Last active
April 10, 2024 01:04
-
-
Save uriid1/77e9efff56b2ce5d833deeda411b57e5 to your computer and use it in GitHub Desktop.
Format unicode blocks to lua table
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
-- | |
-- Format table: | |
-- unicode.blocks = { | |
-- ['Domino-Tiles'] = "\u{1F030}-\u{1F09F}", | |
-- ['Supplemental-Arrows-C'] = "\u{1F800}-\\u{1F8FF}", | |
-- ... | |
-- } | |
-- | |
-- Blocks.txt = https://www.unicode.org/Public/UNIDATA/Blocks.txt | |
local unicodeBlocks = {} | |
for line in io.lines('Blocks.txt', "*l") do | |
local firstChar = line:sub(1, 1) | |
if firstChar == '#' or firstChar == '' then | |
goto continue | |
end | |
-- Capture | |
local startCode, endCode, name = line:match('([A-Z0-9]+)%.%.([A-Z0-9]+); (.+)') | |
if not (startCode and endCode and name) then | |
goto continue | |
end | |
name = name:gsub(' ', '-') | |
-- Add | |
unicodeBlocks[name] = ('\\u{%s}-\\u{%s}'):format(startCode, endCode) | |
::continue:: | |
end | |
local function getChars(property) | |
local start = tonumber(property:match('^\\u{(.+)}%-'), 16) | |
local finish = tonumber(property:match('^\\u{.+}%-\\u{(.+)}'), 16) | |
local result = '' | |
for codepoint = start, finish do | |
result = result .. utf8.char(codepoint) | |
end | |
return result | |
end | |
return { | |
blocks = unicodeBlocks, | |
getChars = getChars, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment