Module:Lang/data/iana languages/make: Difference between revisions

Revision as of 02:56, 3 September 2020

Latest revision as of 14:55, 10 July 2024

(5 intermediate revisions by 2 users not shown)

Line 1:

require('Module:No globalsstrict');

local p = {};

Line 31 ⟶ 30:

before the Comments line.

Records with Deprecatedprivate datesuse or Preferred-Value codessubtags are ignored as are private use codes.

]=]

Line 47 ⟶ 46:

for line in string.gmatch (record, '([^\n]+)\n') do -- get a \n terminated line of text (without the \n)

local before_colonlabel = string.match(line, "(.-):")

if not before_colonlabel and string.find (line, '^ .+') and not in_comments then -- if a continuation line but not a comments continuation

descriptions[#descriptions] = string.gsub (descriptions[#descriptions], '\"$', ''); -- remove trailing quote mark from previous description

descriptions[#descriptions] = descriptions[#descriptions] .. ' ' .. string.match (line, '^ (.+)') .. '\"'; -- extract and save the continuation with new quote mark

elseif before_colonlabel == 'Subtag' then -- if this line is the subtag line

code = string.match (line, 'Subtag: (%w+)'); -- extract and save to subtag's code

elseif before_colonlabel == 'Description' then -- if this line is a description line

local desc = string.match (line, 'Description: (.+)'); -- extract the description

desc = string.gsub (desc, '"', '\\"'); -- in case description contains quote marks (see 1959acad)

table.insert (descriptions, '\"' .. desc .. '\"'); -- save the description wrapped in quote marks

elseif before_colonlabel == 'Prefix' then -- if this line is a prefix line

table.insert (prefixes, '\"' .. string.match (line, 'Prefix: (.+)'):lower() .. '\"'); -- extract and save the prefix wrapped in quote marks

elseif before_colonlabel == 'Comments' then -- if this line is a comments line

in_comments = true;

end

Line 94 ⟶ 93:

before the Comments line.

Records with Deprecatedprivate datesuse or Preferred-Value codessubtags are ignored as are private use codes.

]=]

Line 101 ⟶ 100:

local code;

local suppress; -- Suppress script for this code if specified

local deprecated; -- boolean; true when subtag is deprecated

local descriptions = {};

local in_comments = false;

if string.find (record, 'Deprecated') or string.:find (record, 'Preferred%-Value') or string.find (record, 'Private use') then

return 'skip';

end

for line in string.record:gmatch (record, '([^\n]+)\n') do -- get a \n terminated line of text (without the \n)

local before_colonlabel = string.match(line,:match "('(.-):"');

if before_colon'Subtag' == 'Subtag'label then -- if this line is the subtag line

code = string.line:match (line, 'Subtag: (%w+)'); -- extract and save to subtag's code

elseif before_colon'Description' == 'Description'label then -- if this line is a description line

table.insert (descriptions, '\"' .. string.line:match (line, 'Description: (.+)') .. '\"'); -- extract and save the name wrapped in quote marks

elseif before_colon'Deprecated' == 'Suppress-Script'label then

deprecated = true; -- subtag is deprecated; set our flag

suppress = string.match (line, 'Suppress%-Script: (%S+)');

elseif before_colon'Suppress-Script' == 'Comments'label then -- if this line is a comments line

suppress = string.line:match (line, 'Suppress%-Script: (%S+)');

elseif 'Comments' == label then -- if this line is a comments line

in_comments = true;

elseif string.line:find (line, '^ .+') and not in_comments then -- if a continuation line but not a commnets continuation

descriptions[#descriptions] = string.gsub (descriptions[#descriptions],:gsub ('\"$', ''); -- remove trailing quote mark from previous description

descriptions[#descriptions] = descriptions[#descriptions] .. ' ' .. string.line:match (line, '^ (.+)') .. '\"'; -- extract and save the continuation with new quote mark

end

end

return code, table.concat (descriptions, ', '), suppress, deprecated;

end

Line 131 ⟶ 133:

read a local copy of the IANA language-subtag-registry file and from it build tables to replace the tables in:

[[Module:LanguageLang/data/iana languages]]

[[Module:LanguageLang/data/iana scriptsregions]]

[[Module:LanguageLang/data/iana regionsscripts]]

[[Module:Lang/data/iana supressed cripts]]

[[Module:Lang/data/iana variants]]

current language-subtag-registry file can be found at: http://www.iana.org/assignments/language-subtag-registry

Line 140 ⟶ 144:

]=]

local function p.iana_extract (frame)

local page = mw.title.getCurrentTitle(); -- get a page object for this page

local content = page:getContent(); -- get unparsed content

local lang_table = {}; -- languages go here

local lang_dep_table = {}; -- deprecated languages go here

local script_table = {}; -- scripts go here

local region_table = {}; -- regions go here

local variant_table = {}; -- variants go here

local suppress_table = {}; -- here we collect suppressed scripts and associated language codes

local iso_639_1_table = {}; -- ISO 639-1 languages; not used by Module:Lang but included here to ensure Module:Lang/data/ISO_639-1 gets updated

local file_date; -- first line

Line 154 ⟶ 160:

local prefixes; -- used for language variants only

local suppress; -- a code's suppress script

local deprecated; -- boolean: true when subtag is deprecated

file_date = content:match ('(File%-Date: %d%d%d%d%-%d%d%-%d%d)'); -- get the file date line from this version of the source file

for record in string.gmatch (content, '%%%%([^%%]+)') do -- get a %% delimited 'record' from the file; leave off the delimiters

local record_type = string.match(record, 'Type: (%w+)')

if record_type == 'language' then -- if a language record

code, descriptions, suppress, deprecated = get_lang_script_region_parts (record); -- get the code, description(s), and suppress script, and deprecated flag

if code and ('skip' ~= code) then

if deprecated then

table.insert (lang_table, "[\"" .. code .. "\"] = {" .. descriptions .. "}"); -- make table entries

table.insert (lang_dep_table, "[\"" .. code .. "\"] = {" .. descriptions .. "}"); -- make table entries

else

table.insert (lang_table, "[\"" .. code .. "\"] = {" .. descriptions .. "}"); -- make table entries

if 2 == code:len() then

table.insert (iso_639_1_table, "[\"" .. code .. "\"] = {" .. descriptions .. "}"); -- make table entries

end

end

elseif not code then

table.insert (lang_table, "[\"error\"] = {" .. record .. "}"); -- code should never be nil, but inserting an error entry in the final output can be helpful

Line 222 ⟶ 236:

for script, code_tbl in pairs (suppress_table) do

local LIMIT = 11; -- max number of subtags on a line before a line break

table.insert (pretty_suppressed,

local fragment_tbl = {}; -- groups of LIMIT number of subtags collected here

table.concat ({'[\"', script, '\"] = {', table.concat (code_tbl, ', '), '}'})

for i=1, #code_tbl, LIMIT do

local stop = ((i+LIMIT-1) > #code_tbl) and #code_tbl or i+LIMIT-1; -- calculate a table.concat stop position

table.insert (fragment_tbl, table.concat (code_tbl, ', ', i, stop)); -- get the fragment and save it

end

table.insert (pretty_suppressed, -- and make all pretty

table.concat ({'[\"', script, '\"] = {', table.concat (code_tblfragment_tbl, ', \n\t\t\t\t'), '}'})

);

end

table.sort (pretty_suppressed);

-- make prettyfinal output pretty

return "'<br /><pre>------------------------------< "I ..A file_dateN ..A "<br />return {<brL />&#9;"A ..N table.concatG (lang_table,U ',<brA />&#9;')G ..E "<brS />&#9;}--------------------------------------------------<br />-- "' ..

file_date .. "<br />returnlocal active = {<br />&#9;" .. table.concat (script_tablelang_table, ',<br />&#9;') .. "<br />&#9;}<br />--<br />" ..

file_date"local ..deprecated "<br />return= {<br />&#9;" .. table.concat (region_tablelang_dep_table, ',<br />&#9;') .. "<br />&#9;}<br />--<br />" ..

file_date .. "<br />return {<br />&#9;"active .. table.concat (variant_table,= 'active,<br />&#9;')deprecated ..= "deprecated,<br />&#9;}<br />--<br />" ..

'------------------------------< I A N A S C R I P T S >------------------------------------------------------<br />--' ..

file_date .. "<br />return {<br />&#9;" .. table.concat (pretty_suppressed, ',<br />&#9;') .. "<br />&#9;}<br />" .. "</pre>";

file_date .. "<br />return {<br />&#9;" .. table.concat (script_table, ',<br />&#9;') .. "<br />&#9;}<br /><br />" ..

'------------------------------< I A N A R E G I O N S >------------------------------------------------------<br />--' ..

file_date .. "<br />return {<br />&#9;" .. table.concat (region_table, ',<br />&#9;') .. "<br />&#9;}<br /><br />" ..

'------------------------------< I A N A V A R I A N T S >----------------------------------------------------<br />--' ..

file_date .. "<br />return {<br />&#9;" .. table.concat (variant_table, ',<br />&#9;') .. "<br />&#9;}<br /><br />" ..

'------------------------------< I A N A S U P P R E S S E D S C R I P T S >--------------------------------<br />--' ..

file_date .. "<br />return {<br />&#9;" .. table.concat (pretty_suppressed, ',<br />&#9;') .. "<br />&#9;}<br /><br />" .. "</pre>";

'------------------------------< I S O 6 3 9 - 1 >------------------------------------------------------------<br />--' ..

file_date .. "<br />return {<br />&#9;" .. table.concat (iso_639_1_table, ',<br />&#9;') .. "<br />&#9;}<br /><br />" .. "</pre>";

end

return p;

--[[--------------------------< E X P O R T E D F U N C T I O N >--------------------------------------------

]]

return p;{

iana_extract = iana_extract,

}