Subject: [PATCH] unistr/u8-strchr: speed up searching for ASCII characters
* lib/unistr/u8-strchr.c (u8_strchr): Use strchr() for
the single byte case as it was measured to be 50% faster
than the existing code on x86 linux. Also add a comment
on why not to use memmem() for the moment for the multibyte case.
---
ChangeLog | 4 ++++
lib/unistr/u8-strchr.c | 19 +++++++------------
2 files changed, 11 insertions(+), 12 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index afcae28..8ca0bd7 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,7 @@
+2010-07-07 Pádraig Brady <p...@draigbrady.com>
+
+ * lib/unistr/u8-strchr.c (u8_strchr): Use strchr() as it's faster
+
2010-07-04 Bruno Haible <br...@clisp.org>
fsusage: Clarify which code applies to which platforms.
diff --git a/lib/unistr/u8-strchr.c b/lib/unistr/u8-strchr.c
index 3be14c7..3dbd3ca 100644
--- a/lib/unistr/u8-strchr.c
+++ b/lib/unistr/u8-strchr.c
@@ -21,25 +21,20 @@
/* Specification. */
#include "unistr.h"
+#include <string.h>
+
uint8_t *
u8_strchr (const uint8_t *s, ucs4_t uc)
{
uint8_t c[6];
if (uc < 0x80)
- {
- uint8_t c0 = uc;
-
- for (;; s++)
- {
- if (*s == c0)
- break;
- if (*s == 0)
- goto notfound;
- }
- return (uint8_t *) s;
- }
+ return strchr (s, uc);
else
+ /* The following is equivalent to:
+ return memmem (s, strlen(s), c, csize);
+ but faster for long S with matching UC near the start,
+ and also memmem is sometimes buggy and inefficient. */
switch (u8_uctomb_aux (c, uc, 6))
{
case 2:
--
1.6.2.5
