version 1.6, 2004/12/28 17:27:24
|
version 1.12, 2005/01/05 16:24:33
|
Line 20
|
Line 20
|
|
|
\ short: u8 means utf-8 encoded address |
\ short: u8 means utf-8 encoded address |
|
|
|
s" malformed UTF-8 character" exception Constant UTF-8-err |
|
|
|
$80 Value maxascii |
|
|
: u8len ( u8 -- n ) |
: u8len ( u8 -- n ) |
dup $80 u< IF drop 1 EXIT THEN \ special case ASCII |
dup maxascii u< IF drop 1 EXIT THEN \ special case ASCII |
$800 2 >r |
$800 2 >r |
BEGIN 2dup u>= WHILE 5 lshift r> 1+ >r REPEAT |
BEGIN 2dup u>= WHILE 5 lshift r> 1+ >r REPEAT |
2drop r> ; |
2drop r> ; |
|
|
: u8@+ ( u8addr -- u8addr' u ) |
: u8@+ ( u8addr -- u8addr' u ) |
count dup $80 and 0= ?EXIT \ special case ASCII |
count dup maxascii u< ?EXIT \ special case ASCII |
$7F and $40 >r |
$7F and $40 >r |
BEGIN dup r@ and WHILE r@ xor |
BEGIN dup r@ and WHILE r@ xor |
6 lshift r> 5 lshift >r >r count |
6 lshift r> 5 lshift >r >r count |
\ dup $C0 and $80 <> abort" malformed character" |
dup $C0 and $80 <> IF UTF-8-err throw THEN |
$3F and r> or |
$3F and r> or |
REPEAT rdrop ; |
REPEAT rdrop ; |
|
|
: u8!+ ( u u8addr -- u8addr' ) |
: u8!+ ( u u8addr -- u8addr' ) |
over $80 < IF tuck c! 1+ EXIT THEN \ special case ASCII |
over maxascii u< IF tuck c! 1+ EXIT THEN \ special case ASCII |
>r 0 swap $3F |
>r 0 swap $3F |
BEGIN 2dup u> WHILE |
BEGIN 2dup u> WHILE |
2/ >r dup $3F and $80 or swap 6 rshift r> |
2/ >r dup $3F and $80 or swap 6 rshift r> |
REPEAT $7F xor 2* or r> |
REPEAT $7F xor 2* or r> |
BEGIN over $80 u>= WHILE tuck c! 1+ REPEAT nip ; |
BEGIN over $80 u>= WHILE tuck c! 1+ REPEAT nip ; |
|
|
|
\ plug-in so that char and '<char> work for UTF-8 |
|
|
|
[ifundef] char@ \ !! bootstrapping help |
|
Defer char@ ( addr u -- char addr' u' ) |
|
:noname over c@ -rot 1 /string ; IS char@ |
|
[then] |
|
|
|
:noname ( addr u -- char addr' u' ) |
|
\ !! the if here seems to work around some breakage, but not |
|
\ entirely; e.g., try 'ç' with LANG=C. |
|
dup 1 u<= IF defers char@ EXIT THEN |
|
over + >r u8@+ swap r> over - ; IS char@ |
|
|
\ scan to next/previous character |
\ scan to next/previous character |
|
|
: u8>> ( u8addr -- u8addr' ) |
: u8>> ( u8addr -- u8addr' ) u8@+ drop ; |
BEGIN count $C0 and $80 <> UNTIL ; |
|
: u8<< ( u8addr -- u8addr' ) |
: u8<< ( u8addr -- u8addr' ) |
BEGIN 1- dup c@ $C0 and $80 <> UNTIL ; |
BEGIN 1- dup c@ $C0 and maxascii <> UNTIL ; |
|
|
\ utf key and emit |
\ utf key and emit |
|
|
: u8key ( -- u ) |
: u8key ( -- u ) |
defers key dup $80 and 0= ?EXIT \ special case ASCII |
defers key dup maxascii u< ?EXIT \ special case ASCII |
$7F and $40 >r |
$7F and $40 >r |
BEGIN dup r@ and WHILE r@ xor |
BEGIN dup r@ and WHILE r@ xor |
6 lshift r> 5 lshift >r >r defers key |
6 lshift r> 5 lshift >r >r defers key |
\ dup $C0 and $80 <> abort" malformed character" |
dup $C0 and $80 <> IF UTF-8-err throw THEN |
$3F and r> or |
$3F and r> or |
REPEAT rdrop ; |
REPEAT rdrop ; |
|
|
: u8emit ( u -- ) |
: u8emit ( u -- ) |
dup $80 < IF defers emit EXIT THEN \ special case ASCII |
dup maxascii u< IF defers emit EXIT THEN \ special case ASCII |
0 swap $3F |
0 swap $3F |
BEGIN 2dup u> WHILE |
BEGIN 2dup u> WHILE |
2/ >r dup $3F and $80 or swap 6 rshift r> |
2/ >r dup $3F and $80 or swap 6 rshift r> |
Line 71
|
Line 87
|
|
|
\ input editor |
\ input editor |
|
|
: save-cursor ( -- ) 27 emit '7 emit ; |
[IFUNDEF] #esc 27 Constant #esc [THEN] |
: restore-cursor ( -- ) 27 emit '8 emit ; |
|
|
: save-cursor ( -- ) #esc emit '7 emit ; |
|
: restore-cursor ( -- ) #esc emit '8 emit ; |
: .rest ( addr pos1 -- addr pos1 ) |
: .rest ( addr pos1 -- addr pos1 ) |
restore-cursor 2dup type ; |
restore-cursor 2dup type ; |
: .all ( span addr pos1 -- span addr pos1 ) |
: .all ( span addr pos1 -- span addr pos1 ) |