gh-148729: use memchr in SRE prefix scan

For single byte characters use `memchr` instead of the equivalent
hand-written while loop.

This ensures that `re.search` is typically vectorized through libc for
regexes starting with a `LITERAL`. In the no-match case this means 16 or
32 bytes per iterations instead of a single byte (ok, it was unrolled,
but not auto-vectorized).

Signed-off-by: Harmen Stoppels <harmenstoppels@gmail.com>

Author: haampie

Modules/_sre/sre_lib.h

@@ -1753,10 +1753,19 @@ SRE(search)(SRE_STATE* state, SRE_CODE* pattern)
         end = (SRE_CHAR *)state->end;
         state->must_advance = 0;
         while (ptr < end) {
+#if SIZEOF_SRE_CHAR == 1
+            {
+                SRE_CHAR *found = memchr(ptr, c, end - ptr);
+                if (!found)
+                    return 0;
+                ptr = found;
+            }
+#else
             while (*ptr != c) {
                 if (++ptr >= end)
                     return 0;
             }
+#endif
             TRACE(("|%p|%p|SEARCH LITERAL\n", pattern, ptr));
             state->start = ptr;
             state->ptr = ptr + prefix_skip;
@@ -1786,10 +1795,19 @@ SRE(search)(SRE_STATE* state, SRE_CODE* pattern)
 #endif
         while (ptr < end) {
             SRE_CHAR c = (SRE_CHAR) prefix[0];
+#if SIZEOF_SRE_CHAR == 1
+            {
+                SRE_CHAR *found = memchr(ptr, c, end - ptr);
+                if (!found)
+                    return 0;
+                ptr = found + 1;
+            }
+#else
             while (*ptr++ != c) {
                 if (ptr >= end)
                     return 0;
             }
+#endif
             if (ptr >= end)
                 return 0;