Module:Unicode data: Difference between revisions
Template>Pppery Split noncharacter per request |
m 1 revision imported |
||
| (4 intermediate revisions by 3 users not shown) | |||
| 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" }, -- 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}, | ||
{ 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 440: | 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 448: | 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 547: | 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 | ||