string-similarity 2.0.1 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 46587328eab62395108cbef8c3195326428dab84
-  data.tar.gz: b6066809ed34953ebe8f0ef6111050a05650516d
+SHA256:
+  metadata.gz: 48616210ccc1800386ed7330f6895b7f44eb34008fd7a5e6e27da083c27e9d44
+  data.tar.gz: e0e63ad2772ae5632670f1453a2462b9f481346dc5d9067401fd65edb0ce759d
 SHA512:
-  metadata.gz: 42f448b519b73d26c9db02c14fe2abfb130777bd5e439dba48e71e85edc6e8f898782a70140cfa1f4baefb369e95fa4d99d52d9222d2f52309c4b23b27f27d34
-  data.tar.gz: d4e91894f077ed938907aeba93cc35a0242dafe775e0e28e50598c7e3de27acd4285096885969997be782d2bfff7bfb9ec1dfe553de584e4734089d8d6152fa9
+  metadata.gz: aaaeda7e3961cd455ed4f6679410f4064f4e92d6bd590cd93534a404d502fa2064f8aef858589a03985c8276d46faf6706cc1745784686c5688b52503ef9c5a9
+  data.tar.gz: 76e6389bd17d93a81f3b403a2dee3eedb398affa668e6567568e9e4491b7dc360b50b8f624a1857b8086ac44215a50ecf20ecf51675367d7041a33054d5b5c02

data/.travis.yml

@@ -2,14 +2,16 @@ language: ruby
 cache: bundler
 
 rvm:
-  - 2.4
-  - 2.3
-  - 2.2
+  - 2.7
+  - 2.6
+  - 2.5
   - ruby-head
 matrix:
   allow_failures:
     - rvm: ruby-head
 
+before_install:
+  - gem install bundler
 before_script:
   - curl -L https://codeclimate.com/downloads/test-reporter/test-reporter-latest-linux-amd64 > ./cc-test-reporter
   - chmod +x ./cc-test-reporter

data/CHANGELOG.md

@@ -6,6 +6,12 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 
+## [2.1.0] - 2020-03-17
+### Added
+- Extended `cosine` to allow usage of N-grams (thanks @imustafin)
+### Fixed
+- updated outdated development dependencies
+
 ## [2.0.1] - 2017-11-22
 ### Fixed
 - `require 'string-similarity'` now actually loads the module. (thanks @wppurking)
@@ -32,7 +38,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - Proper Documentation
 
 
-[Unreleased]: https://github.com/mhutter/string-similarity/compare/v2.0.1...HEAD
+[Unreleased]: https://github.com/mhutter/string-similarity/compare/v2.1.0...HEAD
+[2.1.0]: https://github.com/mhutter/string-similarity/compare/v2.0.1...v2.2.0
 [2.0.1]: https://github.com/mhutter/string-similarity/compare/v2.0.0...v2.0.1
 [2.0.0]: https://github.com/mhutter/string-similarity/compare/v1.1.1...v2.0.0
 [1.1.1]: https://github.com/mhutter/string-similarity/compare/v1.1.0...v1.1.1

data/lib/string/similarity.rb

@@ -12,17 +12,20 @@ module String::Similarity
   #
   # @param str1 [String] first string
   # @param str2 [String] second string
+  # @param ngram [Int] how many characters at once to use
   # @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)
+  def self.cosine(str1, str2, ngram: 1)
+    raise ArgumentError.new('ngram should be >= 1') if ngram < 1
+
     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)
+    v1 = vector(str1, ngram)
+    v2 = vector(str2, ngram)
 
     # calculate the dot product
     dot_product = dot(v1, v2)
@@ -94,13 +97,33 @@ module String::Similarity
   end
 
   # create a vector from +str+
+  # keys have a special format:
+  #     '[left padding, right padding, "string"]'
   #
   # @example
-  #     v1 = vector('hello') # => {"h"=>1, "e"=>1, "l"=>2, "o"=>1}
-  #     v1["x"] # => 0
-  def self.vector(str)
+  #     v1 = vector('aba', 1) # => {'[0, 0, "a"]' => 2, '[0, 0, "b"]' => 1}
+  #     v1['[0, 0, "x"]'] # => 0
+  # @example
+  #     vector('abacaba', 2) # => {
+  #       #  '[1, 0, "a"]' => 1,
+  #       #  '[0, 0, "ab"]' => 2,
+  #       #  '[0, 0, "ba"]' => 2,
+  #       #  '[0, 0, "ac"]' => 1,
+  #       #  '[0, 0, "ca"]' => 1
+  #       #  '[0, 1, "a"]' => 1
+  #       # }
+  def self.vector(str, ngram)
     v = Hash.new(0)
-    str.each_char { |c| v[c] += 1 }
+
+    ((1 - ngram)..(str.length - 1)).each do |i|
+      before = [-i, 0].max
+      after = [ngram - (str.length - i), 0].max
+      slice = str[[i, 0].max .. [i + ngram - 1, str.length - 1].min]
+      key = [before, after, slice].to_s
+
+      v[key] += 1
+    end
+
     v
   end
 

data/lib/string/similarity/version.rb

@@ -1,6 +1,6 @@
 class String
   module Similarity
     # Gem version
-    VERSION = '2.0.1'
+    VERSION = '2.1.0'
   end
 end

data/renovate.json

@@ -0,0 +1,5 @@
+{
+  "extends": [
+    "config:base"
+  ]
+}

data/string-similarity.gemspec

@@ -32,8 +32,8 @@ This gem provides some methods for calculating similarities of two strings.
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'bundler', '~> 1.10'
-  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'rake', '~> 13.0'
   spec.add_development_dependency 'rspec'
   spec.add_development_dependency 'pry'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: string-similarity
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.1.0
 platform: ruby
 authors:
 - Manuel Hutter
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-11-22 00:00:00.000000000 Z
+date: 2020-03-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -16,28 +16,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -101,6 +101,7 @@ files:
 - lib/string/similarity.rb
 - lib/string/similarity/version.rb
 - lib/string/similarity_refinements.rb
+- renovate.json
 - string-similarity.gemspec
 homepage: https://github.com/mhutter/string-similarity
 licenses:
@@ -121,8 +122,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.14
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Various methods for calculating string similarities.