share/lua/website/quvi/html.lua

   1
   2 -- libquvi-scripts
   3 -- Copyright (C) 2011  Toni Gundogdu <legatvs@gmail.com>
   4 --
   5 -- This file is part of libquvi-scripts <http://quvi.sourceforge.net/>.
   6 --
   7 -- This library is free software; you can redistribute it and/or
   8 -- modify it under the terms of the GNU Lesser General Public
   9 -- License as published by the Free Software Foundation; either
  10 -- version 2.1 of the License, or (at your option) any later version.
  11 --
  12 -- This library is distributed in the hope that it will be useful,
  13 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15 -- Lesser General Public License for more details.
  16 --
  17 -- You should have received a copy of the GNU Lesser General Public
  18 -- License along with this library; if not, write to the Free Software
  19 -- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
  20 -- 02110-1301  USA
  21 --
  22
  23 --
  24 -- A modularized revision of <http://www.hpelbers.org/lua/utf8>
  25 --
  26 -- convert numeric html entities to utf8
  27 -- example:  &#8364;    ->   €
  28 --
  29
  30 local M    = {}
  31 local char = string.char
  32
  33 function M.tail(n, k)
  34     local u, r=''
  35     for i=1,k do
  36         n,r = math.floor(n/0x40), n%0x40
  37         u = char(r+0x80) .. u
  38     end
  39     return u, n
  40 end
  41
  42 function M.to_utf8(a)
  43     local n, r, u = tonumber(a)
  44     if n<0x80 then                        -- 1 byte
  45         return char(n)
  46     elseif n<0x800 then                   -- 2 byte
  47         u, n = M.tail(n, 1)
  48         return char(n+0xc0) .. u
  49     elseif n<0x10000 then                 -- 3 byte
  50         u, n = M.tail(n, 2)
  51         return char(n+0xe0) .. u
  52     elseif n<0x200000 then                -- 4 byte
  53         u, n = M.tail(n, 3)
  54         return char(n+0xf0) .. u
  55     elseif n<0x4000000 then               -- 5 byte
  56         u, n = M.tail(n, 4)
  57         return char(n+0xf8) .. u
  58     else                                  -- 6 byte
  59         u, n = M.tail(n, 5)
  60         return char(n+0xfc) .. u
  61     end
  62 end
  63
  64 --
  65 --for line in io.lines() do
  66 --    out =  string.gsub(line, '&#(%d+);', to_utf8)
  67 --    print(out)
  68 --end
  69 --
  70
  71 return M
  72
  73 -- vim: set ts=4 sw=4 tw=72 expandtab: