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: $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 REPEAT
31: 2drop r> ;
32:
33: : u8@+ ( u8addr -- u8addr' u )
34: count dup max-single-byte u< ?EXIT \ special case ASCII
35: $7F and $40 >r
36: BEGIN dup r@ and WHILE r@ xor
37: 6 lshift r> 5 lshift >r >r count
38: dup $C0 and $80 <> IF UTF-8-err throw THEN
39: $3F and r> or
40: REPEAT rdrop ;
41:
42: : u8!+ ( u u8addr -- u8addr' )
43: over max-single-byte u< IF tuck c! 1+ EXIT THEN \ special case ASCII
44: >r 0 swap $3F
45: BEGIN 2dup u> WHILE
46: 2/ >r dup $3F and $80 or swap 6 rshift r>
47: REPEAT $7F xor 2* or r>
48: BEGIN over $80 u>= WHILE tuck c! 1+ REPEAT nip ;
49:
50: \ plug-in so that char and '<char> work for UTF-8
51:
52: [ifundef] char@ \ !! bootstrapping help
53: Defer char@ ( addr u -- char addr' u' )
54: :noname over c@ -rot 1 /string ; IS char@
55: [then]
56:
57: :noname ( addr u -- char addr' u' )
58: \ !! the if here seems to work around some breakage, but not
59: \ entirely; e.g., try 'ç' with LANG=C.
60: dup 1 u<= IF defers char@ EXIT THEN
61: over + >r u8@+ swap r> over - ; IS char@
62:
63: \ scan to next/previous character
64:
65: \ alternative names: u8char+ u8char-
66:
67: : u8>> ( u8addr -- u8addr' ) u8@+ drop ;
68: : u8<< ( u8addr -- u8addr' )
69: BEGIN 1- dup c@ $C0 and max-single-byte <> UNTIL ;
70:
71: \ utf key and emit
72:
73: : u8key ( -- u )
74: defers key dup max-single-byte u< ?EXIT \ special case ASCII
75: $7F and $40 >r
76: BEGIN dup r@ and WHILE r@ xor
77: 6 lshift r> 5 lshift >r >r defers key
78: dup $C0 and $80 <> IF UTF-8-err throw THEN
79: $3F and r> or
80: REPEAT rdrop ;
81:
82: : u8emit ( u -- )
83: dup max-single-byte u< IF defers emit EXIT THEN \ special case ASCII
84: 0 swap $3F
85: BEGIN 2dup u> WHILE
86: 2/ >r dup $3F and $80 or swap 6 rshift r>
87: REPEAT $7F xor 2* or
88: BEGIN dup $80 u>= WHILE defers emit REPEAT drop ;
89:
90: \ utf-8 stuff for xchars
91:
92: : +u8/string ( c-addr1 u1 -- c-addr2 u2 )
93: over dup u8>> swap - /string ;
94:
95: : -u8/string ( c-addr1 u1 -- c-addr2 u2 )
96: over dup u8<< swap - /string ;
97:
98: : u8@ ( c-addr -- u )
99: u8@+ nip ;
100:
101: : u8!+? ( xc xc-addr1 u1 -- xc-addr2 u2 f )
102: >r over u8len r@ over u< if ( xc xc-addr1 len r: u1 )
103: \ not enough space
104: drop nip r> false
105: else
106: >r u8!+ r> r> swap - true
107: then ;
108:
109: : u8addrlen ( u8-addr -- u )
110: \ length of UTF-8 char starting at u8-addr (accesses only u8-addr)
111: c@
112: dup $80 u< if drop 1 exit endif
113: dup $c0 u< if UTF-8-err throw endif
114: dup $e0 u< if drop 2 exit endif
115: dup $f0 u< if drop 3 exit endif
116: dup $f8 u< if drop 4 exit endif
117: dup $fc u< if drop 5 exit endif
118: dup $fe u< if drop 6 exit endif
119: UTF-8-err throw ;
120:
121: : -u8trailing-garbage ( addr u1 -- addr u2 )
122: 2dup + dup u8<< ( addr u1 end1 end2 )
123: 2dup dup u8addrlen + = if \ last character ok
124: 2drop
125: else
126: nip nip over -
127: then ;
128:
129: : set-encoding-utf-8 ( -- )
130: ['] u8emit is xemit
131: ['] u8key is xkey
132: ['] u8>> is xchar+
133: ['] u8<< is xchar-
134: ['] +u8/string is +x/string
135: ['] -u8/string is -x/string
136: ['] u8@ is xc@
137: ['] u8!+? is xc!+?
138: ['] u8@+ is xc@+
139: ['] u8len is xc-size
140: ['] -u8trailing-garbage is -trailing-garbage
141: ;
142:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>