fuzzy_tools 1.0.0 → 1.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 1df8f364e469daaf9512eea1f3dd3438670f14a016973122d18449a15c42363c
+  data.tar.gz: e91486a18601f3e7d77bd560b84206609e6a2292e225fe05015ea007a0120445
+SHA512:
+  metadata.gz: 72d976441112c687c50317654e16c9c7a4a4b8343c48af5eeb1b0b56c66333bdf0120b3ef77816d761dfddb37f9baba3aaad6ea86122385492f8c2ac10ce7e64
+  data.tar.gz: 7d8ce7c72f932a2c7cdd41a82d5f7274f6decf6373c38f1c32c28d31687aff0bfa6c7e3e647a6765f74739e9515636601521328693343acea3e6e08c571dc0a2

data/.gitignore

@@ -0,0 +1 @@
+pkg/*

data/.travis.yml

@@ -3,10 +3,15 @@ rvm:
   - 1.8.7
   - 1.9.2
   - 1.9.3
+  - 2.0.0
+  - 2.1.0
+  - jruby-18mode
+  - jruby-19mode
   - ruby-head
-  - jruby-18mode # JRuby in 1.8 mode
-  - jruby-19mode # JRuby in 1.9 mode
-  # - rbx-18mode
-  - rbx-19mode # currently in active development, may or may not work for your project
+  - rbx
+matrix:
+  allow_failures:
+    - rvm: rbx
+    - rvm: ruby-head
 # uncomment this line if your project needs to run something other than `rake`:
 # script: bundle exec rspec spec

data/Gemfile

@@ -1,8 +1,8 @@
 source "http://rubygems.org"
 
 gem 'simple_stats'
-gem 'nokogiri',     :platforms => [:mri_18, :mri_19, :jruby, :rbx]
-gem 'perftools.rb', :platforms => [:mri_18, :mri_19], :require => false
+gem 'nokogiri',     '~> 1.5.0', :platforms => [:mri_18, :mri_19, :jruby]
+gem 'perftools.rb',             :platforms => [:mri_18, :mri_19], :require => false
 gem 'rake'
 
 # Specify your gem's dependencies in fuzzy_tools.gemspec

data/README.md

@@ -1,4 +1,4 @@
-# FuzzyTools [![Build Status](https://secure.travis-ci.org/brianhempel/fuzzy_tools.png)](http://travis-ci.org/brianhempel/fuzzy_tools)
+# FuzzyTools [![Build Status](https://secure.travis-ci.org/brianhempel/fuzzy_tools.png)](http://travis-ci.org/brianhempel/fuzzy_tools) [![Dependency Status](https://gemnasium.com/brianhempel/fuzzy_tools.png)](https://gemnasium.com/brianhempel/fuzzy_tools)
 
 FuzzyTools is a toolset for fuzzy searches in Ruby. The default algorithm has been tuned for accuracy (and reasonable speed) on 23 different [test files](https://github.com/brianhempel/fuzzy_tools/tree/master/accuracy/test_data/query_tests) gathered from [many sources](https://github.com/brianhempel/fuzzy_tools/blob/master/accuracy/test_data/sources/SOURCES.txt).
 
@@ -120,7 +120,7 @@ FuzzyTools::TfIdfIndex.new(:source => books, :attribute => lambda { |book| book.
 
 ## Can it go faster?
 
-If you need to do multiple searches on the same collection, grab a fuzzy index with `my_collection.fuzzy_index` and do finds on that. The `fuzzy_find` and `fuzzy_find_all` methods on Enumerable reindex every time they are called.
+If you need to do multiple searches on the same collection, grab a fuzzy index with `my_collection.fuzzy_index` and do finds on that. The `fuzzy_find`, `fuzzy_find_all`, and `fuzzy_find_all_with_scores` methods on Enumerable reindex every time they are called.
 
 Here's a performance comparison:
 
@@ -151,7 +151,7 @@ If it's still too slow, [open an issue](https://github.com/brianhempel/fuzzy_too
 
 ## How does it work?
 
-FuzzyTools downcases and then tokenizes each value using a [hybrid combination](https://github.com/brianhempel/fuzzy_tools/blob/master/lib/fuzzy/tokenizers.rb#L20-27) of words, [character bigrams](http://en.wikipedia.org/wiki/N-gram), [Soundex](http://en.wikipedia.org/wiki/Soundex), and words without vowels.
+FuzzyTools downcases and then tokenizes each value using a [hybrid combination](https://github.com/brianhempel/fuzzy_tools/blob/master/lib/fuzzy_tools/tokenizers.rb#L20-27) of words, [character bigrams](http://en.wikipedia.org/wiki/N-gram), [Soundex](http://en.wikipedia.org/wiki/Soundex), and words without vowels.
 
 ``` ruby
 FuzzyTools::Tokenizers::HYBRID.call("Till We Have Faces")
@@ -195,7 +195,7 @@ Trust me, it works.
 
 ## Specifying your own tokenizer
 
-If the default tokenizer isn't working for your data or you need more speed, you can try swapping out the tokenizers. You can use one of the various tokenizers are defined in [`FuzzyTools::Tokenizers`](https://github.com/brianhempel/fuzzy_tools/blob/master/lib/fuzzy/tokenizers.rb), or you can write your own.
+If the default tokenizer isn't working for your data or you need more speed, you can try swapping out the tokenizers. You can use one of the various tokenizers defined in [`FuzzyTools::Tokenizers`](https://github.com/brianhempel/fuzzy_tools/blob/master/lib/fuzzy_tools/tokenizers.rb), or you can write your own.
 
 ``` ruby
 # a predefined tokenizer
@@ -233,4 +233,4 @@ The [SecondString](http://secondstring.sourceforge.net/) source code was a valua
 
 ## License
 
-Authored by Brian Hempel. Public domain, no restrictions.
+Authored by Brian Hempel. Public domain, no restrictions.

data/lib/fuzzy_tools/tokenizers.rb

@@ -21,7 +21,7 @@ module FuzzyTools
       str   = str.downcase
       words = str.split
       words.map { |word| FuzzyTools::Helpers.soundex(word) } +
-      FuzzyTools::Helpers.ngrams(str.downcase, 2) +
+      FuzzyTools::Helpers.ngrams(str, 2) +
       words.map { |word| word.gsub(/[aeiou]/, '') } +
       words
     end

data/lib/fuzzy_tools/version.rb

@@ -1,3 +1,3 @@
 module FuzzyTools
-  VERSION = "1.0.0"
+  VERSION = "1.0.1"
 end

data/lib/fuzzy_tools/weighted_document_tokens.rb

@@ -41,13 +41,14 @@ module FuzzyTools
             VALUE  my_weights    = argv[0];
             VALUE  my_tokens     = argv[1];
             VALUE  other_weights = argv[2];
-            int    i;
+            long   i;
             VALUE  token;
             VALUE  my_weight;
             VALUE  other_weight;
+            long len = RARRAY_LEN(my_tokens);
 
-            for(i = 0; i < RARRAY_LEN(RARRAY(my_tokens)); i++) {
-              token        = RARRAY_PTR(RARRAY(my_tokens))[i];
+            for (i = 0; i < len; i++) {
+              token        = rb_ary_entry(my_tokens, i);
               other_weight = rb_hash_aref(other_weights, token);
               if (other_weight != Qnil) {
                 my_weight   = rb_hash_aref(my_weights, token);

data/spec/enumerable_spec.rb

@@ -27,7 +27,7 @@ describe Enumerable do
       before(:each) { @letter_count_tokenizer = lambda { |str| str.size.to_s } }
 
       it "passes :tokenizer through to the index with simple query syntax" do
-        FuzzyTools::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
@@ -35,7 +35,7 @@ describe Enumerable do
       end
 
       it "passes :tokenizer through to the index with :attribute => query syntax" do
-        FuzzyTools::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
@@ -57,7 +57,7 @@ describe Enumerable do
       before(:each) { @letter_count_tokenizer = lambda { |str| str.size.to_s } }
 
       it "passes :tokenizer through to the index with simple query syntax" do
-        FuzzyTools::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
@@ -65,7 +65,7 @@ describe Enumerable do
       end
 
       it "passes :tokenizer through to the index with :attribute => query syntax" do
-        FuzzyTools::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
@@ -93,7 +93,7 @@ describe Enumerable do
       before(:each) { @letter_count_tokenizer = lambda { |str| str.size.to_s } }
 
       it "passes :tokenizer through to the index with simple query syntax" do
-        FuzzyTools::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_with_scores("the", :tokenizer => @letter_count_tokenizer)
         rescue
@@ -101,7 +101,7 @@ describe Enumerable do
       end
 
       it "passes :tokenizer through to the index with :attribute => query syntax" do
-        FuzzyTools::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_with_scores(:title => "the", :tokenizer => @letter_count_tokenizer)
         rescue
@@ -117,7 +117,7 @@ describe Enumerable do
 
     it "passes options along to the index" do
       letter_count_tokenizer = lambda { |str| str.size.to_s }
-      FuzzyTools::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

metadata

@@ -1,62 +1,55 @@
 --- !ruby/object:Gem::Specification
 name: fuzzy_tools
 version: !ruby/object:Gem::Version
-  version: 1.0.0
-  prerelease: 
+  version: 1.0.1
 platform: ruby
 authors:
 - Brian Hempel
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2012-07-24 00:00:00.000000000 Z
+date: 2025-11-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: RubyInline
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   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: rspec
   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: Easy, high quality fuzzy search in Ruby.
@@ -66,8 +59,9 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .rspec
-- .travis.yml
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
 - Gemfile
 - README.md
 - Rakefile
@@ -86,33 +80,25 @@ files:
 - spec/tf_idf_index_spec.rb
 homepage: https://github.com/brianhempel/fuzzy_tools
 licenses: []
-post_install_message: 
+metadata: {}
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -1099286336038854081
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -1099286336038854081
 requirements: []
-rubyforge_project: 
-rubygems_version: 1.8.24
-signing_key: 
-specification_version: 3
+rubygems_version: 3.4.10
+signing_key:
+specification_version: 4
 summary: Easy, high quality fuzzy search in Ruby.
 test_files:
 - spec/enumerable_spec.rb