Detect similar strings from a list in a file. using the Fuzzy Match gem

detect_duplicates.rb

#!/usr/bin/env ruby

require 'ostruct'
require 'fuzzy_match'

file_name = ARGV[0] || 'names.txt'
threshold = ARGV[1].to_i || 0.7

strs    = File.readlines(file_name).collect {|s| s.strip }
matches = strs.collect{|s|
            OpenStruct.new(
              :str   => s,
              :match => FuzzyMatch.new(strs - [s])
                                  .find_with_score(s)
            )
          }
interesting = matches.select{|m| m.match[1] > threshold
interesting.each {|m| puts "#{m.str},#{m.match[0]}" }