File:  [gforth] / gforth / utf-8.fs
Revision 1.8: download - view: text, annotated - select for diffs
Wed Dec 29 14:15:12 2004 UTC (19 years, 3 months ago) by pazsan
Branches: MAIN
CVS tags: HEAD
Added UTF-8 support for char and '<char>

    1: \ UTF-8 handling                                       12dec04py
    2: 
    3: \ Copyright (C) 2004 Free Software Foundation, Inc.
    4: 
    5: \ This file is part of Gforth.
    6: 
    7: \ Gforth is free software; you can redistribute it and/or
    8: \ modify it under the terms of the GNU General Public License
    9: \ as published by the Free Software Foundation; either version 2
   10: \ of the License, or (at your option) any later version.
   11: 
   12: \ This program is distributed in the hope that it will be useful,
   13: \ but WITHOUT ANY WARRANTY; without even the implied warranty of
   14: \ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   15: \ GNU General Public License for more details.
   16: 
   17: \ You should have received a copy of the GNU General Public License
   18: \ along with this program; if not, write to the Free Software
   19: \ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA.
   20: 
   21: \ short: u8 means utf-8 encoded address
   22: 
   23: s" malformed UTF-8 character" exception Constant UTF-8-err
   24: 
   25: : u8len ( u8 -- n )
   26:     dup      $80 u< IF  drop 1  EXIT  THEN \ special case ASCII
   27:     $800  2 >r
   28:     BEGIN  2dup u>=  WHILE  5 lshift r> 1+ >r  REPEAT
   29:     2drop r> ;
   30: 
   31: : u8@+ ( u8addr -- u8addr' u )
   32:     count  dup $80 and 0= ?EXIT  \ special case ASCII
   33:     $7F and  $40 >r
   34:     BEGIN  dup r@ and  WHILE  r@ xor
   35: 	    6 lshift r> 5 lshift >r >r count
   36: 	    dup $C0 and $80 <> IF   UTF-8-err throw  THEN
   37: 	    $3F and r> or
   38:     REPEAT  rdrop ;
   39: 
   40: : u8!+ ( u u8addr -- u8addr' )
   41:     over $80 < IF  tuck c! 1+  EXIT  THEN \ special case ASCII
   42:     >r 0 swap  $3F
   43:     BEGIN  2dup u>  WHILE
   44: 	    2/ >r  dup $3F and $80 or swap 6 rshift r>
   45:     REPEAT  $7F xor 2* or  r>
   46:     BEGIN   over $80 u>= WHILE  tuck c! 1+  REPEAT  nip ;
   47: 
   48: \ plug-in so that char and '<char> work for UTF-8
   49: 
   50: :noname  ( addr u -- char addr' u' )
   51:     dup 1 u<= IF  defers char@  EXIT  THEN
   52:     over + >r u8@+ swap r> over - ; IS char@
   53: 
   54: \ scan to next/previous character
   55: 
   56: : u8>> ( u8addr -- u8addr' )
   57:     BEGIN  count $C0 and $80 <>  UNTIL ;
   58: : u8<< ( u8addr -- u8addr' )
   59:     BEGIN  1- dup c@ $C0 and $80 <>  UNTIL ;
   60: 
   61: \ utf key and emit
   62: 
   63: : u8key ( -- u )
   64:     defers key dup $80 and 0= ?EXIT  \ special case ASCII
   65:     $7F and  $40 >r
   66:     BEGIN  dup r@ and  WHILE  r@ xor
   67: 	    6 lshift r> 5 lshift >r >r defers key
   68: 	    dup $C0 and $80 <> IF  UTF-8-err throw  THEN
   69: 	    $3F and r> or
   70:     REPEAT  rdrop ;
   71: 
   72: : u8emit ( u -- )
   73:     dup $80 < IF  defers emit  EXIT  THEN \ special case ASCII
   74:     0 swap  $3F
   75:     BEGIN  2dup u>  WHILE
   76: 	    2/ >r  dup $3F and $80 or swap 6 rshift r>
   77:     REPEAT  $7F xor 2* or
   78:     BEGIN   dup $80 u>= WHILE  defers emit  REPEAT  drop ;
   79: 
   80: \ input editor
   81: 
   82: [IFUNDEF] #esc  27 Constant #esc  [THEN]
   83: 
   84: : save-cursor ( -- )  #esc emit '7 emit ;
   85: : restore-cursor ( -- )  #esc emit '8 emit ;
   86: : .rest ( addr pos1 -- addr pos1 )
   87:     restore-cursor 2dup type ;
   88: : .all ( span addr pos1 -- span addr pos1 )
   89:     restore-cursor >r 2dup swap type r> ;
   90: 
   91: : <u8ins>  ( max span addr pos1 u8char -- max span addr pos2 )
   92:     >r  2over r@ u8len + u< IF  rdrop bell  EXIT  THEN
   93:     >string over r@ u8len + swap move 2dup chars + r@ swap u8!+ drop
   94:     r> u8len >r  rot r@ chars + -rot r> chars + ;
   95: : (u8ins)  ( max span addr pos1 u8char -- max span addr pos2 )
   96:     <u8ins> .all .rest ;
   97: : u8back  ( max span addr pos1 -- max span addr pos2 f )
   98:     dup  IF  over + u8<< over -  0 max .all .rest
   99:     ELSE  bell  THEN 0 ;
  100: : u8forw  ( max span addr pos1 -- max span addr pos2 f )
  101:     2 pick over <> IF  over + u8@+ u8emit over -  ELSE  bell  THEN 0 ;
  102: : (u8del)  ( max span addr pos1 -- max span addr pos2 )
  103:     over + dup u8<< tuck - >r over -
  104:     >string over r@ + -rot move
  105:     rot r> - -rot ;
  106: : ?u8del ( max span addr pos1 -- max span addr pos2 0 )
  107:   dup  IF  (u8del) .all 2 spaces .rest  THEN  0 ;
  108: : <u8del> ( max span addr pos1 -- max span addr pos2 0 )
  109:   2 pick over <>
  110:     IF  u8forw drop (u8del) .all 2 spaces .rest
  111:     ELSE  bell  THEN  0 ;
  112: : u8eof  2 pick over or 0=  IF  bye  ELSE  <u8del>  THEN ;
  113: 
  114: : u8first-pos  ( max span addr pos1 -- max span addr 0 0 )
  115:   drop 0 .all .rest 0 ;
  116: : u8end-pos  ( max span addr pos1 -- max span addr span 0 )
  117:   drop over .all 0 ;
  118: 
  119: 
  120: : u8clear-line ( max span addr pos1 -- max addr )
  121:     drop restore-cursor swap spaces restore-cursor ;
  122: : u8clear-tib ( max span addr pos -- max 0 addr 0 false )
  123:     u8clear-line 0 tuck dup ;
  124: 
  125: : (u8enter)  ( max span addr pos1 -- max span addr pos2 true )
  126:     >r end^ 2@ hist-setpos
  127:     2dup swap history write-line drop ( throw ) \ don't worry about errors
  128:     hist-pos 2dup backward^ 2! end^ 2!
  129:     r> .all space true ;
  130: 
  131: : u8kill-expand ( max span addr pos1 -- max span addr pos2 )
  132:     prefix-found cell+ @ ?dup IF  >r
  133: 	r@ - >string over r@ + -rot move
  134: 	rot r@ - -rot .all r> spaces .rest THEN ;
  135: 
  136: : insert   ( string length buffer size -- )
  137:     rot over min >r  r@ - ( left over )
  138:     over dup r@ +  rot move   r> move  ;
  139: 
  140: : u8tab-expand ( max span addr pos1 -- max span addr pos2 0 )
  141:     key? IF  #tab (u8ins) 0  EXIT  THEN
  142:     u8kill-expand 2dup extract-word dup 0= IF  nip EXIT  THEN
  143:     search-prefix tib-full?
  144:     IF    7 emit  2drop  prefix-off
  145:     ELSE  dup >r
  146: 	2>r >string r@ + 2r> 2swap insert
  147: 	r@ + rot r> + -rot
  148:     THEN
  149:     prefix-found @ IF  bl (u8ins)  ELSE  .all .rest  THEN  0 ;
  150: 
  151: : utf-8-io ( -- )
  152:     ['] u8forw       ctrl F bindkey
  153:     ['] u8back       ctrl B bindkey
  154:     ['] ?u8del       ctrl H bindkey
  155:     ['] u8eof        ctrl D bindkey
  156:     ['] <u8del>      ctrl X bindkey
  157:     ['] u8clear-tib  ctrl K bindkey
  158:     ['] u8first-pos  ctrl A bindkey
  159:     ['] u8end-pos    ctrl E bindkey
  160:     ['] (u8enter)    #lf    bindkey
  161:     ['] (u8enter)    #cr    bindkey
  162:     ['] u8tab-expand #tab   bindkey
  163:     ['] (u8ins)      IS insert-char
  164:     ['] kill-prefix  IS everychar
  165:     ['] save-cursor  IS everyline
  166:     ['] u8key        IS key
  167:     ['] u8emit       IS emit ;
  168: 

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>