Return to utf-8.fs CVS log

Up to [gforth] / gforth

minor changes

    1: \ UTF-8 handling                                       12dec04py
    2: 
    3: \ Copyright (C) 2004,2005 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: $80 Value max-single-byte
   26: 
   27: : u8len ( u8 -- n )
   28:     dup      max-single-byte u< IF  drop 1  EXIT  THEN \ special case ASCII
   29:     $800  2 >r
   30:     BEGIN  2dup u>=  WHILE  5 lshift r> 1+ >r  dup 0= UNTIL  THEN
   31:     2drop r> ;
   32: 
   33: : u8@+ ( u8addr -- u8addr' u )
   34:     count  dup max-single-byte u< ?EXIT  \ special case ASCII
   35:     dup $C2 u< IF  UTF-8-err throw  THEN  \ malformed character
   36:     $7F and  $40 >r
   37:     BEGIN  dup r@ and  WHILE  r@ xor
   38: 	    6 lshift r> 5 lshift >r >r count
   39: 	    dup $C0 and $80 <> IF   UTF-8-err throw  THEN
   40: 	    $3F and r> or
   41:     REPEAT  rdrop ;
   42: 
   43: : u8!+ ( u u8addr -- u8addr' )
   44:     over max-single-byte u< IF  tuck c! 1+  EXIT  THEN \ special case ASCII
   45:     >r 0 swap  $3F
   46:     BEGIN  2dup u>  WHILE
   47: 	    2/ >r  dup $3F and $80 or swap 6 rshift r>
   48:     REPEAT  $7F xor 2* or  r>
   49:     BEGIN   over $80 u>= WHILE  tuck c! 1+  REPEAT  nip ;
   50: 
   51: \ plug-in so that char and '<char> work for UTF-8
   52: 
   53: [ifundef] char@ \ !! bootstrapping help
   54:     Defer char@ ( addr u -- char addr' u' )
   55:     :noname  over c@ -rot 1 /string ; IS char@
   56: [then]
   57: 
   58: :noname  ( addr u -- char addr' u' )
   59:     \ !! the if here seems to work around some breakage, but not
   60:     \ entirely; e.g., try 'ç' with LANG=C.
   61:     dup 1 u<= IF defers char@ EXIT THEN
   62:     over + >r u8@+ swap r> over - ; IS char@
   63: 
   64: \ scan to next/previous character
   65: 
   66: \ alternative names: u8char+ u8char-
   67: 
   68: : u8>> ( u8addr -- u8addr' )  u8@+ drop ;
   69: : u8<< ( u8addr -- u8addr' )
   70:     BEGIN  1- dup c@ $C0 and max-single-byte <>  UNTIL ;
   71: 
   72: \ utf key and emit
   73: 
   74: : u8key ( -- u )
   75:     defers key dup max-single-byte u< ?EXIT  \ special case ASCII
   76:     dup $C2 u< IF  UTF-8-err throw  THEN  \ malformed character
   77:     $7F and  $40 >r
   78:     BEGIN  dup r@ and  WHILE  r@ xor
   79: 	    6 lshift r> 5 lshift >r >r defers key
   80: 	    dup $C0 and $80 <> IF  UTF-8-err throw  THEN
   81: 	    $3F and r> or
   82:     REPEAT  rdrop ;
   83: 
   84: : u8emit ( u -- )
   85:     dup max-single-byte u< IF  defers emit  EXIT  THEN \ special case ASCII
   86:     0 swap  $3F
   87:     BEGIN  2dup u>  WHILE
   88: 	    2/ >r  dup $3F and $80 or swap 6 rshift r>
   89:     REPEAT  $7F xor 2* or
   90:     BEGIN   dup $80 u>= WHILE  defers emit  REPEAT  drop ;
   91: 
   92: \ utf-8 stuff for xchars
   93: 
   94: : +u8/string ( c-addr1 u1 -- c-addr2 u2 )
   95:     over dup u8>> swap - /string ;
   96: 
   97: : -u8/string ( c-addr1 u1 -- c-addr2 u2 )
   98:     over dup u8<< swap - /string ;
   99: 
  100: : u8@ ( c-addr -- u )
  101:     u8@+ nip ;
  102: 
  103: : u8!+? ( xc xc-addr1 u1 -- xc-addr2 u2 f )
  104:     >r over u8len r@ over u< if ( xc xc-addr1 len r: u1 )
  105: 	\ not enough space
  106: 	drop nip r> false
  107:     else
  108: 	>r u8!+ r> r> swap - true
  109:     then ;
  110: 
  111: : u8addrlen ( u8-addr -- u )
  112:     \ length of UTF-8 char starting at u8-addr (accesses only u8-addr)
  113:     c@
  114:     dup $80 u< if drop 1 exit endif
  115:     dup $c0 u< if UTF-8-err throw endif
  116:     dup $e0 u< if drop 2 exit endif
  117:     dup $f0 u< if drop 3 exit endif
  118:     dup $f8 u< if drop 4 exit endif
  119:     dup $fc u< if drop 5 exit endif
  120:     dup $fe u< if drop 6 exit endif
  121:     UTF-8-err throw ;
  122: 
  123: : -u8trailing-garbage ( addr u1 -- addr u2 )
  124:     2dup + dup u8<< ( addr u1 end1 end2 )
  125:     2dup dup u8addrlen + = if \ last character ok
  126: 	2drop
  127:     else
  128: 	nip nip over -
  129:     then ;
  130: 
  131: [IFUNDEF] wcwidth
  132:     : wcwidth abort ;
  133: [THEN]
  134:     
  135: : u8width ( xcaddr u -- n )
  136:     0 rot rot over + swap ?DO
  137:         I xc@+ swap >r wcwidth +
  138:     r> I - +LOOP ;
  139: 
  140: : set-encoding-utf-8 ( -- )
  141:     ['] u8emit is xemit
  142:     ['] u8key is xkey
  143:     ['] u8>> is xchar+
  144:     ['] u8<< is xchar-
  145:     ['] +u8/string is +x/string
  146:     ['] -u8/string is -x/string
  147:     ['] u8@ is xc@
  148:     ['] u8!+? is xc!+?
  149:     ['] u8@+ is xc@+
  150:     ['] u8len is xc-size
  151: [ [IFDEF] x-width ]
  152:     ['] u8width is x-width
  153: [ [THEN] ]
  154:     ['] -u8trailing-garbage is -trailing-garbage
  155: ;
  156: 
  157: : utf-8-cold ( -- )
  158:     s" LC_ALL" getenv 2dup d0= IF  2drop
  159: 	s" LC_CTYPE" getenv 2dup d0= IF  2drop
  160: 	    s" LANG" getenv 2dup d0= IF  2drop
  161: 		s" C"  THEN THEN THEN
  162:     s" UTF-8" search nip nip
  163:     IF  set-encoding-utf-8  ELSE  set-encoding-fixed-width  THEN ;
  164: 
  165: ' utf-8-cold INIT8 chained
  166: 
  167: utf-8-cold