Function yaml_check_utf8

xs/tools/yaml/api.c:645–682

 */

static int
yaml_check_utf8(yaml_char_t *start, size_t length)
{
    yaml_char_t *end = start+length;
    yaml_char_t *pointer = start;

    while (pointer < end) {
        unsigned char octet;
        unsigned int width;
        unsigned int value;
        size_t k;

        octet = pointer[0];
        width = (octet & 0x80) == 0x00 ? 1 :
                (octet & 0xE0) == 0xC0 ? 2 :
                (octet & 0xF0) == 0xE0 ? 3 :
                (octet & 0xF8) == 0xF0 ? 4 : 0;
        value = (octet & 0x80) == 0x00 ? octet & 0x7F :
                (octet & 0xE0) == 0xC0 ? octet & 0x1F :
                (octet & 0xF0) == 0xE0 ? octet & 0x0F :
                (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0;
        if (!width) return 0;
        if (pointer+width > end) return 0;
        for (k = 1; k < width; k ++) {
            octet = pointer[k];
            if ((octet & 0xC0) != 0x80) return 0;
            value = (value << 6) + (octet & 0x3F);
        }
        if (!((width == 1) ||
            (width == 2 && value >= 0x80) ||
            (width == 3 && value >= 0x800) ||
            (width == 4 && value >= 0x10000))) return 0;

        pointer += width;
    }

    return 1;
}

/*
 * Create STREAM-START.