string-similarity 1.1.1 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cd97efdcd76434ae400e6382b55e54d44ce003d8
-  data.tar.gz: 1ca9a5eb0075b86d30afd03669226425161d510f
+  metadata.gz: 308c3664b419f777c0492b103cb9901e108455c0
+  data.tar.gz: 5e2af01712dc0a08c37b8dd4cbc1f60a5883cb38
 SHA512:
-  metadata.gz: d904adf7b09fc53dadee2e47f3111f4bcce52d4cabfad7c1b7fee542d9af5c65298cbf7fa1be95d729dfb2672b21994c6f7e28ad0498a5f147311f7dc3e2418f
-  data.tar.gz: d849740e7fb49897439baf66f06f3cafd4677f01c6530bb212bb9b406c5c8c974716b3af562fb72c8bcffeaa1602a4d880bed35b5f5289381e01dd57200b313c
+  metadata.gz: a739214fa67e112e179e9b744e9e8afa4c728d963a0d9ef70bbe3cbbe8abdc8485eef391670963ed050ed723e849ce59bddd672c543c8b12a8c330544800f09e
+  data.tar.gz: f6c7b317034c2b9c324cdbda88e33fac62e592663676735168017ef3c8ab23f247fe21a4e3289f202271bcbcb639f50c917cddcd47a26cee7e4ec68177235596

data/.travis.yml

@@ -1,6 +1,10 @@
 language: ruby
 rvm:
-  - 2.0.0-p647
-  - 2.1.7
-  - 2.2.3
+  - ruby-head
+  - 2.3.0
+  - 2.2.4
+  - 2.1.8
+matrix:
+  allow_failures:
+    - rvm: ruby-head
 before_install: gem install bundler -v 1.10.6

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+**2.0.0** (2016-02-19)
+
+* removed: core extensions on `String`
+* added: refinements for `String` (see README!)
+
+
 **1.1.1** (2016-02-19)
 
-* added: `require 'string-similarity'` now works aswell.
+* added: `require 'string-similarity'` now works as well.

data/README.md

@@ -43,26 +43,39 @@ String::Similarity.cosine 'mine', 'thyne'
 String::Similarity.cosine 'foo', 'foo'
 # => 1.0
 
-# or call on a string directly
-'string'.cosine_similarity_to 'strong'
-# => 0.8333333333333335
-
 
 # Same for Levenshtein:
 String::Similarity.levenshtein_distance('kitten', 'sitting') # or ...
-'kitten'.levenshtein_distance_to('sitting')
 # => 3
 String::Similarity.levenshtein('foo', 'far') # or ...
+# => 0.5
+```
+
+If you want, you can use [Refinements](http://ruby-doc.org/core-2.3.0/doc/syntax/refinements_rdoc.html) to add the functionality to the `String` class:
+
+```ruby
+using String::SimilarityRefinements
+
+'string'.cosine_similarity_to 'strong'
+# => 0.8333333333333335
+
+'kitten'.levenshtein_distance_to('sitting')
+# => 3
+
 'far'.levenshtein_similarity_to('foo')
 # => 0.5
 ```
 
+(See this free [Ruby Tapas Episode](http://www.rubytapas.com/episodes/250-Refinements) if you don't know Refinements)
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
 To install this gem onto your local machine, run `bundle exec rake install`.
 
+This Project uses [Semantic Versioning](http://semver.org/).
+
 ## Contributing
 
 1. Fork it ( https://github.com/mhutter/string-similarity/fork )

data/lib/string/similarity.rb

@@ -1,142 +1,122 @@
 require 'string/similarity/version'
-
-# For convenience, String is extended by a couple of helper methods
-class String
-  # Returns the cosine similarity to +other+
-  # @see String::Similarity#cosine
-  def cosine_similarity_to(other)
-    String::Similarity.cosine(self, other)
-  end
-
-  # Returns the Levenshtein distance to +other+
-  # @see String::Similarity.levenshtein_distance
-  def levenshtein_distance_to(other)
-    String::Similarity.levenshtein_distance(self, other)
+require 'string/similarity_refinements'
+
+# +String::Similarity+ provides various methods for
+# calculating string distances.
+module String::Similarity
+  # Calcuate the {https://en.wikipedia.org/wiki/Cosine_similarity
+  # Cosine similarity} of two strings.
+  #
+  # For an explanation of the Cosine similarity of two strings read
+  # {http://stackoverflow.com/a/1750187/405454 this excellent SO answer}.
+  #
+  # @param str1 [String] first string
+  # @param str2 [String] second string
+  # @return [Float] cosine similarity of the two arguments.
+  #   - +1.0+ if the strings are identical
+  #   - +0.0+ if the strings are completely different
+  #   - +0.0+ if one of the strings is empty
+  def self.cosine(str1, str2)
+    return 1.0 if str1 == str2
+    return 0.0 if str1.empty? || str2.empty?
+
+    # convert both texts to vectors
+    v1 = vector(str1)
+    v2 = vector(str2)
+
+    # calculate the dot product
+    dot_product = dot(v1, v2)
+
+    # calculate the magnitude
+    magnitude = mag(v1.values) * mag(v2.values)
+    dot_product / magnitude
   end
 
-  # Returns the Levenshtein similarity to +other+
-  # @see String::Similarity.levenshtein
-  def levenshtein_similarity_to(other)
-    String::Similarity.levenshtein(self, other)
+  # Calculate the Levenshtein similarity for two strings.
+  #
+  # This is basically the inversion of the levenshtein_distance, i.e.
+  #     1 / levenshtein_distance(str1, str2)
+  #
+  # @param str1 [String] first string
+  # @param str2 [String] second string
+  # @return [Float] levenshtein similarity of the two arguments.
+  #   - +1.0+ if the strings are identical
+  #   - +0.0+ if one of the strings is empty
+  # @see #levenshtein_distance
+  def self.levenshtein(str1, str2)
+    return 1.0 if str1.eql?(str2)
+    return 0.0 if str1.empty? || str2.empty?
+    1.0 / levenshtein_distance(str1, str2)
   end
 
-  # +String::Similarity+ provides various methods for
-  # calculating string distances.
-  module Similarity
-    # Calcuate the {https://en.wikipedia.org/wiki/Cosine_similarity
-    # Cosine similarity} of two strings.
-    #
-    # For an explanation of the Cosine similarity of two strings read
-    # {http://stackoverflow.com/a/1750187/405454 this excellent SO answer}.
-    #
-    # @param str1 [String] first string
-    # @param str2 [String] second string
-    # @return [Float] cosine similarity of the two arguments.
-    #   - +1.0+ if the strings are identical
-    #   - +0.0+ if the strings are completely different
-    #   - +0.0+ if one of the strings is empty
-    def self.cosine(str1, str2)
-      return 1.0 if str1 == str2
-      return 0.0 if str1.empty? || str2.empty?
-
-      # convert both texts to vectors
-      v1 = vector(str1)
-      v2 = vector(str2)
-
-      # calculate the dot product
-      dot_product = dot(v1, v2)
-
-      # calculate the magnitude
-      magnitude = mag(v1.values) * mag(v2.values)
-      dot_product / magnitude
-    end
-
-    # Calculate the Levenshtein similarity for two strings.
-    #
-    # This is basically the inversion of the levenshtein_distance, i.e.
-    #     1 / levenshtein_distance(str1, str2)
-    #
-    # @param str1 [String] first string
-    # @param str2 [String] second string
-    # @return [Float] levenshtein similarity of the two arguments.
-    #   - +1.0+ if the strings are identical
-    #   - +0.0+ if one of the strings is empty
-    # @see #levenshtein_distance
-    def self.levenshtein(str1, str2)
-      return 1.0 if str1.eql?(str2)
-      return 0.0 if str1.empty? || str2.empty?
-      1.0 / levenshtein_distance(str1, str2)
-    end
-
-    # Calculate the {https://en.wikipedia.org/wiki/Levenshtein_distance
-    # Levenshtein distance} of two strings.
-    #
-    # @param str1 [String] first string
-    # @param str2 [String] second string
-    # @return [Fixnum] edit distance between the two strings
-    #   - +0+ if the strings are identical
-    def self.levenshtein_distance(str1, str2)
-      # base cases
-      result = base_case?(str1, str2)
-      return result if result
-
-      # Initialize cost-matrix rows
-      previous = (0..str2.length).to_a
-      current = []
-
-      (0...str1.length).each do |i|
-        # first element is always the edit distance from an empty string.
-        current[0] = i + 1
-        (0...str2.length).each do |j|
-          current[j + 1] = [
-            # insertion
-            current[j] + 1,
-            # deletion
-            previous[j + 1] + 1,
-            # substitution or no operation
-            previous[j] + (str1[i].eql?(str2[j]) ? 0 : 1)
-          ].min
-        end
-        previous = current.dup
+  # Calculate the {https://en.wikipedia.org/wiki/Levenshtein_distance
+  # Levenshtein distance} of two strings.
+  #
+  # @param str1 [String] first string
+  # @param str2 [String] second string
+  # @return [Fixnum] edit distance between the two strings
+  #   - +0+ if the strings are identical
+  def self.levenshtein_distance(str1, str2)
+    # base cases
+    result = base_case?(str1, str2)
+    return result if result
+
+    # Initialize cost-matrix rows
+    previous = (0..str2.length).to_a
+    current = []
+
+    (0...str1.length).each do |i|
+      # first element is always the edit distance from an empty string.
+      current[0] = i + 1
+      (0...str2.length).each do |j|
+        current[j + 1] = [
+          # insertion
+          current[j] + 1,
+          # deletion
+          previous[j + 1] + 1,
+          # substitution or no operation
+          previous[j] + (str1[i].eql?(str2[j]) ? 0 : 1)
+        ].min
       end
-
-      current[str2.length]
+      previous = current.dup
     end
 
-    private
+    current[str2.length]
+  end
 
-    def self.base_case?(str1, str2)
-      return 0 if str1.eql?(str2)
-      return str2.length if str1.empty?
-      return str1.length if str2.empty?
-      false
-    end
+  private
 
-    # create a vector from +str+
-    #
-    # @example
-    #     v1 = vector('hello') # => {"h"=>1, "e"=>1, "l"=>2, "o"=>1}
-    #     v1["x"] # => 0
-    def self.vector(str)
-      v = Hash.new(0)
-      str.each_char { |c| v[c] += 1 }
-      v
-    end
+  def self.base_case?(str1, str2)
+    return 0 if str1.eql?(str2)
+    return str2.length if str1.empty?
+    return str1.length if str2.empty?
+    false
+  end
 
-    # calculate the dot product of +vector1+ and +vector2+
-    def self.dot(vector1, vector2)
-      product = 0
-      vector1.each do |k, v|
-        product += v * vector2[k]
-      end
-      product
-    end
+  # create a vector from +str+
+  #
+  # @example
+  #     v1 = vector('hello') # => {"h"=>1, "e"=>1, "l"=>2, "o"=>1}
+  #     v1["x"] # => 0
+  def self.vector(str)
+    v = Hash.new(0)
+    str.each_char { |c| v[c] += 1 }
+    v
+  end
 
-    # calculate the magnitude for +vector+
-    def self.mag(vector)
-      # calculate the sum of squares
-      sq = vector.inject(0) { |a, e| a + e**2 }
-      Math.sqrt(sq)
+  # calculate the dot product of +vector1+ and +vector2+
+  def self.dot(vector1, vector2)
+    product = 0
+    vector1.each do |k, v|
+      product += v * vector2[k]
     end
+    product
+  end
+
+  # calculate the magnitude for +vector+
+  def self.mag(vector)
+    # calculate the sum of squares
+    sq = vector.inject(0) { |a, e| a + e**2 }
+    Math.sqrt(sq)
   end
 end

data/lib/string/similarity/version.rb

@@ -1,6 +1,6 @@
 class String
   module Similarity
     # Gem version
-    VERSION = '1.1.1'
+    VERSION = '2.0.0'
   end
 end

data/lib/string/similarity_refinements.rb

@@ -0,0 +1,22 @@
+# provide refinements for the String class
+module String::SimilarityRefinements
+  refine String do
+    # Returns the cosine similarity to +other+
+    # @see String::Similarity#cosine
+    def cosine_similarity_to(other)
+      String::Similarity.cosine(self, other)
+    end
+
+    # Returns the Levenshtein distance to +other+
+    # @see String::Similarity.levenshtein_distance
+    def levenshtein_distance_to(other)
+      String::Similarity.levenshtein_distance(self, other)
+    end
+
+    # Returns the Levenshtein similarity to +other+
+    # @see String::Similarity.levenshtein
+    def levenshtein_similarity_to(other)
+      String::Similarity.levenshtein(self, other)
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: string-similarity
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 2.0.0
 platform: ruby
 authors:
 - Manuel Hutter
@@ -100,6 +100,7 @@ files:
 - lib/string-similarity.rb
 - lib/string/similarity.rb
 - lib/string/similarity/version.rb
+- lib/string/similarity_refinements.rb
 - string-similarity.gemspec
 homepage: https://github.com/mhutter/string-similarity
 licenses: