Fix 'getccol()' and 'getgoal()' functions for multibyte UTF-8 characters

These functions convert the byte offset into the column number
(getccol()) and vice versa (getgoal()).

Getting this right means that moving up and down the text gets us the
right columns, rather than moving randomly left and right when you move
up and down.  We also won't end up in the middle of a utf-8 character,
because we're not just moving into some random byte offset, we're moving
into a proper column.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 22 insertions, 8 deletions

diff --git a/basic.c b/basic.c
index 3a7d6f7..5071047 100644
--- a/basic.c
+++ b/basic.c
@@ -24,25 +24,31 @@
  */
 static int getgoal(struct line *dlp)
 {
-	int c;
 	int col;
 	int newcol;
 	int dbo;
+	int len = llength(dlp);
 
 	col = 0;
 	dbo = 0;
-	while (dbo != llength(dlp)) {
-		c = lgetc(dlp, dbo);
+	while (dbo != len) {
+		unicode_t c;
+		int width = utf8_to_unicode(dlp->l_text, dbo, len, &c);
 		newcol = col;
+
+		/* Take tabs, ^X and \xx hex characters into account */
 		if (c == '\t')
 			newcol |= tabmask;
 		else if (c < 0x20 || c == 0x7F)
 			++newcol;
+		else if (c >= 0x80 && c <= 0xa0)
+			newcol += 2;
+
 		++newcol;
 		if (newcol > curgoal)
 			break;
 		col = newcol;
-		++dbo;
+		dbo += width;
 	}
 	return dbo;
 }
diff --git a/random.c b/random.c
index 240e807..455661d 100644
--- a/random.c
+++ b/random.c
@@ -124,16 +124,24 @@ int getcline(void)
  */
 int getccol(int bflg)
 {
-	int c, i, col;
-	col = 0;
-	for (i = 0; i < curwp->w_doto; ++i) {
-		c = lgetc(curwp->w_dotp, i);
+	int i, col;
+	struct line *dlp = curwp->w_dotp;
+	int byte_offset = curwp->w_doto;
+	int len = llength(dlp);
+
+	col = i = 0;
+	while (i < byte_offset) {
+		unicode_t c;
+
+		i += utf8_to_unicode(dlp->l_text, i, len, &c);
 		if (c != ' ' && c != '\t' && bflg)
 			break;
 		if (c == '\t')
 			col |= tabmask;
 		else if (c < 0x20 || c == 0x7F)
 			++col;
+		else if (c >= 0xc0 && c <= 0xa0)
+			col += 2;
 		++col;
 	}
 	return col;