「モジュール:Unicode data」の版間の差分

1版 をインポートしました
bsd>Pppery
(Add KCantonese lookup per request)
 
(1版 をインポートしました)
 
(2人の利用者による、間の3版が非表示)
58行目: 58行目:
-- 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
77行目: 78行目:
{  0xD800,  0xDFFF, "<surrogate-%04X>" },
{  0xD800,  0xDFFF, "<surrogate-%04X>" },
{  0xE000,  0xF8FF, "<private-use-%04X>" }, -- Private Use
{  0xE000,  0xF8FF, "<private-use-%04X>" }, -- Private Use
-- CJK Compatibility Ideographs
-- CJK Compatibility Ideographs
{  0xF900,  0xFA6D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
{  0xF900,  0xFA6D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
{  0xFA70,  0xFAD9, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
{  0xFA70,  0xFAD9, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
{  0xFE00,  0xFE0F, function (codepoint) -- Variation Selectors
return ("VARIATION SELECTOR-%d"):format(codepoint - 0xFE00 + 1)
end},
{  0x17000,  0x187F7, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph
{  0x17000,  0x187F7, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph
{  0x18800,  0x18AFF, function (codepoint)
{  0x18800,  0x18AFF, function (codepoint)
91行目: 96行目:
{  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
0x2F8000x2FA1D, "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
{  0x313500x323AF, "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
{  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