Completely clean up UTF-8 handling in the file filename.c:

Employ the usual form of an mbtowc(3) loop, eliminating two calls
to the bad function step_char() and reducing the number of nested
loops by one.  This also removes the last caller of the bad function
binary_char(), which is consequently deleted.
While here, count ASCII C0 non-whitespace control characters as
binary (except backspace and, with -R only, escape).
OK millert@

3 files changed, 12 insertions, 25 deletions

diff --git a/usr.bin/less/charset.c b/usr.bin/less/charset.c
index 4c8db50d553..363d1a80cba 100644
--- a/usr.bin/less/charset.c
+++ b/usr.bin/less/charset.c
@@ -146,18 +146,6 @@ init_charset(void)
 }
 
 /*
- * Is a given character a "binary" character?
- */
-int
-binary_char(LWCHAR c)
-{
-	if (utf_mode)
-		return (is_ubin_char(c));
-	c &= 0377;
-	return (!isprint((unsigned char)c) && !iscntrl((unsigned char)c));
-}
-
-/*
  * Is a given character a "control" character?
  */
 int
diff --git a/usr.bin/less/filename.c b/usr.bin/less/filename.c
index 2e480e6445d..68c37906498 100644
--- a/usr.bin/less/filename.c
+++ b/usr.bin/less/filename.c
@@ -334,25 +334,25 @@ fcomplete(char *s)
 int
 bin_file(int f)
 {
-	int n;
-	int bin_count = 0;
 	char data[256];
-	char *p;
-	char *pend;
+	ssize_t i, n;
+	wchar_t ch;
+	int bin_count, len;
 
 	if (!seekable(f))
 		return (0);
 	if (lseek(f, (off_t)0, SEEK_SET) == (off_t)-1)
 		return (0);
 	n = read(f, data, sizeof (data));
-	pend = &data[n];
-	for (p = data; p < pend; ) {
-		LWCHAR c = step_char(&p, +1, pend);
-		if (ctldisp == OPT_ONPLUS && c == ESC) {
-			do {
-				c = step_char(&p, +1, pend);
-			} while (p < pend && is_ansi_middle(c));
-		} else if (binary_char(c))
+	bin_count = 0;
+	for (i = 0; i < n; i += len) {
+		len = mbtowc(&ch, data + i, n - i);
+		if (len <= 0) {
+			bin_count++;
+			len = 1;
+		} else if (iswprint(ch) == 0 && iswspace(ch) == 0 &&
+		    data[i] != '\b' &&
+		    (ctldisp != OPT_ONPLUS || data[i] != ESC))
 			bin_count++;
 	}
 	/*
diff --git a/usr.bin/less/funcs.h b/usr.bin/less/funcs.h
index abf596f2a45..5c24ba89e96 100644
--- a/usr.bin/less/funcs.h
+++ b/usr.bin/less/funcs.h
@@ -56,7 +56,6 @@ void ch_init(int, int);
 void ch_close(void);
 int ch_getflags(void);
 void init_charset(void);
-int binary_char(LWCHAR);
 int control_char(LWCHAR);
 char *prchar(LWCHAR);
 char *prutfchar(LWCHAR);