;=============================================================
;   eax <- pointer to the memory address of the string
;   * Do not use other register because it may be overwritten.
;   -------PRIVATE--------
;   ebx <- counter of codepoints
;   ecx <- each byte
;   
;=============================================================
count_utf8_codepoints:
        mov     ebx, 0

.read_loop:
        mov     cl, byte [eax]
        
        test    cl, cl        ; if it is an ending byte (0)
        je      .done

        and     cl, 0xC0
        cmp     cl, 0x80
        je      .skip_count
        inc     ebx

.skip_count:
        inc     eax
        jmp     .read_loop
.done:
        mov     eax, ebx
        ret

;=============================================================
;   eax <- pointer to the memory address of the string
;   * Do not use other register because it may be overwritten.
;   -------PRIVATE--------
;   ebx <- counter of grapheme
;   ecx <- each byte
;   
;=============================================================
count_utf8_gramphene:
        mov     ebx, 0

.read_loop:
        mov     cl, byte [eax]
        
        test    cl, cl        ; if it is an ending byte (0)
        je      .done
; Is this accent

        cmp     cl, 0xCC
        je      .skip_count

        cmp     cl, 0xCD
        je      .skip_count

; Check for not a zero width joint
        cmp     cl, 0xE2
        jne     .not_any_special

        cmp byte [eax+1], 0x80
        jne     .not_any_special

        cmp byte [eax+2], 0x8D
        jne     .not_any_special

        dec     ebx
        add     eax, 3
        jmp     .read_loop

.not_any_special:
        and     cl, 0xC0        ; Is this a continution byte
        cmp     cl, 0x80
        je      .skip_count
        inc     ebx

.skip_count:
        inc     eax
        jmp     .read_loop

.done:
        mov     eax, ebx
        ret