init

.rspec

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

lib/jaro_winkler.rb

@@ -0,0 +1,50 @@
+module JaroWinkler
+  module_function
+  def jaro_distance s1, s2
+    return 0.0 if s1.empty? || s2.empty?
+    length1, length2 = s1.length, s2.length
+    window_size      = ([length1, length2].max / 2) - 1
+    matches          = 0.0
+    transpositions   = 0
+    previous_index   = -1
+    s1.chars.each_with_index do |c1, i|
+      max_index = length2 - 1
+      left      = i - window_size
+      right     = i + window_size
+      left      = 0         if left  < 0
+      right     = max_index if right > max_index
+      matched   = false
+      found     = false
+      s2[left..right].chars.each_with_index do |c2, j|
+        if c1 == c2
+          matched  = true
+          s2_index = left + j
+          unless found
+            if s2_index > previous_index
+              previous_index = s2_index
+              found          = true
+            end
+          end
+        end
+      end
+      if matched
+        matches += 1
+        transpositions += 1 unless found
+      end
+    end
+    # Don't divide transpositions by 2 since it's been counted directly by above code.
+    matches == 0 ? 0 : 1.0 / 3.0 * (matches / length1 + matches / length2 + (matches - transpositions) / matches)
+  end
+
+  def jaro_winkler_distance s1, s2, weight: 0.1, threshold: 0.7, case_match: false
+    raise 'Scaling factor should not exceed 0.25, otherwise the distance can become larger than 1' if weight > 0.25
+    s1, s2 = s1.downcase, s2.downcase if case_match
+    distance = jaro_distance(s1, s2)
+    prefix = 0
+    max_length = [4, s1.length, s2.length].min
+    s1[0, max_length].chars.each_with_index do |c1, i|
+      c1 == s2[i] ? prefix += 1 : break
+    end
+    distance < threshold ? distance : distance + ((prefix * weight) * (1 - distance))
+  end
+end

spec/jaro_winkler_spec.rb

@@ -0,0 +1,15 @@
+require 'jaro_winkler'
+
+describe JaroWinkler do
+  it 'works' do
+    expect(JaroWinkler.jaro_winkler_distance("MARTHA", "MARHTA")).to  be_within(0.0001).of(0.9611)
+    expect(JaroWinkler.jaro_winkler_distance("DIXON", "DICKSONX")).to be_within(0.0001).of(0.8133)
+    expect(JaroWinkler.jaro_winkler_distance("abcvwxyz", "cabvwxyz")).to be_within(0.0001).of(0.9583)
+    expect(JaroWinkler.jaro_winkler_distance("DWAYNE", "DUANE")).to   eq 0.84
+    expect(JaroWinkler.jaro_winkler_distance("tony", "tony")).to eq 1.0
+    expect(JaroWinkler.jaro_winkler_distance("tonytonyjan", "tonytonyjan")).to eq 1.0
+    expect(JaroWinkler.jaro_winkler_distance("", "")).to eq 0.0
+    expect(JaroWinkler.jaro_winkler_distance("tony", "")).to eq 0.0
+    expect(JaroWinkler.jaro_winkler_distance("", "tony")).to eq 0.0
+  end
+end

spec/spec_helper.rb

@@ -0,0 +1,89 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause this
+# file to always be loaded, without a need to explicitly require it in any files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  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
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  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
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Limits the available syntax to the non-monkey patched syntax that is recommended.
+  # For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  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
+end