string-similarity 1.0.1 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a0e99a22e06043cfc985e7cda581c9d5b2747ada
-  data.tar.gz: dfc533af4d4b9fc4d138d0505193b51cc934098f
+  metadata.gz: b89926f7398486de02d94f5f1d8742834a95d54f
+  data.tar.gz: 0493548d9494e4855b648551848da77fbef6945d
 SHA512:
-  metadata.gz: 84343e34af35640b92bb708fa3d87d96b35aa1d56892dd33ce1f8843edf0439a349a106b924f500b659d7a87d530116a70d9fbef87165502d83fda58a30c9807
-  data.tar.gz: a458bf9bec226ec89549c7ae7041ee1476e8ba2c2ecac92bc71a89e14f16d7350ee5e00bce3fa206d541613ca620ed373356e6fa399ba34ec60bbe45a8f393e6
+  metadata.gz: 8af14a673396cf5b7b20df9e279621e4301fb5c8c52f14b1a8aae3b096d1ad5a480ce6e4cc64c0b5ba6bef1c0fe72f6b530f8a10aef21bfe1c7f932d00007e3a
+  data.tar.gz: a89455cf5807fb41749d4f4b86e4642e50cf1ff8620d278e8e3b43c2abf6cd3454e740a81337e1fa7d7d3c76704a17b271a1cd61558362d37e109ca01835be6b

data/.rspec

@@ -1,2 +1,3 @@
 --color
 --require spec_helper
+--format doc

data/Gemfile

@@ -3,4 +3,9 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in string-similarity.gemspec
 gemspec
 
-gem 'codeclimate-test-reporter', group: :test, require: nil
+group :test do
+  gem 'codeclimate-test-reporter', require: nil
+  gem 'guard'
+  gem 'guard-rspec'
+  gem 'growl'
+end

data/README.md

@@ -46,6 +46,15 @@ String::Similarity.cosine 'foo', 'foo'
 # 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 ...
+'far'.levenshtein_similarity_to('foo')
+# => 0.5
 ```
 
 ## Development

data/bin/setup

@@ -1,5 +1,8 @@
-#!/bin/bash
-set -euo pipefail
-IFS=$'\n\t'
+#!/bin/sh
+# Install required dependencies and set up for development.
 
-bundle install
+set -e
+
+cd "$(dirname $0)/.."
+
+bundle install && bundle clean

data/lib/string/similarity.rb

@@ -1,23 +1,36 @@
 require 'string/similarity/version'
 
 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)
+  end
+
+  # Returns the Levenshtein similarity to +other+
+  # @see String::Similarity.levenshtein
+  def levenshtein_similarity_to(other)
+    String::Similarity.levenshtein(self, other)
+  end
+
   # +String::Similarity+ provides various methods for
   # calculating string distances.
   module Similarity extend self
-
-
-    # Calcuate the
-    # {https://en.wikipedia.org/wiki/Cosine_similarity Cosine similarity}
-    # of two strings.
+    # 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 distance of the two arguments.
+    # @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
@@ -36,12 +49,66 @@ class String
       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 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 levenshtein_distance(str1, str2)
+      # base cases
+      return 0 if str1.eql?(str2)
+      return str2.length if str1.empty?
+      return str1.length if str2.empty?
+
+      # 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
+      end
+
+      current[str2.length]
+    end
+
     private
 
     # create a vector from +str+
     #
     # @example
-    #     vector('hello') # => {"h"=>1, "e"=>1, "l"=>2, "o"=>1}
+    #     v1 = vector('hello') # => {"h"=>1, "e"=>1, "l"=>2, "o"=>1}
+    #     v1["x"] # => 0
     def vector(str)
       v = Hash.new(0)
       str.each_char { |c| v[c] += 1 }
@@ -51,7 +118,7 @@ class String
     # calculate the dot product of +vector1+ and +vector2+
     def dot(vector1, vector2)
       product = 0
-      vector1.each do |k,v|
+      vector1.each do |k, v|
         product += v * vector2[k]
       end
       product
@@ -60,7 +127,7 @@ class String
     # calculate the magnitude for +vector+
     def mag(vector)
       # calculate the sum of squares
-      sq = vector.inject(0) { |s,n| s + n**2 }
+      sq = vector.inject(0) { |s, n| s + n**2 }
       Math.sqrt(sq)
     end
   end

data/lib/string/similarity/version.rb

@@ -1,5 +1,6 @@
 class String
   module Similarity
-    VERSION = '1.0.1'
+    # Gem version
+    VERSION = '1.1.0'
   end
 end

data/string-similarity.gemspec

@@ -11,14 +11,18 @@ Gem::Specification.new do |spec|
 
   spec.summary       = %q{Various methods for calculating string similarities.}
   spec.description   = <<-EOT
+== Description
+
 This gem provides some methods for calculating similarities of two strings.
 
-Currently implemented:
+=== Currently implemented
+
 - Cosine similarity
+- Levenshtein distance/similarity
+
+=== Planned
 
-Planned:
 - Hamming similarity
-- Levenshtein similarity
   EOT
   spec.homepage      = 'https://github.com/mhutter/string-similarity'
   spec.license       = 'MIT'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: string-similarity
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.1.0
 platform: ruby
 authors:
 - Manuel Hutter
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-09-04 00:00:00.000000000 Z
+date: 2015-09-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -67,14 +67,18 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 description: |
+  == Description
+
   This gem provides some methods for calculating similarities of two strings.
 
-  Currently implemented:
+  === Currently implemented
+
   - Cosine similarity
+  - Levenshtein distance/similarity
+
+  === Planned
 
-  Planned:
   - Hamming similarity
-  - Levenshtein similarity
 email:
 - manuel@hutter.io
 executables: []