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

/* Test program to test dynamic loading with the loadso subsystem.
*/

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "SDL.h"

typedef int (*fntype) (const char *);

int
main(int argc, char *argv[])
{
    int retval = 0;
    int hello = 0;
    const char *libname = NULL;
    const char *symname = NULL;
    void *lib = NULL;
    fntype fn = NULL;

    if (argc != 3) {
        const char *app = argv[0];
        fprintf(stderr, "USAGE: %s <library> <functionname>\n", app);
        fprintf(stderr, "       %s --hello <lib with puts()>\n", app);
        return 1;
    }

    /* Initialize SDL */
    if (SDL_Init(0) < 0) {
        fprintf(stderr, "Couldn't initialize SDL: %s\n", SDL_GetError());
        return 2;
    }

    if (strcmp(argv[1], "--hello") == 0) {
        hello = 1;
        libname = argv[2];
        symname = "puts";
    } else {
        libname = argv[1];
        symname = argv[2];
    }

    lib = SDL_LoadObject(libname);
    if (lib == NULL) {
        fprintf(stderr, "SDL_LoadObject('%s') failed: %s\n",
                libname, SDL_GetError());
        retval = 3;
    } else {
        fn = (fntype) SDL_LoadFunction(lib, symname);
        if (fn == NULL) {
            fprintf(stderr, "SDL_LoadFunction('%s') failed: %s\n",
                    symname, SDL_GetError());
            retval = 4;
        } else {
            printf("Found %s in %s at %p\n", symname, libname, fn);
            if (hello) {
                printf("Calling function...\n");
                fflush(stdout);
                fn("     HELLO, WORLD!\n");
                printf("...apparently, we survived.  :)\n");
                printf("Unloading library...\n");
                fflush(stdout);
            }
        }
        SDL_UnloadObject(lib);
    }
    SDL_Quit();
    return (0);
}