1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
|
module Bundler
class SimilarityDetector
SimilarityScore = Struct.new(:string, :distance)
# initialize with an array of words to be matched against
def initialize(corpus)
@corpus = corpus
end
# return an array of words similar to 'word' from the corpus
def similar_words(word, limit = 3)
words_by_similarity = @corpus.map{|w| SimilarityScore.new(w, levenshtein_distance(word, w)) }
words_by_similarity.select{|s| s.distance<=limit }.sort_by(&:distance).map(&:string)
end
# return the result of 'similar_words', concatenated into a list
# (eg "a, b, or c")
def similar_word_list(word, limit = 3)
words = similar_words(word,limit)
if words.length==1
words[0]
elsif words.length>1
[words[0..-2].join(", "), words[-1]].join(" or ")
end
end
protected
# http://www.informit.com/articles/article.aspx?p=683059&seqNum=36
def levenshtein_distance(this, that, ins = 2, del = 2, sub = 1)
# ins, del, sub are weighted costs
return nil if this.nil?
return nil if that.nil?
dm = [] # distance matrix
# Initialize first row values
dm[0] = (0..this.length).collect {|i| i * ins }
fill = [0] * (this.length - 1)
# Initialize first column values
for i in 1..that.length
dm[i] = [i * del, fill.flatten]
end
# populate matrix
for i in 1..that.length
for j in 1..this.length
# critical comparison
dm[i][j] = [
dm[i-1][j-1] +
(this[j-1] == that[i-1] ? 0 : sub),
dm[i][j-1] + ins,
dm[i-1][j] + del
].min
end
end
# The last value in matrix is the Levenshtein distance between the strings
dm[that.length][this.length]
end
end
end
|
