Fuzzy -> FuzzyTools

Gemfile

@@ -5,5 +5,5 @@ gem 'nokogiri'
 gem 'perftools.rb', :require => false
 gem 'rake'
 
-# Specify your gem's dependencies in fuzzy.gemspec
+# Specify your gem's dependencies in fuzzy_tools.gemspec
 gemspec

Rakefile

@@ -16,7 +16,7 @@ desc "Launch an IRB session with the gem required"
 task :console do
   $:.unshift(File.dirname(__FILE__) + '/../lib')
 
-  require 'fuzzy'
+  require 'fuzzy_tools'
   require 'irb'
 
   IRB.setup(nil)

accuracy/test_accuracy.rb

@@ -1,7 +1,7 @@
 $LOAD_PATH.unshift File.expand_path("../../lib", __FILE__)
 $LOAD_PATH.unshift File.expand_path("../support", __FILE__)
 
-require 'fuzzy'
+require 'fuzzy_tools'
 require 'accuracy_test_case'
 require 'histogram'
 require 'rubygems'
@@ -19,10 +19,10 @@ class Failure < Struct.new(:given, :expected, :actual)
 ENV['CPUPROFILE_REALTIME']      = "1"
 ENV['CPUPROFILE_FREQUENCY=500'] = "50" # default is 100
 require 'perftools'
-PerfTools::CpuProfiler.start("/tmp/fuzzy_ruby_profile")
+PerfTools::CpuProfiler.start("/tmp/fuzzy_tools_ruby_profile")
 at_exit do
   PerfTools::CpuProfiler.stop
-  puts `pprof.rb --text /tmp/fuzzy_ruby_profile`
+  puts `pprof.rb --text /tmp/fuzzy_tools_ruby_profile`
 end
 
 total_time = Benchmark.realtime do

fuzzy.gemspec → fuzzy_tools.gemspec

@@ -1,14 +1,14 @@
 # -*- encoding: utf-8 -*-
 $:.push File.expand_path("../lib", __FILE__)
-require "fuzzy/version"
+require "fuzzy_tools/version"
 
 Gem::Specification.new do |s|
-  s.name        = "fuzzy"
-  s.version     = Fuzzy::VERSION
+  s.name        = "fuzzy_tools_tools"
+  s.version     = FuzzyTools::VERSION
   s.platform    = Gem::Platform::RUBY
   s.authors     = ["Brian Hempel"]
   s.email       = ["plasticchicken@gmail.com"]
-  s.homepage    = ""
+  s.homepage    = "https://github.com/brianhempel/fuzzy_tools"
   s.summary     = %q{High quality fuzzy search and string matching in Ruby.}
   s.description = %q{High quality fuzzy search and string matching in Ruby.}
 

lib/fuzzy_tools.rb

@@ -0,0 +1,4 @@
+require 'fuzzy_tools/helpers'
+require 'fuzzy_tools/index'
+require 'fuzzy_tools/tf_idf_index'
+require 'fuzzy_tools/core_ext/enumerable'

lib/fuzzy/core_ext/enumerable.rb → lib/fuzzy_tools/core_ext/enumerable.rb

@@ -1,4 +1,4 @@
-require 'fuzzy/index'
+require 'fuzzy_tools/index'
 
 module Enumerable
   def fuzzy_find(*args)
@@ -13,7 +13,7 @@ def fuzzy_find_all(*args)
 
   def fuzzy_index(options = {})
     options = options.merge(:source => self)
-    Fuzzy::TfIdfIndex.new(options)
+    FuzzyTools::TfIdfIndex.new(options)
   end
 
   private

lib/fuzzy/helpers.rb → lib/fuzzy_tools/helpers.rb

@@ -1,6 +1,6 @@
 require 'inline'
 
-module Fuzzy
+module FuzzyTools
   module Helpers
     extend self
 

lib/fuzzy/index.rb → lib/fuzzy_tools/index.rb

@@ -1,7 +1,7 @@
-require 'fuzzy/helpers'
-require 'fuzzy/tokenizers'
+require 'fuzzy_tools/helpers'
+require 'fuzzy_tools/tokenizers'
 
-module Fuzzy
+module FuzzyTools
   class Index
     attr_reader :source, :indexed_attribute
 

lib/fuzzy/tf_idf_index.rb → lib/fuzzy_tools/tf_idf_index.rb

@@ -1,8 +1,8 @@
 require 'set'
-require 'fuzzy/index'
-require 'fuzzy/weighted_document_tokens'
+require 'fuzzy_tools/index'
+require 'fuzzy_tools/weighted_document_tokens'
 
-module Fuzzy
+module FuzzyTools
   class TfIdfIndex < Index
     class Token
       attr_accessor :documents, :idf
@@ -13,7 +13,7 @@ def initialize
     end
 
     def self.default_tokenizer
-      Fuzzy::Tokenizers::HYBRID
+      FuzzyTools::Tokenizers::HYBRID
     end
 
     attr_reader :tokenizer

lib/fuzzy_tools/tokenizers.rb

@@ -0,0 +1,30 @@
+module FuzzyTools
+  module Tokenizers
+
+    CHARACTERS           = lambda { |str| str.chars }
+    CHARACTERS_DOWNCASED = lambda { |str| str.downcase.chars }
+    BIGRAMS              = lambda { |str| FuzzyTools::Helpers.ngrams(str,          2) }
+    BIGRAMS_DOWNCASED    = lambda { |str| FuzzyTools::Helpers.ngrams(str.downcase, 2) }
+    TRIGRAMS             = lambda { |str| FuzzyTools::Helpers.ngrams(str,          3) }
+    TRIGRAMS_DOWNCASED   = lambda { |str| FuzzyTools::Helpers.ngrams(str.downcase, 3) }
+    TETRAGRAMS           = lambda { |str| FuzzyTools::Helpers.ngrams(str,          4) }
+    TETRAGRAMS_DOWNCASED = lambda { |str| FuzzyTools::Helpers.ngrams(str.downcase, 4) }
+    PENTAGRAMS           = lambda { |str| FuzzyTools::Helpers.ngrams(str,          5) }
+    PENTAGRAMS_DOWNCASED = lambda { |str| FuzzyTools::Helpers.ngrams(str.downcase, 5) }
+    HEXAGRAMS            = lambda { |str| FuzzyTools::Helpers.ngrams(str,          6) }
+    HEXAGRAMS_DOWNCASED  = lambda { |str| FuzzyTools::Helpers.ngrams(str.downcase, 6) }
+
+    WORDS                = lambda { |str| str.split }
+    WORDS_DOWNCASED      = lambda { |str| str.downcase.split }
+
+    HYBRID = lambda do |str|
+      str   = str.downcase
+      words = str.split
+      words.map { |word| FuzzyTools::Helpers.soundex(word) } +
+      FuzzyTools::Helpers.ngrams(str.downcase, 2) +
+      words.map { |word| word.gsub(/[aeiou]/, '') } +
+      words
+    end
+
+  end
+end

lib/fuzzy/version.rb → lib/fuzzy_tools/version.rb

@@ -1,3 +1,3 @@
-module Fuzzy
+module FuzzyTools
   VERSION = "0.0.1"
 end

lib/fuzzy/weighted_document_tokens.rb → lib/fuzzy_tools/weighted_document_tokens.rb

@@ -1,7 +1,7 @@
-require 'fuzzy/helpers'
+require 'fuzzy_tools/helpers'
 require 'inline'
 
-module Fuzzy
+module FuzzyTools
   class WeightedDocumentTokens
     attr_reader :weights
 
@@ -57,7 +57,7 @@ def tokens
 
     def set_token_weights(tokens, &block)
       @weights = {}
-      counts = Fuzzy::Helpers.term_counts(tokens)
+      counts = FuzzyTools::Helpers.term_counts(tokens)
       counts.each do |token, n|
         @weights[token] = yield(token, n)
       end

performance/profile.rb

@@ -1,7 +1,7 @@
 require 'csv'
 
 $LOAD_PATH.unshift File.expand_path("../../lib", __FILE__)
-require 'fuzzy'
+require 'fuzzy_tools'
 
 
 TEST_FILE_PATH = File.expand_path("../query_tests/bible_verses_daniel_kjv.csv", __FILE__)
@@ -24,10 +24,10 @@
 ENV['CPUPROFILE_REALTIME']      = "1"
 ENV['CPUPROFILE_FREQUENCY=500'] = "200" # default is 100
 require 'perftools'
-PerfTools::CpuProfiler.start("/tmp/fuzzy_ruby_profile")
+PerfTools::CpuProfiler.start("/tmp/fuzzy_tools_ruby_profile")
 at_exit do
   PerfTools::CpuProfiler.stop
-  puts `pprof.rb --text /tmp/fuzzy_ruby_profile`
+  puts `pprof.rb --text /tmp/fuzzy_tools_ruby_profile`
 end
 
 index = targets.fuzzy_index

spec/enumerable_spec.rb

@@ -27,15 +27,15 @@
       before(:each) { @letter_count_tokenizer = lambda { |str| str.size.to_s } }
 
       it "passes :tokenizer through to the index with simple query syntax" do
-        Fuzzy::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer)
+        FuzzyTools::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer)
         begin
           @books.fuzzy_find("the", :tokenizer => @letter_count_tokenizer)
         rescue
         end
       end
 
       it "passes :tokenizer through to the index with :attribute => query syntax" do
-        Fuzzy::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer, :attribute => :title)
+        FuzzyTools::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer, :attribute => :title)
         begin
           @books.fuzzy_find(:title => "the", :tokenizer => @letter_count_tokenizer)
         rescue
@@ -57,15 +57,15 @@
       before(:each) { @letter_count_tokenizer = lambda { |str| str.size.to_s } }
 
       it "passes :tokenizer through to the index with simple query syntax" do
-        Fuzzy::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer)
+        FuzzyTools::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer)
         begin
           @books.fuzzy_find_all("the", :tokenizer => @letter_count_tokenizer)
         rescue
         end
       end
 
       it "passes :tokenizer through to the index with :attribute => query syntax" do
-        Fuzzy::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer, :attribute => :title)
+        FuzzyTools::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => @letter_count_tokenizer, :attribute => :title)
         begin
           @books.fuzzy_find_all(:title => "the", :tokenizer => @letter_count_tokenizer)
         rescue
@@ -76,12 +76,12 @@
 
   describe "#fuzzy_index" do
     it "returns an TfIdfIndex" do
-      @books.fuzzy_index.class.should == Fuzzy::TfIdfIndex
+      @books.fuzzy_index.class.should == FuzzyTools::TfIdfIndex
     end
 
     it "passes options along to the index" do
       letter_count_tokenizer = lambda { |str| str.size.to_s }
-      Fuzzy::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => letter_count_tokenizer, :attribute => :title)
+      FuzzyTools::TfIdfIndex.should_receive(:new).with(:source => @books, :tokenizer => letter_count_tokenizer, :attribute => :title)
       @books.fuzzy_index(:attribute => :title, :tokenizer => letter_count_tokenizer)
     end
   end

spec/helpers_spec.rb

@@ -1,10 +1,10 @@
 require 'spec_helper'
 
-describe Fuzzy::Helpers do
+describe FuzzyTools::Helpers do
   describe ".ngrams" do
 
     it "should do trigrams" do
-      Fuzzy::Helpers.trigrams("hello").should == %w{
+      FuzzyTools::Helpers.trigrams("hello").should == %w{
         __h
         _he
         hel
@@ -16,7 +16,7 @@
     end
 
     it "should do bigrams" do
-      Fuzzy::Helpers.bigrams("hello").should == %w{
+      FuzzyTools::Helpers.bigrams("hello").should == %w{
         _h
         he
         el
@@ -27,7 +27,7 @@
     end
 
     it "should do 1-grams" do
-      Fuzzy::Helpers.ngrams("hello", 1).should == %w{
+      FuzzyTools::Helpers.ngrams("hello", 1).should == %w{
         h
         e
         l
@@ -37,7 +37,7 @@
     end
 
     it "should do x-grams" do
-      Fuzzy::Helpers.ngrams("hello", 4).should == %w{
+      FuzzyTools::Helpers.ngrams("hello", 4).should == %w{
         ___h
         __he
         _hel
@@ -53,11 +53,11 @@
 
   describe ".soundex" do
     it "works" do
-      Fuzzy::Helpers.soundex("Robert").should      == "R163"
-      Fuzzy::Helpers.soundex("Rubin").should       == "R150"
-      Fuzzy::Helpers.soundex("Washington").should  == "W252"
-      Fuzzy::Helpers.soundex("Lee").should         == "L000"
-      Fuzzy::Helpers.soundex("Gutierrez").should   == "G362"
+      FuzzyTools::Helpers.soundex("Robert").should      == "R163"
+      FuzzyTools::Helpers.soundex("Rubin").should       == "R150"
+      FuzzyTools::Helpers.soundex("Washington").should  == "W252"
+      FuzzyTools::Helpers.soundex("Lee").should         == "L000"
+      FuzzyTools::Helpers.soundex("Gutierrez").should   == "G362"
     end
   end
 end

spec/spec_helper.rb

@@ -1,5 +1,5 @@
 $:.unshift(File.join(File.dirname(__FILE__), "..", "lib"))
 
-require 'fuzzy'
+require 'fuzzy_tools'
 
 Book = Struct.new(:title, :author)