performance tuning of rtl_ustr_indexOfAscii_WithLength()

lcov over make check showed

98      4699997 : sal_Int32 rtl_ustr_indexOfAscii_WithLength(
99              :     sal_Unicode const * str, sal_Int32 len,
100             :     char const * subStr, sal_Int32 subLen) SAL_THROW_EXTERN_C()
101             : {
102     4699997 :     assert(len >= 0);
103     4699997 :     assert(subLen >= 0);
104     4699997 :     if (subLen > 0 && subLen <= len) {
105             :         sal_Int32 i;
106    54014537 :         for (i = 0; i <= len - subLen; ++i) {
107    51036513 :             if (rtl_ustr_asciil_reverseEquals_WithLength(
108    51036523 :                     str + i, subStr, subLen))
109             :             {
110      205482 :                 return i;
111             :             }
112             :         }
113             :     }
114     4494505 :     return -1;
115             : }

so
1/ in 95% of the cases the result is not-found.. _that_ is the hot path
2/ we are calling rtl_ustr_asciil_reverseEquals_WithLength close to 11 times
per call.. (average ~ len - subLen, due to the high miss ratio)

so let's first search for the first byte of the substring
to optimize the 'miss' case, which is the most common one.

Change-Id: I20ef0821db2ff0db5935dd562844a947a14aff64
Reviewed-on: https://gerrit.libreoffice.org/16763
Tested-by: Jenkins <ci@libreoffice.org>
Reviewed-by: Stephan Bergmann <sbergman@redhat.com>

1 files changed, 18 insertions, 6 deletions

diff --git a/sal/rtl/ustring.cxx b/sal/rtl/ustring.cxx
index b31bc2fcddeb..9648fc63bfa7 100644
--- a/sal/rtl/ustring.cxx
+++ b/sal/rtl/ustring.cxx
@@ -27,6 +27,7 @@
 #include <cstdlib>
 #include <limits>
 #include <stdexcept>
+#include <string>
 
 #include <osl/diagnose.h>
 #include <osl/interlck.h>
@@ -101,14 +102,25 @@ sal_Int32 rtl_ustr_indexOfAscii_WithLength(
 {
     assert(len >= 0);
     assert(subLen >= 0);
-    if (subLen > 0 && subLen <= len) {
-        sal_Int32 i;
-        for (i = 0; i <= len - subLen; ++i) {
-            if (rtl_ustr_asciil_reverseEquals_WithLength(
-                    str + i, subStr, subLen))
+    if (subLen > 0 && subLen <= len)
+    {
+        sal_Unicode const* end = str + len;
+        sal_Unicode const* cursor = str;
+
+        while(cursor < end)
+        {
+            cursor = std::char_traits<sal_Unicode>::find(cursor, end - cursor, *subStr);
+            if(!cursor || (end - cursor < subLen))
             {
-                return i;
+                /* no enough left to actually have a match */
+                break;
+            }
+            /* now it is worth trying a full match */
+            if (rtl_ustr_asciil_reverseEquals_WithLength(cursor, subStr, subLen))
+            {
+                return cursor - str;
             }
+            cursor += 1;
         }
     }
     return -1;