lrama 0.6.10 → 0.7.0

data/lib/lrama/counterexamples.rb

@@ -32,8 +32,10 @@ module Lrama
       conflict_state.conflicts.flat_map do |conflict|
         case conflict.type
         when :shift_reduce
+          # @type var conflict: State::ShiftReduceConflict
           shift_reduce_example(conflict_state, conflict)
         when :reduce_reduce
+          # @type var conflict: State::ReduceReduceConflict
           reduce_reduce_examples(conflict_state, conflict)
         end
       end.compact
@@ -48,7 +50,7 @@ module Lrama
       @reverse_transitions = {}
 
       @states.states.each do |src_state|
-        trans = {}
+        trans = {} #: Hash[Grammar::Symbol, State]
 
         src_state.transitions.each do |shift, next_state|
           trans[shift.next_sym] = next_state
@@ -66,6 +68,7 @@ module Lrama
 
             @transitions[[src_state_item, sym]] = dest_state_item
 
+            # @type var key: [StateItem, Grammar::Symbol]
             key = [dest_state_item, sym]
             @reverse_transitions[key] ||= Set.new
             @reverse_transitions[key] << src_state_item
@@ -82,7 +85,7 @@ module Lrama
 
       @states.states.each do |state|
         # LHS => Set(Item)
-        h = {}
+        h = {} #: Hash[Grammar::Symbol, Set[States::Item]]
 
         state.closure.each do |item|
           sym = item.lhs
@@ -97,6 +100,7 @@ module Lrama
 
           sym = item.next_sym
           state_item = StateItem.new(state, item)
+          # @type var key: [State, Grammar::Symbol]
           key = [state, sym]
 
           @productions[state_item] = h[sym]
@@ -109,6 +113,7 @@ module Lrama
 
     def shift_reduce_example(conflict_state, conflict)
       conflict_symbol = conflict.symbols.first
+      # @type var shift_conflict_item: ::Lrama::States::Item
       shift_conflict_item = conflict_state.items.find { |item| item.next_sym == conflict_symbol }
       path2 = shortest_path(conflict_state, conflict.reduce.item, conflict_symbol)
       path1 = find_shift_conflict_shortest_path(path2, conflict_state, shift_conflict_item)
@@ -153,12 +158,14 @@ module Lrama
         prev_state_item = prev_path&.to
 
         if target_state_item == state_item || target_state_item.item.start_item?
-          result.concat(reversed_reduce_path[_j..-1].map(&:to))
+          result.concat(
+            reversed_reduce_path[_j..-1] #: Array[StartPath|TransitionPath|ProductionPath]
+              .map(&:to))
           break
         end
 
         if target_state_item.item.beginning_of_rule?
-          queue = []
+          queue = [] #: Array[Array[StateItem]]
           queue << [target_state_item]
 
           # Find reverse production
@@ -174,15 +181,17 @@ module Lrama
             end
 
             if si.item.beginning_of_rule?
+              # @type var key: [State, Grammar::Symbol]
               key = [si.state, si.item.lhs]
               @reverse_productions[key].each do |item|
                 state_item = StateItem.new(si.state, item)
                 queue << (sis + [state_item])
               end
             else
+              # @type var key: [StateItem, Grammar::Symbol]
               key = [si, si.item.previous_sym]
               @reverse_transitions[key].each do |prev_target_state_item|
-                next if prev_target_state_item.state != prev_state_item.state
+                next if prev_target_state_item.state != prev_state_item&.state
                 sis.shift
                 result.concat(sis)
                 result << prev_target_state_item
@@ -195,9 +204,10 @@ module Lrama
           end
         else
           # Find reverse transition
+          # @type var key: [StateItem, Grammar::Symbol]
           key = [target_state_item, target_state_item.item.previous_sym]
           @reverse_transitions[key].each do |prev_target_state_item|
-            next if prev_target_state_item.state != prev_state_item.state
+            next if prev_target_state_item.state != prev_state_item&.state
             result << prev_target_state_item
             target_state_item = prev_target_state_item
             i = j
@@ -224,9 +234,9 @@ module Lrama
 
     def shortest_path(conflict_state, conflict_reduce_item, conflict_term)
       # queue: is an array of [Triple, [Path]]
-      queue = []
-      visited = {}
-      start_state = @states.states.first
+      queue = [] #: Array[[Triple, Array[StartPath|TransitionPath|ProductionPath]]]
+      visited = {} #: Hash[Triple, true]
+      start_state = @states.states.first #: Lrama::State
       raise "BUG: Start state should be just one kernel." if start_state.kernels.count != 1
 
       start = Triple.new(start_state, start_state.kernels.first, Set.new([@states.eof_symbol]))

data/lib/lrama/digraph.rb

@@ -1,23 +1,52 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   # Algorithm Digraph of https://dl.acm.org/doi/pdf/10.1145/69622.357187 (P. 625)
+  #
+  # @rbs generic X < Object -- Type of a member of `sets`
+  # @rbs generic Y < _Or    -- Type of sets assigned to a member of `sets`
   class Digraph
+    # TODO: rbs-inline 0.10.0 doesn't support instance variables.
+    #       Move these type declarations above instance variable definitions, once it's supported.
+    #
+    # @rbs!
+    #   interface _Or
+    #     def |: (self) -> self
+    #   end
+    #   @sets: Array[X]
+    #   @relation: Hash[X, Array[X]]
+    #   @base_function: Hash[X, Y]
+    #   @stack: Array[X]
+    #   @h: Hash[X, (Integer|Float)?]
+    #   @result: Hash[X, Y]
+
+    # @rbs sets: Array[X]
+    # @rbs relation: Hash[X, Array[X]]
+    # @rbs base_function: Hash[X, Y]
+    # @rbs return: void
     def initialize(sets, relation, base_function)
+
       # X in the paper
       @sets = sets
+
       # R in the paper
       @relation = relation
+
       # F' in the paper
       @base_function = base_function
+
       # S in the paper
       @stack = []
+
       # N in the paper
       @h = Hash.new(0)
+
       # F in the paper
       @result = {}
     end
 
+    # @rbs () -> Hash[X, Y]
     def compute
       @sets.each do |x|
         next if @h[x] != 0
@@ -29,6 +58,7 @@ module Lrama
 
     private
 
+    # @rbs (X x) -> void
     def traverse(x)
       @stack.push(x)
       d = @stack.count

data/lib/lrama/grammar/binding.rb

@@ -1,34 +1,66 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   class Grammar
     class Binding
-      attr_reader :actual_args, :count
+      # @rbs @actual_args: Array[Lexer::Token]
+      # @rbs @param_to_arg: Hash[String, Lexer::Token]
 
-      def initialize(parameterizing_rule, actual_args)
-        @parameters = parameterizing_rule.parameters
+      # @rbs (Array[Lexer::Token] params, Array[Lexer::Token] actual_args) -> void
+      def initialize(params, actual_args)
         @actual_args = actual_args
-        @parameter_to_arg = @parameters.zip(actual_args).map do |param, arg|
-          [param.s_value, arg]
-        end.to_h
+        @param_to_arg = map_params_to_args(params, @actual_args)
       end
 
-      def resolve_symbol(symbol)
-        if symbol.is_a?(Lexer::Token::InstantiateRule)
-          resolved_args = symbol.args.map { |arg| resolve_symbol(arg) }
-          Lrama::Lexer::Token::InstantiateRule.new(s_value: symbol.s_value, location: symbol.location, args: resolved_args, lhs_tag: symbol.lhs_tag)
+      # @rbs (Lexer::Token sym) -> Lexer::Token
+      def resolve_symbol(sym)
+        if sym.is_a?(Lexer::Token::InstantiateRule)
+          Lrama::Lexer::Token::InstantiateRule.new(
+            s_value: sym.s_value, location: sym.location, args: resolved_args(sym), lhs_tag: sym.lhs_tag
+          )
         else
-          parameter_to_arg(symbol) || symbol
+          param_to_arg(sym)
         end
       end
 
+      # @rbs (Lexer::Token::InstantiateRule token) -> String
+      def concatenated_args_str(token)
+        "#{token.rule_name}_#{token_to_args_s_values(token).join('_')}"
+      end
+
       private
 
-      def parameter_to_arg(symbol)
-        if (arg = @parameter_to_arg[symbol.s_value].dup)
-          arg.alias_name = symbol.alias_name
+      # @rbs (Array[Lexer::Token] params, Array[Lexer::Token] actual_args) -> Hash[String, Lexer::Token]
+      def map_params_to_args(params, actual_args)
+        params.zip(actual_args).map do |param, arg|
+          [param.s_value, arg]
+        end.to_h
+      end
+
+      # @rbs (Lexer::Token::InstantiateRule sym) -> Array[Lexer::Token]
+      def resolved_args(sym)
+        sym.args.map { |arg| resolve_symbol(arg) }
+      end
+
+      # @rbs (Lexer::Token sym) -> Lexer::Token
+      def param_to_arg(sym)
+        if (arg = @param_to_arg[sym.s_value].dup)
+          arg.alias_name = sym.alias_name
+        end
+        arg || sym
+      end
+
+      # @rbs (Lexer::Token::InstantiateRule token) -> Array[String]
+      def token_to_args_s_values(token)
+        token.args.flat_map do |arg|
+          resolved = resolve_symbol(arg)
+          if resolved.is_a?(Lexer::Token::InstantiateRule)
+            [resolved.s_value] + resolved.args.map(&:s_value)
+          else
+            [resolved.s_value]
+          end
         end
-        arg
       end
     end
   end

data/lib/lrama/grammar/parameterizing_rule/rhs.rb

@@ -16,7 +16,7 @@ module Lrama
           return unless user_code
 
           resolved = Lexer::Token::UserCode.new(s_value: user_code.s_value, location: user_code.location)
-          var_to_arg = {}
+          var_to_arg = {} #: Hash[String, String]
           symbols.each do |sym|
             resolved_sym = bindings.resolve_symbol(sym)
             if resolved_sym != sym

data/lib/lrama/grammar/rule.rb

@@ -21,6 +21,14 @@ module Lrama
       def display_name
         l = lhs.id.s_value
         r = empty_rule? ? "ε" : rhs.map {|r| r.id.s_value }.join(" ")
+        "#{l} -> #{r}"
+      end
+
+      def display_name_without_action
+        l = lhs.id.s_value
+        r = empty_rule? ? "ε" : rhs.map do |r|
+          r.id.s_value if r.first_set.any?
+        end.compact.join(" ")
 
         "#{l} -> #{r}"
       end

data/lib/lrama/grammar/rule_builder.rb

@@ -67,13 +67,13 @@ module Lrama
       end
 
       def resolve_inline_rules
-        resolved_builders = []
+        resolved_builders = [] #: Array[RuleBuilder]
         rhs.each_with_index do |token, i|
           if (inline_rule = @parameterizing_rule_resolver.find_inline(token))
             inline_rule.rhs_list.each do |inline_rhs|
               rule_builder = RuleBuilder.new(@rule_counter, @midrule_action_counter, @parameterizing_rule_resolver, lhs_tag: lhs_tag)
               if token.is_a?(Lexer::Token::InstantiateRule)
-                resolve_inline_rhs(rule_builder, inline_rhs, i, Binding.new(inline_rule, token.args))
+                resolve_inline_rhs(rule_builder, inline_rhs, i, Binding.new(inline_rule.parameters, token.args))
               else
                 resolve_inline_rhs(rule_builder, inline_rhs, i)
               end
@@ -135,8 +135,8 @@ module Lrama
             parameterizing_rule = @parameterizing_rule_resolver.find_rule(token)
             raise "Unexpected token. #{token}" unless parameterizing_rule
 
-            bindings = Binding.new(parameterizing_rule, token.args)
-            lhs_s_value = lhs_s_value(token, bindings)
+            bindings = Binding.new(parameterizing_rule.parameters, token.args)
+            lhs_s_value = bindings.concatenated_args_str(token)
             if (created_lhs = @parameterizing_rule_resolver.created_lhs(lhs_s_value))
               @replaced_rhs << created_lhs
             else
@@ -174,18 +174,6 @@ module Lrama
         end
       end
 
-      def lhs_s_value(token, bindings)
-        s_values = token.args.map do |arg|
-          resolved = bindings.resolve_symbol(arg)
-          if resolved.is_a?(Lexer::Token::InstantiateRule)
-            [resolved.s_value, resolved.args.map(&:s_value)]
-          else
-            resolved.s_value
-          end
-        end
-        "#{token.rule_name}_#{s_values.join('_')}"
-      end
-
       def resolve_inline_rhs(rule_builder, inline_rhs, index, bindings = nil)
         rhs.each_with_index do |token, i|
           if index == i

data/lib/lrama/grammar/symbols/resolver.rb

@@ -57,6 +57,10 @@ module Lrama
           nterm
         end
 
+        def find_term_by_s_value(s_value)
+          terms.find { |s| s.id.s_value == s_value }
+        end
+
         def find_symbol_by_s_value(s_value)
           symbols.find { |s| s.id.s_value == s_value }
         end

data/lib/lrama/grammar.rb

@@ -28,14 +28,14 @@ module Lrama
     attr_reader :percent_codes, :eof_symbol, :error_symbol, :undef_symbol, :accept_symbol, :aux, :parameterizing_rule_resolver
     attr_accessor :union, :expect, :printers, :error_tokens, :lex_param, :parse_param, :initial_action,
                   :after_shift, :before_reduce, :after_reduce, :after_shift_error_token, :after_pop_stack,
-                  :symbols_resolver, :types, :rules, :rule_builders, :sym_to_rules, :no_stdlib, :locations
+                  :symbols_resolver, :types, :rules, :rule_builders, :sym_to_rules, :no_stdlib, :locations, :define
 
-    def_delegators "@symbols_resolver", :symbols, :nterms, :terms, :add_nterm, :add_term,
+    def_delegators "@symbols_resolver", :symbols, :nterms, :terms, :add_nterm, :add_term, :find_term_by_s_value,
                                         :find_symbol_by_number!, :find_symbol_by_id!, :token_to_symbol,
                                         :find_symbol_by_s_value!, :fill_symbol_number, :fill_nterm_type,
                                         :fill_printer, :fill_destructor, :fill_error_token, :sort_by_number!
 
-    def initialize(rule_counter)
+    def initialize(rule_counter, define = {})
       @rule_counter = rule_counter
 
       # Code defined by "%code"
@@ -57,6 +57,7 @@ module Lrama
       @aux = Auxiliary.new
       @no_stdlib = false
       @locations = false
+      @define = define.map {|d| d.split('=') }.to_h
 
       append_special_symbols
     end
@@ -171,6 +172,10 @@ module Lrama
       @sym_to_rules[sym.number]
     end
 
+    def ielr_defined?
+      @define.key?('lr.type') && @define['lr.type'] == 'ielr'
+    end
+
     private
 
     def compute_nullable
@@ -294,7 +299,7 @@ module Lrama
     end
 
     def resolve_inline_rules
-      while @rule_builders.any? {|r| r.has_inline_rules? } do
+      while @rule_builders.any?(&:has_inline_rules?) do
         @rule_builders = @rule_builders.flat_map do |builder|
           if builder.has_inline_rules?
             builder.resolve_inline_rules
@@ -382,7 +387,7 @@ module Lrama
     end
 
     def validate_rule_lhs_is_nterm!
-      errors = []
+      errors = [] #: Array[String]
 
       rules.each do |rule|
         next if rule.lhs.nterm?

data/lib/lrama/lexer/grammar_file.rb

@@ -1,30 +1,37 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   class Lexer
     class GrammarFile
       class Text < String
+        # @rbs () -> String
         def inspect
           length <= 50 ? super : "#{self[0..47]}...".inspect
         end
       end
 
-      attr_reader :path, :text
+      attr_reader :path #: String
+      attr_reader :text #: String
 
+      # @rbs (String path, String text) -> void
       def initialize(path, text)
         @path = path
         @text = Text.new(text).freeze
       end
 
+      # @rbs () -> String
       def inspect
         "<#{self.class}: @path=#{path}, @text=#{text.inspect}>"
       end
 
+      # @rbs (GrammarFile other) -> bool
       def ==(other)
         self.class == other.class &&
         self.path == other.path
       end
 
+      # @rbs () -> Array[String]
       def lines
         @lines ||= text.split("\n")
       end

data/lib/lrama/lexer/location.rb

@@ -1,10 +1,16 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   class Lexer
     class Location
-      attr_reader :grammar_file, :first_line, :first_column, :last_line, :last_column
+      attr_reader :grammar_file #: GrammarFile
+      attr_reader :first_line #: Integer
+      attr_reader :first_column #: Integer
+      attr_reader :last_line #: Integer
+      attr_reader :last_column #: Integer
 
+      # @rbs (grammar_file: GrammarFile, first_line: Integer, first_column: Integer, last_line: Integer, last_column: Integer) -> void
       def initialize(grammar_file:, first_line:, first_column:, last_line:, last_column:)
         @grammar_file = grammar_file
         @first_line = first_line
@@ -13,6 +19,7 @@ module Lrama
         @last_column = last_column
       end
 
+      # @rbs (Location other) -> bool
       def ==(other)
         self.class == other.class &&
         self.grammar_file == other.grammar_file &&
@@ -22,6 +29,7 @@ module Lrama
         self.last_column == other.last_column
       end
 
+      # @rbs (Integer left, Integer right) -> Location
       def partial_location(left, right)
         offset = -first_column
         new_first_line = -1
@@ -52,10 +60,12 @@ module Lrama
         )
       end
 
+      # @rbs () -> String
       def to_s
         "#{path} (#{first_line},#{first_column})-(#{last_line},#{last_column})"
       end
 
+      # @rbs (String error_message) -> String
       def generate_error_message(error_message)
         <<~ERROR.chomp
           #{path}:#{first_line}:#{first_column}: #{error_message}
@@ -63,6 +73,7 @@ module Lrama
         ERROR
       end
 
+      # @rbs () -> String
       def line_with_carets
         <<~TEXT
           #{text}
@@ -72,22 +83,27 @@ module Lrama
 
       private
 
+      # @rbs () -> String
       def path
         grammar_file.path
       end
 
+      # @rbs () -> String
       def blanks
         (text[0...first_column] or raise "#{first_column} is invalid").gsub(/[^\t]/, ' ')
       end
 
+      # @rbs () -> String
       def carets
         blanks + '^' * (last_column - first_column)
       end
 
+      # @rbs () -> String
       def text
         @text ||= _text.join("\n")
       end
 
+      # @rbs () -> Array[String]
       def _text
         @_text ||=begin
           range = (first_line - 1)...last_line

data/lib/lrama/lexer/token/char.rb

@@ -1,3 +1,4 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama

data/lib/lrama/lexer/token/ident.rb

@@ -1,3 +1,4 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama

data/lib/lrama/lexer/token/instantiate_rule.rb

@@ -1,21 +1,26 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   class Lexer
     class Token
       class InstantiateRule < Token
-        attr_reader :args, :lhs_tag
+        attr_reader :args #: Array[Lexer::Token]
+        attr_reader :lhs_tag #: Lexer::Token::Tag?
 
+        # @rbs (s_value: String, ?alias_name: String, ?location: Location, ?args: Array[Lexer::Token], ?lhs_tag: Lexer::Token::Tag?) -> void
         def initialize(s_value:, alias_name: nil, location: nil, args: [], lhs_tag: nil)
           super s_value: s_value, alias_name: alias_name, location: location
           @args = args
           @lhs_tag = lhs_tag
         end
 
+        # @rbs () -> String
         def rule_name
           s_value
         end
 
+        # @rbs () -> Integer
         def args_count
           args.count
         end

data/lib/lrama/lexer/token/tag.rb

@@ -1,11 +1,13 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 module Lrama
   class Lexer
     class Token
       class Tag < Token
-        # Omit "<>"
+        # @rbs () -> String
         def member
+          # Omit "<>"
           s_value[1..-2] or raise "Unexpected Tag format (#{s_value})"
         end
       end

data/lib/lrama/lexer/token/user_code.rb

@@ -1,3 +1,4 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 require "strscan"
@@ -6,17 +7,19 @@ module Lrama
   class Lexer
     class Token
       class UserCode < Token
-        attr_accessor :tag
+        attr_accessor :tag #: Lexer::Token::Tag
 
+        # @rbs () -> Array[Lrama::Grammar::Reference]
         def references
           @references ||= _references
         end
 
         private
 
+        # @rbs () -> Array[Lrama::Grammar::Reference]
         def _references
           scanner = StringScanner.new(s_value)
-          references = []
+          references = [] #: Array[Grammar::Reference]
 
           until scanner.eos? do
             case
@@ -32,6 +35,7 @@ module Lrama
           references
         end
 
+        # @rbs (StringScanner scanner) -> Lrama::Grammar::Reference?
         def scan_reference(scanner)
           start = scanner.pos
           case

data/lib/lrama/lexer/token.rb

@@ -1,3 +1,4 @@
+# rbs_inline: enabled
 # frozen_string_literal: true
 
 require_relative 'token/char'
@@ -9,9 +10,12 @@ require_relative 'token/user_code'
 module Lrama
   class Lexer
     class Token
-      attr_reader :s_value, :location
-      attr_accessor :alias_name, :referred
+      attr_reader :s_value #: String
+      attr_reader :location #: Location
+      attr_accessor :alias_name #: String
+      attr_accessor :referred #: bool
 
+      # @rbs (s_value: String, ?alias_name: String, ?location: Location) -> void
       def initialize(s_value:, alias_name: nil, location: nil)
         s_value.freeze
         @s_value = s_value
@@ -19,36 +23,44 @@ module Lrama
         @location = location
       end
 
+      # @rbs () -> String
       def to_s
         "value: `#{s_value}`, location: #{location}"
       end
 
+      # @rbs (String string) -> bool
       def referred_by?(string)
         [self.s_value, self.alias_name].compact.include?(string)
       end
 
+      # @rbs (Token other) -> bool
       def ==(other)
         self.class == other.class && self.s_value == other.s_value
       end
 
+      # @rbs () -> Integer
       def first_line
         location.first_line
       end
       alias :line :first_line
 
+      # @rbs () -> Integer
       def first_column
         location.first_column
       end
       alias :column :first_column
 
+      # @rbs () -> Integer
       def last_line
         location.last_line
       end
 
+      # @rbs () -> Integer
       def last_column
         location.last_column
       end
 
+      # @rbs (Lrama::Grammar::Reference ref, String message) -> bot
       def invalid_ref(ref, message)
         location = self.location.partial_location(ref.first_column, ref.last_column)
         raise location.generate_error_message(message)