Simple utility to compute the *Display Width* of a UTF-8 string.

strwidth.c

#include <stdio.h>
#include <string.h>
#include <wchar.h>
#include <stdlib.h>
#include <locale.h>
#include <assert.h>

// Tested with:
// Apple LLVM version 4.2 (clang-425.0.24) (based on LLVM 3.2svn)
// Target: x86_64-apple-darwin12.2.0
// Thread model: posix
// on:
// Darwin zen-approach.local 12.2.0 Darwin Kernel Version 12.2.0: Sat Aug 25 00:48:52 PDT 2012; root:xnu-2050.18.24~1/RELEASE_X86_64 x86_64

// Also tested with GCC on Debian Testing (compiling with -W -Wall generates one warning, but doesn't impact the code)

size_t getStringLen(char *str);

size_t
getStringLen(char *str){

    size_t totalStringLength = 0;

    size_t maxBytes = strlen(str); // May be bigger than needed
    wchar_t *output = malloc(sizeof(wchar_t) * maxBytes + 1);
    size_t bytesToConvert = mbstowcs(output, str, maxBytes);
    assert(bytesToConvert <= maxBytes);
    if (output){
        totalStringLength = (size_t)wcswidth(output, maxBytes);
        free(output);
    }

    return totalStringLength;
}

int
main(int argc, char **argv){

    // Hack, should only use this if no default locale is set
    setlocale(LC_ALL, "en_US.UTF-8");

    for (int i = 1; i < argc; i++){
        printf("%5zd, %s\n", getStringLen(argv[i]), argv[i]);
    }

    return 0;
}