regexp_parser 2.11.3 → 2.13.0

data/lib/regexp_parser/syntax/token/unicode_property.rb

@@ -3,7 +3,10 @@
 module Regexp::Syntax
   module Token
     module UnicodeProperty
-      all = proc { |name| constants.grep(/#{name}/).flat_map(&method(:const_get)) }
+      def self.all(name)
+        constants.grep(/#{name}/).flat_map(&method(:const_get)).freeze
+      end
+      private_class_method :all
 
       CharType_V1_9_0 = %i[alnum alpha ascii blank cntrl digit graph
                            lower print punct space upper word xdigit].freeze
@@ -63,9 +66,11 @@ module Regexp::Syntax
 
       Age_V3_2_0 = %i[age=14.0 age=15.0].freeze
 
-      Age_V3_5_0 = %i[age=15.1]
+      Age_V3_5_0 = %i[age=15.1].freeze
+
+      Age_V4_0_0 = %i[age=16.0 age=17.0].freeze
 
-      Age = all[:Age_V]
+      Age = all(:Age_V)
 
       Derived_V1_9_0 = %i[
         ascii_hex_digit
@@ -138,9 +143,13 @@ module Regexp::Syntax
         id_compat_math_continue
         id_compat_math_start
         ids_unary_operator
+      ].freeze
+
+      Derived_V4_0_0 = %i[
+        modifier_combining_mark
       ]
 
-      Derived = all[:Derived_V]
+      Derived = all(:Derived_V)
 
       Script_V1_9_0 = %i[
         arabic
@@ -339,7 +348,21 @@ module Regexp::Syntax
         vithkuqi
       ].freeze
 
-      Script = all[:Script_V]
+      Script_V4_0_0 = %i[
+        beria_erfe
+        garay
+        gurung_khema
+        kirat_rai
+        ol_onal
+        sidetic
+        sunuwar
+        tai_yo
+        todhri
+        tolong_siki
+        tulu_tigalari
+      ].freeze
+
+      Script = all(:Script_V)
 
       UnicodeBlock_V1_9_0 = %i[
         in_alphabetic_presentation_forms
@@ -701,9 +724,30 @@ module Regexp::Syntax
 
       UnicodeBlock_V3_5_0 = %i[
         in_cjk_unified_ideographs_extension_i
-      ]
+      ].freeze
+
+      UnicodeBlock_V4_0_0 = %i[
+        in_beria_erfe
+        in_cjk_unified_ideographs_extension_j
+        in_egyptian_hieroglyphs_extended_a
+        in_garay
+        in_gurung_khema
+        in_kirat_rai
+        in_miscellaneous_symbols_supplement
+        in_myanmar_extended_c
+        in_ol_onal
+        in_sharada_supplement
+        in_sidetic
+        in_sunuwar
+        in_symbols_for_legacy_computing_supplement
+        in_tai_yo
+        in_tangut_components_supplement
+        in_todhri
+        in_tolong_siki
+        in_tulu_tigalari
+      ].freeze
 
-      UnicodeBlock = all[:UnicodeBlock_V]
+      UnicodeBlock = all(:UnicodeBlock_V)
 
       Emoji_V2_5_0 = %i[
         emoji
@@ -733,25 +777,26 @@ module Regexp::Syntax
         grapheme_cluster_break=zwj
       ].freeze
 
-      Enumerated = all[:Enumerated_V]
-
-      Emoji = all[:Emoji_V]
-
-      V1_9_0 = Category::All + POSIX + all[:V1_9_0]
-      V1_9_3 = all[:V1_9_3]
-      V2_0_0 = all[:V2_0_0]
-      V2_2_0 = all[:V2_2_0]
-      V2_3_0 = all[:V2_3_0]
-      V2_4_0 = all[:V2_4_0]
-      V2_5_0 = all[:V2_5_0]
-      V2_6_0 = all[:V2_6_0]
-      V2_6_2 = all[:V2_6_2]
-      V2_6_3 = all[:V2_6_3]
-      V3_1_0 = all[:V3_1_0]
-      V3_2_0 = all[:V3_2_0]
-      V3_5_0 = all[:V3_5_0]
-
-      All = all[/^V\d+_\d+_\d+$/]
+      Enumerated = all(:Enumerated_V)
+
+      Emoji = all(:Emoji_V)
+
+      V1_9_0 = Category::All + POSIX + all(:V1_9_0)
+      V1_9_3 = all(:V1_9_3)
+      V2_0_0 = all(:V2_0_0)
+      V2_2_0 = all(:V2_2_0)
+      V2_3_0 = all(:V2_3_0)
+      V2_4_0 = all(:V2_4_0)
+      V2_5_0 = all(:V2_5_0)
+      V2_6_0 = all(:V2_6_0)
+      V2_6_2 = all(:V2_6_2)
+      V2_6_3 = all(:V2_6_3)
+      V3_1_0 = all(:V3_1_0)
+      V3_2_0 = all(:V3_2_0)
+      V3_5_0 = all(:V3_5_0)
+      V4_0_0 = all(:V4_0_0)
+
+      All = all(/^V\d+_\d+_\d+$/)
 
       Type = :property
       NonType = :nonproperty

data/lib/regexp_parser/syntax/version_lookup.rb

@@ -22,7 +22,11 @@ module Regexp::Syntax
   # Returns the syntax specification class for the given syntax
   # version name. The special names 'any' and '*' return Syntax::Any.
   def for(name)
-    (@alias_map ||= {})[name] ||= version_class(name)
+    return Regexp::Syntax::Any if ['*', 'any'].include?(name.to_s)
+
+    name =~ VERSION_REGEXP || raise(InvalidVersionNameError, name)
+    version_const_name = "V#{name.to_s.scan(/\d+/).join('_')}"
+    const_get(version_const_name)
   end
 
   def new(name)
@@ -31,25 +35,36 @@ module Regexp::Syntax
     self.for(name)
   end
 
-  def supported?(name)
-    name =~ VERSION_REGEXP && comparable(name) >= comparable('1.8.6')
+  def version_class(name)
+    warn 'Regexp::Syntax.version_class is deprecated in favor of Regexp::Syntax.for. '\
+         'It will be removed in regexp_parser v3.0.0.'
+    self.for(name)
   end
 
-  def version_class(version)
-    return Regexp::Syntax::Any if ['*', 'any'].include?(version.to_s)
-
-    version =~ VERSION_REGEXP || raise(InvalidVersionNameError, version)
-    version_const_name = "V#{version.to_s.scan(/\d+/).join('_')}"
-    const_get(version_const_name) || raise(UnknownSyntaxNameError, version)
+  def supported?(name)
+    name =~ VERSION_REGEXP && comparable(name) >= comparable('1.8.6')
   end
 
   def const_missing(const_name)
     if const_name =~ VERSION_CONST_REGEXP
-      return fallback_version_class(const_name)
+      return set_fallback_version_class(const_name) ||
+             raise(UnknownSyntaxNameError, const_name)
     end
     super
   end
 
+  def set_fallback_version_class(const_name)
+    return unless (klass = fallback_version_class(const_name))
+
+    if constants.count { |c| c =~ VERSION_REGEXP } > 1000
+      raise Regexp::Syntax::SyntaxError,
+            "Unexpected high number of syntax versions defined. "\
+            "Do not accept unfiltered user input as Regexp::Syntax version."
+    end
+    const_set(const_name, klass)
+    klass
+  end
+
   def fallback_version_class(version)
     sorted = (specified_versions + [version]).sort_by { |ver| comparable(ver) }
     index = sorted.index(version)

data/lib/regexp_parser/syntax/versions/4.0.0.rb

@@ -0,0 +1,4 @@
+class Regexp::Syntax::V4_0_0 < Regexp::Syntax::V3_5_0
+  implements :property,    UnicodeProperty::V4_0_0
+  implements :nonproperty, UnicodeProperty::V4_0_0
+end

data/lib/regexp_parser/version.rb

@@ -2,6 +2,6 @@
 
 class Regexp
   class Parser
-    VERSION = '2.11.3'
+    VERSION = '2.13.0'
   end
 end

data/regexp_parser.gemspec

@@ -1,8 +1,6 @@
 # frozen_string_literal: true
 
-$:.unshift File.join(File.dirname(__FILE__), 'lib')
-
-require 'regexp_parser/version'
+require_relative 'lib/regexp_parser/version'
 
 Gem::Specification.new do |spec|
   spec.name          = 'regexp_parser'
@@ -14,8 +12,6 @@ Gem::Specification.new do |spec|
 
   spec.metadata['bug_tracker_uri'] = "#{spec.homepage}/issues"
   spec.metadata['changelog_uri']   = "#{spec.homepage}/blob/master/CHANGELOG.md"
-  spec.metadata['homepage_uri']    = spec.homepage
-  spec.metadata['source_code_uri'] = spec.homepage
   spec.metadata['wiki_uri']        = "#{spec.homepage}/wiki"
 
   spec.metadata['rubygems_mfa_required'] = 'true'
@@ -27,10 +23,8 @@ Gem::Specification.new do |spec|
 
   spec.require_paths = ['lib']
 
-  spec.files         = Dir.glob('lib/**/*.{csv,rb,rl}') +
-                       %w[Gemfile Rakefile LICENSE regexp_parser.gemspec]
-
-  spec.platform      = Gem::Platform::RUBY
+  spec.files         = Dir.glob('lib/**/*.{csv,rb}') +
+                       %w[LICENSE regexp_parser.gemspec]
 
   spec.required_ruby_version = '>= 2.0.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 2.11.3
+  version: 2.13.0
 platform: ruby
 authors:
 - Ammar Ali
@@ -18,9 +18,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- Gemfile
 - LICENSE
-- Rakefile
 - lib/regexp_parser.rb
 - lib/regexp_parser/error.rb
 - lib/regexp_parser/expression.rb
@@ -63,14 +61,11 @@ files:
 - lib/regexp_parser/lexer.rb
 - lib/regexp_parser/parser.rb
 - lib/regexp_parser/scanner.rb
-- lib/regexp_parser/scanner/char_type.rl
 - lib/regexp_parser/scanner/errors/premature_end_error.rb
 - lib/regexp_parser/scanner/errors/scanner_error.rb
 - lib/regexp_parser/scanner/errors/validation_error.rb
 - lib/regexp_parser/scanner/properties/long.csv
 - lib/regexp_parser/scanner/properties/short.csv
-- lib/regexp_parser/scanner/property.rl
-- lib/regexp_parser/scanner/scanner.rl
 - lib/regexp_parser/syntax.rb
 - lib/regexp_parser/syntax/any.rb
 - lib/regexp_parser/syntax/base.rb
@@ -106,6 +101,7 @@ files:
 - lib/regexp_parser/syntax/versions/3.1.0.rb
 - lib/regexp_parser/syntax/versions/3.2.0.rb
 - lib/regexp_parser/syntax/versions/3.5.0.rb
+- lib/regexp_parser/syntax/versions/4.0.0.rb
 - lib/regexp_parser/token.rb
 - lib/regexp_parser/version.rb
 - regexp_parser.gemspec
@@ -115,8 +111,6 @@ licenses:
 metadata:
   bug_tracker_uri: https://github.com/ammar/regexp_parser/issues
   changelog_uri: https://github.com/ammar/regexp_parser/blob/master/CHANGELOG.md
-  homepage_uri: https://github.com/ammar/regexp_parser
-  source_code_uri: https://github.com/ammar/regexp_parser
   wiki_uri: https://github.com/ammar/regexp_parser/wiki
   rubygems_mfa_required: 'true'
 rdoc_options: []
@@ -133,7 +127,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.7
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Scanner, lexer, parser for ruby's regular expressions
 test_files: []

data/Gemfile

@@ -1,17 +0,0 @@
-# frozen_string_literal: true
-
-source 'https://rubygems.org'
-
-gemspec
-
-group :development, :test do
-  gem 'leto', '~> 2.1'
-  gem 'rake', '~> 13.1'
-  gem 'regexp_property_values', '~> 1.5'
-  gem 'rspec', '~> 3.10'
-  if RUBY_VERSION.to_f >= 2.7
-    gem 'benchmark-ips', '~> 2.1'
-    gem 'gouteur', '~> 1.1'
-    gem 'rubocop', '>= 1.80.2'
-  end
-end

data/Rakefile

@@ -1,25 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler'
-require 'rubygems'
-require 'rubygems/package_task'
-require 'rake'
-require 'rake/testtask'
-require 'rspec/core/rake_task'
-
-Dir['tasks/**/*.rake'].each { |file| load(file) }
-
-Bundler::GemHelper.install_tasks
-
-RSpec::Core::RakeTask.new(:spec)
-
-task :default => [:'test:full']
-
-namespace :test do
-  task full: [:ragel, :spec]
-end
-
-# Add ragel task as a prerequisite for building the gem to ensure that the
-# latest scanner code is generated and included in the build.
-desc "Runs ragel before building the gem"
-task build: :ragel

data/lib/regexp_parser/scanner/char_type.rl

@@ -1,28 +0,0 @@
-%%{
-  machine re_char_type;
-
-  single_codepoint_char_type = [dDhHsSwW];
-  multi_codepoint_char_type  = [RX];
-
-  char_type_char = single_codepoint_char_type | multi_codepoint_char_type;
-
-  # Char types scanner
-  # --------------------------------------------------------------------------
-  char_type := |*
-    char_type_char {
-      case text = copy(data, ts-1, te)
-      when '\d'; emit(:type, :digit,      text)
-      when '\D'; emit(:type, :nondigit,   text)
-      when '\h'; emit(:type, :hex,        text)
-      when '\H'; emit(:type, :nonhex,     text)
-      when '\s'; emit(:type, :space,      text)
-      when '\S'; emit(:type, :nonspace,   text)
-      when '\w'; emit(:type, :word,       text)
-      when '\W'; emit(:type, :nonword,    text)
-      when '\R'; emit(:type, :linebreak,  text)
-      when '\X'; emit(:type, :xgrapheme,  text)
-      end
-      fret;
-    };
-  *|;
-}%%

data/lib/regexp_parser/scanner/property.rl

@@ -1,30 +0,0 @@
-%%{
-  machine re_property;
-
-  property_char     = [pP];
-
-  property_sequence = property_char . '{' . '^'? (alnum|space|[_\-\.=])+ '}';
-
-  action premature_property_end {
-    raise PrematureEndError.new('unicode property')
-  }
-
-  # Unicode properties scanner
-  # --------------------------------------------------------------------------
-  unicode_property := |*
-
-    property_sequence < eof(premature_property_end) {
-      text = copy(data, ts-1, te)
-      type = (text[1] == 'P') ^ (text[3] == '^') ? :nonproperty : :property
-
-      name = text[3..-2].gsub(/[\^\s_\-]/, '').downcase
-
-      token = self.class.short_prop_map[name] || self.class.long_prop_map[name]
-      raise ValidationError.for(:property, name) unless token
-
-      self.emit(type, token.to_sym, text)
-
-      fret;
-    };
-  *|;
-}%%