[Feature] Added finding duplicates with multiple strategies with O(n) and O(log(n)) runtimes.

Author: exterkamp

README.md

@@ -35,6 +35,7 @@ $ coverage report -m
 * [Breadth First Search](searches/breadth_first_search.py)
   * [2D Grid BFS](searches/breadth_first_search.py)
   * [Graph BFS](searches/breadth_first_search.py)
+* [Finding Duplicates](searches/find_duplicates.py)
 
 ### Data Structures
 * [LRU Cache](structures/lru_cache.py)

searches/find_duplicates.py

@@ -0,0 +1,48 @@
+from searches.binary_search import binary_search
+
+def duplicates_linear(arr1, arr2):
+    arr1_seen = set(arr1)
+    output = []
+
+    for element in arr2:
+        if element in arr1_seen:
+            output.append(element)
+
+    return output
+
+def duplicates_pre_sorted(arr1, arr2):
+    output = []
+  
+    ptr_1 = 0
+    ptr_2 = 0
+    
+    while ptr_1 < len(arr1) and ptr_2 < len(arr2):
+        
+        if arr2[ptr_2] == arr1[ptr_1]:
+            output.append(arr1[ptr_1])
+            ptr_1 += 1
+            ptr_2 += 1
+        elif arr2[ptr_2] > arr1[ptr_1]:
+            ptr_1 += 1
+        else:
+            ptr_2 += 1
+    
+    return output
+
+def duplicates_bin_search(arr1, arr2):
+    """
+    Find duplicates in 2 sets, where one is much larger than the other.
+
+    """
+
+    # if arr1 is greater, swap them
+    if len(arr2) < len(arr1):
+        arr1, arr2 = arr2, arr1
+    
+    output = []
+
+    for element in arr1:
+        if binary_search(arr2, element) > 0:
+            output.append(element)
+
+    return output

tests/test_find_duplicates.py

@@ -0,0 +1,19 @@
+import unittest
+from searches.find_duplicates import duplicates_linear, duplicates_pre_sorted, duplicates_bin_search
+
+class TestFindDuplicates(unittest.TestCase):
+
+    def test_linear(self):
+        self.assertEqual([1,2,3], duplicates_linear([1,2,3,4,5,6],[1,2,3,7,8,9]))
+        self.assertEqual([4,1,3,2], duplicates_linear([4,5,7,1,9,2,10,3],[4,90,23,1,53,3,2,22]))
+    
+    def test_pre_sorted(self):
+        self.assertEqual([1,2,3], duplicates_pre_sorted([1,2,3,4,5,6],[1,2,3,7,8,9]))
+        self.assertNotEqual([1,2,3], duplicates_pre_sorted([5,7,1,9,2,10,3],[4,90,23,1,53,3,2,22]))
+
+    def test_bin_search(self):
+        self.assertEqual([1,2,3], duplicates_linear([1,2,3,4,5,6],[1,2,3,7,8,9]))
+        self.assertEqual([1,2,3], duplicates_linear([1,2,3,4,5,6],[1,2,3,7,8,9,10,11,12,13,14,15]))
+    
+    def test_bin_search_second_shorter(self):
+        self.assertEqual([1,2,3], duplicates_linear([1,2,3,7,8,9,10,11,12,13,14,15],[1,2,3,4,5,6]))