Module:Sandbox/Erutuon: Difference between revisions

Revision as of 20:52, 3 July 2018

Revision as of 20:59, 3 July 2018

Line 358:

-- A previous draft, in [[Module:Lang/sandbox]]:

-- https://en.wikipedia.org/w/index.php?oldid=812819217

-- Based on https://www.w3.org/International/articles/language-tags/.

function p.parse_IETF(tag)

if not tag or tag == "" or type(tag) ~= "string" then

Line 363 ⟶ 365:

end

-- This containsmay contain the special fields "matched_countinvalid" and, "invaliderror".

-- "matched_count" tracks the number of subtags, "error" indicates why the

-- tag is invalid (if applicable).

-- All other fields are subtags, and they appear in the tag in the following

Line 371 ⟶ 373:

-- "invalid" is the portion of the tag after the last valid subtag (minus a

-- hyphen).

local parsed_subtags = {}
local matched_count = 0 }

-- Language tags probably only contain ASCII alphabetic and numerical

-- characters and hyphen-minus, though I am not sure if this is explicitly

-- stated in the spec.

if not tag:find '^[A-Za-z0-9-]+$' then

parsed_subtags.error = "invalid characters"

Line 426 ⟶ 433:

parsed_subtags[type] = subtag

last_matched_subtag_i = subtag_i

parsed_subtags.matched_count = parsed_subtags.matched_count + 1

elseif not subtag_info[index] then

break

Line 432 ⟶ 439:

end

if #subtags > parsed_subtags.matched_count then

-- Not all subtags were matched. The unmatched tail end of the tag

-- (after the subtag at the index last_matched_subtag_i) is a

Line 440 ⟶ 447:

if suffix:sub(1, 1) == "x" then

parsed_subtags.private_use = suffix

parsed_subtags.matched_count = parsed_subtags.matched_count + 1 -- not used after this point

else

parsed_subtags.invalid = suffix