* Beef-up testing of str.__contains__() and str.find().

* Speed-up "x in y" where x has more than one character.

The existing code made excessive calls to the expensive memcmp() function.
The new code uses memchr() to rapidly find a start point for memcmp().
In addition to knowing that the first character is a match, the new code
also checks that the last character is a match.  This significantly reduces
the incidence of false starts (saving memcmp() calls and making quadratic
behavior less likely).

Improves the timings on:
    python -m timeit -r7 -s"x='a'*1000" "'ab' in x"
    python -m timeit -r7 -s"x='a'*1000" "'bc' in x"

Once this code has proven itself, then string_find_internal() should refer
to it rather than running its own version.  Also, something similar may
apply to unicode objects.

1 files changed, 24 insertions, 0 deletions

diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py
index c8ed07c..0ce9618 100644
--- a/Lib/test/string_tests.py
+++ b/Lib/test/string_tests.py
@@ -122,6 +122,30 @@ class CommonTest(unittest.TestCase):
         self.checkraises(TypeError, 'hello', 'find')
         self.checkraises(TypeError, 'hello', 'find', 42)
 
+        # For a variety of combinations,
+        #    verify that str.find() matches __contains__
+        #    and that the found substring is really at that location
+        charset = ['', 'a', 'b', 'c']
+        digits = 5
+        base = len(charset)
+        teststrings = set()
+        for i in xrange(base ** digits):
+            entry = []
+            for j in xrange(digits):
+                i, m = divmod(i, base)
+                entry.append(charset[m])
+            teststrings.add(''.join(entry))
+        for i in teststrings:
+            i = self.fixtype(i)
+            for j in teststrings:
+                loc = i.find(j)
+                r1 = (loc != -1)
+                r2 = j in i
+                if r1 != r2:
+                    self.assertEqual(r1, r2)
+                if loc != -1:
+                    self.assertEqual(i[loc:loc+len(j)], j)
+
     def test_rfind(self):
         self.checkequal(9,  'abcdefghiabc', 'rfind', 'abc')
         self.checkequal(12, 'abcdefghiabc', 'rfind', '')