Created
November 16, 2010 09:46
-
-
Save dknight/701635 to your computer and use it in GitHub Desktop.
Levenshtein distance
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class String | |
def levenstein(other, ins=2, del=1, sub=1) | |
return nil if self.nil? || other.nil? | |
dm = [] | |
dm[0] = (0..self.length).collect { |i| i * ins} | |
fill = [0] * (self.length - 1) | |
for i in 1..other.length | |
dm[i] = [i * del, fill.flatten] | |
end | |
for i in 1..other.length | |
for j in 1..self.length | |
dm[i][j] = [ | |
dm[i-1][j-1] + (self[i-1] == other[i-1] ? 0 : sub), | |
dm[i][j-1] + ins, | |
dm[i-1][j] + del | |
].min | |
end | |
end | |
dm[other.length][self.length] | |
end | |
def similar?(other, thresh = 2) | |
self.levenstein(other) < thresh | |
end | |
end | |
puts "Foobar".similar?("Fuubar", 3) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment