WikipediNyah

Module:Unicode data: Difference between revisions

Created page with "local p = {} local floor = math.floor local function errorf(level, ...) if type(level) == "number" then return error(string.format(...), level + 1) else -- level is actually the format string. return error(string.format(level, ...), 2) end end local function binary_range_search(codepoint, ranges) local low, mid, high low, high = 1, ranges.length or require "Module:TableTools".length(ranges) while low <= high do mid = floor((low + high) / 2) local range =..."
 
No edit summary
 
Line 58: Line 58:
-- Unicode Specification:
-- Unicode Specification:
-- https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf
-- https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf
-- binary_range_search assumes these are ordered by codepoint. Do not place them in a random order!
local name_hooks = {
local name_hooks = {
{    0x00,    0x1F, "<control-%04X>" }, -- C0 control characters
{    0x00,    0x1F, "<control-%04X>" }, -- C0 control characters
Line 91: Line 92:
{  0x2B820,  0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
{  0x2B820,  0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
{  0x2CEB0,  0x2EBE0, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension F
{  0x2CEB0,  0x2EBE0, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension F
-- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
{  0x2EBF0,  0x2EE5D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension I
{  0x2F800,  0x2FA1D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
{  0x2F800,  0x2FA1D, "CJK COMPATIBILITY IDEOGRAPH-%04X" }, -- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
{  0x30000,  0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
{  0x31350,  0x323AF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H
{  0xE0100,  0xE01EF, function (codepoint) -- Variation Selectors Supplement
{  0xE0100,  0xE01EF, function (codepoint) -- Variation Selectors Supplement
return ("VARIATION SELECTOR-%d"):format(codepoint - 0xE0100 + 17)
return ("VARIATION SELECTOR-%d"):format(codepoint - 0xE0100 + 17)
end},
end},
{  0x30000,  0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
{  0x31350,  0x323AF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H
{  0xF0000,  0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
{  0xF0000,  0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
{ 0x100000, 0x10FFFD, "<private-use-%04X>" }  -- Plane 16 Private Use
{ 0x100000, 0x10FFFD, "<private-use-%04X>" }  -- Plane 16 Private Use
Line 125: Line 126:
--]]
--]]


-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8
function p.is_noncharacter(codepoint)
function p.lookup_name(codepoint)
-- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned
-- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned
-- (Cn) and specifically noncharacters:
-- (Cn) and specifically noncharacters:
-- https://www.unicode.org/faq/private_use.html#nonchar4
-- https://www.unicode.org/faq/private_use.html#nonchar4
if 0xFDD0 <= codepoint and (codepoint <= 0xFDEF
return 0xFDD0 <= codepoint and (codepoint <= 0xFDEF
or floor(codepoint % 0x10000) >= 0xFFFE) then
or floor(codepoint % 0x10000) >= 0xFFFE)
end
 
-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8
function p.lookup_name(codepoint)
if p.is_noncharacter(codepoint) then
return ("<noncharacter-%04X>"):format(codepoint)
return ("<noncharacter-%04X>"):format(codepoint)
end
end
Line 161: Line 167:
end
end


--[[
-- No image data modules on Wikipedia yet.
function p.lookup_image(codepoint)
function p.lookup_image(codepoint)
local data = loader[('images/%03X'):format(codepoint / 0x1000)]
local data = loader[('images/%03X'):format(codepoint / 0x1000)]
Line 170: Line 174:
end
end
end
end
--]]


local planes = {
local planes = {
Line 437: Line 440:
local Latn = false
local Latn = false
local i = 0; -- indexer for use in error messages
for codepoint in mw.ustring.gcodepoint(str) do
for codepoint in mw.ustring.gcodepoint(str) do
i = i + 1; -- bump the indexer
local script = lookup_script(codepoint)
local script = lookup_script(codepoint)
Line 445: Line 450:
elseif not (script == "Zyyy" or script == "Zinh"
elseif not (script == "Zyyy" or script == "Zinh"
or script == "Zzzz") then
or script == "Zzzz") then
return false
return false, i -- abandon as not Latn; identify the offending character's position
end
end
end
end
return Latn
return Latn, (not Latn and i) or nil -- when <Latn> false, return offending charactor's position as second return value; nil else
end
end


Line 481: Line 486:
return result
return result
end
end
--[[--------------------------< I S _ R T L _ F R A M E >------------------------------------------------------
external entry from an {{#invoke:}} to determine if a string of text is rtl.  Strips html and html-like tags so
that those tags don't corrupt the is-rtl-is-not-rtl determination; this added for the cases where the rtl text
has <br /> tags.
]]
function p.is_rtl_frame (frame)
local str = frame.args[1]; -- get the string from the {{#invoke:}} frame
str = str:gsub ('%b<>', ''); -- strip any html and html-like tags
return p.is_rtl (str); -- return if whatever remains rtl; false else
end


local function get_codepoint(args, arg)
local function get_codepoint(args, arg)
Line 528: Line 549:
local codepoint = get_codepoint(frame.args, 2)
local codepoint = get_codepoint(frame.args, 2)
return (func(codepoint)) -- Adjust to one result.
return (func(codepoint)) -- Adjust to one result.
end
end
function p.lookup_kCantonese(codepoint)
local data = loader[('Unihan/kCantonese/%02X'):format(floor(codepoint / 0x1000))]
if data then
return data[codepoint]
end
end
end
end


return p
return p
Retrieved from "https://wikis.redgreenblue.art/WikipediNyah/Module:Unicode_data"