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

#include <stdio.h>
#include "SDL.h"

static void
print_devices(int iscapture)
{
    const char *typestr = ((iscapture) ? "capture" : "output");
    int n = SDL_GetNumAudioDevices(iscapture);

    printf("%s devices:\n", typestr);

    if (n == -1)
        printf("  Driver can't detect specific devices.\n\n", typestr);
    else if (n == 0)
        printf("  No %s devices found.\n\n", typestr);
    else {
        int i;
        for (i = 0; i < n; i++) {
            printf("  %s\n", SDL_GetAudioDeviceName(i, iscapture));
        }
        printf("\n");
    }
}

int
main(int argc, char **argv)
{
    /* Print available audio drivers */
    int n = SDL_GetNumAudioDrivers();
    if (n == 0) {
        printf("No built-in audio drivers\n\n");
    } else {
        int i;
        printf("Built-in audio drivers:\n");
        for (i = 0; i < n; ++i) {
            printf("  %s\n", SDL_GetAudioDriver(i));
        }
        printf("\n");
    }

    /* Load the SDL library */
    if (SDL_Init(SDL_INIT_AUDIO) < 0) {
        fprintf(stderr, "Couldn't initialize SDL: %s\n", SDL_GetError());
        return (1);
    }

    printf("Using audio driver: %s\n\n", SDL_GetCurrentAudioDriver());

    print_devices(0);
    print_devices(1);

    SDL_Quit();
    return 0;
}