Fixed bug #896 John Popplewell 2009-12-08 23:05:50 PST Originally reported by AKFoerster on the mailing list. Error decoding UTF8 Russian text to UTF-16LE on Windows, but specifically on platforms without iconv support (the default on Windows). Valid UTF8 characters are flagged as being overlong and then substituted by the UNKNOWN_UNICODE character. After studying the testiconv.c example program, reading the RFCs and putting some printf statements in SDL_iconv.c the problem is in a test for 'Maximum overlong sequences', specifically 4.2.1, which is carried out by the following code: } else if ( p[0] >= 0xC0 ) { if ( (p[0] & 0xE0) != 0xC0 ) { /* Skip illegal sequences return SDL_ICONV_EILSEQ; */ ch = UNKNOWN_UNICODE; } else { if ( (p[0] & 0xCE) == 0xC0 ) { <<<<<<<< here overlong = SDL_TRUE; } ch = (Uint32)(p[0] & 0x1F); left = 1; } } else { Here is the 2-byte encoding of a character in range 00000080 - 000007FF 110xxxxx 10xxxxxx The line in question is supposed to be checking for an overlong sequence which would be less than 11000001 10111111 which should be represented as a single byte. BUT, the mask value (0xCE) is wrong, it isn't checking the top-most bit: 11000001 value 11001110 mask (incorrect) ^ and should be (0xDE): 11000001 value 11011110 mask (correct) making the above code: } else if ( p[0] >= 0xC0 ) { if ( (p[0] & 0xE0) != 0xC0 ) { /* Skip illegal sequences return SDL_ICONV_EILSEQ; */ ch = UNKNOWN_UNICODE; } else { if ( (p[0] & 0xDE) == 0xC0 ) { <<<<<<<< here overlong = SDL_TRUE; } ch = (Uint32)(p[0] & 0x1F); left = 1; } } else { I can supply a test program and/or a patch if required, best regards, John Popplewell

/*
    SDL - Simple DirectMedia Layer
    Copyright (C) 1997-2009 Sam Lantinga

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Library 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
    Library General Public License for more details.

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

    Sam Lantinga
    slouken@libsdl.org
*/
#include "SDL_config.h"

/*
	Turbo veille screensaver

	Patrice Mandin
*/

#ifndef _SDL_xbios_tveille_h
#define _SDL_xbios_tveille_h

#include "SDL_xbios.h"

/*--- Defines ---*/

#ifndef C_VeiL
#define C_VeiL 0x5665694CL
#endif

/*--- Structures ---*/

typedef struct {
	unsigned long	version;
	void		(*prg_ptr)();
	void		(*kbd_ptr)();
	void		(*vbl_ptr)();
	unsigned long	vbl_count;
	void		(*oldkbd_ptr)();
	unsigned long	off_count;
	unsigned long	prg_size;
	unsigned long	dummy1[4];
	unsigned char	dummy2;
	unsigned char	status;
	unsigned short	freq;
	unsigned short	dummy3;
	unsigned char	clear_first;
	unsigned char	enabled;	/* 0=enabled, 0xff=disabled */
	unsigned char	serial_redir;
	unsigned char	dummy4;
	void		(*oldserial_ptr)();
} __attribute__((packed)) tveille_t;

/*--- Functions prototypes ---*/

int SDL_XBIOS_TveillePresent(_THIS);
void SDL_XBIOS_TveilleDisable(_THIS);
void SDL_XBIOS_TveilleEnable(_THIS);

#endif /* _SDL_xbios_tveille_h */