edits 0.3.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1c829d27a322f8c9b3ad50437a3b66d2548ccfc40d435ebaee4c362b22802fb8
-  data.tar.gz: dd351b715125154bd7f9b37b98fd1f75aea504163fe550795c0615af1fea9b65
+  metadata.gz: e464255bd53bdeea1b7a599d4a8463518a46d4b836fca0a65be8148de7e793db
+  data.tar.gz: b65f244baa43185798e50bd0ee486cb40e923e200242d15f5c59ba2df02e0eec
 SHA512:
-  metadata.gz: 8d5b3cd301621b913768f63c50f4876a340f620c22c2fbe68d1659bd1566141f6a737264dfb3da15f0b7a7e1a567a1036dcd978cd9c2001210f843a1e5da8f93
-  data.tar.gz: 821c4cd4acf9e2b9e25c21ce2f61a4f489838c4252fd6c4e0fd323fe9b5f3baaa1948e3ab87b0c1448830e39c9ff2362aa457e4fe9ce902994545dd8c986137e
+  metadata.gz: e3ee90cc881ae7e73affb987052c3bc542e68c9e3538babd25f72c38d22adf76e6eda178ee8fa2b837b06cc84b610faa2695796b690336310a0219c806ea343b
+  data.tar.gz: 71999dca3d06c3cedba61b8ffbe4a9c844884149269b20f0e45a3f9191cdb900f465f61f0b0f3cd3cf0bf67f16a7c071cb20da474a1be88db91df4cf2e09ac33

data/.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+- package-ecosystem: bundler
+  directory: "/"
+  schedule:
+    interval: daily
+  open-pull-requests-limit: 10

data/.github/workflows/gem-push.yml

@@ -0,0 +1,43 @@
+name: Ruby Gem
+
+on:
+  push:
+    tags: [ 'v*.*.*' ]
+
+jobs:
+  build:
+    name: Build + Publish
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Ruby 2.7
+      uses: actions/setup-ruby@v1
+      with:
+        ruby-version: 2.7.x
+
+    - name: Publish to GPR
+      run: |
+        mkdir -p $HOME/.gem
+        touch $HOME/.gem/credentials
+        chmod 0600 $HOME/.gem/credentials
+        printf -- "---\n:github: ${GEM_HOST_API_KEY}\n" > $HOME/.gem/credentials
+        gem build *.gemspec
+        gem push --KEY github --host https://rubygems.pkg.github.com/${OWNER} *.gem
+      env:
+        GEM_HOST_API_KEY: "Bearer ${{secrets.GITHUB_TOKEN}}"
+        OWNER: ${{ github.repository_owner }}
+
+    - name: Publish to RubyGems
+      run: |
+        mkdir -p $HOME/.gem
+        touch $HOME/.gem/credentials
+        chmod 0600 $HOME/.gem/credentials
+        printf -- "---\n:rubygems_api_key: ${GEM_HOST_API_KEY}\n" > $HOME/.gem/credentials
+        gem build *.gemspec
+        gem push *.gem
+      env:
+        GEM_HOST_API_KEY: "${{secrets.RUBYGEMS_AUTH_TOKEN}}"

data/.github/workflows/ruby.yml

@@ -0,0 +1,41 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+# This workflow will download a prebuilt Ruby version, install dependencies and run tests with Rake
+# For more information see: https://github.com/marketplace/actions/setup-ruby-jruby-and-truffleruby
+
+name: Ruby
+
+on:
+  push:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby-version: ["2.7", "3.0", "3.1"]
+        allow-failure: [false]
+        include:
+          - ruby-version: "ruby-head"
+            allow-failure: true
+    continue-on-error: ${{ matrix.allow-failure }}
+
+    steps:
+    - name: Checkout 🛎
+      uses: actions/checkout@v2
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby-version }}
+        bundler-cache: true
+    - name: Run tests
+      run: bundle exec rake
+    - name: Run codacy-coverage-reporter 📈
+      uses: codacy/codacy-coverage-reporter-action@v1
+      with:
+          project-token: ${{ secrets.CODACY_PROJECT_TOKEN }}

data/.rubocop.yml

@@ -1,5 +1,5 @@
 AllCops:
-  TargetRubyVersion: 2.5
+  TargetRubyVersion: 2.7
 Metrics/AbcSize:
   Enabled: false
 Metrics/CyclomaticComplexity:

data/README.md

@@ -1,14 +1,14 @@
 # Edits
 
-[![Gem Version](https://img.shields.io/gem/v/edits.svg)](https://rubygems.org/gems/edits)
-[![Build Status](https://travis-ci.org/tcrouch/edits.svg?branch=master)](https://travis-ci.org/tcrouch/edits)
-[![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)
+[![Gem](https://img.shields.io/gem/v/edits)](https://rubygems.org/gems/edits)
+[![GitHub Workflow Status (branch)](https://img.shields.io/github/workflow/status/tcrouch/edits/Ruby/main)](https://github.com/tcrouch/edits/actions/workflows/ruby.yml)
+[![Inline docs](http://inch-ci.org/github/tcrouch/edits.svg?branch=master)](https://inch-ci.org/github/tcrouch/edits)
+[![Yard Docs](https://img.shields.io/badge/yard-docs-informational)](https://rubydoc.info/github/tcrouch/edits)
 
 A collection of edit distance algorithms in Ruby.
 
-Includes Levenshtein, Restricted Edit (Optimal Alignment) and Damerau-Levenshtein distances, and Jaro & Jaro-Winkler similarity.
+Includes Levenshtein, Restricted Edit (Optimal Alignment) and
+Damerau-Levenshtein distances, and Jaro and Jaro-Winkler similarity.
 
 ## Installation
 
@@ -32,62 +32,57 @@ $ gem install edits
 
 ## Usage
 
-### Levenshtein
+### Levenshtein variants
 
-Edit distance, accounting for deletion, addition and substitution.
+Calculate the edit distance between two sequences with variants of the
+Levenshtein distance algorithm.
 
 ```ruby
 Edits::Levenshtein.distance "raked", "bakers"
 # => 3
-Edits::Levenshtein.distance "iota", "atom"
-# => 4
-Edits::Levenshtein.distance "acer", "earn"
-# => 4
-
-# Max distance
-Edits::Levenshtein.distance_with_max "iota", "atom", 2
-# => 2
-Edits::Levenshtein.most_similar "atom", %w[tree rota toes racer]
-# => "toes"
+Edits::RestrictedEdit.distance "iota", "atom"
+# => 3
+Edits::DamerauLevenshtein.distance "acer", "earn"
+# => 3
 ```
 
-### Restricted Edit (Optimal Alignment)
+- **Levenshtein** edit distance, counting insertion, deletion and
+  substitution.
+- **Restricted Damerau-Levenshtein** edit distance (aka **Optimal Alignment**),
+  counting insertion, deletion, substitution and transposition
+  (adjacent symbols swapped). Restricted by the condition that no substring is
+  edited more than once.
+- **Damerau-Levenshtein** edit distance, counting insertion, deletion,
+  substitution and transposition (adjacent symbols swapped).
 
-Edit distance, accounting for deletion, addition, substitution and
-transposition (two adjacent characters are swapped). This variant is
-restricted by the condition that no sub-string is edited more than once.
+|                      | Levenshtein | Restricted Damerau-Levenshtein | Damerau-Levenshtein |
+|----------------------|-------------|--------------------------------|---------------------|
+| "raked" vs. "bakers" | 3           | 3                              | 3                   |
+| "iota" vs. "atom"    | 4           | 3                              | 3                   |
+| "acer" vs. "earn"    | 4           | 4                              | 3                   |
 
-```ruby
-Edits::RestrictedEdit.distance "raked", "bakers"
-# => 3
-Edits::RestrictedEdit.distance "iota", "atom"
-# => 3
-Edits::RestrictedEdit.distance "acer", "earn"
-# => 4
+Levenshtein and Restricted Edit distances also have a bounded version.
 
+
+```ruby
 # Max distance
-Edits::RestrictedEdit.distance_with_max "iota", "atom", 2
-# => 2
-Edits::RestrictedEdit.most_similar "atom", %w[tree rota toes racer]
-# => "rota"
+Edits::Levenshtein.distance_with_max "fghijk", "abcde", 3
+# => 3
 ```
 
-### Damerau-Levenshtein
-
-Edit distance, accounting for deletions, additions, substitution and
-transposition (two adjacent characters are swapped).
+The convenience method `most_similar` searches for the best match to a
+given sequence from a collection. It is similar to using `min_by`, but leverages
+a maximum bound.
 
 ```ruby
-Edits::DamerauLevenshtein.distance "raked", "bakers"
-# => 3
-Edits::DamerauLevenshtein.distance "iota", "atom"
-# => 3
-Edits::DamerauLevenshtein.distance "acer", "earn"
-# => 3
+Edits::RestrictedEdit.most_similar "atom", ["iota", "tome", "mown", "tame"]
+# => "tome"
 ```
 
 ### Jaro & Jaro-Winkler
 
+Calculate the Jaro and Jaro-Winkler similarity/distance of two sequences.
+
 ```ruby
 Edits::Jaro.similarity "information", "informant"
 # => 0.90235690235690236
@@ -102,6 +97,8 @@ Edits::JaroWinkler.distance "information", "informant"
 
 ### Hamming
 
+Calculate the hamming distance between two sequences.
+
 ```ruby
 Edits::Hamming.distance("explorer", "exploded")
 # => 2

data/edits.gemspec

@@ -25,13 +25,14 @@ Gem::Specification.new do |spec|
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
+  spec.required_ruby_version = ">= 2.7"
 
-  spec.add_development_dependency "benchmark-ips", "~> 2.7"
+  spec.add_development_dependency "benchmark-ips", "~> 2.8"
   spec.add_development_dependency "bundler", "~> 2.0"
   spec.add_development_dependency "rake", "~> 13.0"
-  spec.add_development_dependency "redcarpet", "~> 3.4"
-  spec.add_development_dependency "rspec", "~> 3.6"
-  spec.add_development_dependency "simplecov", "~> 0.18"
+  spec.add_development_dependency "redcarpet", "~> 3.5"
+  spec.add_development_dependency "rspec", "~> 3.9"
+  spec.add_development_dependency "simplecov", "~> 0.21"
   spec.add_development_dependency "simplecov-lcov", "~> 0.8"
   spec.add_development_dependency "yard", "~> 0.9"
 end

data/lib/edits/compare.rb

@@ -22,7 +22,7 @@ module Edits
       min_s = strings[0]
       min_d = distance(prototype, min_s)
 
-      strings[1..-1].each do |s|
+      strings[1..].each do |s|
         return min_s if min_d.zero?
 
         d = distance_with_max(prototype, s, min_d)

data/lib/edits/damerau_levenshtein.rb

@@ -21,70 +21,66 @@ module Edits
       seq1, seq2 = seq2, seq1 if seq1.length > seq2.length
 
       # array of codepoints outperforms String
-      seq1 = seq1.codepoints if seq1.is_a? String
-      seq2 = seq2.codepoints if seq2.is_a? String
+      if seq1.is_a?(String) && seq2.is_a?(String)
+        seq1 = seq1.codepoints
+        seq2 = seq2.codepoints
+      end
 
       rows = seq1.length
       cols = seq2.length
       return cols if rows == 0
       return rows if cols == 0
 
-      # 'infinite' edit distance for padding cost matrix.
-      # Can be any value > max[rows, cols]
-      inf = rows + cols
-
-      # Initialize first two rows of cost matrix.
-      # The full initial state where cols=3, rows=2 (inf=5) would be:
-      #   [[5, 5, 5, 5, 5],
-      #    [5, 0, 1, 2, 3],
-      #    [5, 1, 0, 0, 0],
-      #    [5, 2, 0, 0, 0]]
-      matrix = [Array.new(cols + 2, inf)]
-      matrix << 0.upto(cols).to_a.unshift(inf)
+      # 'infinite' edit distance to pad cost matrix.
+      # Any value > max[rows, cols]
+      inf = cols + 1
 
       # element => last row seen
-      item_history = Hash.new(0)
+      row_history = Hash.new(0)
 
-      1.upto(rows) do |row|
-        # generate next row of cost matrix
-        new_row = Array.new(cols + 2, 0)
-        new_row[0] = inf
-        new_row[1] = row
-        matrix << new_row
+      # initialize alphabet-keyed cost matrix
+      matrix = {}
+      curr_row = 0.upto(cols).to_a
 
-        last_match_col = 0
-        seq1_item = seq1[row - 1]
+      rows.times do |row|
+        seq1_item = seq1[row]
+        match_col = 0
 
-        1.upto(cols) do |col|
-          seq2_item = seq2[col - 1]
-          last_match_row = item_history[seq2_item]
+        # rotate row arrays & generate next
+        matrix[seq1_item] = last_row = curr_row
+        curr_row = Array.new(cols + 1, inf)
+        curr_row[0] = row + 1
 
+        cols.times do |col|
+          seq2_item = seq2[col]
           sub_cost = seq1_item == seq2_item ? 0 : 1
 
-          transposition = 1 + matrix[last_match_row][last_match_col]
-          transposition += row - last_match_row - 1
-          transposition += col - last_match_col - 1
-
-          # TODO: do insertion/deletion need to be considered when
-          # seq1_item == seq2_item ?
-          #
-          # substitution, deletion, insertion, transposition
+          # | Xs | Xd |
+          # | Xi | ?  |
+          # substitution, deletion, insertion
           cost = [
-            matrix[row][col] + sub_cost,
-            matrix[row][col + 1] + 1,
-            matrix[row + 1][col] + 1,
-            transposition
+            last_row[col] + sub_cost,
+            last_row[col + 1] + 1,
+            curr_row[col] + 1
           ].min
 
-          matrix[row + 1][col + 1] = cost
-
-          last_match_col = col if sub_cost == 0
+          # transposition cost
+          # skip missed matrix lookup (inf cost)
+          if sub_cost > 0 && row > 0 && (m = matrix[seq2_item])
+            transpose = 1 + m[match_col] \
+              + (row - row_history[seq2_item] - 1) \
+              + (col - match_col - 1)
+            cost = transpose if transpose < cost
+          end
+
+          match_col = col if sub_cost == 0
+          curr_row[col + 1] = cost
         end
 
-        item_history[seq1_item] = row
+        row_history[seq1_item] = row
       end
 
-      matrix[rows + 1][cols + 1]
+      curr_row[cols]
     end
   end
 end

data/lib/edits/version.rb

@@ -2,5 +2,5 @@
 
 module Edits
   # Current gem version
-  VERSION = "0.3.0"
+  VERSION = "0.5.0"
 end

data/tasks/benchmark/levenshtein.rake

@@ -162,7 +162,7 @@ namespace :benchmark do
 
       x.report "literal, +" do
         m = []
-        m << [rows] + Array.new(cols, 0)
+        m << ([rows] + Array.new(cols, 0))
       end
 
       x.compare!
@@ -195,7 +195,7 @@ namespace :benchmark do
 
       x.report "literal, +" do
         m = []
-        m << [rows, inf] + Array.new(cols, 0)
+        m << ([rows, inf] + Array.new(cols, 0))
       end
 
       x.compare!

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: edits
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Tom Crouch
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-05-21 00:00:00.000000000 Z
+date: 2022-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: benchmark-ips
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '2.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '2.8'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -58,42 +58,42 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.5'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.6'
+        version: '3.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.6'
+        version: '3.9'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.18'
+        version: '0.21'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.18'
+        version: '0.21'
 - !ruby/object:Gem::Dependency
   name: simplecov-lcov
   requirement: !ruby/object:Gem::Requirement
@@ -132,10 +132,12 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/dependabot.yml"
+- ".github/workflows/gem-push.yml"
+- ".github/workflows/ruby.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
-- ".travis.yml"
 - ".yardopts"
 - Gemfile
 - LICENSE.txt
@@ -167,15 +169,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.7'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
+rubygems_version: 3.1.6
 signing_key: 
 specification_version: 4
 summary: A collection of edit distance algorithms.

data/.travis.yml

@@ -1,35 +0,0 @@
-os: linux
-language: ruby
-cache: bundler
-rvm:
-  - 2.4
-  - 2.5
-  - 2.6.5
-  - 2.7
-  - ruby-head
-  - rbx-3
-before_install:
-  - gem update --system
-  - gem install bundler
-  - sudo apt-get install jq
-  - curl -LSs "$(curl -LSs https://api.github.com/repos/codacy/codacy-coverage-reporter/releases/latest | jq -r '.assets | map({name, browser_download_url} | select(.name | endswith(".jar"))) | .[0].browser_download_url')" -o codacy-coverage-reporter-assembly.jar
-after_success:
-  - java -jar codacy-coverage-reporter-assembly.jar report -l Ruby -r coverage/lcov/edits.lcov
-jobs:
-  allow_failures:
-    - rvm: ruby-head
-    - rvm: rbx-3
-  fast_finish: true
-  include:
-    - stage: gem release
-      if: tag IS present
-      rvm: 2.6.5
-      script: echo "Deploying to rubygems.org ..."
-      deploy:
-        provider: rubygems
-        api_key:
-          secure: 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
-        gem: edits
-        on:
-          tags: true
-          repo: tcrouch/edits