[Feature] Added basic Rabin Karp style substring searching.

Author: exterkamp

README.md

@@ -77,4 +77,5 @@ Different algorithmic programs.  Grouped by general topic.
   * [Letters from Phone](algorithms/string/combinations.py)
 * [Longest Common Prefix](algorithms/string/longest_common_prefix.py)
   * [Trie](algorithms/string/longest_common_prefix.py)
-  * [Reduce](algorithms/string/longest_common_prefix.py)
+  * [Reduce](algorithms/string/longest_common_prefix.py)
+* [Finding Substring](algorithms/string/rabin_karp_substring_search.py)

algorithms/string/rabin_karp_substring_search.py

@@ -0,0 +1,44 @@
+def rabin_karp_find_substring(string, substring, base=256):
+    """
+    Finds occurances of a substring in a string.
+
+    Args:
+        string: the string that is being looked in
+        substring: the string to search for
+
+    Returns:
+        Index of the beginning of the first occurance
+        of a substring that is within the string.
+
+    """
+    # substring hash
+    substring_hash = 0
+    rolling_hash = 0
+
+    # get the initial hashes
+    for i in range(len(substring)):
+        rolling_hash = rolling_hash_ord(rolling_hash, base, len(substring) - i - 1, additional_element=string[i])
+        substring_hash = rolling_hash_ord(substring_hash, base, len(substring) - i - 1, additional_element=substring[i])
+    
+    for i in range(len(string) - len(substring)+1):
+        # check if hash matches hash of substring
+        if rolling_hash == substring_hash:
+            # check if the letters are 1:1
+            for s_i, letter in enumerate(substring):
+                if letter != string[i+s_i]:
+                    break
+            else:
+                return i
+        # recalulate hash
+        if i+len(substring) <= len(string) - 1:
+            rolling_hash = rolling_hash_ord(rolling_hash, base, len(substring)-1, removal_element=string[i], additional_element=string[i+len(substring)])
+    return -1
+
+def rolling_hash_ord(previous_hash, base, length, removal_element=None, additional_element=None):
+    if removal_element and additional_element:
+        previous_hash -= ord(removal_element) * (base ** length)
+        previous_hash *= base
+        previous_hash += ord(additional_element)
+    elif additional_element:
+        previous_hash += ord(additional_element) * (base ** length)
+    return previous_hash

tests/test_rabin_karp.py

@@ -0,0 +1,17 @@
+import unittest
+from algorithms.string.rabin_karp_substring_search import rabin_karp_find_substring
+
+class TestRabinKarp(unittest.TestCase):
+
+    def test_rabin_karp(self):
+        self.assertEqual(2, rabin_karp_find_substring('hello','llo'))
+        self.assertEqual(5, rabin_karp_find_substring('aabbababaa','babaa'))
+    
+    def test_rabin_karp_miss(self):
+        self.assertEqual(-1, rabin_karp_find_substring('hello','af'))
+
+    def test_find_first_with_mult(self):
+        self.assertEqual(3, rabin_karp_find_substring('abcabbabcabb', 'abb'))
+    
+    def test_same_hash_diff_order(self):
+        self.assertEqual(15, rabin_karp_find_substring('Where are your ears?', 'ear', base=0))