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

Revision as of 14:11, 4 November 2017

Revision as of 15:23, 4 November 2017

Line 5:

--[=[------------------------< G E T _ L A N G _ S C R I P T _ R E G I O N _ P A R T S >-----------------------

We get an elementrecord that looks more-or-less like this:

%%\n

Type: language\n

Line 22:

than one Description line and Description lines can wrap to the next line. When they do, the first two

characters of the continuation line are spaces.

Comments: lines can also be continued so once in a Comments line (which is otherwise ignored) all further

continuations in the record are also ignored. This is a crude mechanism to prevent comment continuations

from being concatenated onto the end of descriptions and relies on Description line occuring in the record

before the Comments line.

Records with Deprecated dates or Preferred-Value codes are ignored as are private use codes.

]=]

local function get_lang_script_region_parts (elementrecord)

local code;

local descriptions = {};

local in_comments = false;

for line inif mw.ustring.gmatchmatch (elementrecord, '([^\n]+)\nDeprecated') do then -- getor amw.ustring.find \n(record, terminate'Preferred%-Value') lineor of textmw.ustring.find (withoutrecord, the'Private \nuse') then

return 'skip';

end

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

if mw.ustring.match (line, 'Subtag: [%a%d]+') then -- if this line is the subtag line

code = mw.ustring.match (line, 'Subtag: ([%a%d]+)'); -- extract and save to subtag's code

Line 72 ⟶ 83:

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

if mw.ustring.find (elementrecord, 'Type: language') then -- if a language elementrecord

code, descriptions = get_lang_script_region_parts (elementrecord); -- get the code and description(s)

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

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

elseif not code then

else

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

end

elseif mw.ustring.find (elementrecord, 'Type: script') then -- if a script elementrecord

code, descriptions = get_lang_script_region_parts (elementrecord); -- get the code and description(s)

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

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

elseif not code then

else

table.insert (lang_table, "[\"error\"] = {" .. record .. "}"); -- code should never be nil, but ...

end

elseif mw.ustring.find (elementrecord, 'Type: region') then -- if a region elementrecord

code, descriptions = get_lang_script_region_parts (elementrecord); -- get the code and description(s)

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

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

elseif not code then

else

table.insert (lang_table, "[\"error\"] = {" .. record .. "}"); -- code should never be nil, but ...

end

end