dotfiles from arch
This commit is contained in:
@@ -0,0 +1,24 @@
|
||||
local platform = require 'bee.platform'
|
||||
local windows
|
||||
|
||||
if platform.os == 'windows' then
|
||||
windows = require 'bee.windows'
|
||||
end
|
||||
|
||||
local m = {}
|
||||
|
||||
function m.toutf8(text)
|
||||
if not windows then
|
||||
return text
|
||||
end
|
||||
return windows.a2u(text)
|
||||
end
|
||||
|
||||
function m.fromutf8(text)
|
||||
if not windows then
|
||||
return text
|
||||
end
|
||||
return windows.u2a(text)
|
||||
end
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,123 @@
|
||||
local ansi = require 'encoder.ansi'
|
||||
local utf16 = require 'encoder.utf16'
|
||||
local utf16le = utf16('le', utf8.codepoint '<EFBFBD>')
|
||||
local utf16be = utf16('be', utf8.codepoint '<EFBFBD>')
|
||||
|
||||
---@alias encoder.encoding '"utf8"'|'"utf16"'|'"utf16le"'|'"utf16be"'
|
||||
|
||||
---@alias encoder.bom '"no"'|'"yes"'|'"auto"'
|
||||
|
||||
local m = {}
|
||||
|
||||
---@param encoding encoder.encoding
|
||||
---@param s string
|
||||
---@param i? integer
|
||||
---@param j? integer
|
||||
function m.len(encoding, s, i, j)
|
||||
i = i or 1
|
||||
j = j or #s
|
||||
if encoding == 'utf16'
|
||||
or encoding == 'utf16' then
|
||||
local us = utf16le.fromutf8(s:sub(i, j))
|
||||
return #us // 2
|
||||
end
|
||||
if encoding == 'utf16be' then
|
||||
local us = utf16be.fromutf8(s:sub(i, j))
|
||||
return #us // 2
|
||||
end
|
||||
if encoding == 'utf8' then
|
||||
return utf8.len(s, i, j, true)
|
||||
end
|
||||
log.error('Unsupport len encoding:', encoding)
|
||||
return j - i + 1
|
||||
end
|
||||
|
||||
---@param encoding encoder.encoding
|
||||
---@param s string
|
||||
---@param n integer
|
||||
---@param i? integer
|
||||
function m.offset(encoding, s, n, i)
|
||||
i = i or 1
|
||||
if encoding == 'utf16'
|
||||
or encoding == 'utf16le' then
|
||||
local line = s:match('[^\r\n]*', i)
|
||||
if not line:find '[\x80-\xff]' then
|
||||
return n + i - 1
|
||||
end
|
||||
local us = utf16le.fromutf8(line)
|
||||
local os = utf16le.toutf8(us:sub(1, n * 2 - 2))
|
||||
return #os + i
|
||||
end
|
||||
if encoding == 'utf16be' then
|
||||
local line = s:match('[^\r\n]*', i)
|
||||
if not line:find '[\x80-\xff]' then
|
||||
return n + i - 1
|
||||
end
|
||||
local us = utf16be.fromutf8(line)
|
||||
local os = utf16be.toutf8(us:sub(1, n * 2 - 2))
|
||||
return #os + i
|
||||
end
|
||||
if encoding == 'utf8' then
|
||||
return utf8.offset(s, n, i)
|
||||
end
|
||||
log.error('Unsupport offset encoding:', encoding)
|
||||
return n + i - 1
|
||||
end
|
||||
|
||||
---@param encoding encoder.encoding
|
||||
---@param text string
|
||||
---@param bom encoder.bom
|
||||
---@return string
|
||||
function m.encode(encoding, text, bom)
|
||||
if encoding == 'utf8' then
|
||||
if bom == 'yes' then
|
||||
text = '\xEF\xBB\xBF' .. text
|
||||
end
|
||||
return text
|
||||
end
|
||||
if encoding == 'ansi' then
|
||||
return ansi.fromutf8(text)
|
||||
end
|
||||
if encoding == 'utf16'
|
||||
or encoding == 'utf16le' then
|
||||
text = utf16le.fromutf8(text)
|
||||
if bom == 'yes'
|
||||
or bom == 'auto' then
|
||||
text = '\xFF\xFE' .. text
|
||||
end
|
||||
return text
|
||||
end
|
||||
if encoding == 'utf16be' then
|
||||
text = utf16be.fromutf8(text)
|
||||
if bom == 'yes'
|
||||
or bom == 'auto' then
|
||||
text = '\xFE\xFF' .. text
|
||||
end
|
||||
return text
|
||||
end
|
||||
log.error('Unsupport encode encoding:', encoding)
|
||||
return text
|
||||
end
|
||||
|
||||
---@param encoding encoder.encoding
|
||||
---@param text string
|
||||
---@return string
|
||||
function m.decode(encoding, text)
|
||||
if encoding == 'utf8' then
|
||||
return text
|
||||
end
|
||||
if encoding == 'ansi' then
|
||||
return ansi.toutf8(text)
|
||||
end
|
||||
if encoding == 'utf16'
|
||||
or encoding == 'utf16le' then
|
||||
return utf16le.toutf8(text)
|
||||
end
|
||||
if encoding == 'utf16be' then
|
||||
return utf16be.toutf8(text)
|
||||
end
|
||||
log.error('Unsupport encode encoding:', encoding)
|
||||
return text
|
||||
end
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,157 @@
|
||||
local error = error
|
||||
local strchar = string.char
|
||||
local strbyte = string.byte
|
||||
local strmatch = string.match
|
||||
local utf8char = utf8.char
|
||||
local tconcat = table.concat
|
||||
|
||||
local function be_tochar(code)
|
||||
return strchar((code >> 8) & 0xFF, code & 0xFF)
|
||||
end
|
||||
|
||||
local function be_tobyte(s, i)
|
||||
local h, l = strbyte(s, i, i+1)
|
||||
return (h << 8) | l
|
||||
end
|
||||
|
||||
local function le_tochar(code)
|
||||
return strchar(code & 0xFF, (code >> 8) & 0xFF)
|
||||
end
|
||||
|
||||
local function le_tobyte(s, i)
|
||||
local l, h = strbyte(s, i, i+1)
|
||||
return (h << 8) | l
|
||||
end
|
||||
|
||||
local function utf16char(tochar, code)
|
||||
if code < 0x10000 then
|
||||
return tochar(code)
|
||||
else
|
||||
code = code - 0x10000
|
||||
return tochar(0xD800 + (code >> 10))..tochar(0xDC00 + (code & 0x3FF))
|
||||
end
|
||||
end
|
||||
|
||||
local function utf16next(s, n, tobyte)
|
||||
if n > #s then
|
||||
return
|
||||
end
|
||||
local code1 = tobyte(s, n)
|
||||
if code1 < 0xD800 or code1 >= 0xE000 then
|
||||
return n+2, code1
|
||||
elseif code1 >= 0xD800 and code1 < 0xDC00 then
|
||||
n = n + 2
|
||||
if n > #s then
|
||||
return n --invaild
|
||||
end
|
||||
local code2 = tobyte(s, n)
|
||||
if code2 < 0xDC00 or code2 >= 0xE000 then
|
||||
return n --invaild
|
||||
end
|
||||
local code = 0x10000 + ((code1 - 0xD800) << 10) + ((code2 - 0xDC00) & 0x3FF)
|
||||
return n+2, code
|
||||
else
|
||||
return n+2 --invaild
|
||||
end
|
||||
end
|
||||
|
||||
local function utf16codes(s, tobyte)
|
||||
return function (_, n)
|
||||
return utf16next(s, n, tobyte)
|
||||
end, s, 1
|
||||
end
|
||||
|
||||
local _utf8byte = utf8.codes ""
|
||||
local function utf8byte(s, n)
|
||||
local _, code = _utf8byte(s, n-1)
|
||||
return code
|
||||
end
|
||||
|
||||
--[[
|
||||
U+0000.. U+007F 00..7F
|
||||
U+0080.. U+07FF C2..DF 80..BF
|
||||
U+0800.. U+0FFF E0 A0..BF 80..BF
|
||||
U+1000.. U+CFFF E1..EC 80..BF 80..BF
|
||||
U+D000.. U+D7FF ED 80..9F 80..BF
|
||||
U+E000.. U+FFFF EE..EF 80..BF 80..BF
|
||||
U+10000.. U+3FFFF F0 90..BF 80..BF 80..BF
|
||||
U+40000.. U+FFFFF F1..F3 80..BF 80..BF 80..BF
|
||||
U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
|
||||
]]
|
||||
local function utf8next(s, n)
|
||||
if n > #s then
|
||||
return
|
||||
end
|
||||
if strmatch(s, "^[\0-\x7F]", n) then
|
||||
return n+1, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xC2-\xDF][\x80-\xBF]", n) then
|
||||
return n+2, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xE0][\xA0-\xBF][\x80-\xBF]", n) then
|
||||
return n+3, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xE1-\xEC][\x80-\xBF][\x80-\xBF]", n) then
|
||||
return n+3, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xED][\x80-\x9F][\x80-\xBF]", n) then
|
||||
return n+3, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xEE-\xEF][\x80-\xBF][\x80-\xBF]", n) then
|
||||
return n+3, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xF0][\x90-\xBF][\x80-\xBF][\x80-\xBF]", n) then
|
||||
return n+4, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xF1-\xF3][\x80-\xBF][\x80-\xBF][\x80-\xBF]", n) then
|
||||
return n+4, utf8byte(s, n)
|
||||
elseif strmatch(s, "^[\xF4][\x80-\x8F][\x80-\xBF][\x80-\xBF]", n) then
|
||||
return n+4, utf8byte(s, n)
|
||||
else
|
||||
return n+1 --invaild
|
||||
end
|
||||
end
|
||||
|
||||
local function utf8codes(s)
|
||||
return utf8next, s, 1
|
||||
end
|
||||
|
||||
return function (what, replace)
|
||||
local tobyte, tochar
|
||||
if what == "be" then
|
||||
tobyte = be_tobyte
|
||||
tochar = be_tochar
|
||||
else
|
||||
tobyte = le_tobyte
|
||||
tochar = le_tochar
|
||||
end
|
||||
local utf8replace = replace and utf8char(replace)
|
||||
local utf16replace = replace and utf16char(tochar, replace)
|
||||
local function toutf8(s)
|
||||
local r = {}
|
||||
for _, code in utf16codes(s, tobyte) do
|
||||
if code == nil then
|
||||
if replace then
|
||||
r[#r+1] = utf8replace
|
||||
else
|
||||
error "invalid UTF-16 code"
|
||||
end
|
||||
else
|
||||
r[#r+1] = utf8char(code)
|
||||
end
|
||||
end
|
||||
return tconcat(r)
|
||||
end
|
||||
local function fromutf8(s)
|
||||
local r = {}
|
||||
for _, code in utf8codes(s) do
|
||||
if code == nil then
|
||||
if replace then
|
||||
r[#r+1] = utf16replace
|
||||
else
|
||||
error "invalid UTF-8 code"
|
||||
end
|
||||
else
|
||||
r[#r+1] = utf16char(tochar, code)
|
||||
end
|
||||
end
|
||||
return tconcat(r)
|
||||
end
|
||||
return {
|
||||
toutf8 = toutf8,
|
||||
fromutf8 = fromutf8,
|
||||
}
|
||||
end
|
||||
Reference in New Issue
Block a user