firmware/include/rbunicode.h

   1 /***************************************************************************
   2  *             __________               __   ___.
   3  *   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
   4  *   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
   5  *   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
   6  *   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
   7  *                     \/            \/     \/    \/            \/
   8  * $Id$
   9  *
  10  * Copyright (c) 2004,2005 by Marcoen Hirschberg
  11  *
  12  * This program is free software; you can redistribute it and/or
  13  * modify it under the terms of the GNU General Public License
  14  * as published by the Free Software Foundation; either version 2
  15  * of the License, or (at your option) any later version.
  16  *
  17  * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
  18  * KIND, either express or implied.
  19  *
  20  ****************************************************************************/
  21 /*   Some conversion functions for handling UTF-8
  22  *
  23  *   I got all the info from:
  24  *   http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
  25  *   and
  26  *   http://en.wikipedia.org/wiki/Unicode
  27  */
  28 #ifndef _RBUNICODE_H_
  29 #define _RBUNICODE_H_
  30
  31 #include "config.h"
  32
  33 #define MASK   0xC0 /* 11000000 */
  34 #define COMP   0x80 /* 10x      */
  35
  36 #ifdef HAVE_LCD_BITMAP
  37
  38 enum codepages {
  39     ISO_8859_1 = 0, /* Latin1 */
  40     ISO_8859_7,     /* Greek */
  41     ISO_8859_8,     /* Hebrew */
  42     WIN_1251,       /* Cyrillic */
  43     ISO_8859_11,    /* Thai */
  44     WIN_1256,       /* Arabic */
  45     ISO_8859_9,     /* Turkish */
  46     ISO_8859_2,     /* Latin Extended */
  47     WIN_1250,       /* Central European */
  48     SJIS,           /* Japanese */
  49     GB_2312,        /* Simp. Chinese */
  50     KSX_1001,       /* Korean */
  51     BIG_5,          /* Trad. Chinese */
  52     UTF_8,          /* Unicode */
  53     NUM_CODEPAGES
  54 };
  55
  56 #else /* !HAVE_LCD_BITMAP, reduced support */
  57
  58 enum codepages {
  59     ISO_8859_1 = 0, /* Latin1 */
  60     ISO_8859_7,     /* Greek */
  61     WIN_1251,       /* Cyrillic */
  62     ISO_8859_9,     /* Turkish */
  63     ISO_8859_2,     /* Latin Extended */
  64     WIN_1250,       /* Central European */
  65     UTF_8,          /* Unicode */
  66     NUM_CODEPAGES
  67 };
  68
  69 #endif
  70
  71 /* Encode a UCS value as UTF-8 and return a pointer after this UTF-8 char. */
  72 unsigned char* utf8encode(unsigned long ucs, unsigned char *utf8);
  73 unsigned char* iso_decode(const unsigned char *latin1, unsigned char *utf8, int cp, int count);
  74 unsigned char* utf16LEdecode(const unsigned char *utf16, unsigned char *utf8, int count);
  75 unsigned char* utf16BEdecode(const unsigned char *utf16, unsigned char *utf8, int count);
  76 unsigned long utf8length(const unsigned char *utf8);
  77 const unsigned char* utf8decode(const unsigned char *utf8, unsigned short *ucs);
  78 void set_codepage(int cp);
  79 int utf8seek(const unsigned char* utf8, int offset);
  80 const char* get_codepage_name(int cp);
  81 #endif /* _RBUNICODE_H_ */