gh-120397: improve the speed of str.count, bytes.count et al. for single characters by about 2x.

Misc/NEWS.d/next/Core and Builtins/2024-06-12-13-47-25.gh-issue-120397.n-I_cc.rst

@@ -0,0 +1,2 @@
+Improve the througput by up to two times for the :meth:`str.count`, :meth:`bytes.count` and :meth:`bytearray.count`
+methods for counting single characters.

Objects/stringlib/fastsearch.h

@@ -753,6 +753,22 @@ STRINGLIB(count_char)(const STRINGLIB_CHAR *s, Py_ssize_t n,
 }
 
 
+static inline Py_ssize_t
+STRINGLIB(count_char_no_maxcount)(const STRINGLIB_CHAR *s, Py_ssize_t n,
+                                  const STRINGLIB_CHAR p0)
+/* A specialized function of count_char that does not cut off at a maximum.
+   As a result, the compiler is able to vectorize the loop. */
+{
+    Py_ssize_t count = 0;
+    for (Py_ssize_t i = 0; i < n; i++) {
+        if (s[i] == p0) {
+            count++;
+        }
+    }
+    return count;
+}
+
+
 Py_LOCAL_INLINE(Py_ssize_t)
 FASTSEARCH(const STRINGLIB_CHAR* s, Py_ssize_t n,
            const STRINGLIB_CHAR* p, Py_ssize_t m,
@@ -773,6 +789,9 @@ FASTSEARCH(const STRINGLIB_CHAR* s, Py_ssize_t n,
         else if (mode == FAST_RSEARCH)
             return STRINGLIB(rfind_char)(s, n, p[0]);
         else {
+            if (maxcount == PY_SSIZE_T_MAX) {
+                return STRINGLIB(count_char_no_maxcount)(s, n, p[0]);
+            }
             return STRINGLIB(count_char)(s, n, p[0], maxcount);
         }
     }