strings: add hamming_distance/jaro_similarity/jaro_winkler_similarity functions (#22701)

Author: kbkpbot

vlib/strings/similarity.v

@@ -12,6 +12,30 @@ fn min(a u16, b u16, c u16) u16 {
 	return m
 }
 
+@[inline]
+fn max2(a int, b int) int {
+	if a < b {
+		return b
+	}
+	return a
+}
+
+@[inline]
+fn min2(a int, b int) int {
+	if a < b {
+		return a
+	}
+	return b
+}
+
+@[inline]
+fn abs2(a int, b int) int {
+	if a < b {
+		return b - a
+	}
+	return a - b
+}
+
 // levenshtein_distance uses the Levenshtein Distance algorithm to calculate
 // the distance between between two strings `a` and `b` (lower is closer).
 @[direct_array_access]
@@ -85,3 +109,121 @@ pub fn dice_coefficient(s1 string, s2 string) f32 {
 	}
 	return (2.0 * f32(intersection_size)) / (f32(a.len) + f32(b.len) - 2)
 }
+
+// hamming_distance uses the Hamming Distance algorithm to calculate
+// the distance between two strings `a` and `b` (lower is closer).
+@[direct_array_access]
+pub fn hamming_distance(a string, b string) int {
+	if a.len == 0 && b.len == 0 {
+		return 0
+	}
+	mut match_len := min2(a.len, b.len)
+	mut diff_count := abs2(a.len, b.len)
+	for i in 0 .. match_len {
+		if a[i] != b[i] {
+			diff_count++
+		}
+	}
+	return diff_count
+}
+
+// hamming_similarity uses the Hamming Distance algorithm to calculate
+// the distance between two strings `a` and `b`.
+// It returns a coefficient between 0.0 (not similar) and 1.0 (exact match).
+pub fn hamming_similarity(a string, b string) f32 {
+	l := max2(a.len, b.len)
+	if l == 0 {
+		// Both are empty strings, should return 1.0
+		return 1.0
+	}
+	d := hamming_distance(a, b)
+	return 1.00 - f32(d) / f32(l)
+}
+
+// jaro_similarity uses the Jaro Distance algorithm to calculate
+// the distance between two strings `a` and `b`.
+// It returns a coefficient between 0.0 (not similar) and 1.0 (exact match).
+@[direct_array_access]
+pub fn jaro_similarity(a string, b string) f64 {
+	a_len := a.len
+	b_len := b.len
+	if a_len == 0 && b_len == 0 {
+		// Both are empty strings, should return 1.0
+		return 1.0
+	}
+	if a_len == 0 || b_len == 0 {
+		return 0
+	}
+
+	// Maximum distance upto which matching is allowed
+	match_distance := max2(a_len, b_len) / 2 - 1
+
+	mut a_matches := []bool{len: a_len}
+	mut b_matches := []bool{len: b_len}
+	mut matches := 0
+	mut transpositions := 0.0
+
+	// Traverse through the first string
+	for i in 0 .. a_len {
+		start := max2(0, i - match_distance)
+		end := min2(b_len, i + match_distance + 1)
+		for k in start .. end {
+			// If there is a match
+			if b_matches[k] {
+				continue
+			}
+			if a[i] != b[k] {
+				continue
+			}
+			a_matches[i] = true
+			b_matches[k] = true
+			matches++
+			break
+		}
+	}
+	// If there is no match
+	if matches == 0 {
+		return 0
+	}
+	mut k := 0
+	// Count number of occurrences where two characters match but
+	// there is a third matched character in between the indices
+	for i in 0 .. a_len {
+		if !a_matches[i] {
+			continue
+		}
+		// Find the next matched character in second string
+		for !b_matches[k] {
+			k++
+		}
+		if a[i] != b[k] {
+			transpositions++
+		}
+		k++
+	}
+	transpositions /= 2
+	return (matches / f64(a_len) + matches / f64(b_len) + (matches - transpositions) / matches) / 3
+}
+
+// jaro_winkler_similarity uses the Jaro Winkler Distance algorithm to calculate
+// the distance between two strings `a` and `b`.
+// It returns a coefficient between 0.0 (not similar) and 1.0 (exact match).
+// The scaling factor(`p=0.1`) in Jaro-Winkler gives higher weight to prefix
+// similarities, making it especially effective for cases where slight misspellings
+// or prefixes are common.
+@[direct_array_access]
+pub fn jaro_winkler_similarity(a string, b string) f64 {
+	// Maximum of 4 characters are allowed in prefix
+	mut lmax := min2(4, min2(a.len, b.len))
+	mut l := 0
+	for i in 0 .. lmax {
+		if a[i] == b[i] {
+			l++
+		}
+	}
+	js := jaro_similarity(a, b)
+	// select a multiplier (Winkler suggested p=0.1) for the relative importance of the prefix for the word similarity
+	p := 0.1
+	ws := js + f64(l) * p * (1 - js)
+	return ws
+}

vlib/strings/similarity_test.v

@@ -12,3 +12,52 @@ fn test_levenshtein_distance() {
 	assert strings.levenshtein_distance('flomax', 'volmax') == 3
 	assert strings.levenshtein_distance('ab', 'cd') == 2
 }
+
+fn test_hamming_distance() {
+	assert strings.hamming_distance('', '') == 0
+	assert strings.hamming_distance('one', 'one') == 0
+	assert strings.hamming_distance('', 'two') == 3
+	assert strings.hamming_distance('three', '') == 5
+	assert strings.hamming_distance('bananna', '') == 7
+	assert strings.hamming_distance('cats', 'hats') == 1
+	assert strings.hamming_distance('hugs', 'shrugs') == 6
+	assert strings.hamming_distance('broom', 'shroom') == 5
+	assert strings.hamming_distance('flomax', 'volmax') == 3
+	assert strings.hamming_distance('ab', 'cd') == 2
+}
+
+fn test_hamming_similarity() {
+	assert strings.hamming_similarity('', '') == 1.0
+	assert strings.hamming_similarity('one', 'one') == 1.0
+	assert strings.hamming_similarity('', 'two') == 0
+	assert strings.hamming_similarity('three', '') == 0
+	assert strings.hamming_similarity('bananna', '') == 0
+	assert strings.hamming_similarity('cats', 'hats') == 0.75
+	assert strings.hamming_similarity('hugs', 'shrugs') == 0
+	assert strings.hamming_similarity('broom', 'shroom') == 0.1666666865348816
+	assert strings.hamming_similarity('flomax', 'volmax') == 0.5
+	assert strings.hamming_similarity('ab', 'cd') == 0
+}
+
+fn test_jaro_similarity() {
+	assert strings.jaro_similarity('', '') == 1
+	assert strings.jaro_similarity('one', 'one') == 1
+	assert strings.jaro_similarity('', 'two') == 0
+	assert strings.jaro_similarity('three', '') == 0
+	assert strings.jaro_similarity('bananna', '') == 0
+	assert strings.jaro_similarity('MARTHA', 'MARHTA') == 0.9444444444444445
+	assert strings.jaro_similarity('DIXON', 'DICKSONX') == 0.7666666666666666
+	assert strings.jaro_similarity('JELLYFISH', 'SMELLYFISH') == 0.8962962962962964
+}
+
+fn test_jaro_winkler_similarity() {
+	assert strings.jaro_winkler_similarity('', '') == 1
+	assert strings.jaro_winkler_similarity('one', 'one') == 1
+	assert strings.jaro_winkler_similarity('', 'two') == 0
+	assert strings.jaro_winkler_similarity('three', '') == 0
+	assert strings.jaro_winkler_similarity('bananna', '') == 0
+	assert strings.jaro_winkler_similarity('accomodate', 'accommodate') == 0.9818181818181818
+	assert strings.jaro_winkler_similarity('accomodate', 'accompanist') == 0.8672727272727273
+	assert strings.jaro_winkler_similarity('untill', 'huntsville') == 0.8666666666666667
+	assert strings.jaro_winkler_similarity('wich', 'wichita') == 0.9142857142857143
+}