version 1.9, 2004/12/31 11:01:21
|
version 1.39, 2009/05/11 08:07:44
|
Line 1
|
Line 1
|
\ UTF-8 handling 12dec04py |
\ UTF-8 handling 12dec04py |
|
|
\ Copyright (C) 2004 Free Software Foundation, Inc. |
\ Copyright (C) 2004,2005,2006,2007,2008 Free Software Foundation, Inc. |
|
|
\ This file is part of Gforth. |
\ This file is part of Gforth. |
|
|
\ Gforth is free software; you can redistribute it and/or |
\ Gforth is free software; you can redistribute it and/or |
\ modify it under the terms of the GNU General Public License |
\ modify it under the terms of the GNU General Public License |
\ as published by the Free Software Foundation; either version 2 |
\ as published by the Free Software Foundation, either version 3 |
\ of the License, or (at your option) any later version. |
\ of the License, or (at your option) any later version. |
|
|
\ This program is distributed in the hope that it will be useful, |
\ This program is distributed in the hope that it will be useful, |
Line 15
|
Line 15
|
\ GNU General Public License for more details. |
\ GNU General Public License for more details. |
|
|
\ You should have received a copy of the GNU General Public License |
\ You should have received a copy of the GNU General Public License |
\ along with this program; if not, write to the Free Software |
\ along with this program. If not, see http://www.gnu.org/licenses/. |
\ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA. |
|
|
|
\ short: u8 means utf-8 encoded address |
\ short: u8 means utf-8 encoded address |
|
|
s" malformed UTF-8 character" exception Constant UTF-8-err |
s" malformed UTF-8 character" exception Constant UTF-8-err |
|
|
|
$80 Value max-single-byte |
|
|
: u8len ( u8 -- n ) |
: u8len ( u8 -- n ) |
dup $80 u< IF drop 1 EXIT THEN \ special case ASCII |
dup max-single-byte 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 dup 0= UNTIL THEN |
2drop r> ; |
2drop r> ; |
|
|
: u8@+ ( u8addr -- u8addr' u ) |
: u8@+ ( u8addr -- u8addr' u ) |
count dup $80 and 0= ?EXIT \ special case ASCII |
count dup max-single-byte u< ?EXIT \ special case ASCII |
|
dup $C2 u< IF UTF-8-err throw THEN \ malformed character |
$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 |
Line 38 s" malformed UTF-8 character" exception
|
Line 40 s" malformed UTF-8 character" exception
|
REPEAT rdrop ; |
REPEAT rdrop ; |
|
|
: u8!+ ( u u8addr -- u8addr' ) |
: u8!+ ( u u8addr -- u8addr' ) |
over $80 < IF tuck c! 1+ EXIT THEN \ special case ASCII |
over max-single-byte 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> |
Line 54 s" malformed UTF-8 character" exception
|
Line 56 s" malformed UTF-8 character" exception
|
|
|
:noname ( addr u -- char addr' u' ) |
:noname ( addr u -- char addr' u' ) |
\ !! the if here seems to work around some breakage, but not |
\ !! the if here seems to work around some breakage, but not |
\ entirely; e.g., try '็' with LANG=C. |
\ entirely; e.g., try 'รง' with LANG=C. |
dup 1 u<= IF defers char@ EXIT THEN |
dup 1 u<= IF defers char@ EXIT THEN |
over + >r u8@+ swap r> over - ; IS char@ |
over + >r u8@+ swap r> over - ; IS char@ |
|
|
\ scan to next/previous character |
\ scan to next/previous character |
|
|
: u8>> ( u8addr -- u8addr' ) |
\ alternative names: u8char+ u8char- |
BEGIN count $C0 and $80 <> UNTIL ; |
|
|
: u8>> ( u8addr -- u8addr' ) u8@+ drop ; |
: u8<< ( u8addr -- u8addr' ) |
: u8<< ( u8addr -- u8addr' ) |
BEGIN 1- dup c@ $C0 and $80 <> UNTIL ; |
BEGIN 1- dup c@ $C0 and max-single-byte <> UNTIL ; |
|
|
\ utf key and emit |
\ utf key and emit |
|
|
|
Defer check-xy ' noop IS check-xy |
|
|
: u8key ( -- u ) |
: u8key ( -- u ) |
defers key dup $80 and 0= ?EXIT \ special case ASCII |
key dup max-single-byte u< ?EXIT \ special case ASCII |
|
dup $FF = ?EXIT \ special resize character |
|
dup $C2 u< IF UTF-8-err throw THEN \ malformed character |
$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 key |
dup $C0 and $80 <> IF UTF-8-err throw THEN |
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 max-single-byte u< IF 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> |
REPEAT $7F xor 2* or |
REPEAT $7F xor 2* or |
BEGIN dup $80 u>= WHILE defers emit REPEAT drop ; |
BEGIN dup $80 u>= WHILE emit REPEAT drop ; |
|
|
\ input editor |
|
|
|
[IFUNDEF] #esc 27 Constant #esc [THEN] |
\ utf-8 stuff for xchars |
|
|
: save-cursor ( -- ) #esc emit '7 emit ; |
: +u8/string ( xc-addr1 u1 -- xc-addr2 u2 ) |
: restore-cursor ( -- ) #esc emit '8 emit ; |
over dup u8>> swap - /string ; |
: .rest ( addr pos1 -- addr pos1 ) |
: u8\string- ( xcaddr u -- xcaddr u' ) |
restore-cursor 2dup type ; |
over + u8<< over - ; |
: .all ( span addr pos1 -- span addr pos1 ) |
|
restore-cursor >r 2dup swap type r> ; |
: u8@ ( c-addr -- u ) |
|
u8@+ nip ; |
: <u8ins> ( max span addr pos1 u8char -- max span addr pos2 ) |
|
>r 2over r@ u8len + u< IF rdrop bell EXIT THEN |
: u8!+? ( xc xc-addr1 u1 -- xc-addr2 u2 f ) |
>string over r@ u8len + swap move 2dup chars + r@ swap u8!+ drop |
>r over u8len r@ over u< if ( xc xc-addr1 len r: u1 ) |
r> u8len >r rot r@ chars + -rot r> chars + ; |
\ not enough space |
: (u8ins) ( max span addr pos1 u8char -- max span addr pos2 ) |
drop nip r> false |
<u8ins> .all .rest ; |
else |
: u8back ( max span addr pos1 -- max span addr pos2 f ) |
>r u8!+ r> r> swap - true |
dup IF over + u8<< over - 0 max .all .rest |
then ; |
ELSE bell THEN 0 ; |
|
: u8forw ( max span addr pos1 -- max span addr pos2 f ) |
: u8addrlen ( u8-addr u -- u ) drop |
2 pick over <> IF over + u8@+ u8emit over - ELSE bell THEN 0 ; |
\ length of UTF-8 char starting at u8-addr (accesses only u8-addr) |
: (u8del) ( max span addr pos1 -- max span addr pos2 ) |
c@ |
over + dup u8<< tuck - >r over - |
dup $80 u< if drop 1 exit endif |
>string over r@ + -rot move |
dup $c0 u< if UTF-8-err throw endif |
rot r> - -rot ; |
dup $e0 u< if drop 2 exit endif |
: ?u8del ( max span addr pos1 -- max span addr pos2 0 ) |
dup $f0 u< if drop 3 exit endif |
dup IF (u8del) .all 2 spaces .rest THEN 0 ; |
dup $f8 u< if drop 4 exit endif |
: <u8del> ( max span addr pos1 -- max span addr pos2 0 ) |
dup $fc u< if drop 5 exit endif |
2 pick over <> |
dup $fe u< if drop 6 exit endif |
IF u8forw drop (u8del) .all 2 spaces .rest |
dup $ff u< if drop 7 exit endif |
ELSE bell THEN 0 ; |
drop 8 ; |
: u8eof 2 pick over or 0= IF bye ELSE <u8del> THEN ; |
|
|
: -u8trailing-garbage ( addr u1 -- addr u2 ) |
: u8first-pos ( max span addr pos1 -- max span addr 0 0 ) |
2dup + dup u8<< ( addr u1 end1 end2 ) |
drop 0 .all .rest 0 ; |
2dup dup over over - u8addrlen + = if \ last character ok |
: u8end-pos ( max span addr pos1 -- max span addr span 0 ) |
2drop |
drop over .all 0 ; |
else |
|
nip nip over - |
|
then ; |
: u8clear-line ( max span addr pos1 -- max addr ) |
|
drop restore-cursor swap spaces restore-cursor ; |
[IFUNDEF] wcwidth |
: u8clear-tib ( max span addr pos -- max 0 addr 0 false ) |
: wc,3 ( n low high -- ) 1+ , , , ; |
u8clear-line 0 tuck dup ; |
|
|
Create wc-table \ derived from wcwidth source code, for UCS32 |
: (u8enter) ( max span addr pos1 -- max span addr pos2 true ) |
0 $0300 $0357 wc,3 |
>r end^ 2@ hist-setpos |
0 $035D $036F wc,3 |
2dup swap history write-line drop ( throw ) \ don't worry about errors |
0 $0483 $0486 wc,3 |
hist-pos 2dup backward^ 2! end^ 2! |
0 $0488 $0489 wc,3 |
r> .all space true ; |
0 $0591 $05A1 wc,3 |
|
0 $05A3 $05B9 wc,3 |
: u8kill-expand ( max span addr pos1 -- max span addr pos2 ) |
0 $05BB $05BD wc,3 |
prefix-found cell+ @ ?dup IF >r |
0 $05BF $05BF wc,3 |
r@ - >string over r@ + -rot move |
0 $05C1 $05C2 wc,3 |
rot r@ - -rot .all r> spaces .rest THEN ; |
0 $05C4 $05C4 wc,3 |
|
0 $0600 $0603 wc,3 |
: insert ( string length buffer size -- ) |
0 $0610 $0615 wc,3 |
rot over min >r r@ - ( left over ) |
0 $064B $0658 wc,3 |
over dup r@ + rot move r> move ; |
0 $0670 $0670 wc,3 |
|
0 $06D6 $06E4 wc,3 |
: u8tab-expand ( max span addr pos1 -- max span addr pos2 0 ) |
0 $06E7 $06E8 wc,3 |
key? IF #tab (u8ins) 0 EXIT THEN |
0 $06EA $06ED wc,3 |
u8kill-expand 2dup extract-word dup 0= IF nip EXIT THEN |
0 $070F $070F wc,3 |
search-prefix tib-full? |
0 $0711 $0711 wc,3 |
IF 7 emit 2drop prefix-off |
0 $0730 $074A wc,3 |
ELSE dup >r |
0 $07A6 $07B0 wc,3 |
2>r >string r@ + 2r> 2swap insert |
0 $0901 $0902 wc,3 |
r@ + rot r> + -rot |
0 $093C $093C wc,3 |
THEN |
0 $0941 $0948 wc,3 |
prefix-found @ IF bl (u8ins) ELSE .all .rest THEN 0 ; |
0 $094D $094D wc,3 |
|
0 $0951 $0954 wc,3 |
: utf-8-io ( -- ) |
0 $0962 $0963 wc,3 |
['] u8forw ctrl F bindkey |
0 $0981 $0981 wc,3 |
['] u8back ctrl B bindkey |
0 $09BC $09BC wc,3 |
['] ?u8del ctrl H bindkey |
0 $09C1 $09C4 wc,3 |
['] u8eof ctrl D bindkey |
0 $09CD $09CD wc,3 |
['] <u8del> ctrl X bindkey |
0 $09E2 $09E3 wc,3 |
['] u8clear-tib ctrl K bindkey |
0 $0A01 $0A02 wc,3 |
['] u8first-pos ctrl A bindkey |
0 $0A3C $0A3C wc,3 |
['] u8end-pos ctrl E bindkey |
0 $0A41 $0A42 wc,3 |
['] (u8enter) #lf bindkey |
0 $0A47 $0A48 wc,3 |
['] (u8enter) #cr bindkey |
0 $0A4B $0A4D wc,3 |
['] u8tab-expand #tab bindkey |
0 $0A70 $0A71 wc,3 |
['] (u8ins) IS insert-char |
0 $0A81 $0A82 wc,3 |
['] kill-prefix IS everychar |
0 $0ABC $0ABC wc,3 |
['] save-cursor IS everyline |
0 $0AC1 $0AC5 wc,3 |
['] u8key IS key |
0 $0AC7 $0AC8 wc,3 |
['] u8emit IS emit ; |
0 $0ACD $0ACD wc,3 |
|
0 $0AE2 $0AE3 wc,3 |
|
0 $0B01 $0B01 wc,3 |
|
0 $0B3C $0B3C wc,3 |
|
0 $0B3F $0B3F wc,3 |
|
0 $0B41 $0B43 wc,3 |
|
0 $0B4D $0B4D wc,3 |
|
0 $0B56 $0B56 wc,3 |
|
0 $0B82 $0B82 wc,3 |
|
0 $0BC0 $0BC0 wc,3 |
|
0 $0BCD $0BCD wc,3 |
|
0 $0C3E $0C40 wc,3 |
|
0 $0C46 $0C48 wc,3 |
|
0 $0C4A $0C4D wc,3 |
|
0 $0C55 $0C56 wc,3 |
|
0 $0CBC $0CBC wc,3 |
|
0 $0CBF $0CBF wc,3 |
|
0 $0CC6 $0CC6 wc,3 |
|
0 $0CCC $0CCD wc,3 |
|
0 $0D41 $0D43 wc,3 |
|
0 $0D4D $0D4D wc,3 |
|
0 $0DCA $0DCA wc,3 |
|
0 $0DD2 $0DD4 wc,3 |
|
0 $0DD6 $0DD6 wc,3 |
|
0 $0E31 $0E31 wc,3 |
|
0 $0E34 $0E3A wc,3 |
|
0 $0E47 $0E4E wc,3 |
|
0 $0EB1 $0EB1 wc,3 |
|
0 $0EB4 $0EB9 wc,3 |
|
0 $0EBB $0EBC wc,3 |
|
0 $0EC8 $0ECD wc,3 |
|
0 $0F18 $0F19 wc,3 |
|
0 $0F35 $0F35 wc,3 |
|
0 $0F37 $0F37 wc,3 |
|
0 $0F39 $0F39 wc,3 |
|
0 $0F71 $0F7E wc,3 |
|
0 $0F80 $0F84 wc,3 |
|
0 $0F86 $0F87 wc,3 |
|
0 $0F90 $0F97 wc,3 |
|
0 $0F99 $0FBC wc,3 |
|
0 $0FC6 $0FC6 wc,3 |
|
0 $102D $1030 wc,3 |
|
0 $1032 $1032 wc,3 |
|
0 $1036 $1037 wc,3 |
|
0 $1039 $1039 wc,3 |
|
0 $1058 $1059 wc,3 |
|
1 $0000 $1100 wc,3 |
|
2 $1100 $115f wc,3 |
|
0 $1160 $11FF wc,3 |
|
0 $1712 $1714 wc,3 |
|
0 $1732 $1734 wc,3 |
|
0 $1752 $1753 wc,3 |
|
0 $1772 $1773 wc,3 |
|
0 $17B4 $17B5 wc,3 |
|
0 $17B7 $17BD wc,3 |
|
0 $17C6 $17C6 wc,3 |
|
0 $17C9 $17D3 wc,3 |
|
0 $17DD $17DD wc,3 |
|
0 $180B $180D wc,3 |
|
0 $18A9 $18A9 wc,3 |
|
0 $1920 $1922 wc,3 |
|
0 $1927 $1928 wc,3 |
|
0 $1932 $1932 wc,3 |
|
0 $1939 $193B wc,3 |
|
0 $200B $200F wc,3 |
|
0 $202A $202E wc,3 |
|
0 $2060 $2063 wc,3 |
|
0 $206A $206F wc,3 |
|
0 $20D0 $20EA wc,3 |
|
2 $2329 $232A wc,3 |
|
0 $302A $302F wc,3 |
|
2 $2E80 $303E wc,3 |
|
0 $3099 $309A wc,3 |
|
2 $3040 $A4CF wc,3 |
|
2 $AC00 $D7A3 wc,3 |
|
2 $F900 $FAFF wc,3 |
|
0 $FB1E $FB1E wc,3 |
|
0 $FE00 $FE0F wc,3 |
|
0 $FE20 $FE23 wc,3 |
|
2 $FE30 $FE6F wc,3 |
|
0 $FEFF $FEFF wc,3 |
|
2 $FF00 $FF60 wc,3 |
|
2 $FFE0 $FFE6 wc,3 |
|
0 $FFF9 $FFFB wc,3 |
|
0 $1D167 $1D169 wc,3 |
|
0 $1D173 $1D182 wc,3 |
|
0 $1D185 $1D18B wc,3 |
|
0 $1D1AA $1D1AD wc,3 |
|
2 $20000 $2FFFD wc,3 |
|
2 $30000 $3FFFD wc,3 |
|
0 $E0001 $E0001 wc,3 |
|
0 $E0020 $E007F wc,3 |
|
0 $E0100 $E01EF wc,3 |
|
here wc-table - Constant #wc-table |
|
|
|
\ inefficient table walk: |
|
|
|
: wcwidth ( xc -- n ) |
|
wc-table #wc-table over + swap ?DO |
|
dup I 2@ within IF I 2 cells + @ UNLOOP EXIT THEN |
|
3 cells +LOOP 1 ; |
|
[THEN] |
|
|
|
: u8width ( xcaddr u -- n ) |
|
0 rot rot over + swap ?DO |
|
I xc@+ swap >r wcwidth + |
|
r> I - +LOOP ; |
|
|
|
: set-encoding-utf-8 ( -- ) |
|
['] u8emit is xemit |
|
['] u8key is xkey |
|
['] u8>> is xchar+ |
|
['] u8<< is xchar- |
|
[ [IFDEF] xstring+ ] |
|
['] u8\string- is xstring- |
|
['] +u8/string is +xstring |
|
[ [THEN] ] |
|
[ [IFDEF] +x/string ] |
|
['] u8\string- is x\string- |
|
['] +u8/string is +x/string |
|
[ [THEN] ] |
|
['] u8@ is xc@ |
|
['] u8!+? is xc!+? |
|
['] u8@+ is xc@+ |
|
['] u8len is xc-size |
|
[ [IFDEF] x-width ] |
|
['] u8width is x-width |
|
[ [THEN] ] |
|
[ [IFDEF] x-size ] |
|
['] u8addrlen is x-size |
|
[ [THEN] ] |
|
['] -u8trailing-garbage is -trailing-garbage |
|
; |
|
|
|
: utf-8-cold ( -- ) |
|
s" LC_ALL" getenv 2dup d0= IF 2drop |
|
s" LC_CTYPE" getenv 2dup d0= IF 2drop |
|
s" LANG" getenv 2dup d0= IF 2drop |
|
s" C" THEN THEN THEN |
|
s" UTF-8" search nip nip |
|
IF set-encoding-utf-8 ELSE set-encoding-fixed-width THEN ; |
|
|
|
environment-wordlist set-current |
|
: xchar-encoding ( -- addr u ) \ xchar-ext |
|
\G Returns a printable ASCII string that reperesents the encoding, |
|
\G and use the preferred MIME name (if any) or the name in |
|
\G @url{http://www.iana.org/assignments/character-sets} like |
|
\G ``ISO-LATIN-1'' or ``UTF-8'', with the exception of ``ASCII'', where |
|
\G we prefer the alias ``ASCII''. |
|
max-single-byte $80 = IF s" UTF-8" ELSE s" ISO-LATIN-1" THEN ; |
|
: max-xchar ( -- xchar ) |
|
max-single-byte $80 = IF $7FFFFFFF ELSE $FF THEN ; |
|
' noop Alias X:xchar |
|
forth definitions |
|
|
|
:noname ( -- ) |
|
defers 'cold |
|
utf-8-cold |
|
; is 'cold |
|
|
|
utf-8-cold |