How to compare multibyte characters in C

Question

I try to parse text and find some characters in it. I use the code below. It works with normal characters like abcdef but it does not work with öçşğüı

Answer 1

See wiki here: https://en.wikipedia.org/wiki/UTF-8 In particular, there is a table with the bit patterns.

Here's another way to scan/convert a utf-8 string into a codepoint [not exact, just an example--refer to wiki]:

// utf8scan -- convert utf8 to codepoints (example)

char inpbuf[1000];
char uni[8];

typedef union {
    char utf8[4];
    unsigned int code;
} codepoint_t;

codepoint_t outbuf[1000];

// unidecode -- decode utf8 char into codepoint
// RETURNS: updated rhs pointer
char *
unidecode(codepoint_t *lhs,char *rhs)
{
    int idx;
    int chr;

    idx = 0;
    lhs->utf8[idx++] = *rhs++;

    for (;  ;  ++rhs, ++idx) {
        chr = *rhs;

        // end of string
        if (chr == 0)
            break;

        // start of new ascii char
        if ((chr & 0x80) == 0)
            break;

        // start of new unicode char
        if (chr & 0x40)
            break;

        lhs->utf8[idx] = chr;
    }

    return rhs;
}

// main -- main program
int
main(void)
{
    char *rhs;
    codepoint_t *lhs;

    rhs = inpbuf;
    lhs = outbuf;

    for (;  *rhs != 0;  ++lhs) {
        lhs->code = 0;

        // ascii char
        if ((*rhs & 0x80) == 0)
            lhs->utf8[0] = *rhs++;

        // get/skip unicode char
        else
            rhs = unidecode(lhs,rhs);
    }

    // add EOS
    lhs->code = 0;

    return 0;
}