string_similarity 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: f57c49e8e84c841cbe135db15f28e25f62f9097d
+  data.tar.gz: a85ee9d70fa101ce803cb98689c3a2c7ffc46766
+SHA512:
+  metadata.gz: 5dcb000ba65f93a1a23b6aae169ba418fe95a46a92b3fe3772d220f4d78987a58dfae617bd3e6c380cac6c26cc4cc9fc2bd81aa34da968d456da0b8eddf719ca
+  data.tar.gz: 8e35b84d3cdb7e4326f06f2ed2dc651067e1854639fc757a7c49cee5ffd1e542eb52df6815ece8dc6ad2e4ae715a92929c3baf68bf0a82db7f64ce254a4db66a

data/.gitignore

@@ -0,0 +1,22 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--require spec_helper

data/.ruby-version

@@ -0,0 +1 @@
+2.2.2

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in string_similarity.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 Nathanael Burt
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,34 @@
+# StringSimilarity
+
+StringSimilarity provides a very simple api to compare two strings and return a percentage similarity. It is based on the Sørensen–Dice coefficient (https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'string_similarity'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install string_similarity
+
+## Usage
+
+```ruby
+
+StringSimilarity.score('hello', 'hello')
+#=> 100
+
+```
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/string_similarity/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/lib/string_similarity.rb

@@ -0,0 +1,51 @@
+require "string_similarity/version"
+
+class StringSimilarity
+
+  MIN_BIGRAM_LENGTH = 2
+  VERIFIED_BONUS = 5
+
+  def self.score(string_1, string_2)
+    string_1 = String.new(string_1)
+    string_2 = String.new(string_2)
+
+    cleaned_string_1 = remove_special_characters(string_1)
+    cleaned_string_2 = remove_special_characters(string_2)
+
+    bigram_length = (string_1.length.to_f * 0.1).round
+    bigram_length = [MIN_BIGRAM_LENGTH, bigram_length].max
+
+    string_1_ngrams = cleaned_string_1.each_char.each_cons(bigram_length).to_set
+    string_2_ngrams = cleaned_string_2.each_char.each_cons(bigram_length).to_set
+
+    overlap = (string_1_ngrams & string_2_ngrams).size
+    total = string_1_ngrams.size + string_2_ngrams.size
+    return 0 unless overlap > 0 && total > 0
+
+    sorensen_dice = overlap * 2.0 / total
+
+    score = (sorensen_dice * 100).round
+    normalize_score(score, string_1, string_2)
+  end
+
+  private
+
+  def self.remove_special_characters(phrase)
+    phrase.gsub!(/[[:punct:]<>]+/, "") # remove all punctuation
+    phrase.strip! # remove trailing and leading white space
+    phrase.gsub!(/\s+/, " ") # replace extended white space with one space
+    phrase.downcase
+  end
+
+  def self.capitalization_differences(original_phrase, found_phrase)
+    (original_phrase.downcase == found_phrase || found_phrase.downcase == original_phrase ||
+      original_phrase.upcase == found_phrase || found_phrase.upcase == original_phrase) &&
+      found_phrase != original_phrase
+  end
+
+  def self.normalize_score(score, original_phrase, found_phrase)
+    capitalization_differences(original_phrase, found_phrase) ? score - 1 : score
+  end
+
+
+end

data/lib/string_similarity/version.rb

@@ -0,0 +1,3 @@
+class StringSimilarity
+  VERSION = "0.0.1"
+end

data/spec/lib/string_similarity_spec.rb

@@ -0,0 +1,145 @@
+require 'spec_helper'
+
+describe StringSimilarity do
+
+  describe 'short phrases' do
+
+    it 'returns 100 if there is no difference' do
+      string = 'hello'
+      expect(StringSimilarity.score(string, string)).to eq(100)
+    end
+
+    it 'returns 99 if the original is lowercase and found is uppercase' do
+      string_1 = 'test'
+      string_2 = 'TEST'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(99)
+    end
+
+    it 'returns 99 when found is uppercase and original is capitalized' do
+      string_1 = 'Email'
+      string_2 = 'EMAIL'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(99)
+    end
+
+    it 'returns 99 if original is uppercase and found is capitalized' do
+      string_1 = 'EMAIL'
+      string_2 = 'Email'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(99)
+    end
+
+    it 'returns 99 if original is uppercase and found is lowercase' do
+      string_1 = 'EMAIL'
+      string_2 = 'email'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(99)
+    end
+
+    it 'returns 86' do
+      string_1 = 'test'
+      string_2 = 'tests'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(86)
+    end
+
+    it 'returns an 86 with capitalization differences' do
+      string_1 = 'test'
+      string_2 = 'Tests'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(86)
+    end
+
+    it 'returns 6' do
+      string_1 = 'test'
+      string_2 = 'no way is this like the original string'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(6)
+    end
+
+  end
+
+  describe 'long phrases' do
+
+    it 'returns 0 when strings are of much different length' do
+      string_1 = 'We are committed to providing the best products and friendliest customer service. If you should have any questions about ordering or a question about any of our great products, please feel free to contact us with the information provided below.'
+      string_2 = "INFORMATION WE COLLECT. Roomster collects information our users submit to us such as their name and e-mail address to allow us to identify users and notify them of changes or updates to our service. We also collect personal information submitted by our users in filling out their profile on the service such as gender, state of residence, occupation, interests, etc. We collect this personal information when our users: (a) sign up as a member; (b) make changes to their member profile information; and (c) send e-mail messages, forms, or other information to us via Roomster. Members may choose to provide additional information beyond their basic profile for their personal and professional profiles. Providing additional information beyond what is required at registration is entirely optional, but enables our users to better identify each other and more effectively connect and interact with their network.

Roomster also collects information from users that is unique, but cannot be linked to a specific individual, such as IP address and browser type. A user's session will be tracked, but each user will remain anonymous. We gather this information on all visitors to Roomster.com for systems administration purposes and to track user trends, such as our most popular features. We do not link IP addresses to any personally identifiable information."
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(0)
+    end
+
+    it 'returns 0 when the phrase is too long to come up with an accurate percentage' do
+      string_1 = 'A variety of shopping centers housing popular merchants are just a few miles from the oceanfront, offering varied dining options, large retailers and a number of specialty stores. From classic fashions at Talbots to gourmet foods and cookware at Williams-Sonoma, your refined tastes are sure to be rewarded.'
+      string_2 = "Nice is an attractive city situated on the well-reputed French Riviera – France’s Mediterranean coast. There are many beautiful beaches within driving distance as well as a varied array of shopping centers, historical attractions, and museums to satiate the appetite of the cultured traveler. Since it is one of France's largest cities, it is also a major business hub. With both tourists and business executives traveling to Nice, it pays for travelers to plan for their transportation needs in advance. To travel in comfort for an affordable cost, use Blacklane's limousine service for Nice."
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(0)
+    end
+
+    it 'returns 0 when the phrases dont match enough' do
+      string_1 = 'We are committed to providing the best products and friendliest customer service. If you should have any questions about ordering or a question about any of our great products, please feel free to contact us with the information provided below.'
+      string_2 = 'We strive to provide the best music experience for our listeners, and are passionate about providing the largest and broadest catalog of digital music.^^<br />^^'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(0)
+    end
+
+    it 'returns a higher match when the phrases are close' do
+      string_1 = 'A taxi alternative in Prague'
+      string_2 = 'A taxi alternative in Munich'
+
+      expect(StringSimilarity.score(string_1, string_2) > 75).to eq(true)
+    end
+
+  end
+
+  describe 'special characters' do
+
+    it 'strips out carats to mark text to not translate' do
+      string_1 = 'Back to Home'
+      string_2 = '<<Back to Main>>'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(64)
+    end
+
+    it 'strips out punctuation' do
+      string_1 = 'Back to Home!?'
+      string_2 = 'Back to Main...'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(64)
+    end
+
+    it 'converts extended whitespace to one space' do
+      string_1 = 'Back to Home'
+      string_2 = 'Back to     Main'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(64)
+    end
+
+    it 'strips beginning and trailing whitespace' do
+      string_1 = 'Back to Home '
+      string_2 = ' Back to Main'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(64)
+    end
+
+  end
+
+  describe 'phrases with numbers' do
+
+    it 'does not raise FloatDomainError' do
+      string_1 = '1 '
+      string_2 = '< 1'
+
+      expect(StringSimilarity.score(string_1, string_2)).to eq(0)
+    end
+
+    it 'compares strings that have a number within them' do
+      string_1 = 'I work at 1035 Pearl St.'
+      string_2 = 'I work at 1045 Pearl St.'
+
+      expect(StringSimilarity.score(string_1, string_2) > 90).to eq(true)
+    end
+
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,51 @@
+require 'string_similarity'
+require 'rspec'
+
+RSpec.configure do |config|
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+end

data/string_similarity.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'string_similarity/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "string_similarity"
+  spec.version       = StringSimilarity::VERSION
+  spec.authors       = ["Nathanael Burt"]
+  spec.email         = ["nathanael.burt@gmail.com"]
+  spec.summary       = "Gem to find a percentage similarity between two strings"
+  spec.description   = ""
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec", "~> 3.3.0"
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: string_similarity
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Nathanael Burt
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-08-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+description: ''
+email:
+- nathanael.burt@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".ruby-version"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/string_similarity.rb
+- lib/string_similarity/version.rb
+- spec/lib/string_similarity_spec.rb
+- spec/spec_helper.rb
+- string_similarity.gemspec
+homepage: ''
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.8
+signing_key: 
+specification_version: 4
+summary: Gem to find a percentage similarity between two strings
+test_files:
+- spec/lib/string_similarity_spec.rb
+- spec/spec_helper.rb