Knuth–Morris–Pratt algorithm

Author: Shikha-code36

README.md

@@ -28,4 +28,6 @@ Data Structures and Algorithms Patterns implemented in Python.
     - [x] [Shell Sort](Sorting-Algo/shellsort.py)
     - [x] [Selection Sort](Sorting-Algo/selectionsort.py)
     - [x] [Bucket Sort](Sorting-Algo/bucketsort.py)
+- [x] [Strings](Strings)
+    - [x] [KMP (Knuth Morris Pratt) Pattern Searching](Strings/KMP.py)
 

Strings/KMP.py

@@ -0,0 +1,73 @@
+'''
+                            The Knuth-Morris-Pratt (KMP)Algorithm
+
+For a given string ‘S’, string matching algorithm determines whether a pattern ‘p’ occurs in the given string ‘S’.
+
+Input :
+
+String = "Welcome to CodeKMPPattern"
+
+Pattern = "Code"
+Output :Pattern found at index 11.
+
+Time Complexity - O(n)
+'''
+def KMPSearch(pat, txt):
+    M = len(pat)
+    N = len(txt)
+ 
+    # create lps[] that will hold the longest prefix suffix
+    # values for pattern
+    lps = [0]*M
+    j = 0 # index for pat[]
+ 
+    # Preprocess the pattern (calculate lps[] array)
+    compute(pat, M, lps)
+ 
+    i = 0 # index for txt[]
+    while i < N:
+        if pat[j] == txt[i]:
+            i += 1
+            j += 1
+ 
+        if j == M:
+            print ("Found pattern at index", str(i-j))
+            j = lps[j-1]
+ 
+        # mismatch after j matches
+        elif i < N and pat[j] != txt[i]:
+            # Do not match lps[0..lps[j-1]] characters,
+            # they will match anyway
+            if j != 0:
+                j = lps[j-1]
+            else:
+                i += 1
+ 
+def compute(pat, M, lps):
+    len = 0 # length of the previous longest prefix suffix
+ 
+    lps[0] # lps[0] is always 0
+    i = 1
+ 
+    # the loop calculates lps[i] for i = 1 to M-1
+    while i < M:
+        if pat[i]== pat[len]:
+            len += 1
+            lps[i] = len
+            i += 1
+        else:
+            # This is tricky. Consider the example.
+            # AAACAAAA and i = 7. The idea is similar
+            # to search step.
+            if len != 0:
+                len = lps[len-1]
+ 
+                # Also, note that we do not increment i here
+            else:
+                lps[i] = 0
+                i += 1
+ 
+txt = "ABABDABACDABABCABAB"
+pat = "ABABCABAB"
+KMPSearch(pat, txt)
+#Found pattern at index 10