add ons in string directory - Bayer_Moore_Search

Author: Dharni0607

strings/Boyer_Moore_Search.py

@@ -0,0 +1,56 @@
+"""
+This algorithm tries to find the pattern in given text using Bad Character Heuristic method. 
+The bad-character rule considers the character in Text at which there is a mis-match. The next occurrence of that character to the left in Pattern is found, and a shift which brings that occurrence in line with the mismatched occurrence in Text is proposed. If the mismatched character does not occur to the left in Pattern, a shift is proposed that moves the entirety of Pattern past the point of mismatch
+
+Complexity : O(n/m)
+    n=length of main string
+    m=length of pattern string
+"""
+
+class BayerMooreSearch:
+    def __init__(self, text, pattern):
+        self.text, self.pattern = text, pattern
+        self.textLen, self.patLen = len(text), len(pattern)
+    
+
+    """ following functions tries to find the index of given char in pattern, 
+    if not found -1 will be returned"""
+    def matchInPattern(self, char):
+        for i in range(self.patLen-1, -1, -1):
+            if char == self.pattern[i]:
+                return i
+        return -1
+
+
+    """ following functions tries to find the mis-matched character's index in text from last, 
+    If all characters are matched, -1 will be returned"""
+    def misMatchInText(self, currentPos):
+        for i in range(self.patLen-1, -1, -1):
+            if self.pattern[i] != self.text[currentPos + i]:
+                return currentPos + i
+        return -1
+        
+    def badCharacterHeuristic(self):
+        positions = []
+        for i in range(self.textLen - self.patLen + 1):
+            misMatchIndex = self.misMatchInText(i)
+            if misMatchIndex == -1:
+                positions.append(i)
+            else:
+                matchIndex = self.matchInPattern(self.text[misMatchIndex])
+                i = misMatchIndex - matchIndex   #shifting
+        return positions
+
+
+if __name__ == '__main__': 
+    text = "ABAAABCDBBABCDDEBCABC"
+    pattern = "ABC" 
+    bms = BayerMooreSearch(text, pattern)
+    positions = bms.badCharacterHeuristic()
+    if(len(positions) == 0):
+        print("No match found")
+    else:
+        print("Pattern found in following positions: ")
+        print(positions)
+    
+