nano

commit 09cabcad5dda8bc74b527de2b70adadc42f107df
parent f162a6a2ab7c14eef2ad4636a8033e90422c4b3a
Author: Benno Schulenberg <bensberg@justemail.net>
Date:   Tue,  2 May 2017 13:05:58 +0200

chars: probe for a valid UTF-8 starter byte, instead of overstepping

Instead of always stepping back four bytes and then tentatively
moving forward again (which is wasteful when most codes are just
one or two bytes long), inspect the preceding bytes one by one
and begin the move forward at the first valid starter byte.

This reduces the backwards searching time by close to 40 percent.

Diffstat:
M
src/chars.c
 | 
16
++++++++++++++--

1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/src/chars.c b/src/chars.c
@@ -383,8 +383,20 @@ size_t move_mbleft(const char *buf, size_t pos)
      * possible point. */
     if (pos < 4)
 	before = 0;
-    else
-	before = pos - 4;
+    else {
+	const char *ptr = buf + pos;
+
+       if ((signed char)*(--ptr) > -65)
+	    before = pos - 1;
+       else if ((signed char)*(--ptr) > -65)
+	    before = pos - 2;
+       else if ((signed char)*(--ptr) > -65)
+	    before = pos - 3;
+       else if ((signed char)*(--ptr) > -65)
+	    before = pos - 4;
+	else
+	    before = pos - 1;
+    }
 
     while (before < pos) {
 	char_len = parse_mbchar(buf + before, NULL, NULL);