UTF-8 to SJIS conversion

Dependencies:   mbed

This example program converts UTF-8 code to Shift-JIS code.

main.cpp

Committer:
MACRUM
Date:
2013-08-24
Revision:
1:9bd53bc5ff51
Parent:
0:1215a9611188
Child:
2:43bc6ceb9ae5

File content as of revision 1:9bd53bc5ff51:

#include "mbed.h"
#include <locale.h>
#include <cwchar>

#pragma import __use_all_ctype

DigitalOut myled(LED1);

static char  buf_s[1024];
static char  buf_u[1024] = {0xE6,0x97,0xA5,0xE6,0x9C,0xAC,0xE8,0xAA,0x9E,0xE6,0x96,0x87,0xE5,0xAD,0x97,0xE5,0x88,0x97,0x5F,0x41,0x42,0x43,0x44,0x5F,0x30,0x31,0x32,0x33,0x00};
static wchar_t wstr[1024];

static int utf8tosjis(const char* utfBuffer, int utfBufLen, char* sjisBuffer, int sjisBufLen)
{
    int         i, wi;
    wchar_t     wc;
    mbstate_t   state = {0};
    size_t      ret;
    char *      current_locale;
    i = wi = 0;

    current_locale = setlocale(LC_CTYPE, "UTF-8");
    if (current_locale != NULL) {
        printf("Current locale is : %s \n", current_locale);
    }

    while (1) {
        ret = mbrtowc(&wc, utfBuffer+i, 3, &state);
        if (ret == (size_t)-2 || ret == (size_t)-1) {
            printf("\nThere was a problem decoding the multibyte string.\n");
         return ret;
        } else if (ret == 0) {
            break;                     /* we hit \0, end of string */
        } else {
            i += ret;
            wstr[wi++] = wc;
        }
    }
    wstr[wi] = L'\0';
    return ret;
}

int main() {
    int err = 0;
    err = utf8tosjis(buf_u, 29, buf_s, sizeof(buf_s));
    return 0;
}