Question

Can anyone Provide a Simple Example to Read and Write in the Unicode File a Unicode Character ?

Answer 1

On linux I use the iconv (link) library which is very standard. An overly simple program is:

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

#define BUF_SZ  1024
int main( int argc, char* argv[] )
{
    char bin[BUF_SZ];
    char bout[BUF_SZ];
    char* inp;
    char* outp;
    ssize_t bytes_in;
    size_t bytes_out;
    size_t conv_res;
    if( argc != 3 )
    {
        fprintf( stderr, "usage: convert from to\n" );
        return 1;
    }
    iconv_t conv = iconv_open( argv[2], argv[1] );
    if( conv == (iconv_t)(-1) )
    {
        fprintf( stderr, "Cannot conver from %s to %s\n",  argv[1], argv[2] );
        return 1;
    }

    bytes_in = read( 0, bin, BUF_SZ );
    {
        bytes_out = BUF_SZ;
        inp = bin;
        outp = bout;
        conv_res = iconv( conv, &inp, &bytes_in, &outp, &bytes_out );
        if( conv_res >= 0 )
        {
            write( 1, bout, (size_t)(BUF_SZ) - bytes_out );
        }
    }
    iconv_close( conv );
    return 0;
}

This is overly simple to demonstrate the conversion. In the real world you would normally have two nested loops:

• One reading input, so handle when its more than BUF_SZ
• One converting input to output. Remember if you’re converting from ascii to UTF-32LE you will end up with each iunput byte being 4 bytes of output. So the inner loop would handle this by examining conv_res and then checking errno.