Refactor Levenshtein distance implementation (#5138)

* ref: refactor Levenshtein distance implementation
- Rewrite the original levenshtein distance implementation in functional style
- Add optimized version of levenshtein distance

* ref: make `LevenshteinDistance` class a proper utility

* ref: remove duplicated test data

* ref: update tests

---

Co-authored-by: Piotr Idzik <[email protected]>

Author: sozelfist

src/main/java/com/thealgorithms/dynamicprogramming/LevenshteinDistance.java

@@ -1,49 +1,84 @@
 package com.thealgorithms.dynamicprogramming;
 
+import java.util.stream.IntStream;
+
 /**
- * @author Kshitij VERMA (github.com/kv19971) LEVENSHTEIN DISTANCE dyamic
- * programming implementation to show the difference between two strings
- * (https://en.wikipedia.org/wiki/Levenshtein_distance)
+ * Provides functions to calculate the Levenshtein distance between two strings.
+ *
+ * The Levenshtein distance is a measure of the similarity between two strings by calculating the minimum number of single-character
+ * edits (insertions, deletions, or substitutions) required to change one string into the other.
  */
-public class LevenshteinDistance {
-
-    private static int minimum(int a, int b, int c) {
-        if (a < b && a < c) {
-            return a;
-        } else if (b < a && b < c) {
-            return b;
-        } else {
-            return c;
-        }
+public final class LevenshteinDistance {
+    private LevenshteinDistance() {
     }
 
-    public static int calculateLevenshteinDistance(String str1, String str2) {
-        int len1 = str1.length() + 1;
-        int len2 = str2.length() + 1;
-        int[][] distanceMat = new int[len1][len2];
-        for (int i = 0; i < len1; i++) {
-            distanceMat[i][0] = i;
-        }
-        for (int j = 0; j < len2; j++) {
-            distanceMat[0][j] = j;
+    /**
+     * Calculates the Levenshtein distance between two strings using a naive dynamic programming approach.
+     *
+     * This function computes the Levenshtein distance by constructing a dynamic programming matrix and iteratively filling it in.
+     * It follows the standard top-to-bottom, left-to-right approach for filling in the matrix.
+     *
+     * @param string1 The first string.
+     * @param string2 The second string.
+     * @return The Levenshtein distance between the two input strings.
+     *
+     * Time complexity: O(nm),
+     * Space complexity: O(nm),
+     *
+     * where n and m are lengths of `string1` and `string2`.
+     *
+     * Note that this implementation uses a straightforward dynamic programming approach without any space optimization.
+     * It may consume more memory for larger input strings compared to the optimized version.
+     */
+    public static int naiveLevenshteinDistance(final String string1, final String string2) {
+        int[][] distanceMatrix = IntStream.rangeClosed(0, string1.length()).mapToObj(i -> IntStream.rangeClosed(0, string2.length()).map(j -> (i == 0) ? j : (j == 0) ? i : 0).toArray()).toArray(int[][] ::new);
+
+        IntStream.range(1, string1.length() + 1).forEach(i -> IntStream.range(1, string2.length() + 1).forEach(j -> {
+            final int cost = (string1.charAt(i - 1) == string2.charAt(j - 1)) ? 0 : 1;
+            distanceMatrix[i][j] = Math.min(distanceMatrix[i - 1][j - 1] + cost, Math.min(distanceMatrix[i][j - 1] + 1, distanceMatrix[i - 1][j] + 1));
+        }));
+
+        return distanceMatrix[string1.length()][string2.length()];
+    }
+
+    /**
+     * Calculates the Levenshtein distance between two strings using an optimized dynamic programming approach.
+     *
+     * This edit distance is defined as 1 point per insertion, substitution, or deletion required to make the strings equal.
+     *
+     * @param string1 The first string.
+     * @param string2 The second string.
+     * @return The Levenshtein distance between the two input strings.
+     *
+     * Time complexity: O(nm),
+     * Space complexity: O(n),
+     *
+     * where n and m are lengths of `string1` and `string2`.
+     *
+     * Note that this implementation utilizes an optimized dynamic programming approach, significantly reducing the space complexity from O(nm) to O(n), where n and m are the lengths of `string1` and `string2`.
+     *
+     * Additionally, it minimizes space usage by leveraging the shortest string horizontally and the longest string vertically in the computation matrix.
+     */
+    public static int optimizedLevenshteinDistance(final String string1, final String string2) {
+        if (string1.isEmpty()) {
+            return string2.length();
         }
-        for (int i = 1; i < len1; i++) {
-            for (int j = 1; j < len2; j++) {
-                if (str1.charAt(i - 1) == str2.charAt(j - 1)) {
-                    distanceMat[i][j] = distanceMat[i - 1][j - 1];
-                } else {
-                    distanceMat[i][j] = 1 + minimum(distanceMat[i - 1][j], distanceMat[i - 1][j - 1], distanceMat[i][j - 1]);
-                }
+
+        int[] previousDistance = IntStream.rangeClosed(0, string1.length()).toArray();
+
+        for (int j = 1; j <= string2.length(); j++) {
+            int prevSubstitutionCost = previousDistance[0];
+            previousDistance[0] = j;
+
+            for (int i = 1; i <= string1.length(); i++) {
+                final int deletionCost = previousDistance[i] + 1;
+                final int insertionCost = previousDistance[i - 1] + 1;
+                final int substitutionCost = (string1.charAt(i - 1) == string2.charAt(j - 1)) ? prevSubstitutionCost : prevSubstitutionCost + 1;
+                prevSubstitutionCost = previousDistance[i];
+                previousDistance[i] = Math.min(deletionCost, Math.min(insertionCost, substitutionCost));
             }
         }
-        return distanceMat[len1 - 1][len2 - 1];
-    }
-
-    public static void main(String[] args) {
-        String str1 = ""; // enter your string here
-        String str2 = ""; // enter your string here
 
-        System.out.print("Levenshtein distance between " + str1 + " and " + str2 + " is: ");
-        System.out.println(calculateLevenshteinDistance(str1, str2));
+        return previousDistance[string1.length()];
     }
 }

src/test/java/com/thealgorithms/dynamicprogramming/LevenshteinDistanceTests.java

@@ -2,15 +2,44 @@
 
 import static org.junit.jupiter.api.Assertions.assertEquals;
 
+import java.util.Arrays;
+import java.util.List;
+import java.util.function.ToIntBiFunction;
+import java.util.stream.Stream;
 import org.junit.jupiter.params.ParameterizedTest;
-import org.junit.jupiter.params.provider.CsvSource;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
 
 public class LevenshteinDistanceTests {
 
     @ParameterizedTest
-    @CsvSource({"dog,cat,3", "sunday,saturday,3", "cat,cats,1", "rain,train,1"})
-    void levenshteinDistanceTest(String str1, String str2, int distance) {
-        int result = LevenshteinDistance.calculateLevenshteinDistance(str1, str2);
-        assertEquals(distance, result);
+    @MethodSource("testCases")
+    public void testLevenshteinDistance(final int expected, final String str1, final String str2, final ToIntBiFunction<String, String> dist) {
+        assertEquals(expected, dist.applyAsInt(str1, str2));
+        assertEquals(expected, dist.applyAsInt(str2, str1));
+        assertEquals(0, dist.applyAsInt(str1, str1));
+        assertEquals(0, dist.applyAsInt(str2, str2));
+    }
+
+    private static Stream<Arguments> testCases() {
+        final Object[][] testData = {
+            {0, "", ""},
+            {0, "Hello, World!", "Hello, World!"},
+            {4, "", "Rust"},
+            {3, "horse", "ros"},
+            {6, "tan", "elephant"},
+            {8, "execute", "intention"},
+            {1, "a", "b"},
+            {1, "a", "aa"},
+            {1, "a", ""},
+            {1, "a", "ab"},
+            {1, "a", "ba"},
+            {2, "a", "bc"},
+            {2, "a", "cb"},
+        };
+
+        final List<ToIntBiFunction<String, String>> methods = Arrays.asList(LevenshteinDistance::naiveLevenshteinDistance, LevenshteinDistance::optimizedLevenshteinDistance);
+
+        return Stream.of(testData).flatMap(input -> methods.stream().map(method -> Arguments.of(input[0], input[1], input[2], method)));
     }
 }