fuzzyFindStringsInTwoArraysUsingLevenshtein.rb

require 'json'
require 'levenshtein'

# Given two files with lists (one item per line) see if you can fuzzy match strings between the two.
# Only prints out matching strings and the match distance (lower is better, scale is normalized 0.0-1.0)

shortList = []

File.open("shortList", "r") do |f|
  f.each_line do |v|
    shortList << v
  end
end

File.open("longList", "r") do |f|
  f.each_line do |s|
    shortList.each do |v|
      d = Levenshtein.normalized_distance(v, s)
      puts "#{v} matches #{s} --distance #{d}" if d < 0.25 # for my data 0.25 was a good cutoff for fuzzy matches
    end
  end
end