kolibrios/kernel/trunk/fs/parse_fn.inc
pathoswithin 31fad3ee4a UTF-8 file path input, unicode names for apps and libs
git-svn-id: svn://kolibrios.org@6502 a494cfbc-eb01-0410-851d-a64ba20cac60
2016-08-25 19:30:08 +00:00

330 lines
6.7 KiB
PHP

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; ;;
;; Copyright (C) KolibriOS team 2004-2016. All rights reserved. ;;
;; Distributed under terms of the GNU General Public License. ;;
;; ;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
$Revision$
iglobal
full_file_name_table dd sysdir_name
.size dd 1
endg
uglobal
sysdir_name rb 64 ; 'sys',0
sysdir_path rb 64
sysdir_name1 rb 64
sysdir_path1 rb 64
endg
; Example:
; align 64
; sysdir_name1 db 'KolibriOS',0
; align 64
; sysdir_path1 db 'HD0/1',0
proc Parser_params
locals
buff rb 4 ; for test cd
endl
mov eax, [OS_BASE+0x10000+bx_from_load]
mov ecx, sysdir_path
mov [ecx-64], dword 'sys'
mov [ecx-2], byte 3
mov [ecx-1], byte '/'
cmp al, 'r' ; ram disk
jnz @f
mov [ecx], dword 'RD/?'
mov [ecx+3], byte ah
mov [ecx+4], byte 0
ret
@@:
cmp al, 'm'
jnz .hard_disk
mov [ecx], dword 'CD?/'
mov [ecx+4], byte '1'
mov [ecx+5], dword '/KOL'
mov [ecx+9], dword 'IBRI'
mov [ecx+13], byte 0
.next_cd:
mov [ecx+2], byte ah
inc ah
cmp ah, '5'
je @f
lea edx, [buff]
pushad
stdcall read_file, read_firstapp, edx, 0, 4
popad
cmp [edx], dword 'MENU'
jne .next_cd
@@:
ret
.hard_disk:
sub al, '1'
mov [ecx], dword 'HD?/'
mov [ecx+2], byte al
mov [ecx+4], byte ah
mov [ecx+5], dword '/KOL'
mov [ecx+9], dword 'IBRI'
mov [ecx+13], byte 0
ret
endp
cp866toUpper:
; convert cp866 character in al to uppercase
cmp al, 'a'
jb .ret
cmp al, 'z'
jbe @f
cmp al, 0xA0
jb .ret
cmp al, 0xB0
jb @f
cmp al, 0xE0
jb .ret
cmp al, 0xF0
jb .rus
cmp al, 0xF7
ja .ret
and eax, -2
.ret:
ret
@@:
sub eax, 32
ret
.rus:
sub eax, 0xE0-0x90
ret
utf16toUpper:
; convert UTF-16 character in ax to uppercase
cmp ax, 'a'
jb .ret
cmp ax, 'z'
jbe @f
cmp ax, 430h
jb .ret
cmp ax, 450h
jb @f
cmp ax, 460h
jnc .ret
sub eax, 80
.ret:
ret
@@:
sub eax, 32
ret
uni2ansi_char:
; convert UNICODE character in ax to ANSI character in al using cp866 encoding
cmp ax, 0x80
jb .ret
cmp ax, 0xB6
jz .B6
cmp ax, 0x400
jb .unk
cmp ax, 0x410
jb @f
cmp ax, 0x440
jb .rus1
cmp ax, 0x450
jb .rus2
cmp ax, 0x460
jb @f
.unk:
mov al, '_'
.ret:
ret
.B6:
mov al, 20
ret
.rus1: ; 0x410-0x43F -> 0x80-0xAF
add al, 0x70
ret
.rus2: ; 0x440-0x44F -> 0xE0-0xEF
add al, 0xA0
ret
@@:
push ecx edi
mov ecx, 8
mov edi, .table
repnz scasb
mov ah, cl
pop edi ecx
jnz .unk
mov al, 0xF7
sub al, ah
ret
.table db 1, 51h, 4, 54h, 7, 57h, 0Eh, 5Eh
ansi2uni_char:
; convert ANSI character in al to UNICODE character in ax, using cp866 encoding
movzx eax, al
cmp al, 0x80
jb @f ; 0x00-0x7F - trivial map
cmp al, 0xB0
jb .rus ; 0x80-0xAF -> 0x410-0x43F
cmp al, 0xE0
jb .unk
cmp al, 0xF0
jb .rus2 ; 0xE0-0xEF -> 0x440-0x44F
cmp al, 0xF8
jnc .unk
mov al, [eax+uni2ansi_char.table-0xF0]
add ax, 400h
ret
@@:
cmp al, 20
jnz .ret
mov al, 0xB6
.ret:
ret
.rus:
add ax, 0x410-0x80
ret
.rus2:
add ax, 0x440-0xE0
ret
.unk:
mov al, '_'
ret
cp866toUTF8_string:
; in:
; esi -> cp866 string (could be zero terminated)
; edi -> buffer for UTF-8 string
; ecx = buffer size (signed)
lodsb
call ansi2uni_char
push eax
call UTF16to8
pop eax
js @f
test eax, eax
jnz cp866toUTF8_string
@@:
ret
; SF=1 -> counter
; ZF=1 -> zero char
UTF16to8_string:
; in:
; esi -> UTF-16 string (could be zero terminated)
; edi -> buffer for UTF-8 string
; ecx = buffer size (signed)
xor eax, eax
@@:
lodsw
push eax
call UTF16to8
pop eax
js @f
test eax, eax
jnz @b
@@:
ret
UTF16to8:
; in:
; eax = UTF-16 char
; edi -> buffer for UTF-8 char (increasing)
; ecx = byte counter (decreasing)
dec ecx
js .ret
cmp eax, 80h
jnc @f
stosb
test eax, eax ; SF=0
.ret:
ret
@@:
dec ecx
js .ret
cmp eax, 800h
jnc @f
shl eax, 2
shr al, 2
or eax, 1100000010000000b
xchg al, ah
stosw
ret
@@:
dec ecx
js .ret
shl eax, 4
shr ax, 2
shr al, 2
or eax, 111000001000000010000000b
bswap eax
shr eax, 8
stosb
shr eax, 8
stosw
ret
utf8to16:
; in: esi -> UTF-8 char (increasing)
; out: ax = UTF-16 char
lodsb
test al, al
jns .got
shl al, 2
jnc utf8to16
@@:
shl ax, 8
lodsb
test al, al
jns .got
shl al, 2
jc @b
shr ah, 2
shl ax, 3
jnc @f
shl eax, 3
lodsb
test al, al
jns .got
shl al, 2
jc @b
shr eax, 2
ret
@@:
shr ax, 5
ret
.got:
xor ah, ah
ret
strlen:
; in: esi -> source
; out: ecx = length
push edi eax
or ecx, -1
mov edi, esi
xor eax, eax
repnz scasb
inc ecx
not ecx
pop eax edi
ret