UTF-8 character classes for LPeG, using ICU4Lua

lpeg_utf8_locale.lua

local lpeg = require 'lpeg'
local U    = require 'icu.ustring'
local re   = require 'icu.regex'

local utf8_codepoint
do
  -- decode a two-byte UTF-8 sequence
  local function f2 (s)
    local c1, c2 = string.byte(s, 1, 2)
    return c1 * 64 + c2 - 12416
  end

  -- decode a three-byte UTF-8 sequence
  local function f3 (s)
    local c1, c2, c3 = string.byte(s, 1, 3)
    return (c1 * 64 + c2) * 64 + c3 - 925824
  end

  -- decode a four-byte UTF-8 sequence
  local function f4 (s)
    local c1, c2, c3, c4 = string.byte(s, 1, 4)
    return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168
  end

  local cont = lpeg.R("\128\191")   -- continuation byte

  utf8_codepoint = lpeg.R("\0\127") / string.byte
    + lpeg.R("\194\223") * cont / f2
    + lpeg.R("\224\239") * cont * cont / f3
    + lpeg.R("\240\244") * cont * cont * cont / f4
end

local alnum = re.compile('^\\p{alnum}$')
local alpha = re.compile('^\\p{alpha}$')
local cntrl = re.compile('^\\p{cntrl}$')
local digit = re.compile('^\\p{digit}$')
local graph = re.compile('^\\p{graph}$')
local lower = re.compile('^\\p{lower}$')
local print = re.compile('^\\p{print}$')
local punct = re.compile('^\\p{punct}$')
local space = re.compile('^\\p{space}$')
local upper = re.compile('^\\p{upper}$')
local xdigit = re.compile('^\\p{xdigit}$')

return {
  alnum = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(alnum, U.char(c)) end ) ;
  alpha = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(alpha, U.char(c)) end ) ;
  cntrl = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(cntrl, U.char(c)) end ) ;
  digit = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(digit, U.char(c)) end ) ;
  graph = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(graph, U.char(c)) end ) ;
  lower = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(lower, U.char(c)) end ) ;
  print = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(print, U.char(c)) end ) ;
  punct = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(punct, U.char(c)) end ) ;
  space = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(space, U.char(c)) end ) ;
  upper = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(upper, U.char(c)) end ) ;
  xdigit = lpeg.Cmt ( utf8_codepoint , function (s,i,c) return not not re.match(digit, U.char(c)) end ) ;
}