populate gem

.rubocop.yml

@@ -0,0 +1,22 @@
+AllCops:
+  TargetRubyVersion: 2.4
+Metrics/AbcSize:
+  Enabled: false
+Metrics/CyclomaticComplexity:
+  Enabled: false
+Metrics/MethodLength:
+  Enabled: false
+Metrics/PerceivedComplexity:
+  Enabled: false
+Metrics/BlockLength:
+  Exclude:
+    - "tasks/**/*.rake"
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+Layout/AlignParameters:
+  EnforcedStyle: with_fixed_indentation
+Layout/MultilineMethodCallIndentation:
+  EnforcedStyle: indented
+Layout/MultilineOperationIndentation:
+  EnforcedStyle: indented

.yardopts

@@ -0,0 +1 @@
+-m markdown - LICENSE.txt

Gemfile

@@ -1,6 +1,8 @@
+# frozen_string_literal: true
+
 source "https://rubygems.org"
 
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in edits.gemspec
 gemspec

README.md

@@ -1,8 +1,8 @@
 # Edits
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/edits`. To experiment with that code, run `bin/console` for an interactive prompt.
+A collection of edit distance algorithms in Ruby.
 
-TODO: Delete this and the text above, and describe your gem
+Includes Levenshtein, Restricted Edit (Optimal Alignment) and Damerau-Levenshtein distances, and Jaro and Jaro-Winkler similarity.
 
 ## Installation
 
@@ -22,7 +22,66 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+### Levenshtein
+
+Edit distance, accounting for deletion, addition and substitution.
+
+```ruby
+Edits::Levenshtein.distance "raked", "bakers"
+# => 3
+Edits::Levenshtein.distance "iota", "atom"
+# => 4
+Edits::Levenshtein.distance "acer", "earn"
+# => 4
+
+# Max distance
+Edits::Levenshtein.distance_with_max "iota", "atom", 2
+# => 2
+Edits::Levenshtein.most_similar "atom", %w[tram atlas rota racer]
+# => "atlas"
+```
+
+### Restricted Edit (Optimal Alignment)
+
+Edit distance, accounting for deletion, addition, substitution and swapped
+characters.
+
+```ruby
+Edits::RestrictedEdit.distance "raked", "bakers"
+# => 3
+Edits::RestrictedEdit.distance "iota", "atom"
+# => 3
+Edits::RestrictedEdit.distance "acer", "earn"
+# => 4
+```
+
+### Damerau-Levenshtein
+
+Edit distance, accounting for deletions, additions, substitution and
+transposition.
+
+```ruby
+Edits::DamerauLevenshtein.distance "raked", "bakers"
+# => 3
+Edits::DamerauLevenshtein.distance "iota", "atom"
+# => 3
+Edits::DamerauLevenshtein.distance "acer", "earn"
+# => 3
+```
+
+### Jaro & Jaro-Winkler
+
+```ruby
+Edits::Jaro.similarity "information", "informant"
+# => 0.90235690235690236
+Edits::Jaro.distance "information", "informant"
+# => 0.097643097643097643
+
+Edits::JaroWinkler.similarity "information", "informant"
+# => 0.94141414141414137
+Edits::JaroWinkler.distance "information", "informant"
+# => 0.05858585858585863
+```
 
 ## Development
 
@@ -32,7 +91,7 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/edits.
+Bug reports and pull requests are welcome on GitHub at https://github.com/tcrouch/edits.
 
 ## License
 

Rakefile

@@ -1,6 +1,10 @@
+# frozen_string_literal: true
+
 require "bundler/gem_tasks"
 require "rspec/core/rake_task"
 
+Dir["tasks/**/*.rake"].each { |t| load t }
+
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

bin/console

@@ -1,4 +1,5 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
 require "bundler/setup"
 require "edits"

edits.gemspec

@@ -1,4 +1,5 @@
-# coding: utf-8
+# frozen_string_literal: true
+
 lib = File.expand_path("../lib", __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "edits/version"
@@ -9,21 +10,12 @@ Gem::Specification.new do |spec|
   spec.authors       = ["Tom Crouch"]
   spec.email         = ["[email protected]"]
 
-  spec.summary       = %q{TODO: Write a short summary, because Rubygems requires one.}
-  spec.description   = %q{TODO: Write a longer description or delete this line.}
-  spec.homepage      = "TODO: Put your gem's website or public repo URL here."
+  spec.summary       = "A collection of edit distance algorithms."
+  # spec.description   = "TODO: Write a longer description or delete this line."
+  spec.homepage      = "https://github.com/tcrouch/edits"
   spec.license       = "MIT"
 
-  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
-  # to allow pushing to a single host or delete this section to allow pushing to any host.
-  if spec.respond_to?(:metadata)
-    spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
-  else
-    raise "RubyGems 2.0 or newer is required to protect against " \
-      "public gem pushes."
-  end
-
-  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+  spec.files = `git ls-files -z`.split("\x0").reject do |f|
     f.match(%r{^(test|spec|features)/})
   end
   spec.bindir        = "exe"
@@ -32,5 +24,8 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.15"
   spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "rspec", "~> 3.6"
+  spec.add_development_dependency "benchmark-ips"
+  spec.add_development_dependency "redcarpet"
+  spec.add_development_dependency "yard", "~> 0.9.9"
 end

lib/edits.rb

@@ -1,5 +1,15 @@
+# frozen_string_literal: true
+
 require "edits/version"
 
+require "edits/damerau_levenshtein"
+require "edits/hamming"
+require "edits/jaro"
+require "edits/jaro_winkler"
+require "edits/levenshtein"
+require "edits/restricted_edit"
+
+# A collection of edit distance algorithms
 module Edits
   # Your code goes here...
 end

lib/edits/damerau_levenshtein.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+module Edits
+  # Implemention of the Damerau/Levenshtein distance algorithm.
+  #
+  # Determines distance between two strings by counting edits, identifying:
+  # * Insertion
+  # * Deletion
+  # * Substitution
+  # * Transposition
+  module DamerauLevenshtein
+    # Calculate the Damerau/Levenshtein distance of two sequences.
+    #
+    # @example
+    #   DamerauLevenshtein.distance("acer", "earn")
+    #   # => 3
+    # @param seq1 [String, Array]
+    # @param seq2 [String, Array]
+    # @return [Integer]
+    def self.distance(seq1, seq2)
+      if seq1.length > seq2.length
+        temp = seq1
+        seq1 = seq2
+        seq2 = temp
+      end
+
+      # array of Integer codepoints outperforms String
+      seq1 = seq1.codepoints if seq1.is_a? String
+      seq2 = seq2.codepoints if seq2.is_a? String
+
+      rows = seq1.length
+      cols = seq2.length
+      return cols if rows.zero?
+      return rows if cols.zero?
+
+      # 'infinite' edit distance for padding cost matrix.
+      # Can be any value greater than max[rows, cols]
+      inf = rows + cols
+
+      # Initialize first two rows of cost matrix.
+      # The full initial state where cols=3, rows=2 (inf=5) would be:
+      #   [[5, 5, 5, 5, 5],
+      #    [5, 0, 1, 2, 3],
+      #    [5, 1, 0, 0, 0],
+      #    [5, 2, 0, 0, 0]]
+      matrix = [Array.new(cols + 2, inf)]
+      matrix << 0.upto(cols).to_a.unshift(inf)
+
+      # element => last row seen
+      item_history = Hash.new(0)
+
+      1.upto(rows) do |row|
+        # generate next row of cost matrix
+        new_row = Array.new(cols + 2, 0)
+        new_row[0] = inf
+        new_row[1] = row
+        matrix << new_row
+
+        last_match_col = 0
+        seq1_item = seq1[row - 1]
+
+        1.upto(cols) do |col|
+          seq2_item = seq2[col - 1]
+          last_match_row = item_history[seq2_item]
+
+          sub_cost = seq1_item == seq2_item ? 0 : 1
+
+          transposition = 1 + matrix[last_match_row][last_match_col]
+          transposition += row - last_match_row - 1
+          transposition += col - last_match_col - 1
+
+          # TODO: do insertion/deletion need to be considered when
+          # seq1_item == seq2_item ?
+          deletion = matrix[row][col + 1] + 1
+          insertion = matrix[row + 1][col] + 1
+          substitution = matrix[row][col] + sub_cost
+
+          # step cost is min of operation costs
+          cost = substitution < insertion ? substitution : insertion
+          cost = deletion if deletion < cost
+          cost = transposition if transposition < cost
+
+          matrix[row + 1][col + 1] = cost
+
+          last_match_col = col if sub_cost.zero?
+        end
+
+        item_history[seq1_item] = row
+      end
+
+      matrix[rows + 1][cols + 1]
+    end
+  end
+end

lib/edits/hamming.rb

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+module Edits
+  # @see https://en.wikipedia.org/wiki/Hamming_distance
+  module Hamming
+    # Calculate the Hamming distance between two sequences.
+    #
+    # @note A true distance metric, satisfies triangle inequality.
+    #
+    # @param seq1 [String, Array]
+    # @param seq2 [String, Array]
+    # @return [Integer] Hamming distance
+    def self.distance(seq1, seq2)
+      # if seq1.is_a?(Integer) && seq2.is_a?(Integer)
+      #   return (seq1 ^ seq2).to_s(2).count("1")
+      # end
+
+      length = seq1.length < seq2.length ? seq1.length : seq2.length
+      diff = (seq1.length - seq2.length).abs
+
+      length.times.reduce(diff) do |distance, i|
+        seq1[i] == seq2[i] ? distance : distance + 1
+      end
+    end
+  end
+end