Add kmp (keon#611)

* [ADD] Added KMP algorithm.

* [ADD] Added test case for KMP algorithm

* [EDIT] Imported KMP algorithm

* [EDIT] Added KMP algorithm in README

* [EDIT] Added test case for KMP algorithm

* [EDIT] Edited description of algorithm with more detail

* [FIX] Fixed minor bug

* [EDIT] Added test case for edge cases

Author: sonho00

README.md

@@ -330,6 +330,7 @@ If you want to uninstall algorithms, it is as simple as:
     - [first_unique_char](algorithms/strings/first_unique_char.py)
     - [repeat_substring](algorithms/strings/repeat_substring.py)     
 	- [atbash_cipher](algorithms/strings/atbash_cipher.py)
+	- [knuth_morris_pratt](algorithms/strings/knuth_morris_pratt.py)
 - [tree](algorithms/tree)
     - [bst](algorithms/tree/bst)
         - [array_to_bst](algorithms/tree/bst/array_to_bst.py)

algorithms/strings/__init__.py

@@ -35,3 +35,5 @@
 from .first_unique_char import *
 from .repeat_substring import *
 from .atbash_cipher import *
+from .knuth_morris_pratt import *
+

algorithms/strings/knuth_morris_pratt.py

@@ -0,0 +1,34 @@
+"""
+Given two strings text and pattern,
+return the list of  start indexes in text that matches with the pattern
+using knuth_morris_pratt algorithm.
+If idx is in the list, text[idx : idx + M] matches with pattern.
+Time complexity : O(N+M)
+N and M is the length of text and pattern, respectively.
+"""
+
+def knuth_morris_pratt(text, pattern):
+    n = len(text)
+    m = len(pattern)
+    pi = [0 for i in range(m)]
+    i = 0
+    j = 0
+    # making pi table
+    for i in range(1, m):
+        while j and pattern[i] != pattern[j]:
+            j = pi[j - 1]
+        if pattern[i] == pattern[j]:
+            j += 1
+            pi[i] = j
+    # finding pattern
+    j = 0
+    ret = []
+    for i in range(n):
+        while j and text[i] != pattern[j]:
+            j = pi[j - 1]
+        if text[i] == pattern[j]:
+            j += 1
+            if j == m:
+                ret.append(i - m + 1)
+                j = pi[j - 1]
+    return ret

tests/test_strings.py

@@ -37,7 +37,8 @@
     rotate,
     first_unique_char,
     repeat_substring,
-    atbash
+    atbash,
+    knuth_morris_pratt
 )
 
 import unittest
@@ -532,5 +533,17 @@ def test_atbash_cipher(self):
         self.assertEqual("AttaCK at DawN", atbash("ZggzXP zg WzdM"))
         self.assertEqual("ZggzXP zg WzdM", atbash("AttaCK at DawN"))
 
+class TestKnuthMorrisPratt(unittest.TestCase):
+    """[summary]
+    Test for the file knuth_morris_pratt.py
+
+    Arguments:
+        unittest {[type]} -- [description]
+    """
+    def test_knuth_morris_pratt(self):
+        self.assertEqual([0, 1, 2, 3, 4], knuth_morris_pratt("aaaaaaa", "aaa"))
+        self.assertEqual([0, 4], knuth_morris_pratt("abcdabc", "abc"))
+        self.assertEqual([], knuth_morris_pratt("aabcdaab", "aba"))
+
 if __name__ == "__main__":
     unittest.main()