utf8.c: speculatively assume utf-8 in strbuf_add_wrapped_text()

is_utf8() works by calling utf8_width() for each character at the
supplied location.  In strbuf_add_wrapped_text(), we do that anyway
while wrapping the lines.  So instead of checking the encoding
beforehand, optimistically assume that it's utf-8 and wrap along
until an invalid character is hit, and when that happens start over.

This pays off if the text consists only of valid utf-8 characters.
The following command was run against the Linux kernel repo with
git 1.7.0:

	$ time git log --format='%b' v2.6.32 >/dev/null

	real	0m2.679s
	user	0m2.580s
	sys	0m0.100s

	$ time git log --format='%w(60,4,8)%b' >/dev/null

	real	0m4.342s
	user	0m4.230s
	sys	0m0.110s

And with this patch series:

	$ time git log --format='%w(60,4,8)%b' >/dev/null

	real	0m3.741s
	user	0m3.630s
	sys	0m0.110s

So the cost of wrapping is reduced to 70% in this case.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/utf8.c b/utf8.c
index 9f64f59d664c81c9cce41bc51ef26aa913d96fb6..6db9cd9a078266538d8289a98b49d4ec82d39ae7 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -324,16 +324,21 @@ static size_t display_mode_esc_sequence_len(const char *s)
  * consumed (and no extra indent is necessary for the first line).
  */
 int strbuf_add_wrapped_text(struct strbuf *buf,
-               const char *text, int indent, int indent2, int width)
+               const char *text, int indent1, int indent2, int width)
 {
-       int w = indent, assume_utf8 = is_utf8(text);
-       const char *bol = text, *space = NULL;
+       int indent, w, assume_utf8 = 1;
+       const char *bol, *space, *start = text;
+       size_t orig_len = buf->len;
 
        if (width <= 0) {
-               strbuf_add_indented_text(buf, text, indent, indent2);
+               strbuf_add_indented_text(buf, text, indent1, indent2);
                return 1;
        }
 
+retry:
+       bol = text;
+       w = indent = indent1;
+       space = NULL;
        if (indent < 0) {
                w = -indent;
                space = text;
@@ -385,9 +390,15 @@ new_line:
                        }
                        continue;
                }
-               if (assume_utf8)
+               if (assume_utf8) {
                        w += utf8_width(&text, NULL);
-               else {
+                       if (!text) {
+                               assume_utf8 = 0;
+                               text = start;
+                               strbuf_setlen(buf, orig_len);
+                               goto retry;
+                       }
+               } else {
                        w++;
                        text++;
                }