validate_italic (args);
if msg then
if msg then
return make_error_msg (msg, args, template);
return make_error_msg (msg, args, template);
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
if ('latn' == subtags.script) or -- script is latn
args.italic = 'italic'; -- |script=Latn; set for font-style:italic
(this_wiki_lang_tag ~= code and not is_set (subtags.script) and is_latn_text) then -- text is not this wiki's language, no script specified and is wholly latn script (auto-italics)
args.italic = 'italic'; -- set font-style:italic
else
args.italic = 'inherit'; -- italic not set; script not latn; inherit current style
end
end
else -- {{lang-xx}} does not do auto italics; retained for those wikis that don't support {{langx}}
if nil == args.italic then -- args.italic controls
if is_set (subtags.script) then
if 'latn' == subtags.script then
args.italic = 'italic'; -- |script=Latn; set for font-style:italic
else
args.italic = initial_style_state; -- italic not set; script is not latn; set for font-style:<initial_style_state>
end
else
else
args.italic = initial_style_state; -- italic not set; script is not latn; 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
else
args.italic = initial_style_state; -- here when |italic= and |script= not set; set for font-style:<initial_style_state>
end
end
end
end
Line 1,126: Line 1,398:
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
args.proto, msg = validate_proto (args.proto); -- return boolean, or nil, or nil and error message flag
if msg then
if msg then
return make_error_msg (table.concat ({'invalid |proto=: ', args.proto}), args, template);
return make_error_msg (substitute (cfg.lang_t.invalid_proto, {args.proto}), args, template);
end
end


Line 1,140: Line 1,412:
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 mw.ustring.find (language_name, 'languages', 1, true) then
if mw.ustring.find (language_name, 'languages', 1, true) then
table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
table.insert (out, make_wikilink (language_name)); -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
elseif lang_data.article_name[args.code:lower()] then -- is ietf tag in article name over ride?
table.insert (out, make_wikilink (lang_data.article_name[args.code:lower()], language_name)); -- language name with wikilink from override data
elseif 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
table.insert (out, make_wikilink (lang_data.article_name[code], 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 (substitute ('$1 $2', {language_name, cfg.misc_text_t.language}), language_name)); -- language name with wikilink
end
end
end
end
Line 1,154: Line 1,428:
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
Line 1,162: Line 1,436:
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))
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 unicode.is_Latin (args.text) then -- transliteration (not supported in {{lang}}); not supported when args.text is wholly latn text (this is an imperfect test)
if is_set (args.translit) and not 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
Line 1,171: Line 1,445:
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 ({'Romanization of ', translit_script_name})); -- make a title object
 
if translit_title.exists and ('no' ~= args.link) then
local translit_title_obj = mw.title.makeTitle (0, substitute ('$1 $2',{cfg.lang_xx_t.romanization, translit_script_name})); -- make a title object; no engvar, article titles use US spelling
table.insert (out, make_wikilink ('Romanization of ' .. translit_script_name or language_name, 'romanized') .. ':'); -- 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 ('$1 $2', {cfg.lang_xx_t.romanization, translit_script_name or language_name}),
substitute ('$1', {cfg.engvar_t[args.engvar]['romanisz_pt']})) .. ':'); -- make a wikilink if there is an article to link to; engvar the display text
 
else
else
table.insert (out, 'romanized:'); -- else plain text
table.insert (out, substitute ('$1:', {cfg.engvar_t[args.engvar]['romanisz_pt']})); -- else plain text per engvar
 
end
end
table.insert (out, '&nbsp;</small>'); -- close the small tag
table.insert (out, '&nbsp;</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, args.engvar)
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, template);
return 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>
return make_error_msg (cfg.lang_xx_t.xlit_of_latn, args, template); -- emit error message and abandon
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, '<abbr title="literal translation">lit.</abbr>');
else
table.insert (out, make_wikilink ('Literal translation', 'lit.'));
end
table.insert (out, "&thinsp;</small>");
end
table.insert (out, table.concat ({'&#39;', args.translation, '&#39;'})); -- use html entities to avoid wiki markup confusion
end
end
Line 1,211: Line 1,482:
--[[--------------------------< L A N G _ X X _ A R G S _ G E T >----------------------------------------------
--[[--------------------------< L A N G _ X X _ A R G S _ G E T >----------------------------------------------


common function to get args table from {{lang-??}} templates
Common function to get args table from {{lang-??}} templates.
 
Returns table of args.


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)
local function lang_xx_args_get (frame, base_template)
local args = getArgs(frame,
local args_t = getArgs(frame,
{
{
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}}
parentFirst= true, -- parameters in the template override parameters set in the {{#invoke:}}
valueFunc = function (key, value)
valueFunc = function (key, value)
if 1 == key then -- the 'text' parameter; do not trim wite space
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'
return value; -- return untrimmed 'text' positional parameter
elseif value then -- all other values: if the value is not nil
elseif value then -- all other values: if the value is not nil
value = mw.text.trim (value); -- trim whitespace
value = mw.text.trim (value); -- trim whitespace
Line 1,234: Line 1,507:
});
});


return args;
return args_t;
end
end


Line 1,240: Line 1,513:
--[[--------------------------< 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 function lang_xx_italic (frame)
local args = lang_xx_args_get (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 msg then
return make_error_msg (msg, args, cfg.templates_t.langxx); -- when template has unsupported params, abandon with error message
end
initial_style_state = 'italic';
initial_style_state = 'italic';
return _lang_xx (args);
return _lang_xx (args, cfg.templates_t.langxx) .. '[[Category:Pages using Lang-xx templates]]'; -- temporary category
end
end


Line 1,254: Line 1,533:
--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------
--[[--------------------------< _ L A N G _ X X _ I T A L I C >------------------------------------------------


Entry point ffrom another module. Sets the initial style state to italic.
Entry point from another module. Sets the initial style state to italic.


]]
]]
Line 1,260: Line 1,539:
local function _lang_xx_italic (args)
local function _lang_xx_italic (args)
initial_style_state = 'italic';
initial_style_state = 'italic';
return _lang_xx (args);
return _lang_xx (args, cfg.templates_t.langxx);
end
end


Line 1,266: Line 1,545:
--[[--------------------------< 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 function lang_xx_inherit (frame)
local args = lang_xx_args_get (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 msg then
return make_error_msg (msg, args, cfg.templates_t.langxx); -- when template has unsupported params, abandon with error message
end


initial_style_state = 'inherit';
initial_style_state = 'inherit';
return _lang_xx (args);
return _lang_xx (args, cfg.templates_t.langxx) .. '[[Category:Pages using Lang-xx templates]]'; -- temporary category
end
end


Line 1,280: Line 1,565:
--[[--------------------------< _ L A N G _ X X _ I N H E R I T >----------------------------------------------
--[[--------------------------< _ L A N G _ X X _ I N H E R I T >----------------------------------------------


Entry point from another module. Sets the initial style state to inherit.
Entry point from another module. Sets the initial style state to inherit.


]]
]]
Line 1,286: Line 1,571:
local function _lang_xx_inherit (args)
local function _lang_xx_inherit (args)
initial_style_state = 'inherit';
initial_style_state = 'inherit';
return _lang_xx (args);
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>
 
local msg = parameter_validate (args_t, cfg.templates_t.langx);
if msg then
return make_error_msg (msg, args_t, cfg.templates_t.langx);
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
return 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
 
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);
end
 
 
--[[--------------------------< L A N G X >--------------------------------------------------------------------
 
Entry point for {{langx}}.
 
this function calls _lang_xx() to render non-English text. The {{lang-??}} templates have three positional paramters
but {{langx}} has four:
 
|  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
end


Line 1,294: Line 1,641:
Returns true when a language name associated with IETF language tag exists; nil else.  IETF language tag must be valid.
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.
All code combinations supported by {{lang}} and the {{lang-??}} templates are supported by this function.


Module entry point from another module
Module entry point from another module.


]]
]]
Line 1,310: Line 1,657:
--[[--------------------------< I S _ I E T F _ T A G >--------------------------------------------------------
--[[--------------------------< I S _ I E T F _ T A G >--------------------------------------------------------


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


]]
]]
Line 1,336: Line 1,683:
Returns language name associated with IETF language tag if valid; error message else.
Returns language name associated with IETF language tag if valid; error message else.


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


Module entry point from another module
Module entry point from another module.


]]
]]
Line 1,347: Line 1,694:
local subtags = {}; -- IETF subtags script, region, variant, and private
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = args[1]; -- save a copy of the input IETF subtag
local raw_code = args[1]; -- save a copy of the input IETF subtag
local link = 'yes' == args['link']; -- make a boolean
local link = cfg.keywords_t.affirmative == args['link']; -- make a boolean
local label = args.label;
local label = args.label;
local code; -- the language code
local code; -- the language code
Line 1,356: Line 1,703:
if msg then
if msg then
local template = (args['template'] and table.concat ({'{{', args['template'], '}}: '})) or ''; -- make template name (if provided by the template)
local template = (args['template'] and table.concat ({'{{', args['template'], '}}: '})) or ''; -- make template name (if provided by the template)
return table.concat ({'<span style=\"color:#d33\">Error: ', template, msg, '</span>'});
return make_error_span (template, msg);
end
end


Line 1,367: Line 1,714:
if mw.ustring.find (language_name, 'languages', 1, true) then
if mw.ustring.find (language_name, 'languages', 1, true) then
language_name = make_wikilink (language_name, label); -- collective language name uses simple wikilink
language_name = make_wikilink (language_name, label); -- collective language name uses simple wikilink
elseif lang_data.article_name[code] then
elseif lang_data.article_name[raw_code:lower()] then -- is ietf tag in article name override?
language_name = make_wikilink (lang_data.article_name[raw_code:lower()], label or language_name); -- language name with wikilink from override data
elseif lang_data.article_name[code] then -- is language tag in article name override?
language_name = make_wikilink (lang_data.article_name[code], label or language_name); -- language name with wikilink from override data
language_name = make_wikilink (lang_data.article_name[code], label or language_name); -- language name with wikilink from override data
else
else
language_name = make_wikilink (language_name .. ' language', label or language_name); -- language name with wikilink
language_name = make_wikilink (substitute ('$1 $2', {language_name, cfg.misc_text_t.language}), label or language_name); -- language name with wikilink
end
end
end
end
Line 1,380: Line 1,729:
--[[--------------------------< N A M E _ F R O M _ T A G >----------------------------------------------------
--[[--------------------------< N A M E _ F R O M _ T A G >----------------------------------------------------


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


]]
]]
Line 1,395: Line 1,744:
that disambiguator must be omitted (they are not present in the data name-to-tag tables).
that disambiguator must be omitted (they are not present in the data name-to-tag tables).


Module entry point from another module
Module entry point from another module.


]]
]]
Line 1,410: Line 1,759:
return tag, true; -- language name found so return tag and done; second return used by is_lang_name()
return tag, true; -- language name found so return tag and done; second return used by is_lang_name()
else
else
msg = 'language: ' .. args[1] .. ' not found' -- language name not found, error message
msg = substitute (cfg.tag_from_name_t.lang_not_found, {args[1]}); -- language name not found, error message
end
end
else
else
msg = 'missing language name' -- language name not provided, error message
msg = cfg.tag_from_name_t.missing_lang_name; -- language name not found, error message
end
end


Line 1,420: Line 1,769:
template = table.concat ({'{{', args['template'], '}}: '}); -- make template name (if provided by the template)
template = table.concat ({'{{', args['template'], '}}: '}); -- make template name (if provided by the template)
end
end
return table.concat ({'<span style=\"color:#d33\">Error: ', template, msg, '</span>'});
return make_error_span (template, msg);
 
end
end


Line 1,426: Line 1,776:
--[[--------------------------< T A G _ F R O M _ N A M E >----------------------------------------------------
--[[--------------------------< T A G _ F R O M _ N A M E >----------------------------------------------------


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


]]
]]
Line 1,438: Line 1,788:
--[[--------------------------< I S _ L A N G _ N A M E >------------------------------------------------------
--[[--------------------------< I S _ L A N G _ N A M E >------------------------------------------------------


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


]]
]]
Line 1,450: Line 1,800:
--[[--------------------------< _ T R A N S L >----------------------------------------------------------------
--[[--------------------------< _ T R A N S L >----------------------------------------------------------------


Module entry point from another module
Module entry point from another module.


]]
]]
Line 1,460: Line 1,810:
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;


if is_set (args[3]) then -- [3] set when {{transl|code|standard|text}}
maint_cats = {}; -- initialize because when this module required into another module, these only declared once so only initialzed once
maint_msgs = {};
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 ({'unrecognized transliteration standard: ', args.translit_std}), args, 'Transl');
return make_error_msg (substitute (cfg.transl_t.unrecog_xlit_std, {args.translit_std}), args, template);
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?$') then -- args[2] missing; is args[1] a code or is it the transliterated text?
if args[1] and (args[1]:match ('^%a%a%a?%a?$') 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
return make_error_msg (cfg.transl_t.no_text, args, template); -- 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 ('missing language / script code', args, 'Transl');
return make_error_msg (cfg.transl_t.missing_lang_scr, args, template);
end
end
end
end
Line 1,482: Line 1,837:


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 ({'unrecognized language / script code: ', args[1]}), args, 'Transl'); -- invalid language / script code
return make_error_msg (substitute (cfg.transl_t.unrecog_lang_scr, {args[1]}), args, template); -- invalid language / script code
end
end
else
else
return make_error_msg ('missing language / script code', args, 'Transl'); -- missing language / script code so quit
return make_error_msg (cfg.transl_t.missing_lang_scr, args, template); -- missing language / script code so quit
end
 
local latn, pos = is_latin (args.text, nil, true);
if not latn then -- text is not latn
return make_error_msg (substitute (cfg.lang_xx_t.translit_nonlatn, {pos}), args, template);
end
end


args.italic, msg = validate_italic (args);
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, template);
end
end
Line 1,499: Line 1,860:
args.italic = nil; -- set to nil;  
args.italic = nil; -- set to nil;  
end
end
args.engvar = cfg.engvar_sel_t[args.engvar] or cfg.default_engvar; -- |engvar= when valid; cfg.default_engvar else


if override_table[args.code] then -- is code a language code defined in the override table?
if override_table[args.code] then -- is code a language code defined in the override table?
language_name = override_table[args.code];
language_name = override_table[args.code];
args.code = args.code:match ('^%a%a%a?'); -- if private use, strip all but language subtag
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables?
elseif lang_table[args.code] then -- is code a language code defined in the standard language code tables?
language_name = lang_table[args.code];
language_name = lang_table[args.code];
Line 1,511: Line 1,875:
args.code = ''; -- unset because not a language code
args.code = ''; -- unset because not a language code
else
else
return make_error_msg (table.concat ({'unrecognized language / script code: ', args.code}), args, 'Transl'); -- invalid language / script code
return make_error_msg (substitute (cfg.transl_t.unrecog_lang_scr, {args.code}), args, template); -- invalid language / script code
end
end
-- here only when all parameters passed to make_translit() are valid
-- here only when all parameters passed to make_translit() are valid
return make_translit (args.code, language_name, args.text, args.translit_std, script, args.italic);
return make_translit (args.code, language_name, args.text, args.translit_std, script, args.italic, args.engvar);
end
end


Line 1,520: Line 1,884:
--[[--------------------------< T R A N S L >------------------------------------------------------------------
--[[--------------------------< T R A N S L >------------------------------------------------------------------


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


]]
]]
Line 1,531: Line 1,895:
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------


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


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


Module entry point from another module
Module entry point from another module.


]]
]]
Line 1,542: Line 1,906:
local subtags = {}; -- IETF subtags script, region, variant, and private
local subtags = {}; -- IETF subtags script, region, variant, and private
local raw_code = args_t[1]; -- save a copy of the input IETF subtag
local raw_code = args_t[1]; -- save a copy of the input IETF subtag
local link = 'yes' == args_t.link; -- make a boolean
local link = cfg.keywords_t.affirmative == args_t.link; -- make a boolean
local label = args_t.label;
local label = args_t.label;
local code; -- the language code
local code; -- the language code
Line 1,551: Line 1,915:
if msg then
if msg then
local template = (args_t.template and table.concat ({'{{', args_t.template, '}}: '})) or ''; -- make template name (if provided by the template)
local template = (args_t.template and table.concat ({'{{', args_t.template, '}}: '})) or ''; -- make template name (if provided by the template)
return table.concat ({'<span style=\"color:#d33\">Error: ', template, msg, '</span>'});
return make_error_span (template, msg);
end
end


Line 1,568: Line 1,932:
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------
--[[--------------------------< C A T E G O R Y _ F R O M _ T A G >--------------------------------------------


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


]]
]]
Line 1,583: Line 1,947:
category_from_tag = category_from_tag,
category_from_tag = category_from_tag,
lang = lang, -- entry point for {{lang}}
lang = lang, -- entry point for {{lang}}
langx = langx, -- entry point for {{langx}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_inherit = lang_xx_inherit, -- entry points for {{lang-??}}
lang_xx_italic = lang_xx_italic,
lang_xx_italic = lang_xx_italic,
Line 1,590: Line 1,955:
tag_from_name = tag_from_name, -- returns ietf tag associated with language 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
name_from_tag = name_from_tag, -- used for template documentation; possible use in ISO 639 name from code templates
transl = transl, -- entry point for {{transl}}
transl = transl, -- entry point for {{transliteration}}
_category_from_tag = _category_from_tag, -- entry points when this module is require()d into other modules
_category_from_tag = _category_from_tag, -- entry points when this module is require()d into other modules
_lang = _lang,
_lang = _lang,
_langx = _langx,
_lang_xx_inherit = _lang_xx_inherit,
_lang_xx_inherit = _lang_xx_inherit,
_lang_xx_italic = _lang_xx_italic,
_lang_xx_italic = _lang_xx_italic,
Line 1,601: Line 1,967:
_name_from_tag = _name_from_tag,
_name_from_tag = _name_from_tag,
_transl = _transl,
_transl = _transl,
_translation_make = translation_make,
};
};