detect text encoding and convert to utf8

convert.c

#include "unicode/ucsdet.h"
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <iconv.h>
#include <errno.h>

#define DEST_CHARSET "UTF-8"
#define UNKNOWN_CHARSET_DEFAULT "WINDOWS-1252"

static void
toutf8(char* input, char* output) {
    const UCharsetMatch** matches;
    int32_t matchCount = 0;
    const char* input_type;
    size_t input_len = strlen(input);
    size_t output_len = input_len * 4 + 1;
    UErrorCode status = U_ZERO_ERROR;
    UCharsetDetector *csd = ucsdet_open(&status);

    ucsdet_setText(csd, input, input_len, &status);
    matches = ucsdet_detectAll(csd, &matchCount, &status);
    if(status != U_ZERO_ERROR) {
        printf("failed to detect\n");
        input_type = UNKNOWN_CHARSET_DEFAULT;
    } else {
        printf("detected\n");
        input_type = ucsdet_getName(matches[0], &status);
    }

    printf("type: %s\n", input_type);

    iconv_t cd = iconv_open(DEST_CHARSET, input_type);
    iconv(cd, &input, &input_len, &output, &output_len);
    iconv_close(cd);

    ucsdet_close(csd);
    u_cleanup();
}

int
main(int argc, char* argv[]) {
    char* buffer = 0;
    char* buffer2;
    char* utf8;

    long length;
    FILE * f = fopen ("data.txt", "rb");

    if (f) {
        fseek (f, 0, SEEK_END);
        length = ftell(f);
        fseek (f, 0, SEEK_SET);
        buffer = malloc(length);
        buffer2 = malloc(length);
        if (buffer) {
            fread (buffer, 1, length, f);
        }
        fclose (f);
    }

    if (buffer) {
        char* utf8 = (char*) malloc(strlen(buffer) * 4 + 1);
        toutf8(buffer, utf8);
        printf("%s\n", utf8);

        if (buffer2 != NULL) {
            free(buffer2);
        }
        if (buffer != NULL) {
            free(buffer);
        }
        if (utf8 != NULL) {
            free(utf8);
        }
    }
    return 0;
}

gistfile1.sh

cc convert.c -o convert `pkg-config --libs --cflags icu-io`