feat: add levenshtein distance calculator

src/searching/README.md

@@ -7,3 +7,7 @@ The binary search algorithm is a simple search in an ordered array-like compound
 ## [Dijkstra](./src/dijkstra.cairo)
 
 Dijkstra's algorithm is a graph search algorithm that finds the shortest path from a source node to all other nodes in a weighted graph, ensuring the shortest distances are progressively updated as it explores nodes. It maintains a priority queue of nodes based on their tentative distances from the source and greedily selects the node with the smallest distance at each step.
+
+## [Levenshtein distance](./src/levenshtein_distance.cairo)
+
+The Levenshtein distance is a string metric for measuring the difference between two sequences. It is the minimum number of single-character edits (insertions, deletions, or substitutions) required to change one string into the other. This version of the algorithm optmizes the space complexity. Time complexity: O(nm). Space complexity: O(n),

src/searching/src/levenshtein_distance.cairo

@@ -0,0 +1,77 @@
+// The Levenshtein Distance
+use dict::Felt252DictTrait;
+
+
+/// Compute the edit distance between two byte arrays
+/// * `arr1` - The first byte array.
+/// * `arr2` - The second byte array.
+/// # Returns
+/// * `usize` - The edit distance between the two byte arrays.
+fn levenshtein_distance(arr1: @ByteArray, arr2: @ByteArray) -> usize {
+    // Get the lengths of both arrays
+    let arr1_len = arr1.len();
+    let arr2_len = arr2.len();
+
+    // If the first array is empty, the distance is the length of the second array
+    if arr1_len == 0 {
+        return arr2_len;
+    }
+
+    // Initialize a dictionary to store previous distances, with keys and values as indices
+    let mut prev_distances = felt252_dict_new::<usize>();
+    let mut index: usize = 0;
+    loop {
+        // Break the loop when index equals the length of the first array plus 1
+        if index == arr1_len + 1 {
+            break;
+        }
+        prev_distances.insert(index.into(), index);
+        index += 1;
+    };
+
+    // Initialize a variable to keep track of the current row
+    let mut current_row: usize = 0;
+    loop {
+        // Break the loop when current row equals the length of the second array
+        if current_row == arr2_len {
+            break;
+        }
+        let second_array_element = arr2.at(current_row).unwrap();
+        let mut previous_substitution_cost = prev_distances.get(0);
+        prev_distances.insert(0, current_row + 1);
+
+        // Initialize a variable to keep track of the current column
+        let mut current_column: usize = 0;
+        loop {
+            // Break the loop when current column equals the length of the first array
+            if current_column == arr1_len {
+                break;
+            }
+            let first_array_element = arr1.at(current_column).unwrap();
+            let deletion_cost = prev_distances.get(current_column.into()) + 1;
+            let insertion_cost = prev_distances.get((current_column + 1).into()) + 1;
+            let substitution_cost = if first_array_element == second_array_element {
+                previous_substitution_cost
+            } else {
+                previous_substitution_cost + 1
+            };
+
+            previous_substitution_cost = prev_distances.get((current_column + 1).into());
+            let mut min_cost = deletion_cost;
+            if insertion_cost < min_cost {
+                min_cost = insertion_cost;
+            }
+            if substitution_cost < min_cost {
+                min_cost = substitution_cost;
+            }
+            prev_distances.insert((current_column + 1).into(), min_cost);
+
+            current_column += 1
+        };
+
+        current_row += 1;
+    };
+
+    // Return the Levenshtein distance
+    prev_distances.get(arr1_len.into())
+}

src/searching/src/lib.cairo

@@ -1,5 +1,6 @@
 mod binary_search;
 mod dijkstra;
+mod levenshtein_distance;
 
 #[cfg(test)]
 mod tests;

src/searching/src/tests.cairo

@@ -1,2 +1,3 @@
 mod binary_search_test;
 mod dijkstra_test;
+mod levenshtein_distance_test;

src/searching/src/tests/levenshtein_distance_test.cairo

@@ -0,0 +1,114 @@
+use alexandria_searching::levenshtein_distance::levenshtein_distance;
+
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_1() {
+    // FROG -> 46,52,4f,47
+    let mut arr1: ByteArray = Default::default();
+    arr1.append_byte(0x46_u8);
+    arr1.append_byte(0x52_u8);
+    arr1.append_byte(0x4f_u8);
+    arr1.append_byte(0x47_u8);
+    // DOG -> 44,4f,47
+    let mut arr2: ByteArray = Default::default();
+    arr2.append_byte(0x44_u8);
+    arr2.append_byte(0x4f_u8);
+    arr2.append_byte(0x47_u8);
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 2, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_2() {
+    let mut arr1: ByteArray = Default::default();
+    let mut arr2: ByteArray = Default::default();
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 0, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_3() {
+    let mut arr1: ByteArray = Default::default();
+    let mut arr2: ByteArray = Default::default();
+    arr2.append_byte(0x61_u8);
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 1, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_4() {
+    let mut arr1: ByteArray = Default::default();
+    arr1.append_byte(0x61_u8);
+    let mut arr2: ByteArray = Default::default();
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 1, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_5() {
+    let mut arr1: ByteArray = Default::default();
+    arr1.append_byte(0x61_u8);
+    arr1.append_byte(0x62_u8);
+    let mut arr2: ByteArray = Default::default();
+    arr2.append_byte(0x61_u8);
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 1, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_6() {
+    // foobar -> 66,6f,6f,62,61,72
+    let mut arr1: ByteArray = Default::default();
+    arr1.append_byte(0x66_u8);
+    arr1.append_byte(0x6f_u8);
+    arr1.append_byte(0x6f_u8);
+    arr1.append_byte(0x62_u8);
+    arr1.append_byte(0x61_u8);
+    arr1.append_byte(0x72_u8);
+    // foobar -> 66,6f,6f,62,61,72
+    let mut arr2: ByteArray = Default::default();
+    arr2.append_byte(0x66_u8);
+    arr2.append_byte(0x6f_u8);
+    arr2.append_byte(0x6f_u8);
+    arr2.append_byte(0x62_u8);
+    arr2.append_byte(0x61_u8);
+    arr2.append_byte(0x72_u8);
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 0, 'invalid result');
+}
+
+#[test]
+#[available_gas(5000000)]
+fn bm_search_test_7() {
+    // foobar -> 66,6f,6f,62,61,72
+    let mut arr1: ByteArray = Default::default();
+    arr1.append_byte(0x66_u8);
+    arr1.append_byte(0x6f_u8);
+    arr1.append_byte(0x6f_u8);
+    arr1.append_byte(0x62_u8);
+    arr1.append_byte(0x61_u8);
+    arr1.append_byte(0x72_u8);
+    // barfoo -> 62,61,72,66,6f,6f
+    let mut arr2: ByteArray = Default::default();
+    arr2.append_byte(0x62_u8);
+    arr2.append_byte(0x61_u8);
+    arr2.append_byte(0x72_u8);
+    arr2.append_byte(0x66_u8);
+    arr2.append_byte(0x6f_u8);
+    arr2.append_byte(0x6f_u8);
+
+    let dist = levenshtein_distance(@arr1, @arr2);
+    assert(dist == 6, 'invalid result');
+}