*** empty log message ***

1 files changed, 58 insertions, 15 deletions

diff --git a/src/utf8.c b/src/utf8.c
index 18ca3eb..09066db 100644
--- a/src/utf8.c
+++ b/src/utf8.c
@@ -10,6 +10,9 @@ 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 ***
  *
@@ -18,21 +21,61 @@ static char rcsid[] = "$Id$";
 #include "project.h"
 
 
-  /*FIXME: for the moment we bodge utf8 support*/
-  if ((ch>=0xc0) && (ch<0xe0)) /*Start of two byte unicode sequence*/
-  {
-	p->in_utf8=2;
-  } else if ((ch>=0xe0) && (ch<0xf0)) /*Start of three byte unicode sequence*/
-  {
-	p->in_utf8=3;
-  } else if ((ch>=0xf0) && (ch<0xf7)) /*Start of four byte unicode sequence*/
-	p->in_utf8=4;
+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;
 
-  if (p->utf_8) {
-	p->in_utf8--;
-	ch='?';
-  }  
+}
 
-  if (!p->utf_8)  {
-	/*Not first or last byte in sequence*/