regexgen 0.1.1 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bd258fd9b15bddbe8a07ca2636332049cb1861b13003b847704134426bae5575
-  data.tar.gz: b8d8d34569d6fb1c939c410d6963688507f06b5f27c50f2a8822268fee0dc28c
+  metadata.gz: 7d4795aa7ce199e2818f541f0e1bbcb49c75c1767ada19faba309107f119afd9
+  data.tar.gz: 8c6f5e905c16356c643f0d0b9991081023055b74d801613cc6ecb53c2c63edfc
 SHA512:
-  metadata.gz: 82a41dfd15da1004cec3ca972eaef09cf198d5d6a55c75c0ef46ba64fb47e57ab14ae99d0d30a2acbe3f66ebc852edd4b6c32e6893b4f8bb76d7ed6f60737af9
-  data.tar.gz: 0afef5a51a5b6b7015f21486527cc8de29bb950f68aec3be0fbee7c37f229f2ea04afedb14fc644215e8183d7bbf55c5a383e2417f3d5f023cf1886d90fd2836
+  metadata.gz: 7d99428533020d7b8423d6cef3fbb1d5e6000a34d42266869473db0a921a7975b32f24c5f3c126c0ccb64c0c9d63b09d8a438fc5d0d8fbf42c1a4a1131d76053
+  data.tar.gz: d2639356091418e3e74bae4813c904a10100d0306ef255e6f90ac737b2f15609dd31a658610a3525cd445b0414cb24f3f01cd92fa1a5ee33fc1794ceb820d280

data/.dir-locals.el

@@ -0,0 +1,4 @@
+;;; Directory Local Variables
+;;; For more information see (info "(emacs) Directory Variables")
+
+((ruby-mode . ((lsp-solargraph-use-bundler . t))))

data/.github/workflows/main.yml

@@ -1,23 +1,21 @@
-name: CI
+name: Ruby
 
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
+on: [push,pull_request]
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
-
     steps:
     - uses: actions/checkout@v2
-    - name: Setup Ruby, JRuby and TruffleRuby
-      uses: ruby/setup-ruby@v1.40.0
-    - name: Install dependencies
-      run: bundle install
-    - name: Run tests
-      run: bundle exec rake test
-    - name: Lint
-      run: bundle exec rubocop
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 2.7.4
+    - name: Install
+      run: |
+        gem install bundler -v 2.2.29
+        bundle install
+    - name: Type check
+      run: bundle exec solargraph typecheck --level typed
+    - name: Unit tests
+      run: bundle exec rake

data/.rubocop.yml

@@ -8,77 +8,7 @@ Naming/MethodParameterName:
     - 'lib/regexgen/regex.rb'
     - 'lib/regexgen/ast.rb'
 
-Layout/EmptyLinesAroundAttributeAccessor:
-  Enabled: true
-Layout/SpaceAroundMethodCallOperator:
-  Enabled: true
-Lint/BinaryOperatorWithIdenticalOperands:
-  Enabled: true
-Lint/DeprecatedOpenSSLConstant:
-  Enabled: true
-Lint/DuplicateElsifCondition:
-  Enabled: true
-Lint/DuplicateRescueException:
-  Enabled: true
-Lint/EmptyConditionalBody:
-  Enabled: true
-Lint/FloatComparison:
-  Enabled: true
-Lint/MissingSuper:
-  Enabled: true
-Lint/MixedRegexpCaptureTypes:
-  Enabled: true
-Lint/OutOfRangeRegexpRef:
-  Enabled: true
-Lint/RaiseException:
-  Enabled: true
-Lint/SelfAssignment:
-  Enabled: true
-Lint/StructNewOverride:
-  Enabled: true
-Lint/TopLevelReturnWithArgument:
-  Enabled: true
-Lint/UnreachableLoop:
-  Enabled: true
-Style/AccessorGrouping:
-  Enabled: true
-Style/ArrayCoercion:
-  Enabled: true
-Style/BisectedAttrAccessor:
-  Enabled: true
-Style/CaseLikeIf:
-  Enabled: true
-Style/ExplicitBlockArgument:
-  Enabled: true
-Style/ExponentialNotation:
-  Enabled: true
-Style/GlobalStdStream:
-  Enabled: true
-Style/HashAsLastArrayItem:
-  Enabled: true
-Style/HashEachMethods:
-  Enabled: true
-Style/HashLikeCase:
-  Enabled: true
-Style/HashTransformKeys:
-  Enabled: true
-Style/HashTransformValues:
-  Enabled: true
-Style/OptionalBooleanParameter:
-  Enabled: true
-Style/RedundantAssignment:
-  Enabled: true
-Style/RedundantFetchBlock:
-  Enabled: true
-Style/RedundantFileExtensionInRequire:
-  Enabled: true
-Style/RedundantRegexpCharacterClass:
-  Enabled: true
-Style/RedundantRegexpEscape:
-  Enabled: true
-Style/SingleArgumentDig:
-  Enabled: true
-Style/SlicingWithRange:
-  Enabled: true
-Style/StringConcatenation:
-  Enabled: true
+AllCops:
+  TargetRubyVersion: 2.5
+  NewCops: enable
+  SuggestExtensions: false

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2020-08-10 13:40:30 UTC using RuboCop version 0.89.0.
+# on 2020-08-18 06:34:11 UTC using RuboCop version 0.89.1.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
@@ -9,7 +9,7 @@
 # Offense count: 5
 # Configuration parameters: IgnoredMethods.
 Metrics/AbcSize:
-  Max: 66
+  Max: 73
 
 # Offense count: 7
 # Configuration parameters: IgnoredMethods.
@@ -19,7 +19,7 @@ Metrics/CyclomaticComplexity:
 # Offense count: 6
 # Configuration parameters: CountComments, CountAsOne, ExcludedMethods.
 Metrics/MethodLength:
-  Max: 39
+  Max: 47
 
 # Offense count: 1
 # Configuration parameters: CountComments, CountAsOne.

data/.ruby-version

@@ -1 +1 @@
-2.6.5
+2.7.4

data/.solargraph.yml

@@ -0,0 +1,17 @@
+---
+include:
+- "**/*.rb"
+exclude:
+- spec/**/*
+- test/**/*
+- vendor/**/*
+- ".bundle/**/*"
+require: []
+domains: []
+reporters:
+- rubocop
+- require_not_found
+- typecheck:typed
+require_paths: []
+plugins: []
+max_files: 5000

data/CHANGELOG.md

@@ -0,0 +1,27 @@
+## [Unreleased]
+
+## [0.3.1] - 2021-10-14
+
+- Fix missing `require 'set'`
+
+## [0.3.0] - 2020-08-18
+
+- Improve performance
+
+## [0.2.1] - 2020-08-11
+
+- Bug fix
+- Correct link in readme
+
+## [0.2.0] - 2020-08-11
+
+- Bug fix
+- Now includes `bin/regexgen` executable
+
+## [0.1.1] - 2020-08-11
+
+- Correct gem metadata
+
+## [0.1.0] - 2020-08-10
+
+- Initial release

data/Gemfile.lock

@@ -1,44 +1,79 @@
 PATH
   remote: .
   specs:
-    regexgen (0.1.1)
+    regexgen (0.3.1)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    ast (2.4.1)
+    ast (2.4.2)
+    backport (1.2.0)
+    benchmark (0.1.1)
     byebug (11.1.3)
-    minitest (5.14.1)
-    parallel (1.19.2)
-    parser (2.7.1.4)
+    diff-lcs (1.4.4)
+    e2mmap (0.1.0)
+    jaro_winkler (1.5.4)
+    kramdown (2.3.1)
+      rexml
+    kramdown-parser-gfm (1.1.0)
+      kramdown (~> 2.0)
+    mini_portile2 (2.6.1)
+    minitest (5.14.4)
+    nokogiri (1.12.5)
+      mini_portile2 (~> 2.6.1)
+      racc (~> 1.4)
+    parallel (1.21.0)
+    parser (3.0.2.0)
       ast (~> 2.4.1)
+    racc (1.5.2)
     rainbow (3.0.0)
     rake (12.3.3)
-    regexp_parser (1.7.1)
-    rexml (3.2.4)
-    rubocop (0.89.0)
+    regexp_parser (2.1.1)
+    reverse_markdown (2.0.0)
+      nokogiri
+    rexml (3.2.5)
+    rubocop (1.22.1)
       parallel (~> 1.10)
-      parser (>= 2.7.1.1)
+      parser (>= 3.0.0.0)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.7)
+      regexp_parser (>= 1.8, < 3.0)
       rexml
-      rubocop-ast (>= 0.1.0, < 1.0)
+      rubocop-ast (>= 1.12.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 2.0)
-    rubocop-ast (0.3.0)
-      parser (>= 2.7.1.4)
-    ruby-progressbar (1.10.1)
-    unicode-display_width (1.7.0)
+      unicode-display_width (>= 1.4.0, < 3.0)
+    rubocop-ast (1.12.0)
+      parser (>= 3.0.1.1)
+    ruby-progressbar (1.11.0)
+    solargraph (0.44.0)
+      backport (~> 1.2)
+      benchmark
+      bundler (>= 1.17.2)
+      diff-lcs (~> 1.4)
+      e2mmap
+      jaro_winkler (~> 1.5)
+      kramdown (~> 2.3)
+      kramdown-parser-gfm (~> 1.1)
+      parser (~> 3.0)
+      reverse_markdown (>= 1.0.5, < 3)
+      rubocop (>= 0.52)
+      thor (~> 1.0)
+      tilt (~> 2.0)
+      yard (~> 0.9, >= 0.9.24)
+    thor (1.1.0)
+    tilt (2.0.10)
+    unicode-display_width (2.1.0)
+    yard (0.9.26)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  byebug (~> 11)
+  byebug
   minitest (~> 5.0)
   rake (~> 12.0)
   regexgen!
-  rubocop (~> 0.89)
+  rubocop
+  solargraph
 
 BUNDLED WITH
-   2.1.4
+   2.2.29

data/README.md

@@ -29,6 +29,19 @@ require 'regexgen'
 Regexgen.generate(['foobar', 'foobaz', 'foozap', 'fooza']) #=> /foo(?:zap?|ba[rz])/
 ```
 
+## CLI
+
+`regexgen` also has a simple CLI to generate regexes using inputs from the
+command line.
+
+```sh
+$ regexgen
+usage: regexgen [-mix] strings...
+    -m                               Multiline flag
+    -i                               Case-insensitive flag
+    -x                               Extended flag
+```
+
 ## Unicode handling
 
 Unlike the JavaScript version, this package does not do any special Unicode
@@ -76,7 +89,7 @@ git commits and tags, and push the `.gem` file to
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at
-https://github.com/amake/regexgen.
+https://github.com/amake/regexgen-ruby.
 
 
 ## License

data/Rakefile

@@ -9,4 +9,8 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList['test/**/*_test.rb']
 end
 
-task default: :test
+require 'rubocop/rake_task'
+
+RuboCop::RakeTask.new
+
+task default: %i[test rubocop]

data/bin/regexgen

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'regexgen'
+require 'optparse'
+
+REGEX_FLAGS = {
+  'm' => 'Multiline flag',
+  'i' => 'Case-insensitive flag',
+  'x' => 'Extended flag'
+}.freeze
+
+flags = []
+op = OptionParser.new do |opts|
+  opts.banner = "usage: regexgen [-#{REGEX_FLAGS.keys.join}] strings..."
+  REGEX_FLAGS.each do |flag, description|
+    opts.on("-#{flag}", description) { |_| flags << flag }
+  end
+end
+
+begin
+  op.parse!
+rescue OptionParser::InvalidOption => e
+  puts e, op.help
+  exit(1)
+end
+
+if ARGV.empty?
+  puts op.help
+  exit(1)
+end
+
+puts Regexgen.generate(ARGV, flags)

data/lib/regexgen/ast.rb

@@ -178,21 +178,23 @@ module Regexgen
       end
 
       def remove_substring(side, len)
-        return Literal.new(@value[len..]) if side == :start
-        return Literal.new(@value[0...(@value.length - len)]) if side == :end
+        case side
+        when :start then Literal.new(@value[len...@value.length])
+        when :end then Literal.new(@value[0...(@value.length - len)])
+        else raise "Unknown side: #{side}"
+        end
       end
     end
 
-    class<<self
+    class << self
       def parens(exp, parent)
-        str = exp.to_s
-        if exp.precedence < parent.precedence
-          unless exp.respond_to?(:single_character?) && exp.single_character?
-            return "(?:#{str})" unless exp.respond_to?(:single_codepoint?) && exp.single_codepoint?
-          end
+        if exp.precedence < parent.precedence &&
+           !(exp.respond_to?(:single_character?) && exp.single_character?) &&
+           !(exp.respond_to?(:single_codepoint?) && exp.single_codepoint?)
+          "(?:#{exp})"
+        else
+          exp.to_s
         end
-
-        str
       end
     end
   end

data/lib/regexgen/minimize.rb

@@ -5,7 +5,7 @@ require 'regexgen/set'
 module Regexgen
   using SetUtil
 
-  class<<self
+  class << self
     # Hopcroft's DSA minimization algorithm
     # https://en.wikipedia.org/wiki/DFA_minimization#Hopcroft's_algorithm
     #
@@ -41,20 +41,34 @@ module Regexgen
     # c is a letter of the alphabet
     # A ∩ B is intersection (A & B)
     # |A| is the cardinality of A (A.size)
-    def minimize(root, alphabet)
+    def minimize(root)
       states = root.visit
       final_states = states.select(&:accepting).to_set
 
+      # Create a map of incoming transitions to each state, grouped by
+      # character.
+      transitions = Hash.new { |h, k| h[k] = Hash.new { |h_, k_| h_[k_] = Set.new } }
+      states.each_with_object(transitions) do |s, acc|
+        s.transitions.each do |t, st|
+          acc[st][t] << s
+        end
+      end
+
       p = Set[states, final_states]
       w = Set.new(p)
       until w.empty?
         a = w.shift
-        alphabet.each do |c|
-          x = states.each_with_object(Set.new) do |s, acc|
-            next unless s.transitions.key?(c)
 
-            acc.add(s) if a.include?(s.transitions[c])
+        # Collect states that have transitions leading to states in a, grouped
+        # by character.
+        t = Hash.new { |h, k| h[k] = Set.new }
+        a.each_with_object(t) do |s, acc|
+          transitions[s].each do |t_, x|
+            acc[t_].merge(x)
           end
+        end
+
+        t.each_value do |x|
           p.to_a.each do |y|
             intersection = x & y
             next if intersection.empty?
@@ -62,9 +76,9 @@ module Regexgen
             complement = y - x
             next if complement.empty?
 
-            p.replace(y, intersection, complement)
+            p.replace_item(y, intersection, complement)
             if w.include?(y)
-              w.replace(y, intersection, complement)
+              w.replace_item(y, intersection, complement)
             elsif intersection.size <= complement.size
               w.add(intersection)
             else

data/lib/regexgen/regex.rb

@@ -3,7 +3,43 @@
 require 'regexgen/ast'
 
 module Regexgen
-  class<<self
+  class << self
+    # Brzozowski algebraic method
+    # https://cs.stackexchange.com/a/2392
+    #
+    # Largely ported from
+    # https://github.com/devongovett/regexgen/blob/7ef10aef3a414b10554822cdf6e90389582b1890/src/regex.js
+    #
+    # Initialize B
+    #
+    #   for i = 1 to m:
+    #     if final(i):
+    #       B[i] := ε
+    #     else:
+    #       B[i] := ∅
+    #
+    # Initialize A
+    #
+    #   for i = 1 to m:
+    #     for j = 1 to m:
+    #       for a in Σ:
+    #         if trans(i, a, j):
+    #           A[i,j] := a
+    #         else:
+    #           A[i,j] := ∅
+    #
+    # Solve
+    #
+    #   for n = m decreasing to 1:
+    #     B[n] := star(A[n,n]) . B[n]
+    #     for j = 1 to n:
+    #       A[n,j] := star(A[n,n]) . A[n,j];
+    #     for i = 1 to n:
+    #       B[i] += A[i,n] . B[n]
+    #       for j = 1 to n:
+    #         A[i,j] += A[i,n] . A[n,j]
+    #
+    # Result is e := B[1]
     def to_regex(root)
       states = root.visit.to_a
 
@@ -22,9 +58,9 @@ module Regexgen
 
       (states.length - 1).downto(0) do |n|
         if a[n][n]
-          b[n] = concat(star(a[n][n], b[n]))
+          b[n] = concat(star(a[n][n]), b[n])
           (0...n).each do |j|
-            a[n][j] = concat(start(a[n][n]), a[n][j])
+            a[n][j] = concat(star(a[n][n]), a[n][j])
           end
         end
 

data/lib/regexgen/set.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'set'
+
 module Regexgen
   module SetUtil
     refine Set do
@@ -9,8 +11,8 @@ module Regexgen
         item
       end
 
-      def replace(search, *replacements)
-        raise unless delete?(search)
+      def replace_item(search, *replacements)
+        raise("Failed to delete #{search}") unless delete?(search)
 
         merge(replacements)
       end

data/lib/regexgen/trie.rb

@@ -27,7 +27,7 @@ module Regexgen
     end
 
     def minimize
-      Regexgen.minimize(@root, @alphabet)
+      Regexgen.minimize(@root)
     end
 
     def to_s

data/lib/regexgen/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Regexgen
-  VERSION = '0.1.1'
+  VERSION = '0.3.1'
 end

data/lib/regexgen.rb

@@ -5,7 +5,7 @@ require 'regexgen/trie'
 
 # Generate regular expressions that match a set of strings
 module Regexgen
-  class <<self
+  class << self
     def generate(strings, flags = nil)
       Trie.new.tap { |t| strings.each(&t.method(:add)) }
           .to_regex(flags)

data/regexgen.gemspec

@@ -11,7 +11,7 @@ Gem::Specification.new do |spec|
   spec.summary       = 'Generate a minimal regex matching a set of strings'
   spec.homepage      = 'https://github.com/amake/regexgen-ruby'
   spec.license       = 'MIT'
-  spec.required_ruby_version = Gem::Requirement.new('>= 2.3.0')
+  spec.required_ruby_version = Gem::Requirement.new('>= 2.5.0')
 
   spec.metadata['homepage_uri'] = spec.homepage
   spec.metadata['source_code_uri'] = 'https://github.com/amake/regexgen-ruby.git'
@@ -25,6 +25,7 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'byebug', '~> 11'
-  spec.add_development_dependency 'rubocop', '~> 0.89'
+  spec.add_development_dependency 'byebug'
+  spec.add_development_dependency 'rubocop'
+  spec.add_development_dependency 'solargraph'
 end

metadata

@@ -1,43 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: regexgen
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.3.1
 platform: ruby
 authors:
 - Aaron Madlon-Kay
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-08-10 00:00:00.000000000 Z
+date: 2021-10-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: byebug
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '11'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '11'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.89'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.89'
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: solargraph
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 
 email:
 - aaron@madlon-kay.com
@@ -45,18 +59,22 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".dir-locals.el"
 - ".github/workflows/main.yml"
 - ".gitignore"
 - ".rubocop.yml"
 - ".rubocop_todo.yml"
 - ".ruby-version"
+- ".solargraph.yml"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile
 - bin/console
+- bin/regexgen
 - bin/setup
 - lib/regexgen.rb
 - lib/regexgen/ast.rb
@@ -81,14 +99,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.3.0
+      version: 2.5.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.6
 signing_key: 
 specification_version: 4
 summary: Generate a minimal regex matching a set of strings