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>

René Scharfe committed Feb 19, 2010 at 23:20 UTC 462749b728f72079a67202d4d0d1ef19ef993f61

1 file changed +17 -6

utf8.c

+17 -6

@@ -324,16 +324,21 @@ static size_t display_mode_esc_sequence_len(const char *s)

324 * consumed (and no extra indent is necessary for the first line).

325 */

326 int strbuf_add_wrapped_text(struct strbuf *buf,

327 - const char *text, int indent, int indent2, int width)

327 + const char *text, int indent1, int indent2, int width)

328 {

329 - int w = indent, assume_utf8 = is_utf8(text);

330 - const char *bol = text, *space = NULL;

329 + int indent, w, assume_utf8 = 1;

330 + const char *bol, *space, *start = text;

331 + size_t orig_len = buf->len;

332

333 if (width <= 0) {

333 - strbuf_add_indented_text(buf, text, indent, indent2);

334 + strbuf_add_indented_text(buf, text, indent1, indent2);

335 return 1;

336 }

337

338 +retry:

339 + bol = text;

340 + w = indent = indent1;

341 + space = NULL;

342 if (indent < 0) {

343 w = -indent;

344 space = text;

@@ -385,9 +390,15 @@ new_line:

390 }

391 continue;

392 }

388 - if (assume_utf8)

393 + if (assume_utf8) {

394 w += utf8_width(&text, NULL);

390 - else {

395 + if (!text) {

396 + assume_utf8 = 0;

397 + text = start;

398 + strbuf_setlen(buf, orig_len);

399 + goto retry;

400 + }

401 + } else {

402 w++;

403 text++;

404 }