share/common/quvi/html.lua

   1 -- libquvi-scripts
   2 -- Copyright (C) 2011  Toni Gundogdu <legatvs@gmail.com>
   3 --
   4 -- This file is part of libquvi-scripts <http://quvi.sourceforge.net/>.
   5 --
   6 -- This program is free software: you can redistribute it and/or
   7 -- modify it under the terms of the GNU Affero General Public
   8 -- License as published by the Free Software Foundation, either
   9 -- version 3 of the License, or (at your option) any later version.
  10 --
  11 -- This program is distributed in the hope that it will be useful,
  12 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 -- GNU Affero General Public License for more details.
  15 --
  16 -- You should have received a copy of the GNU Affero General
  17 -- Public License along with this program.  If not, see
  18 -- <http://www.gnu.org/licenses/>.
  19 --
  20
  21 --
  22 -- A modularized version of <http://www.hpelbers.org/lua/utf8>
  23 --
  24 -- convert numeric html entities to utf8
  25 -- example:  &#8364;    ->   €
  26 --
  27
  28 local M    = {}
  29 local char = string.char
  30
  31 function M.tail(n, k)
  32   local u, r=''
  33   for i=1,k do
  34     n,r = math.floor(n/0x40), n%0x40
  35     u = char(r+0x80) .. u
  36   end
  37   return u,n
  38 end
  39
  40 function M.to_utf8(a)
  41   local n, r, u = tonumber(a)
  42   if n<0x80 then                        -- 1 byte
  43     return char(n)
  44   elseif n<0x800 then                   -- 2 byte
  45     u,n = M.tail(n, 1)
  46     return char(n+0xc0) .. u
  47   elseif n<0x10000 then                 -- 3 byte
  48     u,n = M.tail(n, 2)
  49     return char(n+0xe0) .. u
  50   elseif n<0x200000 then                -- 4 byte
  51     u,n = M.tail(n, 3)
  52     return char(n+0xf0) .. u
  53   elseif n<0x4000000 then               -- 5 byte
  54     u,n = M.tail(n, 4)
  55     return char(n+0xf8) .. u
  56   else                                  -- 6 byte
  57     u,n = M.tail(n, 5)
  58     return char(n+0xfc) .. u
  59   end
  60 end
  61
  62 --[[
  63 for s in io.lines() do
  64   local o = s:gsub('&#(%d+);', M.to_utf8)
  65   print(o)
  66 end
  67 ]]--
  68
  69 return M
  70
  71 -- vim: set ts=2 sw=2 tw=72 expandtab: