/*
   (c) Copyright 2000-2002  convergence integrated media GmbH.
   (c) Copyright 2002       convergence GmbH.
   
   All rights reserved.

   Written by Denis Oliver Kropp <dok@directfb.org>,
              Andreas Hundt <andi@fischlustig.de> and
              Sven Neumann <sven@convergence.de>.

   UTF8 routines ported from glib-2.0

   This library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2 of the License, or (at your option) any later version.

   This library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with this library; if not, write to the
   Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.
*/

#include "directfb.h"

#include "core/coretypes.h"

#include "utf8.h"


/* 
 *  Actually the last two fields used to be zero since they indicate an
 *  invalid UTF-8 string. Changed it to 1 to avoid endless looping on
 *  invalid input.
 */
const char dfb_utf8_skip[256] = {
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
     2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
     3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};

unichar dfb_utf8_get_char (const char *p)
{
     unichar result;
     unsigned char c = (unsigned char) *p;
     int i, len;

     if (!(c & 0x80))
          return (unichar) c;

     if (c > 0xfd)
          return (unichar) -1;

     len = dfb_utf8_skip[c];

     result = p[0] & (0x7c >> len);

     for (i = 1; i < len; i++) {

          if ((p[i] & 0xc0) != 0x80)
               return (unichar) -1;

          result <<= 6;
          result |= p[i] & 0x3f;
     }

     return result;
}