share/lua/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 library is free software; you can redistribute it and/or
   7 -- modify it under the terms of the GNU Lesser General Public
   8 -- License as published by the Free Software Foundation; either
   9 -- version 2.1 of the License, or (at your option) any later version.
  10 --
  11 -- This library 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 GNU
  14 -- Lesser General Public License for more details.
  15 --
  16 -- You should have received a copy of the GNU Lesser General Public
  17 -- License along with this library; if not, write to the Free Software
  18 -- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
  19 -- 02110-1301  USA
  20 --
  21
  22 --
  23 -- A modularized version of <http://www.hpelbers.org/lua/utf8>
  24 --
  25 -- convert numeric html entities to utf8
  26 -- example:  &#8364;    ->   €
  27 --
  28
  29 local M    = {}
  30 local char = string.char
  31
  32 function M.tail(n, k)
  33   local u, r=''
  34   for i=1,k do
  35     n,r = math.floor(n/0x40), n%0x40
  36     u = char(r+0x80) .. u
  37   end
  38   return u,n
  39 end
  40
  41 function M.to_utf8(a)
  42   local n, r, u = tonumber(a)
  43   if n<0x80 then                        -- 1 byte
  44     return char(n)
  45   elseif n<0x800 then                   -- 2 byte
  46     u,n = M.tail(n, 1)
  47     return char(n+0xc0) .. u
  48   elseif n<0x10000 then                 -- 3 byte
  49     u,n = M.tail(n, 2)
  50     return char(n+0xe0) .. u
  51   elseif n<0x200000 then                -- 4 byte
  52     u,n = M.tail(n, 3)
  53     return char(n+0xf0) .. u
  54   elseif n<0x4000000 then               -- 5 byte
  55     u,n = M.tail(n, 4)
  56     return char(n+0xf8) .. u
  57   else                                  -- 6 byte
  58     u,n = M.tail(n, 5)
  59     return char(n+0xfc) .. u
  60   end
  61 end
  62
  63 --[[
  64 for s in io.lines() do
  65   local o = s:gsub('&#(%d+);', M.to_utf8)
  66   print(o)
  67 end
  68 ]]--
  69
  70 return M
  71
  72 -- vim: set ts=2 sw=2 tw=72 expandtab: