对指定字符串进行`Unicode`编码、解码.

README.md

Unicode 编码 / 解码

测试代码:

local unicode = require "unicode"

print(unicode.encode("我是谁abc"))
print(unicode.encode("我是谁abc", true))
print(unicode.decode('\\u6211\\u662F\\u8C01\\u0061\\u0062\\u0063'))

结果:

\u6211\u662f\u8c01\u0061\u0062\u0063
\u6211\u662F\u8C01\u0061\u0062\u0063
我是谁abc

unicode.lua

local tonumber = tonumber

local gsub = string.gsub
local fmt = string.format

local u8_char = utf8.char
local u8_codepoint = utf8.codepoint
local u8_charpattern = utf8.charpattern

local unicode = { }

local function u8_dec(s)
  local ord = tonumber(s, 16)
  if not ord then
    return '\\u' ..  s
  end
  return ord < 32 and fmt("\\u%x", ord) or u8_char(ord)
end

local function u8_upper_enc(s)
  return fmt("\\u%04X", u8_codepoint(s))
end

local function u8_lower_enc(s)
  return fmt("\\u%04x", u8_codepoint(s))
end

---comment 对文本进行`Unicode`编码
---@param text string      @原始文本
---@param upper boolean?   @是否大写
function unicode.encode(text, upper)
  local v = gsub(text, u8_charpattern, upper and u8_upper_enc or u8_lower_enc)
  return v
end

---comment 对文本进行`Unicode`解码
---@param text string   @原始文本
function unicode.decode(text)
  local v = gsub(text, '\\u([%da-fA-F][%da-fA-F][%da-fA-F][%da-fA-F]+)', u8_dec)
  return v
end

return unicode