aboutsummaryrefslogtreecommitdiffstats
path: root/src/utf8.c
blob: 09066db0a282bac7bb71b6d2490b91bff2d357fe (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
/*
 * utf8.c:
 *
 * Copyright (c) 2008 James McKenzie <james@fishsoup.dhs.org>,
 * All rights reserved.
 *
 */

static char rcsid[] = "$Id$";

/*
 * $Log$
 * Revision 1.2  2008/02/22 23:39:27  james
 * *** empty log message ***
 *
 * Revision 1.1  2008/02/22 19:12:05  james
 * *** empty log message ***
 *
 */

#include "project.h"


void utf8_flush(Context *c)
{
UTF8 *u=c->u;
int i;

for (i=0;i<u->utf_ptr;++i) 
	vt102_parse(c,u->utf_buf[i]);

u->utf_ptr=0;
u->in_utf8=0;
}

int utf8_parse(Context *c,int ch)
{
UTF8 *u=&c->u;
  
  if (!u->in_utf8) {
	  /*FIXME: for the moment we bodge utf8 support*/
	  if (ch==0xb9) { /*CSI, not a valid utf8 start char*/
		vt102_parse(c,ch);
	  } else if ((ch & 0xe0) == 0xc0) { /*Start of two byte unicode sequence*/
		u->in_utf8=2;
		u->utf_ptr=0;
		u->utf_buf[u->utf_ptr++]=ch;
	  } else if ((ch & 0xf0) ==0xe0) { /*Start of three byte unicode sequence*/
		u->in_utf8=3;
		u->utf_ptr=0;
		u->utf_buf[u->utf_ptr++]=ch;
	  } else if ((ch & 0xf8) ==0xf0) {
		u->in_utf8=4;
		u->utf_ptr=0;
		u->utf_buf[u->utf_ptr++]=ch;
	  } else {
		vt102_parse(c,ch);
	  } 
  } else {
	if ((ch & 0xc0) != 0x80) {
		utf8_flush(c);
		vt102_parse(c,ch);
	} else {
		u->utf_buf[u->utf_ptr++]=ch;
		u->in_utf8--;
	}
  }
}



UTF8 *utf8_new(void)
{
UTF8 *ret;

ret=(UTF8 *) malloc(sizeof(UTF8));

ret->in_utf8=0;

}