regexp_parser 2.11.0 → 2.11.2

data/lib/regexp_parser/scanner.rb

@@ -1,9 +1,9 @@
-# -*- warn-indent:false;  -*-
+# -*- frozen_string_literal: true; warn-indent: false -*-
 #
 # THIS IS A GENERATED FILE, DO NOT EDIT DIRECTLY
 #
 # This file was generated from scanner.rl
-# by running `bundle exec rake `
+# by running `$ bundle exec rake ragel`
 
 
 require_relative 'scanner/errors/scanner_error'
@@ -28,7 +28,7 @@ class Regexp::Scanner
 
     input = input_object.is_a?(Regexp) ? input_object.source : input_object
     self.free_spacing = free_spacing?(input_object, options)
-    self.regexp_encoding = input_object.encoding if input_object.is_a?(::Regexp)
+    self.regexp_encoding = extract_encoding(input_object, options)
     self.spacing_stack = [{:free_spacing => free_spacing, :depth => 0}]
 
     data  = input.unpack("c*")
@@ -1464,7 +1464,7 @@ p = p - 1; begin
       # If not enough groups have been opened, there is a fallback to either an
       # octal or literal interpretation for 2+ digit numerical escapes.
       digits = text[1..-1]
-      if digits.size == 1 || digits.to_i <= self.capturing_group_count
+      if digits.size == 1 || digits.to_i <= capturing_group_count
         emit(:backref, :number, text)
       elsif digits =~ /\A[0-7]{2,}\z/
         emit(:escape, :octal, text)
@@ -1888,7 +1888,7 @@ p = p - 1; begin
 		begin
 te = p
 p = p - 1; begin
-      self.capturing_group_count += 1
+      self.capturing_group_count = capturing_group_count + 1
       text = copy(data, ts, te)
       emit(:group, :capture, text)
      end
@@ -2382,9 +2382,11 @@ end
     File.read("#{__dir__}/scanner/properties/#{name}.csv").scan(/(.+),(.+)/).to_h
   end
 
+  # Use each_with_object for required_ruby_version >= 2.2,or #to_h for >= 2.6
   POSIX_CLASSES =
     %w[alnum alpha ascii blank cntrl digit graph
-       lower print punct space upper word xdigit].to_h { |c| [c, true] }.freeze
+       lower print punct space upper word xdigit]
+      .inject({}) { |o, e| o.merge(e => true) }.freeze
 
   # Emits an array with the details of the scanned pattern
   def emit(type, token, text)
@@ -2412,7 +2414,7 @@ end
     end
   end
 
-  attr_accessor :literal_run # only public for #||= to work on ruby <= 2.5
+  attr_accessor :capturing_group_count, :literal_run # only public for #||= to work on ruby <= 2.5
 
   private
 
@@ -2421,9 +2423,16 @@ end
                 :free_spacing, :spacing_stack,
                 :regexp_encoding,
                 :group_depth, :set_depth, :conditional_stack,
-                :capturing_group_count,
                 :char_pos
 
+  def extract_encoding(input_object, options)
+    if input_object.is_a?(::Regexp)
+      input_object.encoding
+    elsif options && (options & Regexp::NOENCODING)
+      Encoding::BINARY
+    end
+  end
+
   def free_spacing?(input_object, options)
     if options && !input_object.is_a?(String)
       raise ArgumentError, 'options cannot be supplied unless scanning a String'

data/lib/regexp_parser/syntax/any.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   # A syntax that always returns true, passing all tokens as implemented. This
   # is useful during development, testing, and should be useful for some types

data/lib/regexp_parser/syntax/base.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   class NotImplementedError < Regexp::Syntax::SyntaxError
     def initialize(syntax, type, token)

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

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Anchor
-      Basic       = %i[bol eol]
+      Basic       = %i[bol eol].freeze
       Extended    = Basic + %i[word_boundary nonword_boundary]
-      String      = %i[bos eos eos_ob_eol]
-      MatchStart  = %i[match_start]
+      String      = %i[bos eos eos_ob_eol].freeze
+      MatchStart  = %i[match_start].freeze
 
       All = Extended + String + MatchStart
       Type = :anchor

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

@@ -1,8 +1,10 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Assertion
-      Lookahead = %i[lookahead nlookahead]
-      Lookbehind = %i[lookbehind nlookbehind]
+      Lookahead = %i[lookahead nlookahead].freeze
+      Lookbehind = %i[lookbehind nlookbehind].freeze
 
       All = Lookahead + Lookbehind
       Type = :assertion

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

@@ -1,12 +1,14 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Backreference
-      Plain     = %i[number]
-      NumberRef = %i[number_ref number_rel_ref]
+      Plain     = %i[number].freeze
+      NumberRef = %i[number_ref number_rel_ref].freeze
       Number    = Plain + NumberRef
-      Name      = %i[name_ref]
+      Name      = %i[name_ref].freeze
 
-      RecursionLevel = %i[name_recursion_ref number_recursion_ref]
+      RecursionLevel = %i[name_recursion_ref number_recursion_ref].freeze
 
       V1_8_6 = Plain
 
@@ -18,8 +20,8 @@ module Regexp::Syntax
 
     # Type is the same as Backreference so keeping it here, for now.
     module SubexpressionCall
-      Name      = %i[name_call]
-      Number    = %i[number_call number_rel_call]
+      Name      = %i[name_call].freeze
+      Number    = %i[number_call number_rel_call].freeze
 
       All = Name + Number
     end

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

@@ -1,7 +1,9 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module CharacterSet
-      Basic     = %i[open close negate range]
+      Basic     = %i[open close negate range].freeze
       Extended  = Basic + %i[intersection]
 
       All = Extended

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

@@ -1,11 +1,13 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module CharacterType
-      Basic     = []
-      Extended  = %i[digit nondigit space nonspace word nonword]
-      Hex       = %i[hex nonhex]
+      Basic     = [].freeze
+      Extended  = %i[digit nondigit space nonspace word nonword].freeze
+      Hex       = %i[hex nonhex].freeze
 
-      Clustered = %i[linebreak xgrapheme]
+      Clustered = %i[linebreak xgrapheme].freeze
 
       All = Basic + Extended + Hex + Clustered
       Type = :type

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

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Conditional
-      Delimiters = %i[open close]
+      Delimiters = %i[open close].freeze
 
-      Condition  = %i[condition_open condition condition_close]
-      Separator  = %i[separator]
+      Condition  = %i[condition_open condition condition_close].freeze
+      Separator  = %i[separator].freeze
 
       All = Conditional::Delimiters + Conditional::Condition + Conditional::Separator
 

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

@@ -1,25 +1,27 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Escape
-      Basic = %i[backslash literal]
+      Basic = %i[backslash literal].freeze
 
-      Control = %i[control meta_sequence]
+      Control = %i[control meta_sequence].freeze
 
       ASCII = %i[bell backspace escape form_feed newline carriage
-                 tab vertical_tab]
+                 tab vertical_tab].freeze
 
-      Unicode = %i[codepoint codepoint_list]
+      Unicode = %i[codepoint codepoint_list].freeze
 
       Meta  = %i[dot alternation
                  zero_or_one zero_or_more one_or_more
                  bol eol
                  group_open group_close
                  interval_open interval_close
-                 set_open set_close]
+                 set_open set_close].freeze
 
-      Hex   = %i[hex utf8_hex]
+      Hex   = %i[hex utf8_hex].freeze
 
-      Octal = %i[octal]
+      Octal = %i[octal].freeze
 
       All   = Basic + Control + ASCII + Unicode + Meta + Hex + Octal
       Type  = :escape

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

@@ -1,18 +1,20 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Group
-      Basic     = %i[capture close]
+      Basic     = %i[capture close].freeze
       Extended  = Basic + %i[options options_switch]
 
-      Named     = %i[named]
-      Atomic    = %i[atomic]
-      Passive   = %i[passive]
-      Comment   = %i[comment]
+      Named     = %i[named].freeze
+      Atomic    = %i[atomic].freeze
+      Passive   = %i[passive].freeze
+      Comment   = %i[comment].freeze
 
       V1_8_6 = Group::Extended + Group::Named + Group::Atomic +
                Group::Passive + Group::Comment
 
-      V2_4_1 = %i[absence]
+      V2_4_1 = %i[absence].freeze
 
       All = V1_8_6 + V2_4_1
       Type = :group

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

@@ -1,7 +1,9 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Keep
-      Mark = %i[mark]
+      Mark = %i[mark].freeze
 
       All  = Mark
       Type = :keep

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

@@ -1,8 +1,10 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Meta
-      Basic       = %i[dot]
-      Alternation = %i[alternation]
+      Basic       = %i[dot].freeze
+      Alternation = %i[alternation].freeze
       Extended    = Basic + Alternation
 
       All = Extended

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

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module PosixClass
       Standard = %i[alnum alpha blank cntrl digit graph
-                    lower print punct space upper xdigit]
+                    lower print punct space upper xdigit].freeze
 
-      Extensions = %i[ascii word]
+      Extensions = %i[ascii word].freeze
 
       All = Standard + Extensions
       Type = :posixclass

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

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Quantifier
@@ -5,23 +7,23 @@ module Regexp::Syntax
         zero_or_one
         zero_or_more
         one_or_more
-      ]
+      ].freeze
 
       Reluctant = %i[
         zero_or_one_reluctant
         zero_or_more_reluctant
         one_or_more_reluctant
-      ]
+      ].freeze
 
       Possessive = %i[
         zero_or_one_possessive
         zero_or_more_possessive
         one_or_more_possessive
-      ]
+      ].freeze
 
-      Interval             = %i[interval]
-      IntervalReluctant    = %i[interval_reluctant]
-      IntervalPossessive   = %i[interval_possessive]
+      Interval             = %i[interval].freeze
+      IntervalReluctant    = %i[interval_reluctant].freeze
+      IntervalPossessive   = %i[interval_possessive].freeze
 
       IntervalAll = Interval + IntervalReluctant + IntervalPossessive
 

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

@@ -1,37 +1,39 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module UnicodeProperty
       all = proc { |name| constants.grep(/#{name}/).flat_map(&method(:const_get)) }
 
       CharType_V1_9_0 = %i[alnum alpha ascii blank cntrl digit graph
-                           lower print punct space upper word xdigit]
+                           lower print punct space upper word xdigit].freeze
 
-      CharType_V2_5_0 = %i[xposixpunct]
+      CharType_V2_5_0 = %i[xposixpunct].freeze
 
-      POSIX = %i[any assigned newline]
+      POSIX = %i[any assigned newline].freeze
 
       module Category
         Letter        = %i[letter uppercase_letter lowercase_letter
-                           titlecase_letter modifier_letter other_letter]
+                           titlecase_letter modifier_letter other_letter].freeze
 
         Mark          = %i[mark nonspacing_mark spacing_mark
-                           enclosing_mark]
+                           enclosing_mark].freeze
 
         Number        = %i[number decimal_number letter_number
-                           other_number]
+                           other_number].freeze
 
         Punctuation   = %i[punctuation connector_punctuation dash_punctuation
                            open_punctuation close_punctuation initial_punctuation
-                           final_punctuation other_punctuation]
+                           final_punctuation other_punctuation].freeze
 
         Symbol        = %i[symbol math_symbol currency_symbol
-                           modifier_symbol other_symbol]
+                           modifier_symbol other_symbol].freeze
 
         Separator     = %i[separator space_separator line_separator
-                           paragraph_separator]
+                           paragraph_separator].freeze
 
         Codepoint     = %i[other control format
-                           surrogate private_use unassigned]
+                           surrogate private_use unassigned].freeze
 
         All = Letter + Mark + Number + Punctuation +
               Symbol + Separator + Codepoint
@@ -39,27 +41,29 @@ module Regexp::Syntax
 
       Age_V1_9_3 = %i[age=1.1 age=2.0 age=2.1 age=3.0 age=3.1
                       age=3.2 age=4.0 age=4.1 age=5.0 age=5.1
-                      age=5.2 age=6.0]
+                      age=5.2 age=6.0].freeze
+
+      Age_V2_0_0 = %i[age=6.1].freeze
 
-      Age_V2_0_0 = %i[age=6.1]
+      Age_V2_2_0 = %i[age=6.2 age=6.3 age=7.0].freeze
 
-      Age_V2_2_0 = %i[age=6.2 age=6.3 age=7.0]
+      Age_V2_3_0 = %i[age=8.0].freeze
 
-      Age_V2_3_0 = %i[age=8.0]
+      Age_V2_4_0 = %i[age=9.0].freeze
 
-      Age_V2_4_0 = %i[age=9.0]
+      Age_V2_5_0 = %i[age=10.0].freeze
 
-      Age_V2_5_0 = %i[age=10.0]
+      Age_V2_6_0 = %i[age=11.0].freeze
 
-      Age_V2_6_0 = %i[age=11.0]
+      Age_V2_6_2 = %i[age=12.0].freeze
 
-      Age_V2_6_2 = %i[age=12.0]
+      Age_V2_6_3 = %i[age=12.1].freeze
 
-      Age_V2_6_3 = %i[age=12.1]
+      Age_V3_1_0 = %i[age=13.0].freeze
 
-      Age_V3_1_0 = %i[age=13.0]
+      Age_V3_2_0 = %i[age=14.0 age=15.0].freeze
 
-      Age_V3_2_0 = %i[age=14.0 age=15.0]
+      Age_V3_5_0 = %i[age=15.1]
 
       Age = all[:Age_V]
 
@@ -115,19 +119,25 @@ module Regexp::Syntax
         white_space
         xid_start
         xid_continue
-      ]
+      ].freeze
 
       Derived_V2_0_0 = %i[
         cased_letter
         combining_mark
-      ]
+      ].freeze
 
       Derived_V2_4_0 = %i[
         prepended_concatenation_mark
-      ]
+      ].freeze
 
       Derived_V2_5_0 = %i[
         regional_indicator
+      ].freeze
+
+      Derived_V3_5_0 = %i[
+        id_compat_math_continue
+        id_compat_math_start
+        ids_unary_operator
       ]
 
       Derived = all[:Derived_V]
@@ -226,13 +236,13 @@ module Regexp::Syntax
         inherited
         common
         unknown
-      ]
+      ].freeze
 
       Script_V1_9_3 = %i[
         brahmi
         batak
         mandaic
-      ]
+      ].freeze
 
       Script_V2_0_0 = %i[
         chakma
@@ -242,7 +252,7 @@ module Regexp::Syntax
         sharada
         sora_sompeng
         takri
-      ]
+      ].freeze
 
       Script_V2_2_0 = %i[
         caucasian_albanian
@@ -268,7 +278,7 @@ module Regexp::Syntax
         khudawadi
         tirhuta
         warang_citi
-      ]
+      ].freeze
 
       Script_V2_3_0 = %i[
         ahom
@@ -277,7 +287,7 @@ module Regexp::Syntax
         multani
         old_hungarian
         signwriting
-      ]
+      ].freeze
 
       Script_V2_4_0 = %i[
         adlam
@@ -286,14 +296,14 @@ module Regexp::Syntax
         newa
         osage
         tangut
-      ]
+      ].freeze
 
       Script_V2_5_0 = %i[
         masaram_gondi
         nushu
         soyombo
         zanabazar_square
-      ]
+      ].freeze
 
       Script_V2_6_0 = %i[
         dogra
@@ -303,21 +313,21 @@ module Regexp::Syntax
         medefaidrin
         old_sogdian
         sogdian
-      ]
+      ].freeze
 
       Script_V2_6_2 = %i[
         elymaic
         nandinagari
         nyiakeng_puachue_hmong
         wancho
-      ]
+      ].freeze
 
       Script_V3_1_0 = %i[
         chorasmian
         dives_akuru
         khitan_small_script
         yezidi
-      ]
+      ].freeze
 
       Script_V3_2_0 = %i[
         cypro_minoan
@@ -327,7 +337,7 @@ module Regexp::Syntax
         tangsa
         toto
         vithkuqi
-      ]
+      ].freeze
 
       Script = all[:Script_V]
 
@@ -428,7 +438,7 @@ module Regexp::Syntax
         in_yi_radicals
         in_yi_syllables
         in_yijing_hexagram_symbols
-      ]
+      ].freeze
 
       UnicodeBlock_V2_0_0 = %i[
         in_aegean_numbers
@@ -556,7 +566,7 @@ module Regexp::Syntax
         in_variation_selectors_supplement
         in_vedic_extensions
         in_vertical_forms
-      ]
+      ].freeze
 
       UnicodeBlock_V2_2_0 = %i[
         in_bassa_vah
@@ -591,7 +601,7 @@ module Regexp::Syntax
         in_supplemental_arrows_c
         in_tirhuta
         in_warang_citi
-      ]
+      ].freeze
 
       UnicodeBlock_V2_3_0 = %i[
         in_ahom
@@ -604,7 +614,7 @@ module Regexp::Syntax
         in_old_hungarian
         in_supplemental_symbols_and_pictographs
         in_sutton_signwriting
-      ]
+      ].freeze
 
       UnicodeBlock_V2_4_0 = %i[
         in_adlam
@@ -618,7 +628,7 @@ module Regexp::Syntax
         in_osage
         in_tangut
         in_tangut_components
-      ]
+      ].freeze
 
       UnicodeBlock_V2_5_0 = %i[
         in_cjk_unified_ideographs_extension_f
@@ -628,7 +638,7 @@ module Regexp::Syntax
         in_soyombo
         in_syriac_supplement
         in_zanabazar_square
-      ]
+      ].freeze
 
       UnicodeBlock_V2_6_0 = %i[
         in_chess_symbols
@@ -642,7 +652,7 @@ module Regexp::Syntax
         in_medefaidrin
         in_old_sogdian
         in_sogdian
-      ]
+      ].freeze
 
       UnicodeBlock_V2_6_2 = %i[
         in_egyptian_hieroglyph_format_controls
@@ -654,7 +664,7 @@ module Regexp::Syntax
         in_symbols_and_pictographs_extended_a
         in_tamil_supplement
         in_wancho
-      ]
+      ].freeze
 
       UnicodeBlock_V3_1_0 = %i[
         in_chorasmian
@@ -665,7 +675,7 @@ module Regexp::Syntax
         in_symbols_for_legacy_computing
         in_tangut_supplement
         in_yezidi
-      ]
+      ].freeze
 
       UnicodeBlock_V3_2_0 = %i[
         in_arabic_extended_b
@@ -687,6 +697,10 @@ module Regexp::Syntax
         in_unified_canadian_aboriginal_syllabics_extended_a
         in_vithkuqi
         in_znamenny_musical_notation
+      ].freeze
+
+      UnicodeBlock_V3_5_0 = %i[
+        in_cjk_unified_ideographs_extension_i
       ]
 
       UnicodeBlock = all[:UnicodeBlock_V]
@@ -697,11 +711,11 @@ module Regexp::Syntax
         emoji_modifier
         emoji_modifier_base
         emoji_presentation
-      ]
+      ].freeze
 
       Emoji_V2_6_0 = %i[
         extended_pictographic
-      ]
+      ].freeze
 
       Enumerated_V2_4_0 = %i[
         grapheme_cluster_break=control
@@ -717,7 +731,7 @@ module Regexp::Syntax
         grapheme_cluster_break=t
         grapheme_cluster_break=v
         grapheme_cluster_break=zwj
-      ]
+      ].freeze
 
       Enumerated = all[:Enumerated_V]
 
@@ -735,6 +749,7 @@ module Regexp::Syntax
       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+$/]
 

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

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 module Regexp::Syntax
   module Token
     module Virtual
-      Root     = %i[root]
-      Sequence = %i[sequence]
+      Root     = %i[root].freeze
+      Sequence = %i[sequence].freeze
 
-      All  = %i[root sequence]
+      All  = %i[root sequence].freeze
       Type = :expression
     end
   end