Difference between revisions of "Module:Unicode data"
Jump to navigation
Jump to search
Module:Unicode data (view source)
Revision as of 16:56, 12 September 2023
, 16:56, 12 September 2023Add new block for Unicode v15.1
m (1 revision imported) |
en>Drmccreedy (Add new block for Unicode v15.1) |
||
| Line 87: | Line 87: | ||
{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu | { 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu | ||
{ 0x20000, 0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B | { 0x20000, 0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B | ||
{ 0x2A700, | { 0x2A700, 0x2B739, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C | ||
{ 0x2B740, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D | { 0x2B740, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D | ||
{ 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E | { 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E | ||
| Line 97: | Line 97: | ||
end}, | end}, | ||
{ 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G | { 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G | ||
{ 0x31350, 0x323AF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H | |||
{ 0x2EBF0, 0x2EE5D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension I | |||
{ 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 480: | Line 482: | ||
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) | ||