15 * Mac Unicode-handling routines.
18 * What we _should_ do is to use the Text Encoding Conversion Manager
19 * when it's available, and have our own routines for converting to
20 * standard Mac OS scripts when it's not. Support for ATSUI might be
23 * I (OSD) am unsure any of the above is necessary if we just use
27 * Determine whether a byte is the first byte of a double-byte
28 * character in a system character set. Only MI use is by clipme()
29 * when copying direct-to-font text to the clipboard.
31 int is_dbcs_leadbyte(int codepage
, char byte
)
33 return 0; /* we don't do DBCS */
37 * Convert from Unicode to a system character set. MI uses are:
38 * (1) by lpage_send(), whose only MI use is to convert the answerback
39 * string to Unicode, and
40 * (2) by clipme() when copying direct-to-font text to the clipboard.
42 int mb_to_wc(int codepage
, int flags
, char *mbstr
, int mblen
,
43 wchar_t *wcstr
, int wclen
)
46 while (mblen
> 0 && wclen
> 0) {
47 *wcstr
++ = (unsigned char) *mbstr
++;
48 mblen
--, wclen
--, ret
++;
50 return ret
; /* FIXME: check error codes! */
54 * Convert from a system character set to Unicode. Used by luni_send
55 * to convert Unicode into the line character set.
57 int wc_to_mb(int codepage
, int flags
, wchar_t *wcstr
, int wclen
,
58 char *mbstr
, int mblen
, char *defchr
, int *defused
,
59 struct unicode_data
*ucsdata
)
64 while (mblen
> 0 && wclen
> 0) {
65 if (*wcstr
>= 0x100) {
73 *mbstr
++ = (unsigned char) *wcstr
;
75 mblen
--, wclen
--, ret
++;
77 return ret
; /* FIXME: check error codes! */
80 /* Character conversion array,
81 * the xterm one has the four scanlines that have no unicode 2.0
82 * equivalents mapped to their unicode 3.0 locations.
84 static const wchar_t unitab_xterm_std
[32] = {
85 0x2666, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
86 0x2424, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba,
87 0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c,
88 0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x0020
91 void init_ucs(Session
*s
)
95 s
->ucsdata
.line_codepage
= decode_codepage(s
->cfg
.line_codepage
);
97 /* Find the line control characters. FIXME: this is not right. */
98 for (i
= 0; i
< 256; i
++)
99 if (i
< ' ' || (i
>= 0x7F && i
< 0xA0))
100 s
->ucsdata
.unitab_ctrl
[i
] = i
;
102 s
->ucsdata
.unitab_ctrl
[i
] = 0xFF;
104 for (i
= 0; i
< 256; i
++)
105 s
->ucsdata
.unitab_line
[i
] = s
->ucsdata
.unitab_scoacs
[i
] = i
;
107 /* VT100 graphics - NB: Broken for non-ascii CP's */
108 memcpy(s
->ucsdata
.unitab_xterm
, s
->ucsdata
.unitab_line
,
109 sizeof(s
->ucsdata
.unitab_xterm
));
110 memcpy(s
->ucsdata
.unitab_xterm
+ '`', unitab_xterm_std
,
111 sizeof(unitab_xterm_std
));
112 s
->ucsdata
.unitab_xterm
['_'] = ' ';
116 int decode_codepage(char *cp_name
)
119 return CS_NONE
; /* use font encoding */
120 return charset_from_localenc(cp_name
);
123 char const *cp_enumerate (int index
)
127 return "Use font encoding";
128 charset
= charset_localenc_nth(index
-1);
129 if (charset
== CS_NONE
)
131 return charset_to_localenc(charset
);
134 char const *cp_name(int codepage
)
136 if (codepage
== CS_NONE
)
137 return "Use font encoding";
138 return charset_to_localenc(codepage
);