mirror of
https://github.com/rails/rails.git
synced 2022-11-09 12:12:34 -05:00
f7ba69436a
Calculating ------------------------------------- each_char 924.000 i/100ms each_codepoint 1.381k i/100ms ------------------------------------------------- each_char 9.320k (¡Þ 5.1%) i/s - 47.124k each_codepoint 13.857k (¡Þ 3.6%) i/s - 70.431k Comparison: each_codepoint: 13857.4 i/s each_char: 9319.5 i/s - 1.49x slower The full report can be found here: https://gist.github.com/yuki24/a80988f35aceac76f1d5
40 lines
923 B
Ruby
40 lines
923 B
Ruby
module RailsGuides
|
|
module Levenshtein
|
|
# This code is based directly on the Text gem implementation
|
|
# Returns a value representing the "cost" of transforming str1 into str2
|
|
def self.distance str1, str2
|
|
s = str1
|
|
t = str2
|
|
n = s.length
|
|
m = t.length
|
|
|
|
return m if (0 == n)
|
|
return n if (0 == m)
|
|
|
|
d = (0..m).to_a
|
|
x = nil
|
|
|
|
# avoid duplicating an enumerable object in the loop
|
|
str2_codepoint_enumerable = str2.each_codepoint
|
|
|
|
str1.each_codepoint.with_index do |char1, i|
|
|
e = i+1
|
|
|
|
str2_codepoint_enumerable.with_index do |char2, j|
|
|
cost = (char1 == char2) ? 0 : 1
|
|
x = [
|
|
d[j+1] + 1, # insertion
|
|
e + 1, # deletion
|
|
d[j] + cost # substitution
|
|
].min
|
|
d[j] = e
|
|
e = x
|
|
end
|
|
|
|
d[m] = x
|
|
end
|
|
|
|
return x
|
|
end
|
|
end
|
|
end
|