fuzzy_match 1.3.3 → 1.4.0

data/CHANGELOG

@@ -1,4 +1,16 @@
-== 1.3.3 / 2012-04-13
+1.4.0 / 2012-09-07
+
+* Breaking changes
+
+  * Option keys are no longer symbolized automatically - make sure you do that if there's any chance they'll be strings
+  * active_record_inline_schema is no longer a runtime dependency - add it to your Gemfile if you use FuzzyMatch::CachedResult
+
+* Enhancements
+
+  * Tiny bit better #explain(needle)
+  * Remove dependency on ActiveSupport
+
+1.3.3 / 2012-04-13
 
 * Enhancements
 
@@ -7,7 +19,7 @@
   * Test against CohortAnalysis, the replacement for CohortScope
   * Fix some other random deprecations (like set_primary_key)
 
-== 1.3.2 / 2012-02-24
+1.3.2 / 2012-02-24
 
 * Enhancements
 

data/Gemfile

@@ -1,18 +1,3 @@
 source :rubygems
 
 gemspec
-
-# bin dependencies
-gem 'remote_table'
-gem 'thor'
-
-# development dependencies
-gem 'minitest-reporters'
-gem "minitest"
-gem 'activerecord', '>=3'
-gem 'mysql2'
-gem 'cohort_analysis'
-gem 'weighted_average'
-gem 'rake'
-gem 'yard'
-gem 'amatch'

data/README.markdown

@@ -4,6 +4,21 @@ Find a needle in a haystack based on string similarity and regular expression ru
 
 Replaces [`loose_tight_dictionary`](https://github.com/seamusabshere/loose_tight_dictionary) because that was a confusing name.
 
+## Real-world usage
+
+<p><a href="http://brighterplanet.com"><img src="https://s3.amazonaws.com/static.brighterplanet.com/assets/logos/flush-left/inline/green/rasterized/brighter_planet-160-transparent.png" alt="Brighter Planet logo"/></a></p>
+
+We use `fuzzy_match` for [data science at Brighter Planet](http://brighterplanet.com/research) and in production at
+
+* [Brighter Planet's impact estimate web service](http://impact.brighterplanet.com)
+* [Brighter Planet's reference data web service](http://data.brighterplanet.com)
+
+We often combine it with [`remote_table`](https://github.com/seamusabshere/remote_table) and [`errata`](https://github.com/seamusabshere/errata):
+
+- download table with `remote_table`
+- correct serious or repeated errors with `errata`
+- `fuzzy_match` the rest
+
 ## Quickstart
 
     >> require 'fuzzy_match'
@@ -114,18 +129,10 @@ In edge cases where Dice's finds that two strings are equally similar to a third
     >> 'RITZ'.levenshtein_similar 'CATZ'
     => 0.5                                  # which properly shows that RATZ should win
 
-## Production use
-
-Over 2 years in [Brighter Planet's impact estimate API](http://impact.brighterplanet.com) and [reference data service](http://data.brighterplanet.com).
-
-We often combine `fuzzy_match` with [`remote_table`](https://github.com/seamusabshere/remote_table) and [`errata`](https://github.com/seamusabshere/errata):
-
-- download table with `remote_table`
-- correct serious or repeated errors with `errata`
-- `fuzzy_match` the rest
-
 ## Cached results
 
+Make sure you add active\_record\_inline\_schema to your gemfile.
+
 TODO write documentation. For now, please see how [we manually cache matches between aircraft and flight segments](https://github.com/brighterplanet/earth/blob/master/lib/earth/air/aircraft.rb).
 
 ## Glossary

data/bin/fuzzy_match_checker

@@ -1,10 +1,14 @@
 #!/usr/bin/env ruby
 
-if File.exist?(File.join(Dir.pwd, 'fuzzy_match.gemspec'))
-  require 'bundler/setup'
+if File.exist?(File.join(Dir.pwd, 'lib', 'fuzzy_match.rb'))
+  $LOAD_PATH.unshift File.join(Dir.pwd, 'lib')
+  require File.join(Dir.pwd, 'lib', 'fuzzy_match')
+else
+  require 'fuzzy_match'
 end
+require 'fuzzy_match/version'
 
-require 'fuzzy_match'
+# note: not included in gemfile but neither is bundler used here
 require 'active_support/core_ext'
 require 'remote_table'
 require 'thor'
@@ -52,6 +56,7 @@ class FuzzyMatch
         end
         unless match == correct_match
           puts "MISMATCH: #{needle.inspect} should match #{correct_match.inspect}"
+          puts fm.explain needle
           exit 1
         end
         count += 1

data/fuzzy_match.gemspec

@@ -17,7 +17,20 @@ Gem::Specification.new do |s|
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
 
-  s.add_runtime_dependency 'activesupport', '>=3'
   s.add_runtime_dependency 'to_regexp', '>=0.0.3'
-  s.add_runtime_dependency 'active_record_inline_schema', '>=0.4.0'
+  
+  # needed if you use FuzzyMatch::CachedResult
+  s.add_development_dependency 'active_record_inline_schema', '>=0.4.0'
+
+  # development dependencies
+  s.add_development_dependency "minitest"
+  s.add_development_dependency 'activerecord', '>=3'
+  s.add_development_dependency 'mysql2'
+  s.add_development_dependency 'cohort_analysis'
+  s.add_development_dependency 'weighted_average'
+  s.add_development_dependency 'yard'
+  s.add_development_dependency 'amatch'
+  if RUBY_VERSION >= '1.9'
+    s.add_development_dependency 'minitest-reporters'
+  end
 end

data/lib/fuzzy_match.rb

@@ -1,8 +1,3 @@
-require 'active_support'
-require 'active_support/version'
-if ::ActiveSupport::VERSION::MAJOR >= 3
-  require 'active_support/core_ext'
-end
 require 'to_regexp'
 
 require 'fuzzy_match/rule'
@@ -19,11 +14,11 @@ require 'fuzzy_match/score'
 class FuzzyMatch
   class << self
     def engine
-      @@engine ||= :pure_ruby
+      @engine
     end
     
     def engine=(alt_engine)
-      @@engine = alt_engine
+      @engine = alt_engine
     end
     
     def score_class
@@ -47,6 +42,8 @@ class FuzzyMatch
     :gather_last_result => false,
     :find_all => false
   }
+
+  self.engine = DEFAULT_ENGINE
   
   attr_reader :haystack
   attr_reader :groupings
@@ -71,7 +68,7 @@ class FuzzyMatch
   # * :<tt>first_grouping_decides</tt> - force records into the first grouping they match, rather than choosing a grouping that will give them a higher score
   # * :<tt>gather_last_result</tt> - enable <tt>last_result</tt>
   def initialize(competitors, options_and_rules = {})
-    options_and_rules = options_and_rules.symbolize_keys
+    options_and_rules = options_and_rules.dup
 
     # rules
     self.groupings = options_and_rules.delete(:groupings) || options_and_rules.delete(:blockings) || []
@@ -87,7 +84,7 @@ class FuzzyMatch
     if deprecated = options_and_rules.delete(:must_match_blocking)
       options_and_rules[:must_match_grouping] = deprecated
     end
-    @default_options = options_and_rules.reverse_merge(DEFAULT_OPTIONS).freeze
+    @default_options = DEFAULT_OPTIONS.merge(options_and_rules).freeze
 
     # do this last
     self.haystack = competitors
@@ -118,12 +115,12 @@ class FuzzyMatch
   end
   
   def find_all(needle, options = {})
-    options = options.symbolize_keys.merge(:find_all => true)
+    options = options.merge(:find_all => true)
     find needle, options
   end
   
   def find(needle, options = {})
-    options = options.symbolize_keys.reverse_merge default_options
+    options = default_options.merge options
     
     gather_last_result = options[:gather_last_result]
     is_find_all = options[:find_all]
@@ -193,7 +190,9 @@ EOS
     if groupings.any?
       joint = passed_word_requirement.select do |straw|
         if first_grouping_decides
-          groupings.detect { |grouping| grouping.match? needle }.try :join?, needle, straw
+          if first_grouping = groupings.detect { |grouping| grouping.match? needle }
+            first_grouping.join? needle, straw
+          end
         else
           groupings.any? { |grouping| grouping.join? needle, straw }
         end
@@ -237,21 +236,21 @@ EOS
       if gather_last_result
         last_result.timeline << <<-EOS
 Since there were identities, the competition was reduced to records that might be identical to the needle (in other words, are not certainly different)
-\Identities (first 3): #{identities[0,3].map(&:inspect).join(', ')}
-\tPassed (first 3): #{possibly_identical[0,3].map(&:render).map(&:inspect).join(', ')}
-\tFailed (first 3): #{(joint-possibly_identical)[0,3].map(&:render).map(&:inspect).join(', ')}
+\tIdentities (first 10 of #{identities.length}): #{identities[0,9].map(&:inspect).join(', ')}
+\tPassed (first 10 of #{possibly_identical.length}): #{possibly_identical[0,9].map(&:render).map(&:inspect).join(', ')}
+\tFailed (first 10 of #{(joint-possibly_identical).length}): #{(joint-possibly_identical)[0,9].map(&:render).map(&:inspect).join(', ')}
 EOS
       end
     else
       possibly_identical = joint.dup
     end
-        
+    
     similarities = possibly_identical.map { |straw| needle.similarity straw }.sort.reverse
         
     if gather_last_result
-        last_result.timeline << <<-EOS
+      last_result.timeline << <<-EOS
 The competition was sorted in order of similarity to the needle.
-\tSimilar (first 3): #{(similarities)[0,3].map(&:wrapper2).map(&:render).map(&:inspect).join(', ')}
+\tSimilar (first 10 of #{similarities.length}): #{similarities[0,9].map { |s| "#{s.wrapper2.render.inspect} (#{[s.best_score.dices_coefficient_similar, s.best_score.levenshtein_similar].map { |v| '%0.5f' % v }.join('/')})" }.join(', ')}
 EOS
     end
     
@@ -272,8 +271,11 @@ A winner was determined because the Dice's Coefficient similarity (#{best_simila
 EOS
       end
     elsif gather_last_result
-        last_result.timeline << <<-EOS
-No winner assigned because the score of the best similarity (#{best_similarity.try(:wrapper2).try(:record).try(:inspect)}) was zero and it didn't match any words with the needle (#{needle.inspect}).
+      best_similarity_record = if best_similarity and best_similarity.wrapper2
+        best_similarity.wrapper2.record
+      end
+      last_result.timeline << <<-EOS
+No winner assigned because the score of the best similarity (#{best_similarity_record.inspect}) was zero and it didn't match any words with the needle (#{needle.inspect}).
 EOS
     end
     

data/lib/fuzzy_match/result.rb

@@ -19,10 +19,6 @@ The haystack contained <%= haystack.length %> records like <%= haystack[0, 3].ma
 <% end %>
 ERB
 
-    def timeline
-      @timeline ||= []
-    end
-
     attr_accessor :needle
     attr_accessor :read
     attr_accessor :haystack
@@ -33,6 +29,11 @@ ERB
     attr_accessor :stop_words
     attr_accessor :winner
     attr_accessor :score
+    attr_reader :timeline
+
+    def initialize
+      @timeline = []
+    end
     
     def explain
       $stdout.puts ::ERB.new(EXPLANATION, 0, '%<').result(binding)

data/lib/fuzzy_match/score/pure_ruby.rb

@@ -10,84 +10,81 @@ class FuzzyMatch
 
       # http://stackoverflow.com/questions/653157/a-better-similarity-ranking-algorithm-for-variable-length-strings
       def dices_coefficient_similar
-        return @dices_coefficient_similar if @dices_coefficient_similar.is_a?(::Float)
-      
-        if str1 == str2
-          @dices_coefficient_similar = 1.0
-          return @dices_coefficient_similar
-        elsif str1.length == 1 and str2.length == 1
-          @dices_coefficient_similar = 0.0
-          return @dices_coefficient_similar
-        end
-      
-        pairs1 = (0..str1.length-2).map do |i|
-          str1[i,2]
-        end.reject do |pair|
-          pair.include? SPACE
-        end
-        pairs2 = (0..str2.length-2).map do |i|
-          str2[i,2]
-        end.reject do |pair|
-          pair.include? SPACE
-        end
-        union = pairs1.size + pairs2.size
-        intersection = 0
-        pairs1.each do |p1|
-          0.upto(pairs2.size-1) do |i|
-            if p1 == pairs2[i]
-              intersection += 1
-              pairs2.slice!(i)
-              break
+        @dices_coefficient_similar ||= begin
+          if str1 == str2
+            1.0
+          elsif str1.length == 1 and str2.length == 1
+            0.0
+          else
+            pairs1 = (0..str1.length-2).map do |i|
+              str1[i,2]
+            end.reject do |pair|
+              pair.include? SPACE
+            end
+            pairs2 = (0..str2.length-2).map do |i|
+              str2[i,2]
+            end.reject do |pair|
+              pair.include? SPACE
+            end
+            union = pairs1.size + pairs2.size
+            intersection = 0
+            pairs1.each do |p1|
+              0.upto(pairs2.size-1) do |i|
+                if p1 == pairs2[i]
+                  intersection += 1
+                  pairs2.slice!(i)
+                  break
+                end
+              end
             end
+            (2.0 * intersection) / union
           end
         end
-        @dices_coefficient_similar = (2.0 * intersection) / union
       end
 
       # extracted/adapted from the text gem version 1.0.2
       # normalization added for utf-8 strings
       # lib/text/levenshtein.rb
       def levenshtein_similar
-        return @levenshtein_similar if @levenshtein_similar.is_a?(::Float)
-      
-        if utf8?
-          unpack_rule = 'U*'
-        else
-          unpack_rule = 'C*'
-        end
-        s = str1.unpack(unpack_rule)
-        t = str2.unpack(unpack_rule)
-        n = s.length
-        m = t.length
-      
-        if n == 0 or m == 0
-          @levenshtein_similar = 0.0
-          return @levenshtein_similar
-        end
-      
-        d = (0..m).to_a
-        x = nil
-        (0...n).each do |i|
-          e = i+1
-          (0...m).each do |j|
-            cost = (s[i] == t[j]) ? 0 : 1
-            x = [
-              d[j+1] + 1, # insertion
-              e + 1,      # deletion
-              d[j] + cost # substitution
-            ].min
-            d[j] = e
-            e = x
+        @levenshtein_similar ||= begin
+          if utf8?
+            unpack_rule = 'U*'
+          else
+            unpack_rule = 'C*'
+          end
+          s = str1.unpack(unpack_rule)
+          t = str2.unpack(unpack_rule)
+          n = s.length
+          m = t.length
+        
+          if n == 0 or m == 0
+            0.0
+          else
+            d = (0..m).to_a
+            x = nil
+            (0...n).each do |i|
+              e = i+1
+              (0...m).each do |j|
+                cost = (s[i] == t[j]) ? 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
+            # normalization logic from https://github.com/flori/amatch/blob/master/ext/amatch_ext.c#L301
+            # if (b_len > a_len) {
+            #     result = rb_float_new(1.0 - ((double) v[p][b_len]) / b_len);
+            # } else {
+            #     result = rb_float_new(1.0 - ((double) v[p][b_len]) / a_len);
+            # }
+            1.0 - x.to_f / [n, m].max
           end
-          d[m] = x
         end
-        # normalization logic from https://github.com/flori/amatch/blob/master/ext/amatch_ext.c#L301
-        # if (b_len > a_len) {
-        #     result = rb_float_new(1.0 - ((double) v[p][b_len]) / b_len);
-        # } else {
-        #     result = rb_float_new(1.0 - ((double) v[p][b_len]) / a_len);
-        # }
-        @levenshtein_similar = 1.0 - x.to_f / [n, m].max
       end
 
       private

data/lib/fuzzy_match/similarity.rb

@@ -17,15 +17,21 @@ class FuzzyMatch
       end
     end
     
+    def best_score
+      @best_score ||= FuzzyMatch.score_class.new(best_wrapper1_variant, best_wrapper2_variant)
+    end
+
+    def inspect
+      %{#<FuzzyMatch::Similarity #{wrapper2.render.inspect}=>#{best_wrapper2_variant.inspect} versus #{wrapper1.render.inspect}=>#{best_wrapper1_variant.inspect} original_weight=#{"%0.5f" % original_weight} best_score=#{best_score.inspect}>}
+    end
+
     # Weight things towards short original strings
     def original_weight
       @original_weight ||= (1.0 / (wrapper1.render.length * wrapper2.render.length))
     end
-    
-    def best_score
-      @best_score ||= FuzzyMatch.score_class.new best_wrapper1_variant, best_wrapper2_variant
-    end
-    
+
+    private
+        
     def best_wrapper1_variant
       best_variants[0]
     end
@@ -35,19 +41,15 @@ class FuzzyMatch
     end
     
     def best_variants
-      @best_variants ||= wrapper1.variants.product(wrapper2.variants).sort do |tuple1, tuple2|
-        wrapper1_variant1, wrapper2_variant1 = tuple1
-        wrapper1_variant2, wrapper2_variant2 = tuple2
-
-        score1 = FuzzyMatch.score_class.new wrapper1_variant1, wrapper2_variant1
-        score2 = FuzzyMatch.score_class.new wrapper1_variant2, wrapper2_variant2
-        
-        score1 <=> score2
-      end[-1]
-    end
-    
-    def inspect
-      %{#<FuzzyMatch::Similarity #{wrapper2.render.inspect}=>#{best_wrapper2_variant.inspect} versus #{wrapper1.render.inspect}=>#{best_wrapper1_variant.inspect} original_weight=#{"%0.5f" % original_weight} best_score=#{best_score.inspect}>}
+      @best_variants ||= begin
+        wrapper1.variants.product(wrapper2.variants).sort do |tuple1, tuple2|
+          wrapper1_variant1, wrapper2_variant1 = tuple1
+          wrapper1_variant2, wrapper2_variant2 = tuple2
+          score1 = FuzzyMatch.score_class.new wrapper1_variant1, wrapper2_variant1
+          score2 = FuzzyMatch.score_class.new wrapper1_variant2, wrapper2_variant2
+          score1 <=> score2
+        end.last
+      end
     end
   end
 end

data/lib/fuzzy_match/version.rb

@@ -1,3 +1,3 @@
 class FuzzyMatch
-  VERSION = '1.3.3'
+  VERSION = '1.4.0'
 end

data/lib/fuzzy_match/wrapper.rb

@@ -1,6 +1,11 @@
 class FuzzyMatch
   # Wrappers are the tokens that are passed around when doing scoring and optimizing.
   class Wrapper #:nodoc: all
+    # "Foo's" is one word
+    # "North-west" is just one word
+    # "Bolivia," is just Bolivia
+    WORD_BOUNDARY = %r{\W*(?:\s+|$)}
+
     attr_reader :fuzzy_match
     attr_reader :record
     attr_reader :literal
@@ -21,36 +26,31 @@ class FuzzyMatch
     end
 
     def render
-      return @render if rendered
-      str = case read
-      when ::Proc
-        read.call record
-      when ::Symbol
-        if record.respond_to?(read)
-          record.send read
+      @render ||= begin
+        memo = case read
+        when ::Proc
+          read.call record
+        when ::Symbol
+          if record.respond_to?(read)
+            record.send read
+          else
+            record[read]
+          end
+        when ::NilClass
+          record
         else
           record[read]
+        end.to_s.dup
+        fuzzy_match.stop_words.each do |stop_word|
+          stop_word.apply! memo
         end
-      when ::NilClass
-        record
-      else
-        record[read]
-      end.to_s.dup
-      fuzzy_match.stop_words.each do |stop_word|
-        stop_word.apply! str
+        memo.strip!
+        @render = memo.freeze
       end
-      str.strip!
-      @render = str.freeze
-      @rendered = true
-      @render
     end
 
     alias :to_str :render
 
-    # "Foo's" is one word
-    # "North-west" is just one word
-    # "Bolivia," is just Bolivia
-    WORD_BOUNDARY = %r{\W*(?:\s+|$)}
     def words
       @words ||= render.downcase.split(WORD_BOUNDARY)
     end
@@ -60,12 +60,14 @@ class FuzzyMatch
     end
 
     def variants
-      @variants ||= fuzzy_match.normalizers.inject([ render ]) do |memo, normalizer|
-        if normalizer.apply? render
-          memo.push normalizer.apply(render)
-        end
-        memo
-      end.uniq
+      @variants ||= begin
+        fuzzy_match.normalizers.inject([ render ]) do |memo, normalizer|
+          if normalizer.apply? render
+            memo << normalizer.apply(render)
+          end
+          memo
+        end.uniq
+      end
     end
   end
 end

data/test/helper.rb

@@ -3,10 +3,10 @@ require 'bundler'
 Bundler.setup
 require 'minitest/spec'
 require 'minitest/autorun'
-require 'minitest/reporters'
-MiniTest::Unit.runner = MiniTest::SuiteRunner.new
-MiniTest::Unit.runner.reporters << MiniTest::Reporters::SpecReporter.new
 
-$LOAD_PATH.unshift(File.dirname(__FILE__))
-$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+if RUBY_VERSION >= '1.9'
+  require 'minitest/reporters'
+  MiniTest::Reporters.use! MiniTest::Reporters::SpecReporter.new
+end
+
 require 'fuzzy_match'

data/test/test_cache.rb

@@ -1,6 +1,5 @@
 require 'helper'
 
-require 'active_support/all'
 require 'active_record'
 require 'cohort_analysis'
 require 'weighted_average'
@@ -25,6 +24,7 @@ require 'fuzzy_match/cached_result'
 ::FuzzyMatch::CachedResult.setup(true)
 
 class Aircraft < ActiveRecord::Base
+  MUTEX = ::Mutex.new
   self.primary_key = 'icao_code'
   
   cache_fuzzy_match_with :flight_segments, :primary_key => :aircraft_description, :foreign_key => :aircraft_description
@@ -34,7 +34,9 @@ class Aircraft < ActiveRecord::Base
   end
   
   def self.fuzzy_match
-    @fuzzy_match ||= FuzzyMatch.new all, :read => ::Proc.new { |straw| straw.aircraft_description }
+    @fuzzy_match || MUTEX.synchronize do
+      @fuzzy_match||= FuzzyMatch.new(all, :read => ::Proc.new { |straw| straw.aircraft_description })
+    end
   end
   
   def self.create_table
@@ -115,7 +117,8 @@ describe FuzzyMatch::CachedResult do
   
   it %{works with cohort_scope (albeit rather clumsily)} do
     aircraft = Aircraft.find('B742')
-    FlightSegment.cohort({:aircraft_description => aircraft.flight_segments_foreign_keys}, :minimum_size => 2).count.must_equal 2
+    cohort = FlightSegment.cohort({:aircraft_description => aircraft.flight_segments_foreign_keys}, :minimum_size => 2)
+    FlightSegment.connection.select_value(cohort.project('COUNT(*)').to_sql).must_equal 2
     # FlightSegment.cohort(:aircraft_description => aircraft.flight_segments_foreign_keys).must_equal []
   end
   

data/test/test_fuzzy_match.rb

@@ -12,11 +12,6 @@ describe FuzzyMatch do
       d.find('X').must_equal 'X'
       d.find('A').must_be_nil
     end
-
-    it %{does the right thing} do
-      d = FuzzyMatch.new [ 'Artyom Makarov', 'Karl' ], :must_match_at_least_one_word => true
-      puts d.explain('art')#.must_equal 'Artyom Makarov'
-    end
   
     it %{not return any result if the maximum score is zero} do
       FuzzyMatch.new(['a']).find('b').must_be_nil

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fuzzy_match
 version: !ruby/object:Gem::Version
-  version: 1.3.3
+  version: 1.4.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,18 +9,66 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-13 00:00:00.000000000 Z
+date: 2012-09-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: activesupport
+  name: to_regexp
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '3'
+        version: 0.0.3
   type: :runtime
   prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.0.3
+- !ruby/object:Gem::Dependency
+  name: active_record_inline_schema
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.4.0
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: activerecord
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '3'
+  type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
@@ -28,37 +76,101 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3'
 - !ruby/object:Gem::Dependency
-  name: to_regexp
+  name: mysql2
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.0.3
-  type: :runtime
+        version: '0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.0.3
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: active_record_inline_schema
+  name: cohort_analysis
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.4.0
-  type: :runtime
+        version: '0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.4.0
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: weighted_average
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: amatch
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest-reporters
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Find a needle in a haystack using string similarity and (optionally)
   regexp rules. Replaces loose_tight_dictionary.
 email:
@@ -68,7 +180,6 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- .document
 - .gitignore
 - CHANGELOG
 - Gemfile
@@ -139,7 +250,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: fuzzy_match
-rubygems_version: 1.8.21
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Find a needle in a haystack using string similarity and (optionally) regexp

data/.document

@@ -1,5 +0,0 @@
-README.rdoc
-lib/**/*.rb
-bin/*
-features/**/*.feature
-LICENSE