Swarnadeep Paul
6de88d5fd0
- Added libunicode.asm to parse UTF-8 strings. - Implemented count_utf8_codepoints to skip continuation bytes. - Implemented count_utf8_graphemes to handle ZWJ (E2 80 8D) and combining marks (CC/CD). - Added console.asm to the examples folder to test and print the results. - Submitted for GSoC qualification task.
82 lines
1.9 KiB
NASM
82 lines
1.9 KiB
NASM
;=============================================================
|
|
; 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_graph:
|
|
mov cl, byte [eax]
|
|
|
|
test cl, cl ; if it is an ending byte (0)
|
|
je done_graph
|
|
; Is this accent
|
|
|
|
cmp cl, 0xCC
|
|
je skip_count_graph
|
|
|
|
cmp cl, 0xCD
|
|
je skip_count_graph
|
|
|
|
; 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_graph
|
|
|
|
not_any_special:
|
|
and cl, 0xC0 ; Is this a continution byte
|
|
cmp cl, 0x80
|
|
je skip_count_graph
|
|
inc ebx
|
|
|
|
skip_count_graph:
|
|
inc eax
|
|
jmp read_loop_graph
|
|
|
|
done_graph:
|
|
mov eax, ebx
|
|
ret
|
|
|