2007-07-05 Markus Deuling <deuling@de.ibm.com>

[deliverable/binutils-gdb.git] / binutils / winduni.c

/* winduni.c -- unicode support for the windres program.
   Copyright 1997, 1998, 2000, 2001, 2003, 2007
   Free Software Foundation, Inc.
   Written by Ian Lance Taylor, Cygnus Support.
   Rewritten by Kai Tietz, Onevision.

   This file is part of GNU Binutils.

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

   This program 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 General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
   02110-1301, USA.  */

/* This file contains unicode support routines for the windres
   program.  Ideally, we would have generic unicode support which
   would work on all systems.  However, we don't.  Instead, on a
   Windows host, we are prepared to call some Windows routines.  This
   means that we will generate different output on Windows and Unix
   hosts, but that seems better than not really supporting unicode at
   all.  */

#include "sysdep.h"
#include "bfd.h"
#include "libiberty.h" /* for xstrdup */
#include "bucomm.h"
/* Must be include before windows.h and winnls.h.  */
#if defined (_WIN32) || defined (__CYGWIN__)
#include <windows.h>
#include <winnls.h>
#endif
#include "winduni.h"
#include "safe-ctype.h"

#if HAVE_ICONV_H
#include <iconv.h>
#endif

static rc_uint_type wind_WideCharToMultiByte (rc_uint_type, const unichar *, char *, rc_uint_type);
static rc_uint_type wind_MultiByteToWideChar (rc_uint_type, const char *, unichar *, rc_uint_type);
static int unichar_isascii (const unichar *, rc_uint_type);

/* Convert an ASCII string to a unicode string.  We just copy it,
   expanding chars to shorts, rather than doing something intelligent.  */
 
#if !defined (_WIN32) && !defined (__CYGWIN__)

/* Codepages mapped.  */
static local_iconv_map codepages[] =
{
  { 0, "MS-ANSI" },
  { 1, "WINDOWS-1252" },
  { 437, "MS-ANSI" },
  { 737, "MS-GREEK" },
  { 775, "WINBALTRIM" },
  { 850, "MS-ANSI" },
  { 852, "MS-EE" },
  { 857, "MS-TURK" },
  { 862, "CP862" },
  { 864, "CP864" },
  { 866, "MS-CYRL" },
  { 874, "WINDOWS-874" },
  { 932, "CP932" },
  { 936, "CP936" },
  { 949, "CP949" },
  { 950, "CP950" },
  { 1250, "WINDOWS-1250" },
  { 1251, "WINDOWS-1251" },
  { 1252, "WINDOWS-1252" },
  { 1253, "WINDOWS-1253" },
  { 1254, "WINDOWS-1254" },
  { 1255, "WINDOWS-1255" },
  { 1256, "WINDOWS-1256" },
  { 1257, "WINDOWS-1257" },
  { 1258, "WINDOWS-1258" },
  { CP_UTF7, "UTF-7" },
  { CP_UTF8, "UTF-8" },
  { CP_UTF16, "UTF-16" },
  { (rc_uint_type) -1, NULL }
};

/* Languages supported.  */
static const wind_language_t languages[] =
{
  { 0x0000, 437, 1252, "Neutral", "Neutral" },
  { 0x0401, 864, 1256, "Arabic", "Saudi Arabia" },    { 0x0402, 866, 1251, "Bulgarian", "Bulgaria" },
  { 0x0403, 850, 1252, "Catalan", "Spain" },	      { 0x0404, 950,  950, "Chinese", "Taiwan" },
  { 0x0405, 852, 1250, "Czech", "Czech Republic" },   { 0x0406, 850, 1252, "Danish", "Denmark" },
  { 0x0407, 850, 1252, "German", "Germany" },	      { 0x0408, 737, 1253, "Greek", "Greece" },
  { 0x0409, 437, 1252, "English", "United States" },  { 0x040A, 850, 1252, "Spanish - Traditional Sort", "Spain" },
  { 0x040B, 850, 1252, "Finnish", "Finland" },	      { 0x040C, 850, 1252, "French", "France" },
  { 0x040D, 862, 1255, "Hebrew", "Israel" },	      { 0x040E, 852, 1250, "Hungarian", "Hungary" },
  { 0x040F, 850, 1252, "Icelandic", "Iceland" },      { 0x0410, 850, 1252, "Italian", "Italy" },
  { 0x0411, 932,  932, "Japanese", "Japan" },	      { 0x0412, 949,  949, "Korean", "Korea (south)" },