edits 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e40f01c34af084cdf604c0fa99586d2c45b9e76ac6324ba6c279ef9cc0d02062
-  data.tar.gz: efceac3eee3f9a6997378751b1cc32970622027d5c7e68e32e02fc15c77048f2
+  metadata.gz: f1b79624e5ce72cbf1e7623ecb909c42b1fc6a82763e922b30b25589a040f2c1
+  data.tar.gz: 26175c109066ecc63c4df37493493011724e9e4dfe0c57cbae47411f6a4daf85
 SHA512:
-  metadata.gz: 998ed35ade1b507c8fb21070ef79e1be31d5edaf187a5e5b7499cbcb2605cbce3661fd9af42c598e90c8a191616a5dad57417e704b8a33002931b4b68d106f66
-  data.tar.gz: cad3e77feebc2d5d7f56f482f5ba9c26d12cead3a2d140bbe3c290f01c8d26dd7ae31cc9068f8ebfab51ed10b3b4d0f7b15506af3b2d8b0e8c3c81229f0dec9c
+  metadata.gz: 7c4b25223ef3db51afad11160fab94028fe5ab9d35f8918b63ac6cc5c3894245bea843247717ef1f93e627923dbdaf6c5844a4a0863f00598515bf0e07aa87a8
+  data.tar.gz: 4d060b4eebc4a2cad7b37b1ba6e4e30a4c5c2f38640ce2244960bf5ee0cba06b62ac577beb271e0919df784c999e69a740d4ec47daedac0cf1f06f4c395d7ce4

data/.rubocop.yml

@@ -1,5 +1,5 @@
 AllCops:
-  TargetRubyVersion: 2.4
+  TargetRubyVersion: 2.5
 Metrics/AbcSize:
   Enabled: false
 Metrics/CyclomaticComplexity:

data/.travis.yml

@@ -3,8 +3,9 @@ language: ruby
 cache: bundler
 rvm:
   - 2.3
-  - 2.4.3
-  - 2.5
+  - 2.4
+  - 2.5.3
+  - 2.6
   - ruby-head
   - rbx-3
 matrix:
@@ -19,7 +20,7 @@ jobs:
   include:
     - stage: gem release
       if: tag IS present
-      rvm: 2.4.3
+      rvm: 2.5.3
       script: echo "Deploying to rubygems.org ..."
       deploy:
         provider: rubygems

data/README.md

@@ -1,7 +1,7 @@
 # Edits
 
 [![Build Status](https://travis-ci.org/tcrouch/edits.svg?branch=master)](https://travis-ci.org/tcrouch/edits)
-[![codebeat badge](https://codebeat.co/badges/005039fa-25c2-4005-8974-97c1ae9ff6eb)](https://codebeat.co/projects/github-com-tcrouch-edits-master)
+[![Codacy Badge](https://api.codacy.com/project/badge/Grade/64cb50b8e9ce4ec2a752d091e441b09d)](https://app.codacy.com/app/t.crouch/edits?utm_source=github.com&utm_medium=referral&utm_content=tcrouch/edits&utm_campaign=Badge_Grade_Dashboard)
 [![Inline docs](http://inch-ci.org/github/tcrouch/edits.svg?branch=master)](http://inch-ci.org/github/tcrouch/edits)
 [![Yard Docs](http://img.shields.io/badge/yard-docs-blue.svg)](http://rubydoc.info/github/tcrouch/edits)
 
@@ -95,6 +95,13 @@ Edits::JaroWinkler.distance "information", "informant"
 # => 0.05858585858585863
 ```
 
+### Hamming
+
+```ruby
+Edits::Hamming.distance("explorer", "exploded")
+# => 2
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/edits.gemspec

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path("lib", __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "edits/version"
 
@@ -27,7 +27,8 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_development_dependency "benchmark-ips", "~> 2.7"
-  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "bundler", "~> 2.0"
+  spec.add_development_dependency "codacy-coverage", "~> 2.1"
   spec.add_development_dependency "rake", "~> 12.1"
   spec.add_development_dependency "redcarpet", "~> 3.4"
   spec.add_development_dependency "rspec", "~> 3.6"

data/lib/edits/compare.rb

@@ -18,11 +18,13 @@ module Edits
     # @return [String, nil] most similar string, or nil for empty array
     def most_similar(prototype, strings)
       return nil if strings.empty?
+
       min_s = strings[0]
       min_d = distance(prototype, min_s)
 
       strings[1..-1].each do |s|
         return min_s if min_d.zero?
+
         d = distance_with_max(prototype, s, min_d)
         if d < min_d
           min_d = d

data/lib/edits/damerau_levenshtein.rb

@@ -16,7 +16,7 @@ module Edits
     #   # => 3
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
-    # @return [Integer]
+    # @return [Integer] distance, 0 (identical) or greater (more distant)
     def self.distance(seq1, seq2)
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 

data/lib/edits/hamming.rb

@@ -8,10 +8,12 @@ module Edits
     # Calculate the Hamming distance between two sequences.
     #
     # @note A true distance metric, satisfies triangle inequality.
-    #
+    # @example
+    #   Edits::Hamming.distance("explorer", "exploded")
+    #   # => 2
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
-    # @return [Integer] Hamming distance
+    # @return [Integer] distance, 0 (identical) or greater (more distant)
     def self.distance(seq1, seq2)
       # if seq1.is_a?(Integer) && seq2.is_a?(Integer)
       #   return (seq1 ^ seq2).to_s(2).count("1")

data/lib/edits/jaro.rb

@@ -16,7 +16,7 @@ module Edits
     #   # => 0.9023569023569024
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
-    # @return [Float] similarity, between 0.0 (none) and 1.0 (identical)
+    # @return [Float] similarity, from 0.0 (none) to 1.0 (identical)
     def self.similarity(seq1, seq2)
       return 1.0 if seq1 == seq2
       return 0.0 if seq1.empty? || seq2.empty?
@@ -39,7 +39,7 @@ module Edits
     #   Edits::Jaro.distance("information", "informant")
     #   # => 0.09764309764309764
     # @param (see #distance)
-    # @return [Float] distance, between 0.0 (identical) and 1.0 (distant)
+    # @return [Float] distance, from 0.0 (identical) to 1.0 (distant)
     def self.distance(str1, str2)
       1.0 - similarity(str1, str2)
     end
@@ -87,6 +87,7 @@ module Edits
       seq1.length.times do |i|
         # find a match in first string
         next unless seq1_flags[i] == true
+
         # go to location of next match on second string
         j += 1 until seq2_flags[j]
 

data/lib/edits/jaro_winkler.rb

@@ -9,7 +9,7 @@ module Edits
     # Should not exceed 0.25 or metric range will leave 0..1
     WINKLER_PREFIX_WEIGHT = 0.1
 
-    # Threshold for boosting Jaro with winkler prefix multiplier.
+    # Threshold for boosting Jaro with Winkler prefix multiplier.
     # Default is 0.7
     WINKLER_THRESHOLD = 0.7
 
@@ -31,27 +31,24 @@ module Edits
     # @param seq2 [String, Array]
     # @param threshold [Float] threshold for applying Winkler prefix weighting
     # @param weight [Float] weighting for common prefix, should not exceed 0.25
-    # @return [Float] similarity, between 0.0 (none) and 1.0 (identical)
+    # @return [Float] similarity, from 0.0 (none) to 1.0 (identical)
     def self.similarity(
       seq1, seq2,
       threshold: WINKLER_THRESHOLD,
       weight: WINKLER_PREFIX_WEIGHT
     )
 
-      dj = Jaro.similarity(seq1, seq2)
+      sj = Jaro.similarity(seq1, seq2)
+      return sj unless sj > threshold
 
-      if dj > threshold
-        # size of common prefix, max 4
-        max_bound = seq1.length > seq2.length ? seq2.length : seq1.length
-        max_bound = 4 if max_bound > 4
+      # size of common prefix, max 4
+      max_bound = seq1.length > seq2.length ? seq2.length : seq1.length
+      max_bound = 4 if max_bound > 4
 
-        l = 0
-        l += 1 until seq1[l] != seq2[l] || l >= max_bound
+      l = 0
+      l += 1 until seq1[l] != seq2[l] || l >= max_bound
 
-        l < 1 ? dj : dj + (l * weight * (1 - dj))
-      else
-        dj
-      end
+      l < 1 ? sj : sj + (l * weight * (1 - sj))
     end
 
     # Calculate Jaro-Winkler distance
@@ -62,7 +59,7 @@ module Edits
     #   Edits::JaroWinkler.distance("information", "informant")
     #   # => 0.05858585858585863
     # @param (see #distance)
-    # @return [Float] distance, between 0.0 (identical) and 1.0 (distant)
+    # @return [Float] distance, from 0.0 (identical) to 1.0 (distant)
     def self.distance(
       seq1, seq2,
       threshold: WINKLER_THRESHOLD,

data/lib/edits/levenshtein.rb

@@ -7,6 +7,8 @@ module Edits
   # * Insertion
   # * Deletion
   # * Substitution
+  #
+  # @see https://en.wikipedia.org/wiki/Levenshtein_distance
   module Levenshtein
     extend Compare
 
@@ -14,11 +16,11 @@ module Edits
     #
     # @note A true distance metric, satisfies triangle inequality.
     # @example
-    #   Levenshtein.distance('sand', 'hands')
+    #   Levenshtein.distance("sand", "hands")
     #   # => 2
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
-    # @return [Integer]
+    # @return [Integer] distance, 0 (identical) or greater (more distant)
     def self.distance(seq1, seq2)
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 
@@ -74,7 +76,7 @@ module Edits
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
     # @param max [Integer] maximum distance
-    # @return [Integer]
+    # @return [Integer] distance, from 0 (identical) to max (more distant)
     def self.distance_with_max(seq1, seq2, max)
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 

data/lib/edits/restricted_edit.rb

@@ -24,7 +24,7 @@ module Edits
     #   # => 3
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
-    # @return [Integer]
+    # @return [Integer] distance, 0 (identical) or greater (more distant)
     def self.distance(seq1, seq2)
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 
@@ -96,7 +96,7 @@ module Edits
     # @param seq1 [String, Array]
     # @param seq2 [String, Array]
     # @param max [Integer] maximum distance
-    # @return [Integer]
+    # @return [Integer] distance, from 0 (identical) to max (more distant)
     def self.distance_with_max(seq1, seq2, max)
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 

data/lib/edits/version.rb

@@ -2,5 +2,5 @@
 
 module Edits
   # Current gem version
-  VERSION = "0.2.1"
+  VERSION = "0.2.2"
 end

data/tasks/benchmark/levenshtein.rake

@@ -5,7 +5,7 @@ require "benchmark/ips"
 require "edits"
 
 namespace :benchmark do
-  desc "levenshtein distance vs. distance_with_max (x100)"
+  desc "levenshtein distance vs distance_with_max (x100)"
   task :lev_max do
     words = File.read("/usr/share/dict/words")
       .split(/\n/).compact.shuffle(random: Random.new(1))
@@ -64,7 +64,7 @@ namespace :benchmark do
     end
   end
 
-  desc "restricted distance vs. distance_with_max (x100)"
+  desc "restricted distance vs distance_with_max (x100)"
   task :restricted_max do
     words = File.read("/usr/share/dict/words")
       .split(/\n/).compact.shuffle(random: Random.new(1))
@@ -123,7 +123,7 @@ namespace :benchmark do
     end
   end
 
-  desc "most_similar vs. min_by (100 words)"
+  desc "most_similar vs min_by (100 words)"
   task :lev_similar do
     words = File.read("/usr/share/dict/words")
       .split(/\n/).compact.shuffle(random: Random.new(1))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: edits
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Tom Crouch
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-02-19 00:00:00.000000000 Z
+date: 2019-04-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: benchmark-ips
@@ -30,14 +30,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.15'
+        version: '2.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.15'
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: codacy-coverage
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -146,8 +160,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: A collection of edit distance algorithms.