regexp_parser 1.7.1 → 2.2.1

data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb}

@@ -1,16 +1,22 @@
 module Regexp::Expression
+  # TODO: unify naming with Token::Escape, on way or the other, in v3.0.0
   module EscapeSequence
     class Base < Regexp::Expression::Base
-      require 'yaml'
-
-      def char
-        # poor man's unescape without using eval
-        YAML.load(%Q(---\n"#{text}"\n))
-      end
-
       def codepoint
         char.ord
       end
+
+      if ''.respond_to?(:undump)
+        def char
+          %("#{text}").undump
+        end
+      else
+        # poor man's unescape without using eval
+        require 'yaml'
+        def char
+          YAML.load(%Q(---\n"#{text}"\n))
+        end
+      end
     end
 
     class Literal < EscapeSequence::Base

data/lib/regexp_parser/expression/classes/free_space.rb

@@ -1,8 +1,7 @@
 module Regexp::Expression
-
   class FreeSpace < Regexp::Expression::Base
-    def quantify(token, text, min = nil, max = nil, mode = :greedy)
-      raise "Can not quantify a free space object"
+    def quantify(_token, _text, _min = nil, _max = nil, _mode = :greedy)
+      raise Regexp::Parser::Error, 'Can not quantify a free space object'
     end
   end
 
@@ -13,5 +12,4 @@ module Regexp::Expression
       text << exp.text
     end
   end
-
 end

data/lib/regexp_parser/expression/classes/group.rb

@@ -10,11 +10,36 @@ module Regexp::Expression
       def comment?; false end
     end
 
-    class Atomic  < Group::Base; end
-    class Passive < Group::Base; end
+    class Passive < Group::Base
+      attr_writer :implicit
+
+      def initialize(*)
+        @implicit = false
+        super
+      end
+
+      def to_s(format = :full)
+        if implicit?
+          "#{expressions.join}#{quantifier_affix(format)}"
+        else
+          super
+        end
+      end
+
+      def implicit?
+        @implicit
+      end
+    end
+
     class Absence < Group::Base; end
+    class Atomic  < Group::Base; end
     class Options < Group::Base
       attr_accessor :option_changes
+
+      def initialize_copy(orig)
+        self.option_changes = orig.option_changes.dup
+        super
+      end
     end
 
     class Capture < Group::Base
@@ -33,7 +58,7 @@ module Regexp::Expression
         super
       end
 
-      def initialize_clone(orig)
+      def initialize_copy(orig)
         @name = orig.name.dup
         super
       end

data/lib/regexp_parser/expression/classes/literal.rb

@@ -1,7 +1,3 @@
 module Regexp::Expression
-
-  class Literal < Regexp::Expression::Base
-    # Obviously nothing special here, yet.
-  end
-
+  class Literal < Regexp::Expression::Base; end
 end

data/lib/regexp_parser/expression/classes/property.rb

@@ -1,5 +1,4 @@
 module Regexp::Expression
-
   module UnicodeProperty
     class Base < Regexp::Expression::Base
       def negative?
@@ -7,7 +6,7 @@ module Regexp::Expression
       end
 
       def name
-        text =~ /\A\\[pP]\{([^}]+)\}\z/; $1
+        text[/\A\\[pP]\{([^}]+)\}\z/, 1]
       end
 
       def shortcut
@@ -116,5 +115,4 @@ module Regexp::Expression
     class Script  < UnicodeProperty::Base; end
     class Block   < UnicodeProperty::Base; end
   end
-
 end # module Regexp::Expression

data/lib/regexp_parser/expression/classes/root.rb

@@ -1,24 +1,11 @@
 module Regexp::Expression
-
   class Root < Regexp::Expression::Subexpression
-    # TODO: this override is here for backwards compatibility, remove in 2.0.0
-    def initialize(*args)
-      unless args.first.is_a?(Regexp::Token)
-        warn('WARNING: Root.new without a Token argument is deprecated and '\
-             'will be removed in 2.0.0. Use Root.build for the old behavior.')
-        return super(self.class.build_token, *args)
-      end
-      super
+    def self.build(options = {})
+      new(build_token, options)
     end
 
-    class << self
-      def build(options = {})
-        new(build_token, options)
-      end
-
-      def build_token
-        Regexp::Token.new(:expression, :root, '', 0)
-      end
+    def self.build_token
+      Regexp::Token.new(:expression, :root, '', 0)
     end
   end
 end

data/lib/regexp_parser/expression/classes/type.rb

@@ -1,5 +1,4 @@
 module Regexp::Expression
-
   module CharacterType
     class Base < Regexp::Expression::Base; end
 
@@ -15,5 +14,4 @@ module Regexp::Expression
     class Linebreak        < CharacterType::Base; end
     class ExtendedGrapheme < CharacterType::Base; end
   end
-
 end

data/lib/regexp_parser/expression/methods/match_length.rb

@@ -10,7 +10,7 @@ class Regexp::MatchLength
     self.exp_class = exp.class
     self.min_rep = exp.repetitions.min
     self.max_rep = exp.repetitions.max
-    if base = opts[:base]
+    if (base = opts[:base])
       self.base_min = base
       self.base_max = base
       self.reify = ->{ '.' * base }
@@ -32,7 +32,7 @@ class Regexp::MatchLength
     end
   end
 
-  def endless_each(&block)
+  def endless_each
     return enum_for(__method__) unless block_given?
     (min..max).each { |num| yield(num) if include?(num) }
   end

data/lib/regexp_parser/expression/methods/strfregexp.rb

@@ -43,7 +43,7 @@ module Regexp::Expression
 
       # Order is important! Fields that use other fields in their
       # definition must appear before the fields they use.
-      part_keys = %w{a m b o i l x s e S y k c q Q z Z t ~t T >}
+      part_keys = %w[a m b o i l x s e S y k c q Q z Z t ~t T >]
       part.keys.each {|k| part[k] = "<?#{k}?>"}
 
       part['>'] = print_level ? ('  ' * (print_level + indent_offset)) : ''

data/lib/regexp_parser/expression/methods/traverse.rb

@@ -36,7 +36,7 @@ module Regexp::Expression
 
     # Iterates over the expressions of this expression as an array, passing
     # the expression and its index within its parent to the given block.
-    def each_expression(include_self = false, &block)
+    def each_expression(include_self = false)
       return enum_for(__method__, include_self) unless block_given?
 
       traverse(include_self) do |event, exp, index|
@@ -47,7 +47,7 @@ module Regexp::Expression
     # Returns a new array with the results of calling the given block once
     # for every expression. If a block is not given, returns an array with
     # each expression and its level index as an array.
-    def flat_map(include_self = false, &block)
+    def flat_map(include_self = false)
       result = []
 
       each_expression(include_self) do |exp, index|

data/lib/regexp_parser/expression/quantifier.rb

@@ -1,6 +1,6 @@
 module Regexp::Expression
   class Quantifier
-    MODES = [:greedy, :possessive, :reluctant]
+    MODES = %i[greedy possessive reluctant]
 
     attr_reader :token, :text, :min, :max, :mode
 
@@ -12,7 +12,7 @@ module Regexp::Expression
       @max   = max
     end
 
-    def initialize_clone(orig)
+    def initialize_copy(orig)
       @text = orig.text.dup
       super
     end
@@ -40,5 +40,14 @@ module Regexp::Expression
       RUBY
     end
     alias :lazy? :reluctant?
+
+    def ==(other)
+      other.class == self.class &&
+        other.token == token &&
+        other.mode == mode &&
+        other.min == min &&
+        other.max == max
+    end
+    alias :eq :==
   end
 end

data/lib/regexp_parser/expression/sequence.rb

@@ -1,5 +1,4 @@
 module Regexp::Expression
-
   # A sequence of expressions. Differs from a Subexpressions by how it handles
   # quantifiers, as it applies them to its last element instead of itself as
   # a whole subexpression.
@@ -7,16 +6,6 @@ module Regexp::Expression
   # Used as the base class for the Alternation alternatives, Conditional
   # branches, and CharacterSet::Intersection intersected sequences.
   class Sequence < Regexp::Expression::Subexpression
-    # TODO: this override is here for backwards compatibility, remove in 2.0.0
-    def initialize(*args)
-      if args.count == 3
-        warn('WARNING: Sequence.new without a Regexp::Token argument is '\
-             'deprecated and will be removed in 2.0.0.')
-        return self.class.at_levels(*args)
-      end
-      super
-    end
-
     class << self
       def add_to(subexpression, params = {}, active_opts = {})
         sequence = at_levels(
@@ -51,17 +40,11 @@ module Regexp::Expression
     alias :ts :starts_at
 
     def quantify(token, text, min = nil, max = nil, mode = :greedy)
-      offset = -1
-      target = expressions[offset]
-      while target.is_a?(FreeSpace)
-        target = expressions[offset -= 1]
-      end
-
-      target || raise(ArgumentError, "No valid target found for '#{text}' "\
-                                     'quantifier')
+      target = expressions.reverse.find { |exp| !exp.is_a?(FreeSpace) }
+      target or raise Regexp::Parser::Error,
+        "No valid target found for '#{text}' quantifier"
 
       target.quantify(token, text, min, max, mode)
     end
   end
-
 end

data/lib/regexp_parser/expression/subexpression.rb

@@ -1,5 +1,4 @@
 module Regexp::Expression
-
   class Subexpression < Regexp::Expression::Base
     include Enumerable
 
@@ -12,7 +11,7 @@ module Regexp::Expression
     end
 
     # Override base method to clone the expressions as well.
-    def initialize_clone(orig)
+    def initialize_copy(orig)
       self.expressions = orig.expressions.map(&:clone)
       super
     end

data/lib/regexp_parser/expression.rb

@@ -1,138 +1,6 @@
-module Regexp::Expression
-
-  class Base
-    attr_accessor :type, :token
-    attr_accessor :text, :ts
-    attr_accessor :level, :set_level, :conditional_level, :nesting_level
-
-    attr_accessor :quantifier
-    attr_accessor :options
-
-    def initialize(token, options = {})
-      self.type              = token.type
-      self.token             = token.token
-      self.text              = token.text
-      self.ts                = token.ts
-      self.level             = token.level
-      self.set_level         = token.set_level
-      self.conditional_level = token.conditional_level
-      self.nesting_level     = 0
-      self.quantifier        = nil
-      self.options           = options
-    end
-
-    def initialize_clone(orig)
-      self.text       = (orig.text       ? orig.text.dup         : nil)
-      self.options    = (orig.options    ? orig.options.dup      : nil)
-      self.quantifier = (orig.quantifier ? orig.quantifier.clone : nil)
-      super
-    end
-
-    def to_re(format = :full)
-      ::Regexp.new(to_s(format))
-    end
-
-    alias :starts_at :ts
-
-    def full_length
-      to_s.length
-    end
-
-    def offset
-      [starts_at, full_length]
-    end
-
-    def coded_offset
-      '@%d+%d' % offset
-    end
-
-    def to_s(format = :full)
-      "#{text}#{quantifier_affix(format)}"
-    end
-
-    def quantifier_affix(expression_format)
-      quantifier.to_s if quantified? && expression_format != :base
-    end
-
-    def terminal?
-      !respond_to?(:expressions)
-    end
-
-    def quantify(token, text, min = nil, max = nil, mode = :greedy)
-      self.quantifier = Quantifier.new(token, text, min, max, mode)
-    end
-
-    def unquantified_clone
-      clone.tap { |exp| exp.quantifier = nil }
-    end
-
-    def quantified?
-      !quantifier.nil?
-    end
-
-    # Deprecated. Prefer `#repetitions` which has a more uniform interface.
-    def quantity
-      return [nil,nil] unless quantified?
-      [quantifier.min, quantifier.max]
-    end
-
-    def repetitions
-      return 1..1 unless quantified?
-      min = quantifier.min
-      max = quantifier.max < 0 ? Float::INFINITY : quantifier.max
-      # fix Range#minmax - https://bugs.ruby-lang.org/issues/15807
-      (min..max).tap { |r| r.define_singleton_method(:minmax) { [min, max] } }
-    end
-
-    def greedy?
-      quantified? and quantifier.greedy?
-    end
-
-    def reluctant?
-      quantified? and quantifier.reluctant?
-    end
-    alias :lazy? :reluctant?
-
-    def possessive?
-      quantified? and quantifier.possessive?
-    end
-
-    def attributes
-      {
-        type:              type,
-        token:             token,
-        text:              to_s(:base),
-        starts_at:         ts,
-        length:            full_length,
-        level:             level,
-        set_level:         set_level,
-        conditional_level: conditional_level,
-        options:           options,
-        quantifier:        quantified? ? quantifier.to_h : nil,
-      }
-    end
-    alias :to_h :attributes
-  end
-
-  def self.parsed(exp)
-    warn('WARNING: Regexp::Expression::Base.parsed is buggy and '\
-         'will be removed in 2.0.0. Use Regexp::Parser.parse instead.')
-    case exp
-    when String
-      Regexp::Parser.parse(exp)
-    when Regexp
-      Regexp::Parser.parse(exp.source) # <- causes loss of root options
-    when Regexp::Expression            # <- never triggers
-      exp
-    else
-      raise ArgumentError, 'Expression.parsed accepts a String, Regexp, or '\
-                           'a Regexp::Expression as a value for exp, but it '\
-                           "was given #{exp.class.name}."
-    end
-  end
-
-end # module Regexp::Expression
+require 'regexp_parser/error'
 
+require 'regexp_parser/expression/base'
 require 'regexp_parser/expression/quantifier'
 require 'regexp_parser/expression/subexpression'
 require 'regexp_parser/expression/sequence'
@@ -140,9 +8,12 @@ require 'regexp_parser/expression/sequence_operation'
 
 require 'regexp_parser/expression/classes/alternation'
 require 'regexp_parser/expression/classes/anchor'
-require 'regexp_parser/expression/classes/backref'
+require 'regexp_parser/expression/classes/backreference'
+require 'regexp_parser/expression/classes/character_set'
+require 'regexp_parser/expression/classes/character_set/intersection'
+require 'regexp_parser/expression/classes/character_set/range'
 require 'regexp_parser/expression/classes/conditional'
-require 'regexp_parser/expression/classes/escape'
+require 'regexp_parser/expression/classes/escape_sequence'
 require 'regexp_parser/expression/classes/free_space'
 require 'regexp_parser/expression/classes/group'
 require 'regexp_parser/expression/classes/keep'
@@ -150,9 +21,6 @@ require 'regexp_parser/expression/classes/literal'
 require 'regexp_parser/expression/classes/posix_class'
 require 'regexp_parser/expression/classes/property'
 require 'regexp_parser/expression/classes/root'
-require 'regexp_parser/expression/classes/set'
-require 'regexp_parser/expression/classes/set/intersection'
-require 'regexp_parser/expression/classes/set/range'
 require 'regexp_parser/expression/classes/type'
 
 require 'regexp_parser/expression/methods/match'

data/lib/regexp_parser/lexer.rb

@@ -4,18 +4,20 @@
 # given syntax flavor.
 class Regexp::Lexer
 
-  OPENING_TOKENS = [
-    :capture, :passive, :lookahead, :nlookahead, :lookbehind, :nlookbehind,
-    :atomic, :options, :options_switch, :named, :absence
+  OPENING_TOKENS = %i[
+    capture passive lookahead nlookahead lookbehind nlookbehind
+    atomic options options_switch named absence
   ].freeze
 
-  CLOSING_TOKENS = [:close].freeze
+  CLOSING_TOKENS = %i[close].freeze
 
-  def self.lex(input, syntax = "ruby/#{RUBY_VERSION}", &block)
-    new.lex(input, syntax, &block)
+  CONDITION_TOKENS = %i[condition condition_close].freeze
+
+  def self.lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block)
+    new.lex(input, syntax, options: options, &block)
   end
 
-  def lex(input, syntax = "ruby/#{RUBY_VERSION}", &block)
+  def lex(input, syntax = "ruby/#{RUBY_VERSION}", options: nil, &block)
     syntax = Regexp::Syntax.new(syntax)
 
     self.tokens = []
@@ -25,7 +27,7 @@ class Regexp::Lexer
     self.shift = 0
 
     last = nil
-    Regexp::Scanner.scan(input) do |type, token, text, ts, te|
+    Regexp::Scanner.scan(input, options: options) do |type, token, text, ts, te|
       type, token = *syntax.normalize(type, token)
       syntax.check! type, token
 
@@ -40,7 +42,7 @@ class Regexp::Lexer
                                   nesting, set_nesting, conditional_nesting)
 
       current = merge_condition(current) if type == :conditional and
-        [:condition, :condition_close].include?(token)
+        CONDITION_TOKENS.include?(token)
 
       last.next = current if last
       current.previous = last if last
@@ -96,10 +98,10 @@ class Regexp::Lexer
 
     tokens.pop
     tokens << Regexp::Token.new(:literal, :literal, lead,
-              token.ts, (token.te - last.bytesize),
+              token.ts, (token.te - last.length),
               nesting, set_nesting, conditional_nesting)
     tokens << Regexp::Token.new(:literal, :literal, last,
-              (token.ts + lead.bytesize), token.te,
+              (token.ts + lead.length), token.te,
               nesting, set_nesting, conditional_nesting)
   end