addrkit/internal/domain/match/levenshtein.go

package match

import "strings"

// levenshtein returns the edit distance between two strings, measured in
// runes. It uses the rolling-row formulation: O(min(n,m)) memory.
//
// The resolver uses it only to tolerate typos in the *street name*; house
// numbers are always compared exactly, because a wrong house is worse than a
// missing one.
func levenshtein(a, b string) int {
	ra, rb := []rune(a), []rune(b)
	if len(ra) == 0 {
		return len(rb)
	}
	if len(rb) == 0 {
		return len(ra)
	}
	prev := make([]int, len(rb)+1)
	curr := make([]int, len(rb)+1)
	for j := range prev {
		prev[j] = j
	}
	for i := 1; i <= len(ra); i++ {
		curr[0] = i
		for j := 1; j <= len(rb); j++ {
			cost := 1
			if ra[i-1] == rb[j-1] {
				cost = 0
			}
			curr[j] = min3(prev[j]+1, curr[j-1]+1, prev[j-1]+cost)
		}
		prev, curr = curr, prev
	}
	return prev[len(rb)]
}

// ratio returns a 0..1 similarity where 1 means identical. It is
// 1 - distance/max(len), which is stable and easy to reason about.
func ratio(a, b string) float64 {
	if a == b {
		return 1
	}
	la, lb := len([]rune(a)), len([]rune(b))
	m := la
	if lb > m {
		m = lb
	}
	if m == 0 {
		return 1
	}
	return 1 - float64(levenshtein(a, b))/float64(m)
}

// damerau returns the optimal string alignment (Damerau-Levenshtein) distance,
// where an adjacent transposition costs 1. Typos are very often transpositions
// ("Гоглоя" vs "Гоголя"), so counting them as a single edit matters.
func damerau(a, b string) int {
	ra, rb := []rune(a), []rune(b)
	la, lb := len(ra), len(rb)
	if la == 0 {
		return lb
	}
	if lb == 0 {
		return la
	}
	// Three rolling rows: d[i-2], d[i-1], d[i].
	prev2 := make([]int, lb+1)
	prev := make([]int, lb+1)
	curr := make([]int, lb+1)
	for j := 0; j <= lb; j++ {
		prev[j] = j
	}
	for i := 1; i <= la; i++ {
		curr[0] = i
		for j := 1; j <= lb; j++ {
			cost := 1
			if ra[i-1] == rb[j-1] {
				cost = 0
			}
			best := min3(prev[j]+1, curr[j-1]+1, prev[j-1]+cost)
			if i > 1 && j > 1 && ra[i-1] == rb[j-2] && ra[i-2] == rb[j-1] {
				if t := prev2[j-2] + 1; t < best {
					best = t
				}
			}
			curr[j] = best
		}
		prev2, prev, curr = prev, curr, prev2
	}
	return prev[lb]
}

func min3(a, b, c int) int {
	m := a
	if b < m {
		m = b
	}
	if c < m {
		m = c
	}
	return m
}

// tokenScore scores two name tokens. A single edit is tolerated for tokens of
// length >= 4 and two edits for length >= 8; otherwise it falls back to the
// plain ratio. Short names (<= 3 chars) are intentionally not fuzzy-matched:
// one edit is too large a fraction of the word to be safe.
func tokenScore(a, b string) float64 {
	if a == b {
		return 1
	}
	d := levenshtein(a, b)
	minLen := len([]rune(a))
	if lb := len([]rune(b)); lb < minLen {
		minLen = lb
	}
	switch {
	case d == 1 && minLen >= 4:
		return 0.95
	case d == 2 && minLen >= 8:
		return 0.90
	default:
		return ratio(a, b)
	}
}

// nameSimilarity compares two canonical name keys (space-joined, sorted
// tokens) in a token-aware, order-insensitive way. A typo in one word of a
// multi-word name therefore does not sink the whole match, and reordered words
// still score 1.
func nameSimilarity(a, b string) float64 {
	if a == b {
		return 1
	}
	ta, tb := strings.Fields(a), strings.Fields(b)
	if len(ta) == 0 || len(tb) == 0 {
		return 0
	}
	sum, n := 0.0, 0
	for _, x := range ta {
		best := 0.0
		for _, y := range tb {
			if s := tokenScore(x, y); s > best {
				best = s
			}
		}
		sum += best
		n++
	}
	for _, y := range tb {
		best := 0.0
		for _, x := range ta {
			if s := tokenScore(x, y); s > best {
				best = s
			}
		}
		sum += best
		n++
	}
	return sum / float64(n)
}