Christian Weisgerber wrote:
> Ted Unangst:
>
> > --- ul.c 10 Oct 2015 16:15:03 -0000 1.19
> > +++ ul.c 23 Oct 2015 10:29:43 -0000
> > @@ -241,6 +241,8 @@ mfilter(FILE *f)
> > obuf[col].c_mode |= BOLD|mode;
> > else
> > obuf[col].c_mode = mode;
> > + if ((c & (0x80 | 0x40)) == 0x80 && col > 0)
> > + obuf[col].c_mode = obuf[col - 1].c_mode;
> > col++;
> > if (col > maxcol)
> > maxcol = col;
>
> That doesn't quite work. Check out this:
>
> mandoc /usr/share/man/man1/ksh.1 | sed -n 1185,1190p | ul
so that works with the diff below. i'm not sure how far down this road we need
to travel, but i figure it's worth a little exploration.
note that i don't think this handles the case of one character, backspace, a
different character correctly, though it can asymptotically approach
correct with some care.
Index: ul.c
===================================================================
RCS file: /cvs/src/usr.bin/ul/ul.c,v
retrieving revision 1.19
diff -u -p -r1.19 ul.c
--- ul.c 10 Oct 2015 16:15:03 -0000 1.19
+++ ul.c 23 Oct 2015 13:31:45 -0000
@@ -151,6 +151,12 @@ main(int argc, char *argv[])
exit(0);
}
+int
+isu8cont(unsigned char c)
+{
+ return (c & (0x80 | 0x40)) == 0x80;
+}
+
void
mfilter(FILE *f)
{
@@ -158,8 +164,11 @@ mfilter(FILE *f)
while ((c = getc(f)) != EOF && col < MAXBUF) switch(c) {
case '\b':
- if (col > 0)
+ while (col > 0) {
col--;
+ if (!isu8cont(obuf[col].c_char))
+ break;
+ }
continue;
case '\t':
col = (col+8) & ~07;
@@ -241,6 +250,8 @@ mfilter(FILE *f)
obuf[col].c_mode |= BOLD|mode;
else
obuf[col].c_mode = mode;
+ if ((c & (0x80 | 0x40)) == 0x80 && col > 0)
+ obuf[col].c_mode = obuf[col - 1].c_mode;
col++;
if (col > maxcol)
maxcol = col;
