Merge branch 'master' into lru_improve

Author: Hardvan

src/main/java/com/thealgorithms/datastructures/bloomfilter/BloomFilter.java

@@ -4,6 +4,11 @@
 
 /**
  * A generic BloomFilter implementation for probabilistic membership checking.
+ * <p>
+ * Bloom filters are space-efficient data structures that provide a fast way to test whether an
+ * element is a member of a set. They may produce false positives, indicating an element is
+ * in the set when it is not, but they will never produce false negatives.
+ * </p>
  *
  * @param <T> The type of elements to be stored in the Bloom filter.
  */
@@ -17,18 +22,22 @@ public class BloomFilter<T> {
      * Constructs a BloomFilter with a specified number of hash functions and bit array size.
      *
      * @param numberOfHashFunctions the number of hash functions to use
-     * @param bitArraySize          the size of the bit array
+     * @param bitArraySize          the size of the bit array, which determines the capacity of the filter
+     * @throws IllegalArgumentException if numberOfHashFunctions or bitArraySize is less than 1
      */
     @SuppressWarnings("unchecked")
     public BloomFilter(int numberOfHashFunctions, int bitArraySize) {
+        if (numberOfHashFunctions < 1 || bitArraySize < 1) {
+            throw new IllegalArgumentException("Number of hash functions and bit array size must be greater than 0");
+        }
         this.numberOfHashFunctions = numberOfHashFunctions;
         this.bitArray = new BitSet(bitArraySize);
         this.hashFunctions = new Hash[numberOfHashFunctions];
         initializeHashFunctions();
     }
 
     /**
-     * Initializes the hash functions with unique indices.
+     * Initializes the hash functions with unique indices to ensure different hashing.
      */
     private void initializeHashFunctions() {
         for (int i = 0; i < numberOfHashFunctions; i++) {
@@ -38,8 +47,12 @@ private void initializeHashFunctions() {
 
     /**
      * Inserts an element into the Bloom filter.
+     * <p>
+     * This method hashes the element using all defined hash functions and sets the corresponding
+     * bits in the bit array.
+     * </p>
      *
-     * @param key the element to insert
+     * @param key the element to insert into the Bloom filter
      */
     public void insert(T key) {
         for (Hash<T> hash : hashFunctions) {
@@ -50,8 +63,13 @@ public void insert(T key) {
 
     /**
      * Checks if an element might be in the Bloom filter.
+     * <p>
+     * This method checks the bits at the positions computed by each hash function. If any of these
+     * bits are not set, the element is definitely not in the filter. If all bits are set, the element
+     * might be in the filter.
+     * </p>
      *
-     * @param key the element to check
+     * @param key the element to check for membership in the Bloom filter
      * @return {@code true} if the element might be in the Bloom filter, {@code false} if it is definitely not
      */
     public boolean contains(T key) {
@@ -66,6 +84,9 @@ public boolean contains(T key) {
 
     /**
      * Inner class representing a hash function used by the Bloom filter.
+     * <p>
+     * Each instance of this class represents a different hash function based on its index.
+     * </p>
      *
      * @param <T> The type of elements to be hashed.
      */
@@ -76,27 +97,35 @@ private static class Hash<T> {
         /**
          * Constructs a Hash function with a specified index.
          *
-         * @param index the index of this hash function
+         * @param index the index of this hash function, used to create a unique hash
          */
         Hash(int index) {
             this.index = index;
         }
 
         /**
          * Computes the hash of the given key.
+         * <p>
+         * The hash value is calculated by multiplying the index of the hash function
+         * with the ASCII sum of the string representation of the key.
+         * </p>
          *
          * @param key the element to hash
-         * @return the hash value
+         * @return the computed hash value
          */
         public int compute(T key) {
             return index * asciiString(String.valueOf(key));
         }
 
         /**
          * Computes the ASCII value sum of the characters in a string.
+         * <p>
+         * This method iterates through each character of the string and accumulates
+         * their ASCII values to produce a single integer value.
+         * </p>
          *
          * @param word the string to compute
-         * @return the sum of ASCII values of the characters
+         * @return the sum of ASCII values of the characters in the string
          */
         private int asciiString(String word) {
             int sum = 0;

src/test/java/com/thealgorithms/datastructures/bloomfilter/BloomFilterTest.java

@@ -62,4 +62,55 @@ void testMultipleInsertions() {
 
         Assertions.assertFalse(bloomFilter.contains("key" + 200));
     }
+
+    @Test
+    void testEmptyFilterContains() {
+        Assertions.assertFalse(bloomFilter.contains("notInserted"), "Filter should not contain any elements when empty");
+        Assertions.assertFalse(bloomFilter.contains(null), "Filter should not contain null elements");
+    }
+
+    @Test
+    void testDifferentTypes() {
+        BloomFilter<Object> filter = new BloomFilter<>(3, 100);
+        filter.insert("string");
+        filter.insert(123);
+        filter.insert(45.67);
+
+        Assertions.assertTrue(filter.contains("string"), "Filter should contain the string 'string'");
+        Assertions.assertTrue(filter.contains(123), "Filter should contain the integer 123");
+        Assertions.assertTrue(filter.contains(45.67), "Filter should contain the double 45.67");
+        Assertions.assertFalse(filter.contains("missing"), "Filter should not contain elements that were not inserted");
+    }
+
+    @Test
+    void testFalsePositiveAfterInsertions() {
+        bloomFilter.insert("cat");
+        bloomFilter.insert("dog");
+        bloomFilter.insert("fish");
+
+        // Checking for an element that was not added
+        Assertions.assertFalse(bloomFilter.contains("bird"), "Filter should not contain 'bird' which was never inserted");
+
+        // To increase chances of false positives, we can add more items
+        for (int i = 0; i < 100; i++) {
+            bloomFilter.insert("item" + i);
+        }
+
+        Assertions.assertFalse(bloomFilter.contains("nonexistent"), "Filter should not contain 'nonexistent' which was never inserted");
+    }
+
+    @Test
+    void testBoundaryConditions() {
+        BloomFilter<String> filter = new BloomFilter<>(3, 10);
+        filter.insert("a");
+        filter.insert("b");
+        filter.insert("c");
+        filter.insert("d");
+
+        Assertions.assertTrue(filter.contains("a"), "Filter should contain 'a'");
+        Assertions.assertTrue(filter.contains("b"), "Filter should contain 'b'");
+        Assertions.assertTrue(filter.contains("c"), "Filter should contain 'c'");
+        Assertions.assertTrue(filter.contains("d"), "Filter should contain 'd'");
+        Assertions.assertFalse(filter.contains("e"), "Filter should not contain 'e' which was not inserted");
+    }
 }