2018-04-09 05:36:35 +00:00
|
|
|
package levenshtein
|
|
|
|
|
2018-04-10 05:11:03 +00:00
|
|
|
import (
|
|
|
|
"math"
|
|
|
|
"strings"
|
|
|
|
)
|
|
|
|
|
|
|
|
// DamerauLevenshteinDistance calculates the damerau-levenshtein distance between s1 and s2.
|
|
|
|
// Reference: [Damerau-Levenshtein Distance](http://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance)
|
|
|
|
// Note that this calculation's result isn't normalized. (not between 0 and 1.)
|
|
|
|
// and if s1 and s2 are exactly the same, the result is 0.
|
|
|
|
func DamerauLevenshteinDistance(s1, s2 string) int {
|
|
|
|
if s1 == s2 {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
s1Array := strings.Split(s1, "")
|
|
|
|
s2Array := strings.Split(s2, "")
|
|
|
|
lenS1Array := len(s1Array)
|
|
|
|
lenS2Array := len(s2Array)
|
|
|
|
m := make([][]int, lenS1Array+1)
|
|
|
|
var cost int
|
|
|
|
for i := range m {
|
|
|
|
m[i] = make([]int, lenS2Array+1)
|
|
|
|
}
|
|
|
|
for i := 0; i < lenS1Array+1; i++ {
|
|
|
|
for j := 0; j < lenS2Array+1; j++ {
|
|
|
|
if i == 0 {
|
|
|
|
m[i][j] = j
|
|
|
|
} else if j == 0 {
|
|
|
|
m[i][j] = i
|
|
|
|
} else {
|
|
|
|
cost = 0
|
|
|
|
if s1Array[i-1] != s2Array[j-1] {
|
|
|
|
cost = 1
|
|
|
|
}
|
|
|
|
m[i][j] = min(m[i-1][j]+1, m[i][j-1]+1, m[i-1][j-1]+cost)
|
|
|
|
if i > 1 && j > 1 && s1Array[i-1] == s2Array[j-2] && s1Array[i-2] == s2Array[j-1] {
|
|
|
|
m[i][j] = min(m[i][j], m[i-2][j-2]+cost)
|
|
|
|
}
|
|
|
|
}
|
2018-04-09 05:36:35 +00:00
|
|
|
}
|
2018-04-10 05:11:03 +00:00
|
|
|
}
|
|
|
|
return m[lenS1Array][lenS2Array]
|
|
|
|
}
|
|
|
|
|
|
|
|
// min returns the minimum number of passed int slices.
|
|
|
|
func min(is ...int) int {
|
2018-04-15 20:28:36 +00:00
|
|
|
min := int(math.MaxInt32)
|
2018-04-10 05:11:03 +00:00
|
|
|
for _, v := range is {
|
|
|
|
if min > v {
|
|
|
|
min = v
|
2018-04-09 05:36:35 +00:00
|
|
|
}
|
|
|
|
}
|
2018-04-10 05:11:03 +00:00
|
|
|
return min
|
2018-04-09 05:36:35 +00:00
|
|
|
}
|