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

/*
 * Copyright 1993-2001 by Xi Graphics, Inc.
 * All Rights Reserved.
 *
 * Please see the LICENSE file accompanying this distribution for licensing 
 * information. 
 *
 * Please send any bug fixes and modifications to src@xig.com.
 *
 * $XiGId: xme.h,v 1.1.1.1 2001/11/19 19:01:10 jon Exp $
 *
 */


#ifndef _XME_H_INCLUDED 
#define _XME_H_INCLUDED

typedef struct {        
  short		        x;
  short		        y;
  unsigned short	w;
  unsigned short	h;
} XiGMiscViewInfo;

typedef struct {        
  unsigned short        width;
  unsigned short        height;
  int                   refresh;
} XiGMiscResolutionInfo;

extern Bool XiGMiscQueryVersion(Display *dpy, int *major, int *minor);
extern int XiGMiscQueryViews(Display *dpy, int screen, 
			     XiGMiscViewInfo **pviews);
extern int XiGMiscQueryResolutions(Display *dpy, int screen, int view, 
			    int *pactive, 
			    XiGMiscResolutionInfo **presolutions);
extern void XiGMiscChangeResolution(Display *dpy, int screen, int view, 
			     int width, int height, int refresh);

/* SDL addition from Ryan: free memory used by xme. */
extern void XiGMiscDestroy(void);

#endif /* _XME_H_INCLUDED */